From 1ae246ed9308b4051b05bccc99ac9b8698567391 Mon Sep 17 00:00:00 2001 From: alruvamora Date: Sun, 1 Dec 2024 23:15:46 +0100 Subject: [PATCH] payments_alvaro_ruedas Done --- .ipynb_checkpoints/readme-checkpoint.md | 49 + .../Untitled-checkpoint.ipynb | 3359 +++++++++++++++++ project_dataset/Untitled.ipynb | 3359 +++++++++++++++++ 3 files changed, 6767 insertions(+) create mode 100644 .ipynb_checkpoints/readme-checkpoint.md create mode 100644 project_dataset/.ipynb_checkpoints/Untitled-checkpoint.ipynb create mode 100644 project_dataset/Untitled.ipynb diff --git a/.ipynb_checkpoints/readme-checkpoint.md b/.ipynb_checkpoints/readme-checkpoint.md new file mode 100644 index 0000000..8a78b0f --- /dev/null +++ b/.ipynb_checkpoints/readme-checkpoint.md @@ -0,0 +1,49 @@ +![logo_ironhack_blue 7](https://user-images.githubusercontent.com/23629340/40541063-a07a0a8a-601a-11e8-91b5-2f13e4e6b441.png) + +# Business Challenge: Cohort Analysis for Ironhack Payments (Project 1) + +## Introduction + +IronHack Payments, a forward-thinking financial services company, has been offering innovative cash advance solutions since its inception in 2020. With a commitment to providing money advancements for free and transparent pricing, IronHack Payments has garnered a substantial user base. As part of their continuous effort to enhance their services and understand user behavior, IronHack Payments has commissioned a cohort analysis project. + +## Project Overview + +In this project, you will conduct a comprehensive cohort analysis based on data provided by IronHack Payments. The main objective is to analyze user cohorts defined by the month of creation of their first cash advance. You will track the monthly evolution of key metrics for these cohorts, enabling IronHack Payments to gain valuable insights into user behavior and the performance of their financial services. + +### Metrics to Analyze + +You will calculate and analyze the following metrics for each cohort: + +1. **Frequency of Service Usage:** Understand how often users from each cohort utilize IronHack Payments' cash advance services over time. +2. **Incident Rate:** Determine the incident rate, specifically focusing on payment incidents, for each cohort. Identify if there are variations in incident rates among different cohorts. +3. **Revenue Generated by the Cohort:** Calculate the total revenue generated by each cohort over months to assess the financial impact of user behavior. +4. **New Relevant Metric:** Propose and calculate a new relevant metric that provides additional insights into user behavior or the performance of IronHack Payments' services. + +### Data Analysis Tools + +You are expected to perform the cohort analysis using Python, primarily leveraging the Pandas library for data manipulation and analysis. However, the main analysis should be conducted using Python. + +### Exploratory Data Analysis (EDA) + +Before diving into cohort analysis, conduct an exploratory data analysis to gain a comprehensive understanding of the dataset. Explore key statistics, distributions, and visualizations to identify patterns and outliers. EDA will help you make informed decisions on data preprocessing and analysis strategies. + +### Data Quality Analysis + +Assess the quality of the dataset by identifying missing values, data inconsistencies, and potential errors. Implement data cleaning and preprocessing steps to ensure the reliability of your analysis. Document any data quality issues encountered and the steps taken to address them. + +### Deliverables + +1. **Python Code:** Provide well-documented Python code that conducts the cohort analysis, including data loading, preprocessing, cohort creation, metric calculation, and visualization. +2. **Tableau Dashboard**: Publish a dashboard in Tableau Public regarding your analysis. +3. **Exploratory Data Analysis Report:** Prepare a report summarizing the findings from your exploratory data analysis. Include visualizations and insights that help understand the dataset. +4. **Data Quality Analysis Report:** Document the results of your data quality analysis, highlighting any issues and the steps taken to resolve them. +5. **Short Presentation:** Create a concise presentation (maximum of 4 slides) summarizing your findings from the cohort analysis and key insights gained from EDA and data quality analysis. This presentation should be suitable for sharing with the IronHack Payments team. + +### Bonus: +1. **Operationalize your analysis**: Make sure all the code is in a .py that can be called from the Terminal and whose execution makes sense (if in doubt, ask the Teacher for clarification on this) +2. **StreamLit**: Read about the StreamLit package and create a StreamLit app about this data (you can leverage on ideias from your dashboard) +3. **OPP vs Function**: Take your code and replicate it using an oposite strategy than you have done. + + + + diff --git a/project_dataset/.ipynb_checkpoints/Untitled-checkpoint.ipynb b/project_dataset/.ipynb_checkpoints/Untitled-checkpoint.ipynb new file mode 100644 index 0000000..ad563f3 --- /dev/null +++ b/project_dataset/.ipynb_checkpoints/Untitled-checkpoint.ipynb @@ -0,0 +1,3359 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "id": "349dbdcc-4061-4b54-babd-7601df74b01b", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "RangeIndex: 32094 entries, 0 to 32093\n", + "Data columns (total 29 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 id_x 32094 non-null int64 \n", + " 1 amount 32094 non-null float64\n", + " 2 status_x 32094 non-null object \n", + " 3 created_at_x 32094 non-null object \n", + " 4 updated_at_x 32094 non-null object \n", + " 5 user_id 29522 non-null float64\n", + " 6 moderated_at 21759 non-null object \n", + " 7 deleted_account_id 2573 non-null float64\n", + " 8 reimbursement_date 32094 non-null object \n", + " 9 cash_request_received_date 24149 non-null object \n", + " 10 money_back_date 23917 non-null object \n", + " 11 transfer_type 32094 non-null object \n", + " 12 send_at 22678 non-null object \n", + " 13 recovery_status 7200 non-null object \n", + " 14 reco_creation 7200 non-null object \n", + " 15 reco_last_update 7200 non-null object \n", + " 16 id_y 21057 non-null float64\n", + " 17 cash_request_id 21057 non-null float64\n", + " 18 type 21057 non-null object \n", + " 19 status_y 21057 non-null object \n", + " 20 category 2196 non-null object \n", + " 21 total_amount 21057 non-null float64\n", + " 22 reason 21057 non-null object \n", + " 23 created_at_y 21057 non-null object \n", + " 24 updated_at_y 21057 non-null object \n", + " 25 paid_at 15531 non-null object \n", + " 26 from_date 7766 non-null object \n", + " 27 to_date 7766 non-null object \n", + " 28 charge_moment 21057 non-null object \n", + "dtypes: float64(6), int64(1), object(22)\n", + "memory usage: 7.1+ MB\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Frequency of service use by cohort:\n", + "month\n", + "1 223\n", + "2 184\n", + "3 244\n", + "4 473\n", + "5 997\n", + "6 3662\n", + "7 4793\n", + "8 5250\n", + "9 6227\n", + "10 9611\n", + "11 141\n", + "12 289\n", + "Name: id_x, dtype: int64\n", + "Revenue generated by cohort:\n", + "month\n", + "1 0.0\n", + "2 0.0\n", + "3 0.0\n", + "4 5.0\n", + "5 1285.0\n", + "6 8725.0\n", + "7 10395.0\n", + "8 17565.0\n", + "9 22935.0\n", + "10 43815.0\n", + "11 565.0\n", + "12 0.0\n", + "Name: total_amount, dtype: float64\n", + "Incident rate by cohort:\n", + "month\n", + "1 0.107623\n", + "2 0.032609\n", + "3 0.061475\n", + "4 0.095137\n", + "5 0.183551\n", + "6 0.188422\n", + "7 0.151888\n", + "8 0.201905\n", + "9 0.177774\n", + "10 0.132660\n", + "11 0.141844\n", + "12 0.048443\n", + "Name: id_x, dtype: float64\n", + "None\n", + "None\n", + "Values of 'time_to_reimbursement' after calculation:\n", + "0 30.0\n", + "1 30.0\n", + "2 30.0\n", + "3 30.0\n", + "4 NaN\n", + "Name: time_to_reimbursement, dtype: float64\n", + "Null values in 'time_to_reimbursement': 28033\n", + "None\n", + "None\n", + "Values of 'time_to_reimbursement' after calculation:\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# %% [markdown]\n", + "# Business Understanding\n", + "# %%\n", + "# objective\n", + "\"\"\" 1. how often users from different cohorts use the cash advance services.(Frequency of service usage over the time - trend analysis - bar chart)\n", + " 2. Incident rate for payment-related issues across cohorts (trend variation to understand in which periods this appear and for each cohort)\n", + " 3. Revenue Analysis over the time: total revenue generated by each cohort over months to assess the financial impact of user behavior (trend)\n", + "4.New Metric to track this:\n", + "- how long time to happen the first incident rate / min and max\n", + "- avg of users that need the cash advance\n", + "-measure of insights into user behavior or the performance of IronHack Payments' services.\n", + "Columns_to_use:\n", + " track the data of first request - [id,amount,created_at,updated_at,user_id,status]\n", + " revenue analysis = transfer_type,cash_request_received_date,\n", + " incident rate = [deleted_account_i, reimbursement_date (charge_date),recovery_status,reco_last_update]\n", + "\"\"\"\n", + "# %% [markdown]\n", + "# Data Mining\n", + "# %%\n", + "#Libraries used for this project\n", + "import pandas as pd # painel data, dataframes\n", + "import numpy as np # numerical data\n", + "import os # manage directories folders\n", + "import seaborn as sns # visualization\n", + "from datetime import datetime # format dates\n", + "from openpyxl import load_workbook # excel file with folders/tabs\n", + "# %% [markdown]\n", + "# Data Collection\n", + "# %%\n", + "#dataset1\n", + "cash_req = pd.read_csv(\"extract - cash request - data analyst.csv\")\n", + "df1 = cash_req.copy()\n", + "df1 = pd.DataFrame(df1)\n", + "df1\n", + "# %%\n", + "#dataset2\n", + "fee = pd.read_csv(\"extract - fees - data analyst - .csv\")\n", + "df2 = fee.copy()\n", + "df2 = pd.DataFrame(df2)\n", + "df2\n", + "# %%\n", + "df3_path = \"Lexique - Data Analyst.xlsx\" # sourcefile\n", + "df3 = pd.read_excel(df3_path) # coverting into dataframe\n", + "df3_workbook = load_workbook(df3_path) # open the workbook\n", + "cash_request_workbook = df3_workbook.worksheets[1] # acessing to the second folder of the workbook\n", + "cash_request_workbook\n", + "fees_workbook = df3_workbook.worksheets[0] # acessing to the first folder of the workbook\n", + "fees_workbook\n", + "df3_cash_request = []\n", + "for row in cash_request_workbook.iter_rows(values_only=True):\n", + " df3_cash_request.append(row) # junta todas as rows ao dicionario vazio\n", + "df3_cash_request = pd.DataFrame(df3_cash_request)\n", + "df3_cash_request\n", + "df3_fees = []\n", + "for row in fees_workbook.iter_rows(values_only=True):\n", + " df3_fees.append(row)\n", + "df3_fees = pd.DataFrame(df3_fees)\n", + "df3_fees.head(13)\n", + "df3\n", + "# %%\n", + "merged_df = pd.merge(df1,df2,how='left',left_on='id',right_on='cash_request_id')\n", + "merged_df # left join based on the id\n", + "merged_df.head()\n", + "merged_df2 = merged_df.copy()\n", + "# %%\n", + "merged_df2.info()\n", + "merged_df2.isnull().mean()\n", + "# %%\n", + "merged_df.isnull().mean()\n", + "merged_df.duplicated().sum()\n", + "(merged_df =='').sum() # no spaces on the dataframe\n", + "# %%\n", + "import matplotlib.pyplot as plt # review\n", + "import seaborn as sns\n", + "plt.figure(figsize=(10, 6))\n", + "sns.histplot(merged_df['amount'], kde=True, bins=50)\n", + "plt.title('Distribution of the value of advance requests')\n", + "plt.show()\n", + "# %%\n", + "merged_df2 = merged_df2[['id_x','created_at_x', 'total_amount', 'recovery_status', 'reimbursement_date']]\n", + "merged_df2.head() # columns to keep\n", + "merged_df2.isnull().mean()\n", + "#merged_df2.dtypes\n", + "# %%\n", + "merged_df2['total_amount'] = merged_df2['total_amount'].fillna(0)\n", + "merged_df2['total_amount'].isnull().mean()\n", + "merged_df2['recovery_status'] = merged_df2['recovery_status'].fillna(\"Not Aplicable\")\n", + "merged_df2['recovery_status'].isnull().mean()\n", + "merged_df2['created_at_x'] = pd.to_datetime(merged_df2['created_at_x'], errors='coerce')\n", + "merged_df2['created_at_x'] = merged_df2['created_at_x'].dt.strftime(\"%Y/%m/%d\")\n", + "merged_df2['created_at_x'] = pd.to_datetime(merged_df2['created_at_x'],format=\"%Y/%m/%d\")\n", + "merged_df2['reimbursement_date'] = pd.to_datetime(merged_df2['reimbursement_date'], errors='coerce')\n", + "merged_df2['reimbursement_date'] = merged_df2['reimbursement_date'].dt.strftime('%Y/%m/%d')\n", + "merged_df2['reimbursement_date'] = pd.to_datetime(merged_df2['reimbursement_date'], format='%Y/%m/%d')\n", + "merged_df2.dtypes\n", + "merged_df2.isnull().mean()\n", + "# alternative way\n", + "# merged_df2['reimbursement_date'] = merged_df2['reimbursement_date'].apply(lambda x:x.date().strftime(\"%Y/%m/%d\"))\n", + "# %%\n", + "# Month Column\n", + "merged_df2['month'] = merged_df2['created_at_x'].dt.month\n", + "merged_df2\n", + "cohort_counts = merged_df2.groupby('month')['id_x'].count()\n", + "cohort_counts\n", + "plt.figure(figsize=(10, 6))\n", + "# Criando o barplot para cohort_counts\n", + "sns.barplot(x=cohort_counts.index, y=cohort_counts.values,\n", + " palette='viridis', hue=cohort_counts.index, legend=False)\n", + "# Criando a linha de tendência para cohort_counts\n", + "sns.lineplot(x=cohort_counts.index, y=cohort_counts.values, color='red', marker='o', linewidth=2)\n", + "# Adicionando títulos e rótulos\n", + "plt.title('Frequency of Service Use per Month', fontsize=14)\n", + "plt.xlabel('Cohort Month', fontsize=12)\n", + "plt.ylabel('Number of Requests', fontsize=12)\n", + "# Personalizando os rótulos do eixo x para meses\n", + "plt.xticks(ticks=range(len(cohort_counts.index)), labels=['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'])\n", + "# Exibindo o gráfico\n", + "plt.show()\n", + "# %%\n", + "cohort_revenue = merged_df2.groupby('month')['total_amount'].sum()\n", + "cohort_revenue\n", + "cohort_revenue = merged_df2.groupby('month')['total_amount'].sum()\n", + "# Visualização do cohort_revenue\n", + "plt.figure(figsize=(10, 6))\n", + "# Criando o barplot para cohort_revenue\n", + "sns.barplot(x=cohort_revenue.index, y=cohort_revenue.values,\n", + " palette='viridis', hue=cohort_revenue.index, legend=False)\n", + "# Criando a linha de tendência para cohort_revenue\n", + "sns.lineplot(x=cohort_revenue.index, y=cohort_revenue.values, color='red', marker='o', linewidth=2)\n", + "# Adicionando títulos e rótulos\n", + "plt.title('Revenue Generated per Month', fontsize=14)\n", + "plt.xlabel('Cohort Month', fontsize=12)\n", + "plt.ylabel('Total Revenue', fontsize=12)\n", + "# Personalizando os rótulos do eixo x para meses\n", + "plt.xticks(ticks=range(len(cohort_revenue.index)), labels=['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'])\n", + "# Exibindo o gráfico\n", + "plt.show()\n", + "# %%\n", + "merged_df.isnull().mean()\n", + "# merged_clean_df_cohort_analysis = merged_df[['created_at_x', 'paid_at', 'total_amount', 'recovery_status'])\n", + "# %%\n", + "merged_df2\n", + "# %%\n", + "\"\"\" # Convert 'paid_at' to datetime if not already\n", + "merged_df2['paid_at'] = pd.to_datetime(merged_df2['paid_at'])\n", + "# Extract the year, quarter, month, and bi-annual period from 'paid_at'\n", + "merged_df2['year'] = merged_df2['paid_at'].dt.year\n", + "merged_df2['quarter'] = merged_df2['paid_at'].dt.to_period('Q')\n", + "merged_df2['semester'] = (merged_df2['paid_at'].dt.month - 1) // 6 + 1\n", + "merged_df2['month'] = merged_df2['paid_at'].dt.month\n", + "# Calculate total revenue per cohort for each period type\n", + "monthly_revenue = merged_df2.groupby(['month', 'month']).agg({'total_amount': 'sum'}).reset_index()\n", + "quarterly_revenue = merged_df2.groupby(['quarter']).agg({'total_amount': 'sum'}).reset_index()\n", + "semester_revenue = merged_df2.groupby(['semester']).agg({'total_amount': 'sum'}).reset_index()\n", + "annual_revenue = merged_df2.groupby(['year']).agg({'total_amount': 'sum'}).reset_index()\n", + "# Plotting the cohort revenue\n", + "plt.figure(figsize=(12, 6))\n", + "# Plot monthly revenue\n", + "sns.barplot(x='month', y='total_amount', data=monthly_revenue, color='blue', label='Monthly Revenue')\n", + "# Plot quarterly revenue\n", + "sns.barplot(x='quarter', y='total_amount', data=quarterly_revenue, color='green', label='Quarterly Revenue')\n", + "# Plot semester revenue\n", + "sns.barplot(x='semester', y='total_amount', data=semester_revenue, color='orange', label='Semester Revenue')\n", + "# Plot annual revenue\n", + "sns.barplot(x='year', y='total_amount', data=annual_revenue, color='purple', label='Annual Revenue')\n", + "# Customize plot\n", + "plt.title('Cohort Revenue per Time Period', fontsize=14)\n", + "plt.xlabel('Time Period', fontsize=12)\n", + "plt.ylabel('Total Revenue (in currency)', fontsize=12)\n", + "plt.legend()\n", + "plt.show()\"\"\"\n", + "# %%\n", + "# Calculate the incident rate\n", + "incident_rate = merged_df2[merged_df2['recovery_status'] == 'completed'].groupby('month')['id_x'].count() / cohort_counts\n", + "# Create the plot\n", + "plt.figure(figsize=(10, 6))\n", + "sns.barplot(x=incident_rate.index, y=incident_rate.values,\n", + " hue=incident_rate.index, palette='viridis', legend=False)\n", + "sns.lineplot(x=incident_rate.index, y=incident_rate.values, color='red', marker='o', linewidth=2)\n", + "plt.title('Incident Rate by Cohort', fontsize=14)\n", + "plt.xlabel('Cohort Month', fontsize=12)\n", + "plt.ylabel('Incident Rate', fontsize=12)\n", + "# Customize x-axis labels for months\n", + "plt.xticks(ticks=range(len(incident_rate.index)), labels=['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'])\n", + "# Display the plot\n", + "plt.show()\n", + "# %%\n", + "print(\"Frequency of service use by cohort:\")\n", + "print(cohort_counts)\n", + "print(\"Revenue generated by cohort:\")\n", + "print(cohort_revenue)\n", + "print(\"Incident rate by cohort:\")\n", + "print(incident_rate)\n", + "# %%\n", + "print(merged_df2['created_at_x'].dt.tz)\n", + "print(merged_df2['reimbursement_date'].dt.tz)\n", + "# %%\n", + "# Calcular a diferença entre 'reimbursement_date' e 'created_at_x'\n", + "merged_df2['time_to_reimbursement'] = (merged_df2['reimbursement_date'] - merged_df2['created_at_x']).dt.days\n", + "# Verificar os valores da coluna 'time_to_reimbursement'\n", + "print(\"Values of 'time_to_reimbursement' after calculation:\")\n", + "print(merged_df2['time_to_reimbursement'].head())\n", + "# Checar valores nulos na coluna 'time_to_reimbursement'\n", + "print(\"Null values in 'time_to_reimbursement':\", merged_df2['time_to_reimbursement'].isnull().sum())\n", + "plt.show()\n", + "# %%\n", + "print(merged_df2['created_at_x'].dt.tz)\n", + "print(merged_df2['reimbursement_date'].dt.tz)\n", + "# %%\n", + "# Remover linhas com valores nulos nas colunas 'created_at_x' e 'reimbursement_date'\n", + "merged_df2_clean = merged_df2.dropna(subset=['created_at_x', 'reimbursement_date'])\n", + "merged_df2_clean\n", + "(merged_df2_clean['reimbursement_date'] - merged_df2_clean['created_at_x']).dt.days\n", + "print(\"Values of 'time_to_reimbursement' after calculation:\")\n", + "merged_df2_clean['time_to_reimbursement'].head(20)\n", + "plt.figure(figsize=(10, 6))\n", + "sns.boxplot(x=merged_df2_clean['time_to_reimbursement'], color='green')\n", + "plt.title('Time to Refund Boxplot', fontsize=14)\n", + "plt.xlabel('Time until Refund (days)', fontsize=12)\n", + "plt.show()\n", + "# %%\n", + "import matplotlib.pyplot as plt\n", + "import seaborn as sns\n", + "plt.figure(figsize=(10, 6))\n", + "sns.histplot(merged_df2_clean['time_to_reimbursement'], kde=True, color='blue', bins=30)\n", + "plt.title('Distribution of Time until Reimbursement', fontsize=14)\n", + "plt.xlabel('Time until Refund (days)', fontsize=12)\n", + "plt.ylabel('Frequency', fontsize=12)\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 409, + "id": "f2824fa0-41b4-43da-baca-c63f4da6414a", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "RangeIndex: 32094 entries, 0 to 32093\n", + "Data columns (total 29 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 id_x 32094 non-null int64 \n", + " 1 amount 32094 non-null float64\n", + " 2 status_x 32094 non-null object \n", + " 3 created_at_x 32094 non-null object \n", + " 4 updated_at_x 32094 non-null object \n", + " 5 user_id 29522 non-null float64\n", + " 6 moderated_at 21759 non-null object \n", + " 7 deleted_account_id 2573 non-null float64\n", + " 8 reimbursement_date 32094 non-null object \n", + " 9 cash_request_received_date 24149 non-null object \n", + " 10 money_back_date 23917 non-null object \n", + " 11 transfer_type 32094 non-null object \n", + " 12 send_at 22678 non-null object \n", + " 13 recovery_status 7200 non-null object \n", + " 14 reco_creation 7200 non-null object \n", + " 15 reco_last_update 7200 non-null object \n", + " 16 id_y 21057 non-null float64\n", + " 17 cash_request_id 21057 non-null float64\n", + " 18 type 21057 non-null object \n", + " 19 status_y 21057 non-null object \n", + " 20 category 2196 non-null object \n", + " 21 total_amount 21057 non-null float64\n", + " 22 reason 21057 non-null object \n", + " 23 created_at_y 21057 non-null object \n", + " 24 updated_at_y 21057 non-null object \n", + " 25 paid_at 15531 non-null object \n", + " 26 from_date 7766 non-null object \n", + " 27 to_date 7766 non-null object \n", + " 28 charge_moment 21057 non-null object \n", + "dtypes: float64(6), int64(1), object(22)\n", + "memory usage: 7.1+ MB\n" + ] + }, + { + "data": { + "text/plain": [ + "id_x 0.000000\n", + "created_at_x 0.000000\n", + "total_amount 0.343896\n", + "recovery_status 0.775659\n", + "reimbursement_date 0.000000\n", + "dtype: float64" + ] + }, + "execution_count": 409, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import pandas as pd # painel data, dataframes\n", + "import numpy as np # numerical data\n", + "import os # manage directories folders\n", + "import seaborn as sns # visualization\n", + "from datetime import datetime # format dates\n", + "from openpyxl import load_workbook # excel file with folders/tabs\n", + "\n", + "# %% [markdown]\n", + "# Data Collection\n", + "# %%\n", + "\n", + "#dataset1\n", + "\n", + "#Se lee un archivo CSV con datos relacionados con solicitudes de efectivo\n", + "cash_req = pd.read_csv(\"extract - cash request - data analyst.csv\")\n", + "\n", + "#Se copia el dataframe para trabajar sin modificar el original:\n", + "df1 = cash_req.copy()\n", + "df1 = pd.DataFrame(df1)\n", + "df1\n", + "\n", + "# %%\n", + "#dataset2\n", + "\n", + "#Se lee otro archivo CSV con información sobre tarifas:\n", + "fee = pd.read_csv(\"extract - fees - data analyst - .csv\")\n", + "\n", + "#Se convierte a un dataframe y se almacena en df2.\n", + "df2 = fee.copy()\n", + "df2 = pd.DataFrame(df2)\n", + "df2\n", + "\n", + "\"\"\"\n", + "# %%\n", + "df3_path = \"Lexique - Data Analyst.xlsx\" # sourcefile\n", + "df3 = pd.read_excel(df3_path) # coverting into dataframe\n", + "df3_workbook = load_workbook(df3_path) # open the workbook\n", + "cash_request_workbook = df3_workbook.worksheets[1] # acessing to the second folder of the workbook\n", + "cash_request_workbook\n", + "fees_workbook = df3_workbook.worksheets[0] # acessing to the first folder of the workbook\n", + "fees_workbook\n", + "df3_cash_request = []\n", + "for row in cash_request_workbook.iter_rows(values_only=True):\n", + " df3_cash_request.append(row) # junta todas as rows ao dicionario vazio\n", + "df3_cash_request = pd.DataFrame(df3_cash_request)\n", + "df3_cash_request\n", + "df3_fees = []\n", + "for row in fees_workbook.iter_rows(values_only=True):\n", + " df3_fees.append(row)\n", + "df3_fees = pd.DataFrame(df3_fees)\n", + "df3_fees.head(13)\n", + "df3\n", + "\"\"\"\n", + "\n", + "# %% Se realiza un merge (combinación de tablas) entre df1 y df2, usando una \"unión izquierda\" basada en las claves id y cash_request_id:\n", + "merged_df = pd.merge(df1,df2,how='left',left_on='id',right_on='cash_request_id')\n", + "merged_df # left join based on the id\n", + "merged_df.head()\n", + "merged_df2 = merged_df.copy()\n", + "\n", + "# %%\n", + "\n", + "merged_df2.info() # Información básica del dataframe combinado:\n", + "merged_df2.isnull().mean() # Proporción de valores nulos en cada columna:\n", + "\n", + "# %%\n", + "merged_df.isnull().mean()\n", + "merged_df.duplicated().sum() # Detección de duplicados:\n", + "(merged_df =='').sum() # Revisión de espacios vacíos: no spaces on the dataframe\n", + "\n", + "# %%\n", + "\"\"\"\n", + "import matplotlib.pyplot as plt # review\n", + "import seaborn as sns\n", + "plt.figure(figsize=(10, 6))\n", + "sns.histplot(merged_df['amount'], kde=True, bins=50)\n", + "plt.title('Distribuição do valor das solicitações de adiantamento')\n", + "plt.show()\n", + "\"\"\"\n", + "\n", + "# %%\n", + "merged_df2 = merged_df2[['id_x','created_at_x', 'total_amount', 'recovery_status', 'reimbursement_date']]\n", + "merged_df2.head() # columns to keep\n", + "merged_df2.isnull().mean()\n", + "#merged_df2.dtypes\n", + "#merged_df2\n" + ] + }, + { + "cell_type": "code", + "execution_count": 413, + "id": "8c8babdf-c9c1-4c14-97bb-3d58ebded186", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
id_xcreated_at_xtotal_amountrecovery_statusreimbursement_date
052019-12-10 19:05:21.596873+00NaNNaN2020-01-09 19:05:21.596363+00
1702019-12-10 19:50:12.34778+00NaNNaN2020-01-09 19:50:12.34778+00
272019-12-10 19:13:35.82546+00NaNNaN2020-01-09 19:13:35.825041+00
3102019-12-10 19:16:10.880172+00NaNNaN2020-01-09 19:16:10.879606+00
415942020-05-06 09:59:38.877376+00NaNNaN2020-06-05 22:00:00+00
..................
32089223572020-10-20 07:58:04.006937+005.0NaN2021-02-05 11:00:00+00
32090202562020-10-10 05:40:55.700422+005.0NaN2021-02-05 11:00:00+00
32091202562020-10-10 05:40:55.700422+005.0NaN2021-02-05 11:00:00+00
32092198862020-10-08 14:16:52.155661+005.0NaN2021-02-05 11:00:00+00
32093198862020-10-08 14:16:52.155661+005.0NaN2021-02-05 11:00:00+00
\n", + "

32094 rows × 5 columns

\n", + "
" + ], + "text/plain": [ + " id_x created_at_x total_amount recovery_status \\\n", + "0 5 2019-12-10 19:05:21.596873+00 NaN NaN \n", + "1 70 2019-12-10 19:50:12.34778+00 NaN NaN \n", + "2 7 2019-12-10 19:13:35.82546+00 NaN NaN \n", + "3 10 2019-12-10 19:16:10.880172+00 NaN NaN \n", + "4 1594 2020-05-06 09:59:38.877376+00 NaN NaN \n", + "... ... ... ... ... \n", + "32089 22357 2020-10-20 07:58:04.006937+00 5.0 NaN \n", + "32090 20256 2020-10-10 05:40:55.700422+00 5.0 NaN \n", + "32091 20256 2020-10-10 05:40:55.700422+00 5.0 NaN \n", + "32092 19886 2020-10-08 14:16:52.155661+00 5.0 NaN \n", + "32093 19886 2020-10-08 14:16:52.155661+00 5.0 NaN \n", + "\n", + " reimbursement_date \n", + "0 2020-01-09 19:05:21.596363+00 \n", + "1 2020-01-09 19:50:12.34778+00 \n", + "2 2020-01-09 19:13:35.825041+00 \n", + "3 2020-01-09 19:16:10.879606+00 \n", + "4 2020-06-05 22:00:00+00 \n", + "... ... \n", + "32089 2021-02-05 11:00:00+00 \n", + "32090 2021-02-05 11:00:00+00 \n", + "32091 2021-02-05 11:00:00+00 \n", + "32092 2021-02-05 11:00:00+00 \n", + "32093 2021-02-05 11:00:00+00 \n", + "\n", + "[32094 rows x 5 columns]" + ] + }, + "execution_count": 413, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "merged_df2" + ] + }, + { + "cell_type": "code", + "execution_count": 431, + "id": "7caf7124-1c58-4f60-a0d0-3587836c67bc", + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\EliteBook\\AppData\\Local\\Temp\\ipykernel_26244\\2759623616.py:7: UserWarning: Converting to PeriodArray/Index representation will drop timezone information.\n", + " merged_df2['cohort'] = merged_df2['created_at_x'].dt.to_period('M')\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Cohorte2019-112019-122020-012020-022020-032020-042020-052020-062020-072020-082020-092020-102020-11
Ingresos Totales0.00.00.00.00.05.01285.08725.010395.017565.022935.043815.0565.0
\n", + "
" + ], + "text/plain": [ + "Cohorte 2019-11 2019-12 2020-01 2020-02 2020-03 2020-04 \\\n", + "Ingresos Totales 0.0 0.0 0.0 0.0 0.0 5.0 \n", + "\n", + "Cohorte 2020-05 2020-06 2020-07 2020-08 2020-09 2020-10 \\\n", + "Ingresos Totales 1285.0 8725.0 10395.0 17565.0 22935.0 43815.0 \n", + "\n", + "Cohorte 2020-11 \n", + "Ingresos Totales 565.0 " + ] + }, + "execution_count": 431, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#Calcular ingresos generados por cohortes\n", + "\n", + "# Convertir la columna de fechas a tipo datetime\n", + "merged_df2['created_at_x'] = pd.to_datetime(merged_df2['created_at_x'])\n", + "\n", + "# Crear una columna de cohorte basada en el mes y año de registro\n", + "merged_df2['cohort'] = merged_df2['created_at_x'].dt.to_period('M')\n", + "\n", + "# Calcular los ingresos totales generados por cohorte\n", + "cohort_revenue = merged_df2.groupby('cohort')['total_amount'].sum().reset_index()\n", + "\n", + "# Renombrar columnas\n", + "cohort_revenue.columns = ['Cohorte', 'Ingresos Totales']\n", + "\n", + "# Convertirlo a Dataframe\n", + "df_cohort_revenue = pd.DataFrame(cohort_revenue)\n", + "df_cohort_revenue = df_cohort_revenue.set_index(\"Cohorte\")\n", + "\n", + "# Mostrar los resultados\n", + "df_cohort_revenue.T\n" + ] + }, + { + "cell_type": "code", + "execution_count": 421, + "id": "c704625d-3021-4387-aa84-838f7d5b6b32", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Visualización de resultados\n", + "\n", + "import matplotlib.pyplot as plt\n", + "\n", + "\n", + "plt.figure(figsize=(12, 6))\n", + "sns.barplot(data=cohort_revenue, x='Cohorte', y='Ingresos Totales', color='blue')\n", + "plt.title('Ingresos Totales por Cohorte')\n", + "plt.xlabel('Cohorte (Mes y Año)')\n", + "plt.ylabel('Ingresos Totales')\n", + "plt.xticks(rotation=45)\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 407, + "id": "4d774073-670d-4865-a5d4-a8454599787d", + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\EliteBook\\AppData\\Local\\Temp\\ipykernel_26244\\2138421487.py:19: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n", + "The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n", + "\n", + "For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n", + "\n", + "\n", + " cohort_metrics['Recuperaciones Exitosas'].fillna(0, inplace=True)\n", + "C:\\Users\\EliteBook\\AppData\\Local\\Temp\\ipykernel_26244\\2138421487.py:20: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n", + "The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n", + "\n", + "For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n", + "\n", + "\n", + " cohort_metrics['Tasa de Recuperación Exitosa'].fillna(0, inplace=True)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
CohorteTotal SolicitudesRecuperaciones ExitosasTasa de Recuperación Exitosa
\n", + "
" + ], + "text/plain": [ + "Empty DataFrame\n", + "Columns: [Cohorte, Total Solicitudes, Recuperaciones Exitosas, Tasa de Recuperación Exitosa]\n", + "Index: []" + ] + }, + "execution_count": 407, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Proponer y calcular un nuevo métrico relevante\n", + "# Nuevo métrica: Tasa de recuperación exitosa\n", + "\n", + "# Calcular la cantidad total de solicitudes por cohorte\n", + "cohort_counts = merged_df2.groupby('cohort')['id_x'].count().reset_index()\n", + "cohort_counts.columns = ['Cohorte', 'Total Solicitudes']\n", + "\n", + "# Calcular la cantidad de solicitudes recuperadas con éxito por cohorte\n", + "successful_recoveries = merged_df2[merged_df2['recovery_status'] == 'successful'].groupby('cohort')['id_x'].count().reset_index()\n", + "successful_recoveries.columns = ['Cohorte', 'Recuperaciones Exitosas']\n", + "\n", + "# Combinar los dos resultados en un dataframe\n", + "cohort_metrics = pd.merge(cohort_counts, successful_recoveries, on='Cohorte')\n", + "\n", + "# Calcular la tasa de recuperación exitosa\n", + "cohort_metrics['Tasa de Recuperación Exitosa'] = cohort_metrics['Recuperaciones Exitosas'] / cohort_metrics['Total Solicitudes']\n", + "\n", + "# Llenar valores nulos con 0 para cohortes sin recuperaciones exitosas\n", + "cohort_metrics['Recuperaciones Exitosas'].fillna(0, inplace=True)\n", + "cohort_metrics['Tasa de Recuperación Exitosa'].fillna(0, inplace=True)\n", + "cohort_metrics['Recuperaciones Exitosas'] = cohort_metrics['Recuperaciones Exitosas'].fillna(0)\n", + "cohort_metrics['Tasa de Recuperación Exitosa'] = cohort_metrics['Tasa de Recuperación Exitosa'].fillna(0)\n", + "\n", + "df_cohort_metrics = pd.DataFrame(cohort_metrics)\n", + "\n", + "# Mostrar los resultados\n", + "df_cohort_metrics\n" + ] + }, + { + "cell_type": "code", + "execution_count": 385, + "id": "c9b54b38-f287-4eeb-a64d-261976c23796", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " cohort total_solicitado total_reembolsado tasa_reembolso_promedio\n", + "0 2019-11 0.0 0.0 NaN\n", + "1 2019-12 0.0 0.0 NaN\n", + "2 2020-01 0.0 0.0 NaN\n", + "3 2020-02 0.0 0.0 NaN\n", + "4 2020-03 0.0 0.0 NaN\n", + "5 2020-04 5.0 5.0 1.0\n", + "6 2020-05 1285.0 1285.0 1.0\n", + "7 2020-06 8725.0 8725.0 1.0\n", + "8 2020-07 10395.0 10395.0 1.0\n", + "9 2020-08 17565.0 17565.0 1.0\n", + "10 2020-09 22935.0 22935.0 1.0\n", + "11 2020-10 43815.0 43815.0 1.0\n", + "12 2020-11 565.0 565.0 1.0\n" + ] + }, + { + "ename": "TypeError", + "evalue": "Invalid object type at position 0", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)", + "File \u001b[1;32mlib.pyx:2391\u001b[0m, in \u001b[0;36mpandas._libs.lib.maybe_convert_numeric\u001b[1;34m()\u001b[0m\n", + "\u001b[1;31mTypeError\u001b[0m: Invalid object type", + "\nDuring handling of the above exception, another exception occurred:\n", + "\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)", + "Cell \u001b[1;32mIn[385], line 24\u001b[0m\n\u001b[0;32m 19\u001b[0m \u001b[38;5;28mprint\u001b[39m(cohort_reimbursement)\n\u001b[0;32m 23\u001b[0m plt\u001b[38;5;241m.\u001b[39mfigure(figsize\u001b[38;5;241m=\u001b[39m(\u001b[38;5;241m12\u001b[39m, \u001b[38;5;241m6\u001b[39m))\n\u001b[1;32m---> 24\u001b[0m sns\u001b[38;5;241m.\u001b[39mlineplot(data\u001b[38;5;241m=\u001b[39mcohort_reimbursement, x\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mcohort\u001b[39m\u001b[38;5;124m'\u001b[39m, y\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtasa_reembolso_promedio\u001b[39m\u001b[38;5;124m'\u001b[39m, marker\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mo\u001b[39m\u001b[38;5;124m'\u001b[39m, color\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mpurple\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m 25\u001b[0m plt\u001b[38;5;241m.\u001b[39mtitle(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mTasa de Reembolso Promedio por Cohorte\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m 26\u001b[0m plt\u001b[38;5;241m.\u001b[39mxlabel(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mCohorte (Mes y Año)\u001b[39m\u001b[38;5;124m'\u001b[39m)\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\seaborn\\relational.py:515\u001b[0m, in \u001b[0;36mlineplot\u001b[1;34m(data, x, y, hue, size, style, units, weights, palette, hue_order, hue_norm, sizes, size_order, size_norm, dashes, markers, style_order, estimator, errorbar, n_boot, seed, orient, sort, err_style, err_kws, legend, ci, ax, **kwargs)\u001b[0m\n\u001b[0;32m 512\u001b[0m color \u001b[38;5;241m=\u001b[39m kwargs\u001b[38;5;241m.\u001b[39mpop(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcolor\u001b[39m\u001b[38;5;124m\"\u001b[39m, kwargs\u001b[38;5;241m.\u001b[39mpop(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mc\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m))\n\u001b[0;32m 513\u001b[0m kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcolor\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m _default_color(ax\u001b[38;5;241m.\u001b[39mplot, hue, color, kwargs)\n\u001b[1;32m--> 515\u001b[0m p\u001b[38;5;241m.\u001b[39mplot(ax, kwargs)\n\u001b[0;32m 516\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m ax\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\seaborn\\relational.py:276\u001b[0m, in \u001b[0;36m_LinePlotter.plot\u001b[1;34m(self, ax, kws)\u001b[0m\n\u001b[0;32m 268\u001b[0m \u001b[38;5;66;03m# TODO How to handle NA? We don't want NA to propagate through to the\u001b[39;00m\n\u001b[0;32m 269\u001b[0m \u001b[38;5;66;03m# estimate/CI when some values are present, but we would also like\u001b[39;00m\n\u001b[0;32m 270\u001b[0m \u001b[38;5;66;03m# matplotlib to show \"gaps\" in the line when all values are missing.\u001b[39;00m\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 273\u001b[0m \n\u001b[0;32m 274\u001b[0m \u001b[38;5;66;03m# Loop over the semantic subsets and add to the plot\u001b[39;00m\n\u001b[0;32m 275\u001b[0m grouping_vars \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhue\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msize\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstyle\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m--> 276\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m sub_vars, sub_data \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39miter_data(grouping_vars, from_comp_data\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m):\n\u001b[0;32m 278\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msort:\n\u001b[0;32m 279\u001b[0m sort_vars \u001b[38;5;241m=\u001b[39m [\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124munits\u001b[39m\u001b[38;5;124m\"\u001b[39m, orient, other]\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\seaborn\\_base.py:902\u001b[0m, in \u001b[0;36mVectorPlotter.iter_data\u001b[1;34m(self, grouping_vars, reverse, from_comp_data, by_facet, allow_empty, dropna)\u001b[0m\n\u001b[0;32m 899\u001b[0m grouping_vars \u001b[38;5;241m=\u001b[39m [var \u001b[38;5;28;01mfor\u001b[39;00m var \u001b[38;5;129;01min\u001b[39;00m grouping_vars \u001b[38;5;28;01mif\u001b[39;00m var \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mvariables]\n\u001b[0;32m 901\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m from_comp_data:\n\u001b[1;32m--> 902\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcomp_data\n\u001b[0;32m 903\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m 904\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mplot_data\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\seaborn\\_base.py:1000\u001b[0m, in \u001b[0;36mVectorPlotter.comp_data\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 995\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m var \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mvar_levels:\n\u001b[0;32m 996\u001b[0m \u001b[38;5;66;03m# TODO this should happen in some centralized location\u001b[39;00m\n\u001b[0;32m 997\u001b[0m \u001b[38;5;66;03m# it is similar to GH2419, but more complicated because\u001b[39;00m\n\u001b[0;32m 998\u001b[0m \u001b[38;5;66;03m# supporting `order` in categorical plots is tricky\u001b[39;00m\n\u001b[0;32m 999\u001b[0m orig \u001b[38;5;241m=\u001b[39m orig[orig\u001b[38;5;241m.\u001b[39misin(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mvar_levels[var])]\n\u001b[1;32m-> 1000\u001b[0m comp \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mto_numeric(converter\u001b[38;5;241m.\u001b[39mconvert_units(orig))\u001b[38;5;241m.\u001b[39mastype(\u001b[38;5;28mfloat\u001b[39m)\n\u001b[0;32m 1001\u001b[0m transform \u001b[38;5;241m=\u001b[39m converter\u001b[38;5;241m.\u001b[39mget_transform()\u001b[38;5;241m.\u001b[39mtransform\n\u001b[0;32m 1002\u001b[0m parts\u001b[38;5;241m.\u001b[39mappend(pd\u001b[38;5;241m.\u001b[39mSeries(transform(comp), orig\u001b[38;5;241m.\u001b[39mindex, name\u001b[38;5;241m=\u001b[39morig\u001b[38;5;241m.\u001b[39mname))\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\pandas\\core\\tools\\numeric.py:232\u001b[0m, in \u001b[0;36mto_numeric\u001b[1;34m(arg, errors, downcast, dtype_backend)\u001b[0m\n\u001b[0;32m 230\u001b[0m coerce_numeric \u001b[38;5;241m=\u001b[39m errors \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m (\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mignore\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mraise\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m 231\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 232\u001b[0m values, new_mask \u001b[38;5;241m=\u001b[39m lib\u001b[38;5;241m.\u001b[39mmaybe_convert_numeric( \u001b[38;5;66;03m# type: ignore[call-overload]\u001b[39;00m\n\u001b[0;32m 233\u001b[0m values,\n\u001b[0;32m 234\u001b[0m \u001b[38;5;28mset\u001b[39m(),\n\u001b[0;32m 235\u001b[0m coerce_numeric\u001b[38;5;241m=\u001b[39mcoerce_numeric,\n\u001b[0;32m 236\u001b[0m convert_to_masked_nullable\u001b[38;5;241m=\u001b[39mdtype_backend \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m lib\u001b[38;5;241m.\u001b[39mno_default\n\u001b[0;32m 237\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(values_dtype, StringDtype)\n\u001b[0;32m 238\u001b[0m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m values_dtype\u001b[38;5;241m.\u001b[39mstorage \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpyarrow_numpy\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m 239\u001b[0m )\n\u001b[0;32m 240\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mValueError\u001b[39;00m, \u001b[38;5;167;01mTypeError\u001b[39;00m):\n\u001b[0;32m 241\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m errors \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mraise\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n", + "File \u001b[1;32mlib.pyx:2433\u001b[0m, in \u001b[0;36mpandas._libs.lib.maybe_convert_numeric\u001b[1;34m()\u001b[0m\n", + "\u001b[1;31mTypeError\u001b[0m: Invalid object type at position 0" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Crear una columna binaria que indique si la solicitud fue reembolsada\n", + "merged_df2['reembolsado'] = ~merged_df2['reimbursement_date'].isnull()\n", + "\n", + "# Asumimos que el monto total reembolsado es igual a `total_amount` para solicitudes con reembolso\n", + "merged_df2['monto_reembolsado'] = merged_df2['total_amount'] * merged_df2['reembolsado']\n", + "\n", + "\n", + "\n", + "# Calcular la suma del monto reembolsado y el total solicitado por cohorte\n", + "cohort_reimbursement = merged_df2.groupby('cohort').agg(\n", + " total_solicitado=('total_amount', 'sum'),\n", + " total_reembolsado=('monto_reembolsado', 'sum')\n", + ").reset_index()\n", + "\n", + "# Calcular la tasa de reembolso promedio\n", + "cohort_reimbursement['tasa_reembolso_promedio'] = cohort_reimbursement['total_reembolsado'] / cohort_reimbursement['total_solicitado']\n", + "\n", + "# Mostrar los resultados\n", + "print(cohort_reimbursement)" + ] + }, + { + "cell_type": "code", + "execution_count": 348, + "id": "3c5f9ee8-735a-47e7-af7f-fa0172e07637", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " cohort total_solicitado total_reembolsado tasa_reembolso_promedio\n", + "5 NaT 5.0 5.0 1.0\n", + "6 NaT 1285.0 1285.0 1.0\n", + "7 NaT 8725.0 8725.0 1.0\n", + "8 NaT 10395.0 10395.0 1.0\n", + "9 NaT 17565.0 17565.0 1.0\n", + "10 NaT 22935.0 22935.0 1.0\n", + "11 NaT 43815.0 43815.0 1.0\n", + "12 NaT 565.0 565.0 1.0\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "import seaborn as sns\n", + "import matplotlib.pyplot as plt\n", + "import pandas as pd\n", + "\n", + "# Crear una columna binaria que indique si la solicitud fue reembolsada\n", + "merged_df2['reembolsado'] = ~merged_df2['reimbursement_date'].isnull()\n", + "\n", + "# Asumimos que el monto total reembolsado es igual a `total_amount` para solicitudes con reembolso\n", + "merged_df2['monto_reembolsado'] = merged_df2['total_amount'] * merged_df2['reembolsado']\n", + "\n", + "# Calcular la suma del monto reembolsado y el total solicitado por cohorte\n", + "cohort_reimbursement = merged_df2.groupby('cohort').agg(\n", + " total_solicitado=('total_amount', 'sum'),\n", + " total_reembolsado=('monto_reembolsado', 'sum')\n", + ").reset_index()\n", + "\n", + "# Calcular la tasa de reembolso promedio\n", + "cohort_reimbursement['tasa_reembolso_promedio'] = cohort_reimbursement['total_reembolsado'] / cohort_reimbursement['total_solicitado']\n", + "\n", + "# Verifica y convierte tipos de datos si es necesario\n", + "cohort_reimbursement['cohort'] = pd.to_datetime(cohort_reimbursement['cohort'], errors='coerce')\n", + "cohort_reimbursement['tasa_reembolso_promedio'] = pd.to_numeric(cohort_reimbursement['tasa_reembolso_promedio'], errors='coerce')\n", + "\n", + "# Eliminar filas con valores nulos en 'tasa_reembolso_promedio'\n", + "cohort_reimbursement = cohort_reimbursement.dropna(subset=['tasa_reembolso_promedio'])\n", + "\n", + "# Mostrar los resultados\n", + "print(cohort_reimbursement)\n", + "\n", + "# Graficar\n", + "plt.figure(figsize=(12, 6))\n", + "sns.lineplot(data=cohort_reimbursement, x='cohort', y='tasa_reembolso_promedio', marker='o', color='purple')\n", + "plt.title('Tasa de Reembolso Promedio por Cohorte')\n", + "plt.xlabel('Cohorte (Mes y Año)')\n", + "plt.ylabel('Tasa de Reembolso Promedio')\n", + "plt.xticks(rotation=45)\n", + "plt.ylim(0, 1)\n", + "plt.show()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 350, + "id": "86457065-0242-4727-9da6-5ff9c2a472ff", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Visualización de resultados\n", + "\n", + "import matplotlib.pyplot as plt\n", + "\n", + "\n", + "plt.figure(figsize=(12, 6))\n", + "sns.barplot(data=cohort_revenue, x='Cohorte', y='Ingresos Totales', color='blue')\n", + "plt.title('Ingresos Totales por Cohorte')\n", + "plt.xlabel('Cohorte (Mes y Año)')\n", + "plt.ylabel('Ingresos Totales')\n", + "plt.xticks(rotation=45)\n", + "plt.show()\n", + "\n", + "plt.figure(figsize=(12, 6))\n", + "sns.barplot(data=cohort_metrics, x='Cohorte', y='Tasa de Recuperación Exitosa', color='green')\n", + "plt.title('Tasa de Recuperación Exitosa por Cohorte')\n", + "plt.xlabel('Cohorte (Mes y Año)')\n", + "plt.ylabel('Tasa de Recuperación Exitosa')\n", + "plt.xticks(rotation=45)\n", + "plt.show()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 352, + "id": "099099eb-f333-4f78-b678-4ff55423cc2b", + "metadata": {}, + "outputs": [], + "source": [ + "# Puesto que todas las " + ] + }, + { + "cell_type": "code", + "execution_count": 354, + "id": "4df8bdeb-2513-469e-b25d-af7382c428c7", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idamountstatuscreated_atupdated_atuser_idmoderated_atdeleted_account_idreimbursement_datecash_request_received_datemoney_back_datetransfer_typesend_atrecovery_statusreco_creationreco_last_update
05100.0rejected2019-12-10 19:05:21.596873+002019-12-11 16:47:42.40783+00804.02019-12-11 16:47:42.405646+00NaN2020-01-09 19:05:21.596363+00NaNNaNregularNaNNaNNaNNaN
170100.0rejected2019-12-10 19:50:12.34778+002019-12-11 14:24:22.900054+00231.02019-12-11 14:24:22.897988+00NaN2020-01-09 19:50:12.34778+00NaNNaNregularNaNNaNNaNNaN
27100.0rejected2019-12-10 19:13:35.82546+002019-12-11 09:46:59.779773+00191.02019-12-11 09:46:59.777728+00NaN2020-01-09 19:13:35.825041+00NaNNaNregularNaNNaNNaNNaN
31099.0rejected2019-12-10 19:16:10.880172+002019-12-18 14:26:18.136163+00761.02019-12-18 14:26:18.128407+00NaN2020-01-09 19:16:10.879606+00NaNNaNregularNaNNaNNaNNaN
41594100.0rejected2020-05-06 09:59:38.877376+002020-05-07 09:21:55.34008+007686.02020-05-07 09:21:55.320193+00NaN2020-06-05 22:00:00+00NaNNaNregularNaNNaNNaNNaN
...................................................
2396520616100.0money_back2020-10-12 13:54:11.686225+002021-02-06 20:17:49.292493+0013681.0NaNNaN2021-02-06 11:00:00+002020-10-132021-02-06 20:17:49.257521+00instant2020-10-12 13:54:24.352856+00NaNNaNNaN
239662524350.0money_back2020-10-27 14:41:25.73491+002020-12-18 13:15:40.843946+00NaNNaN30367.02020-11-03 22:00:00+002020-10-282020-12-01 13:26:53.787672+00instant2020-10-27 14:41:57.901946+00completed2020-11-12 23:20:41.928788+002020-12-01 13:26:53.815504+00
2396722357100.0money_back2020-10-20 07:58:04.006937+002021-02-05 12:19:30.656816+0082122.0NaNNaN2021-02-05 11:00:00+002020-10-212021-02-05 12:19:30.626289+00instant2020-10-20 07:58:14.171553+00NaNNaNNaN
2396820256100.0money_back2020-10-10 05:40:55.700422+002021-02-05 13:14:19.707627+0064517.0NaNNaN2021-02-05 11:00:00+002020-10-122021-02-05 13:14:19.689906+00instant2020-10-10 05:41:23.368363+00NaNNaNNaN
2396919886100.0direct_debit_sent2020-10-08 14:16:52.155661+002021-01-05 15:45:52.645536+0044867.0NaNNaN2021-02-05 11:00:00+002020-10-10NaNinstant2020-10-08 14:17:04.526139+00NaNNaNNaN
\n", + "

23970 rows × 16 columns

\n", + "
" + ], + "text/plain": [ + " id amount status created_at \\\n", + "0 5 100.0 rejected 2019-12-10 19:05:21.596873+00 \n", + "1 70 100.0 rejected 2019-12-10 19:50:12.34778+00 \n", + "2 7 100.0 rejected 2019-12-10 19:13:35.82546+00 \n", + "3 10 99.0 rejected 2019-12-10 19:16:10.880172+00 \n", + "4 1594 100.0 rejected 2020-05-06 09:59:38.877376+00 \n", + "... ... ... ... ... \n", + "23965 20616 100.0 money_back 2020-10-12 13:54:11.686225+00 \n", + "23966 25243 50.0 money_back 2020-10-27 14:41:25.73491+00 \n", + "23967 22357 100.0 money_back 2020-10-20 07:58:04.006937+00 \n", + "23968 20256 100.0 money_back 2020-10-10 05:40:55.700422+00 \n", + "23969 19886 100.0 direct_debit_sent 2020-10-08 14:16:52.155661+00 \n", + "\n", + " updated_at user_id moderated_at \\\n", + "0 2019-12-11 16:47:42.40783+00 804.0 2019-12-11 16:47:42.405646+00 \n", + "1 2019-12-11 14:24:22.900054+00 231.0 2019-12-11 14:24:22.897988+00 \n", + "2 2019-12-11 09:46:59.779773+00 191.0 2019-12-11 09:46:59.777728+00 \n", + "3 2019-12-18 14:26:18.136163+00 761.0 2019-12-18 14:26:18.128407+00 \n", + "4 2020-05-07 09:21:55.34008+00 7686.0 2020-05-07 09:21:55.320193+00 \n", + "... ... ... ... \n", + "23965 2021-02-06 20:17:49.292493+00 13681.0 NaN \n", + "23966 2020-12-18 13:15:40.843946+00 NaN NaN \n", + "23967 2021-02-05 12:19:30.656816+00 82122.0 NaN \n", + "23968 2021-02-05 13:14:19.707627+00 64517.0 NaN \n", + "23969 2021-01-05 15:45:52.645536+00 44867.0 NaN \n", + "\n", + " deleted_account_id reimbursement_date \\\n", + "0 NaN 2020-01-09 19:05:21.596363+00 \n", + "1 NaN 2020-01-09 19:50:12.34778+00 \n", + "2 NaN 2020-01-09 19:13:35.825041+00 \n", + "3 NaN 2020-01-09 19:16:10.879606+00 \n", + "4 NaN 2020-06-05 22:00:00+00 \n", + "... ... ... \n", + "23965 NaN 2021-02-06 11:00:00+00 \n", + "23966 30367.0 2020-11-03 22:00:00+00 \n", + "23967 NaN 2021-02-05 11:00:00+00 \n", + "23968 NaN 2021-02-05 11:00:00+00 \n", + "23969 NaN 2021-02-05 11:00:00+00 \n", + "\n", + " cash_request_received_date money_back_date transfer_type \\\n", + "0 NaN NaN regular \n", + "1 NaN NaN regular \n", + "2 NaN NaN regular \n", + "3 NaN NaN regular \n", + "4 NaN NaN regular \n", + "... ... ... ... \n", + "23965 2020-10-13 2021-02-06 20:17:49.257521+00 instant \n", + "23966 2020-10-28 2020-12-01 13:26:53.787672+00 instant \n", + "23967 2020-10-21 2021-02-05 12:19:30.626289+00 instant \n", + "23968 2020-10-12 2021-02-05 13:14:19.689906+00 instant \n", + "23969 2020-10-10 NaN instant \n", + "\n", + " send_at recovery_status \\\n", + "0 NaN NaN \n", + "1 NaN NaN \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "... ... ... \n", + "23965 2020-10-12 13:54:24.352856+00 NaN \n", + "23966 2020-10-27 14:41:57.901946+00 completed \n", + "23967 2020-10-20 07:58:14.171553+00 NaN \n", + "23968 2020-10-10 05:41:23.368363+00 NaN \n", + "23969 2020-10-08 14:17:04.526139+00 NaN \n", + "\n", + " reco_creation reco_last_update \n", + "0 NaN NaN \n", + "1 NaN NaN \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "... ... ... \n", + "23965 NaN NaN \n", + "23966 2020-11-12 23:20:41.928788+00 2020-12-01 13:26:53.815504+00 \n", + "23967 NaN NaN \n", + "23968 NaN NaN \n", + "23969 NaN NaN \n", + "\n", + "[23970 rows x 16 columns]" + ] + }, + "execution_count": 354, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df1" + ] + }, + { + "cell_type": "code", + "execution_count": 356, + "id": "da10a2b4-4f88-4777-9584-745ad4581b0e", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idcash_request_idtypestatuscategorytotal_amountreasoncreated_atupdated_atpaid_atfrom_dateto_datecharge_moment
0653714941.0instant_paymentrejectedNaN5.0Instant Payment Cash Request 149412020-09-07 10:47:27.42315+002020-10-13 14:25:09.396112+002020-12-17 14:50:07.47011+00NaNNaNafter
1696111714.0incidentacceptedrejected_direct_debit5.0rejected direct debit2020-09-09 20:51:17.998653+002020-10-13 14:25:15.537063+002020-12-08 17:13:10.45908+00NaNNaNafter
21629623371.0instant_paymentacceptedNaN5.0Instant Payment Cash Request 233712020-10-23 10:10:58.352972+002020-10-23 10:10:58.352994+002020-11-04 19:34:37.43291+00NaNNaNafter
32077526772.0instant_paymentacceptedNaN5.0Instant Payment Cash Request 267722020-10-31 15:46:53.643958+002020-10-31 15:46:53.643982+002020-11-19 05:09:22.500223+00NaNNaNafter
41124219350.0instant_paymentacceptedNaN5.0Instant Payment Cash Request 193502020-10-06 08:20:17.170432+002020-10-13 14:25:03.267983+002020-11-02 14:45:20.355598+00NaNNaNafter
..........................................
210561237220262.0instant_paymentrejectedNaN5.0Instant Payment Cash Request 202622020-10-10 06:42:22.822743+002020-10-13 14:25:04.18049+002020-11-17 05:14:00.080854+00NaNNaNafter
210572076826764.0instant_paymentrejectedNaN5.0Instant Payment Cash Request 267642020-10-31 15:24:18.680694+002020-10-31 15:24:18.680715+002020-12-16 07:10:54.697639+00NaNNaNafter
210581877925331.0instant_paymentrejectedNaN5.0Instant Payment Cash Request 253312020-10-27 17:28:51.749177+002020-10-27 17:28:51.7492+002020-11-18 04:35:42.915511+00NaNNaNafter
210591654223628.0instant_paymentrejectedNaN5.0Instant Payment Cash Request 236282020-10-23 16:27:52.047457+002020-10-23 16:27:52.047486+002020-12-18 05:18:01.465317+00NaNNaNafter
210601330120982.0instant_paymentacceptedNaN5.0Instant Payment Cash Request 209822020-10-14 07:12:43.958192+002020-10-14 07:12:43.958219+002021-02-12 13:02:46.95022+00NaNNaNafter
\n", + "

21061 rows × 13 columns

\n", + "
" + ], + "text/plain": [ + " id cash_request_id type status \\\n", + "0 6537 14941.0 instant_payment rejected \n", + "1 6961 11714.0 incident accepted \n", + "2 16296 23371.0 instant_payment accepted \n", + "3 20775 26772.0 instant_payment accepted \n", + "4 11242 19350.0 instant_payment accepted \n", + "... ... ... ... ... \n", + "21056 12372 20262.0 instant_payment rejected \n", + "21057 20768 26764.0 instant_payment rejected \n", + "21058 18779 25331.0 instant_payment rejected \n", + "21059 16542 23628.0 instant_payment rejected \n", + "21060 13301 20982.0 instant_payment accepted \n", + "\n", + " category total_amount \\\n", + "0 NaN 5.0 \n", + "1 rejected_direct_debit 5.0 \n", + "2 NaN 5.0 \n", + "3 NaN 5.0 \n", + "4 NaN 5.0 \n", + "... ... ... \n", + "21056 NaN 5.0 \n", + "21057 NaN 5.0 \n", + "21058 NaN 5.0 \n", + "21059 NaN 5.0 \n", + "21060 NaN 5.0 \n", + "\n", + " reason created_at \\\n", + "0 Instant Payment Cash Request 14941 2020-09-07 10:47:27.42315+00 \n", + "1 rejected direct debit 2020-09-09 20:51:17.998653+00 \n", + "2 Instant Payment Cash Request 23371 2020-10-23 10:10:58.352972+00 \n", + "3 Instant Payment Cash Request 26772 2020-10-31 15:46:53.643958+00 \n", + "4 Instant Payment Cash Request 19350 2020-10-06 08:20:17.170432+00 \n", + "... ... ... \n", + "21056 Instant Payment Cash Request 20262 2020-10-10 06:42:22.822743+00 \n", + "21057 Instant Payment Cash Request 26764 2020-10-31 15:24:18.680694+00 \n", + "21058 Instant Payment Cash Request 25331 2020-10-27 17:28:51.749177+00 \n", + "21059 Instant Payment Cash Request 23628 2020-10-23 16:27:52.047457+00 \n", + "21060 Instant Payment Cash Request 20982 2020-10-14 07:12:43.958192+00 \n", + "\n", + " updated_at paid_at from_date \\\n", + "0 2020-10-13 14:25:09.396112+00 2020-12-17 14:50:07.47011+00 NaN \n", + "1 2020-10-13 14:25:15.537063+00 2020-12-08 17:13:10.45908+00 NaN \n", + "2 2020-10-23 10:10:58.352994+00 2020-11-04 19:34:37.43291+00 NaN \n", + "3 2020-10-31 15:46:53.643982+00 2020-11-19 05:09:22.500223+00 NaN \n", + "4 2020-10-13 14:25:03.267983+00 2020-11-02 14:45:20.355598+00 NaN \n", + "... ... ... ... \n", + "21056 2020-10-13 14:25:04.18049+00 2020-11-17 05:14:00.080854+00 NaN \n", + "21057 2020-10-31 15:24:18.680715+00 2020-12-16 07:10:54.697639+00 NaN \n", + "21058 2020-10-27 17:28:51.7492+00 2020-11-18 04:35:42.915511+00 NaN \n", + "21059 2020-10-23 16:27:52.047486+00 2020-12-18 05:18:01.465317+00 NaN \n", + "21060 2020-10-14 07:12:43.958219+00 2021-02-12 13:02:46.95022+00 NaN \n", + "\n", + " to_date charge_moment \n", + "0 NaN after \n", + "1 NaN after \n", + "2 NaN after \n", + "3 NaN after \n", + "4 NaN after \n", + "... ... ... \n", + "21056 NaN after \n", + "21057 NaN after \n", + "21058 NaN after \n", + "21059 NaN after \n", + "21060 NaN after \n", + "\n", + "[21061 rows x 13 columns]" + ] + }, + "execution_count": 356, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df2" + ] + }, + { + "cell_type": "code", + "execution_count": 358, + "id": "f41eed0d-5916-410a-b048-75af28accc5f", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
id_xamountstatus_xcreated_at_xupdated_at_xuser_idmoderated_atdeleted_account_idreimbursement_datecash_request_received_date...status_ycategorytotal_amountreasoncreated_at_yupdated_at_ypaid_atfrom_dateto_datecharge_moment
05100.0rejected2019-12-10 19:05:21.596873+002019-12-11 16:47:42.40783+00804.02019-12-11 16:47:42.405646+00NaN2020-01-09 19:05:21.596363+00NaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
170100.0rejected2019-12-10 19:50:12.34778+002019-12-11 14:24:22.900054+00231.02019-12-11 14:24:22.897988+00NaN2020-01-09 19:50:12.34778+00NaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
27100.0rejected2019-12-10 19:13:35.82546+002019-12-11 09:46:59.779773+00191.02019-12-11 09:46:59.777728+00NaN2020-01-09 19:13:35.825041+00NaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
31099.0rejected2019-12-10 19:16:10.880172+002019-12-18 14:26:18.136163+00761.02019-12-18 14:26:18.128407+00NaN2020-01-09 19:16:10.879606+00NaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
41594100.0rejected2020-05-06 09:59:38.877376+002020-05-07 09:21:55.34008+007686.02020-05-07 09:21:55.320193+00NaN2020-06-05 22:00:00+00NaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
..................................................................
3208922357100.0money_back2020-10-20 07:58:04.006937+002021-02-05 12:19:30.656816+0082122.0NaNNaN2021-02-05 11:00:00+002020-10-21...acceptedNaN5.0Instant Payment Cash Request 223572020-10-20 07:58:19.637461+002020-10-20 07:58:19.637491+002021-02-05 12:19:30.685779+00NaNNaNafter
3209020256100.0money_back2020-10-10 05:40:55.700422+002021-02-05 13:14:19.707627+0064517.0NaNNaN2021-02-05 11:00:00+002020-10-12...acceptedNaN5.0Postpone Cash Request 202562020-10-30 17:08:16.906449+002020-10-30 17:08:21.967966+002020-10-30 17:08:21.416796+002020-11-06 11:00:00+002020-12-07 11:00:00+00before
3209120256100.0money_back2020-10-10 05:40:55.700422+002021-02-05 13:14:19.707627+0064517.0NaNNaN2021-02-05 11:00:00+002020-10-12...acceptedNaN5.0Instant Payment Cash Request 202562020-10-10 05:42:11.679401+002020-10-13 14:25:03.460352+002021-02-05 13:14:19.731397+00NaNNaNafter
3209219886100.0direct_debit_sent2020-10-08 14:16:52.155661+002021-01-05 15:45:52.645536+0044867.0NaNNaN2021-02-05 11:00:00+002020-10-10...acceptedNaN5.0Postpone Cash Request 198862020-10-10 21:22:00.083739+002020-10-13 14:25:18.501716+002020-10-10 21:22:04.456828+002020-11-06 22:00:00+002020-12-06 11:00:00+00before
3209319886100.0direct_debit_sent2020-10-08 14:16:52.155661+002021-01-05 15:45:52.645536+0044867.0NaNNaN2021-02-05 11:00:00+002020-10-10...acceptedNaN5.0Instant Payment Cash Request 198862020-10-08 14:17:09.126909+002020-10-13 14:25:16.470702+002021-02-11 04:24:07.529815+00NaNNaNafter
\n", + "

32094 rows × 29 columns

\n", + "
" + ], + "text/plain": [ + " id_x amount status_x created_at_x \\\n", + "0 5 100.0 rejected 2019-12-10 19:05:21.596873+00 \n", + "1 70 100.0 rejected 2019-12-10 19:50:12.34778+00 \n", + "2 7 100.0 rejected 2019-12-10 19:13:35.82546+00 \n", + "3 10 99.0 rejected 2019-12-10 19:16:10.880172+00 \n", + "4 1594 100.0 rejected 2020-05-06 09:59:38.877376+00 \n", + "... ... ... ... ... \n", + "32089 22357 100.0 money_back 2020-10-20 07:58:04.006937+00 \n", + "32090 20256 100.0 money_back 2020-10-10 05:40:55.700422+00 \n", + "32091 20256 100.0 money_back 2020-10-10 05:40:55.700422+00 \n", + "32092 19886 100.0 direct_debit_sent 2020-10-08 14:16:52.155661+00 \n", + "32093 19886 100.0 direct_debit_sent 2020-10-08 14:16:52.155661+00 \n", + "\n", + " updated_at_x user_id moderated_at \\\n", + "0 2019-12-11 16:47:42.40783+00 804.0 2019-12-11 16:47:42.405646+00 \n", + "1 2019-12-11 14:24:22.900054+00 231.0 2019-12-11 14:24:22.897988+00 \n", + "2 2019-12-11 09:46:59.779773+00 191.0 2019-12-11 09:46:59.777728+00 \n", + "3 2019-12-18 14:26:18.136163+00 761.0 2019-12-18 14:26:18.128407+00 \n", + "4 2020-05-07 09:21:55.34008+00 7686.0 2020-05-07 09:21:55.320193+00 \n", + "... ... ... ... \n", + "32089 2021-02-05 12:19:30.656816+00 82122.0 NaN \n", + "32090 2021-02-05 13:14:19.707627+00 64517.0 NaN \n", + "32091 2021-02-05 13:14:19.707627+00 64517.0 NaN \n", + "32092 2021-01-05 15:45:52.645536+00 44867.0 NaN \n", + "32093 2021-01-05 15:45:52.645536+00 44867.0 NaN \n", + "\n", + " deleted_account_id reimbursement_date \\\n", + "0 NaN 2020-01-09 19:05:21.596363+00 \n", + "1 NaN 2020-01-09 19:50:12.34778+00 \n", + "2 NaN 2020-01-09 19:13:35.825041+00 \n", + "3 NaN 2020-01-09 19:16:10.879606+00 \n", + "4 NaN 2020-06-05 22:00:00+00 \n", + "... ... ... \n", + "32089 NaN 2021-02-05 11:00:00+00 \n", + "32090 NaN 2021-02-05 11:00:00+00 \n", + "32091 NaN 2021-02-05 11:00:00+00 \n", + "32092 NaN 2021-02-05 11:00:00+00 \n", + "32093 NaN 2021-02-05 11:00:00+00 \n", + "\n", + " cash_request_received_date ... status_y category total_amount \\\n", + "0 NaN ... NaN NaN NaN \n", + "1 NaN ... NaN NaN NaN \n", + "2 NaN ... NaN NaN NaN \n", + "3 NaN ... NaN NaN NaN \n", + "4 NaN ... NaN NaN NaN \n", + "... ... ... ... ... ... \n", + "32089 2020-10-21 ... accepted NaN 5.0 \n", + "32090 2020-10-12 ... accepted NaN 5.0 \n", + "32091 2020-10-12 ... accepted NaN 5.0 \n", + "32092 2020-10-10 ... accepted NaN 5.0 \n", + "32093 2020-10-10 ... accepted NaN 5.0 \n", + "\n", + " reason created_at_y \\\n", + "0 NaN NaN \n", + "1 NaN NaN \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "... ... ... \n", + "32089 Instant Payment Cash Request 22357 2020-10-20 07:58:19.637461+00 \n", + "32090 Postpone Cash Request 20256 2020-10-30 17:08:16.906449+00 \n", + "32091 Instant Payment Cash Request 20256 2020-10-10 05:42:11.679401+00 \n", + "32092 Postpone Cash Request 19886 2020-10-10 21:22:00.083739+00 \n", + "32093 Instant Payment Cash Request 19886 2020-10-08 14:17:09.126909+00 \n", + "\n", + " updated_at_y paid_at \\\n", + "0 NaN NaN \n", + "1 NaN NaN \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "... ... ... \n", + "32089 2020-10-20 07:58:19.637491+00 2021-02-05 12:19:30.685779+00 \n", + "32090 2020-10-30 17:08:21.967966+00 2020-10-30 17:08:21.416796+00 \n", + "32091 2020-10-13 14:25:03.460352+00 2021-02-05 13:14:19.731397+00 \n", + "32092 2020-10-13 14:25:18.501716+00 2020-10-10 21:22:04.456828+00 \n", + "32093 2020-10-13 14:25:16.470702+00 2021-02-11 04:24:07.529815+00 \n", + "\n", + " from_date to_date charge_moment \n", + "0 NaN NaN NaN \n", + "1 NaN NaN NaN \n", + "2 NaN NaN NaN \n", + "3 NaN NaN NaN \n", + "4 NaN NaN NaN \n", + "... ... ... ... \n", + "32089 NaN NaN after \n", + "32090 2020-11-06 11:00:00+00 2020-12-07 11:00:00+00 before \n", + "32091 NaN NaN after \n", + "32092 2020-11-06 22:00:00+00 2020-12-06 11:00:00+00 before \n", + "32093 NaN NaN after \n", + "\n", + "[32094 rows x 29 columns]" + ] + }, + "execution_count": 358, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "merged_df" + ] + }, + { + "cell_type": "code", + "execution_count": 360, + "id": "2037d717-919a-4601-8d44-4dbe0a37b6a4", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
id_xcreated_at_xtotal_amountrecovery_statusreimbursement_datecohortreembolsadomonto_reembolsado
052019-12-10 19:05:21.596873+00:00NaNNaN2020-01-09 19:05:21.596363+002019-12TrueNaN
1702019-12-10 19:50:12.347780+00:00NaNNaN2020-01-09 19:50:12.34778+002019-12TrueNaN
272019-12-10 19:13:35.825460+00:00NaNNaN2020-01-09 19:13:35.825041+002019-12TrueNaN
3102019-12-10 19:16:10.880172+00:00NaNNaN2020-01-09 19:16:10.879606+002019-12TrueNaN
415942020-05-06 09:59:38.877376+00:00NaNNaN2020-06-05 22:00:00+002020-05TrueNaN
...........................
32089223572020-10-20 07:58:04.006937+00:005.0NaN2021-02-05 11:00:00+002020-10True5.0
32090202562020-10-10 05:40:55.700422+00:005.0NaN2021-02-05 11:00:00+002020-10True5.0
32091202562020-10-10 05:40:55.700422+00:005.0NaN2021-02-05 11:00:00+002020-10True5.0
32092198862020-10-08 14:16:52.155661+00:005.0NaN2021-02-05 11:00:00+002020-10True5.0
32093198862020-10-08 14:16:52.155661+00:005.0NaN2021-02-05 11:00:00+002020-10True5.0
\n", + "

32094 rows × 8 columns

\n", + "
" + ], + "text/plain": [ + " id_x created_at_x total_amount recovery_status \\\n", + "0 5 2019-12-10 19:05:21.596873+00:00 NaN NaN \n", + "1 70 2019-12-10 19:50:12.347780+00:00 NaN NaN \n", + "2 7 2019-12-10 19:13:35.825460+00:00 NaN NaN \n", + "3 10 2019-12-10 19:16:10.880172+00:00 NaN NaN \n", + "4 1594 2020-05-06 09:59:38.877376+00:00 NaN NaN \n", + "... ... ... ... ... \n", + "32089 22357 2020-10-20 07:58:04.006937+00:00 5.0 NaN \n", + "32090 20256 2020-10-10 05:40:55.700422+00:00 5.0 NaN \n", + "32091 20256 2020-10-10 05:40:55.700422+00:00 5.0 NaN \n", + "32092 19886 2020-10-08 14:16:52.155661+00:00 5.0 NaN \n", + "32093 19886 2020-10-08 14:16:52.155661+00:00 5.0 NaN \n", + "\n", + " reimbursement_date cohort reembolsado monto_reembolsado \n", + "0 2020-01-09 19:05:21.596363+00 2019-12 True NaN \n", + "1 2020-01-09 19:50:12.34778+00 2019-12 True NaN \n", + "2 2020-01-09 19:13:35.825041+00 2019-12 True NaN \n", + "3 2020-01-09 19:16:10.879606+00 2019-12 True NaN \n", + "4 2020-06-05 22:00:00+00 2020-05 True NaN \n", + "... ... ... ... ... \n", + "32089 2021-02-05 11:00:00+00 2020-10 True 5.0 \n", + "32090 2021-02-05 11:00:00+00 2020-10 True 5.0 \n", + "32091 2021-02-05 11:00:00+00 2020-10 True 5.0 \n", + "32092 2021-02-05 11:00:00+00 2020-10 True 5.0 \n", + "32093 2021-02-05 11:00:00+00 2020-10 True 5.0 \n", + "\n", + "[32094 rows x 8 columns]" + ] + }, + "execution_count": 360, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "merged_df2" + ] + }, + { + "cell_type": "code", + "execution_count": 362, + "id": "0a6faf49-b336-478b-8d83-58df39a3250d", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
id_xcreated_at_xtotal_amountrecovery_statusreimbursement_datecohortreembolsadomonto_reembolsadoaprobada
052019-12-10 19:05:21.596873+00:00NaNNaN2020-01-09 19:05:21.596363+002019-12TrueNaNFalse
1702019-12-10 19:50:12.347780+00:00NaNNaN2020-01-09 19:50:12.34778+002019-12TrueNaNFalse
272019-12-10 19:13:35.825460+00:00NaNNaN2020-01-09 19:13:35.825041+002019-12TrueNaNFalse
3102019-12-10 19:16:10.880172+00:00NaNNaN2020-01-09 19:16:10.879606+002019-12TrueNaNFalse
415942020-05-06 09:59:38.877376+00:00NaNNaN2020-06-05 22:00:00+002020-05TrueNaNFalse
..............................
32089223572020-10-20 07:58:04.006937+00:005.0NaN2021-02-05 11:00:00+002020-10True5.0False
32090202562020-10-10 05:40:55.700422+00:005.0NaN2021-02-05 11:00:00+002020-10True5.0False
32091202562020-10-10 05:40:55.700422+00:005.0NaN2021-02-05 11:00:00+002020-10True5.0False
32092198862020-10-08 14:16:52.155661+00:005.0NaN2021-02-05 11:00:00+002020-10True5.0False
32093198862020-10-08 14:16:52.155661+00:005.0NaN2021-02-05 11:00:00+002020-10True5.0False
\n", + "

32094 rows × 9 columns

\n", + "
" + ], + "text/plain": [ + " id_x created_at_x total_amount recovery_status \\\n", + "0 5 2019-12-10 19:05:21.596873+00:00 NaN NaN \n", + "1 70 2019-12-10 19:50:12.347780+00:00 NaN NaN \n", + "2 7 2019-12-10 19:13:35.825460+00:00 NaN NaN \n", + "3 10 2019-12-10 19:16:10.880172+00:00 NaN NaN \n", + "4 1594 2020-05-06 09:59:38.877376+00:00 NaN NaN \n", + "... ... ... ... ... \n", + "32089 22357 2020-10-20 07:58:04.006937+00:00 5.0 NaN \n", + "32090 20256 2020-10-10 05:40:55.700422+00:00 5.0 NaN \n", + "32091 20256 2020-10-10 05:40:55.700422+00:00 5.0 NaN \n", + "32092 19886 2020-10-08 14:16:52.155661+00:00 5.0 NaN \n", + "32093 19886 2020-10-08 14:16:52.155661+00:00 5.0 NaN \n", + "\n", + " reimbursement_date cohort reembolsado monto_reembolsado \\\n", + "0 2020-01-09 19:05:21.596363+00 2019-12 True NaN \n", + "1 2020-01-09 19:50:12.34778+00 2019-12 True NaN \n", + "2 2020-01-09 19:13:35.825041+00 2019-12 True NaN \n", + "3 2020-01-09 19:16:10.879606+00 2019-12 True NaN \n", + "4 2020-06-05 22:00:00+00 2020-05 True NaN \n", + "... ... ... ... ... \n", + "32089 2021-02-05 11:00:00+00 2020-10 True 5.0 \n", + "32090 2021-02-05 11:00:00+00 2020-10 True 5.0 \n", + "32091 2021-02-05 11:00:00+00 2020-10 True 5.0 \n", + "32092 2021-02-05 11:00:00+00 2020-10 True 5.0 \n", + "32093 2021-02-05 11:00:00+00 2020-10 True 5.0 \n", + "\n", + " aprobada \n", + "0 False \n", + "1 False \n", + "2 False \n", + "3 False \n", + "4 False \n", + "... ... \n", + "32089 False \n", + "32090 False \n", + "32091 False \n", + "32092 False \n", + "32093 False \n", + "\n", + "[32094 rows x 9 columns]" + ] + }, + "execution_count": 362, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "merged_df2_clean" + ] + }, + { + "cell_type": "code", + "execution_count": 364, + "id": "e6bcb820-75f0-4c90-8423-7bfdd347edf6", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
id_xamountcreated_at_xupdated_at_xuser_idmoderated_atdeleted_account_idreimbursement_datecash_request_received_datemoney_back_date...status_ycategorytotal_amountreasoncreated_at_yupdated_at_ypaid_atfrom_dateto_datecharge_moment
status_x
active228463013825.02020-07-01 09:30:03.14541+002020-07-01 09:30:0...2020-08-11 22:27:58.240406+002020-08-11 22:27:...4929215.02020-07-01 16:44:53.070844+002020-07-01 16:44:...0.02020-08-03 22:00:00+002020-08-03 22:00:00+0020...2020-07-032020-07-032020-07-032020-07-032020-0...2020-06-11 22:37:13.182826+002020-08-06 22:00:......cancelledcancelledcancelledcancelledcancelledr...month_delay_on_paymentrejected_direct_debitmon...775.0Postpone Cash Request 6098Postpone Cash Reques...2020-08-13 10:58:39.63422+002020-08-13 10:58:5...2020-10-13 14:25:16.660127+002020-10-13 14:25:...2020-06-25 23:41:23.810387+002020-07-12 04:34:...2020-08-03 22:00:00+002020-08-03 22:00:00+0020...2020-09-03 10:58:32.274+002020-09-03 10:58:32....afterafterafterafterafterafterafterafteraftera...
canceled4074112721.02020-06-28 12:06:33.71284+002020-06-29 06:26:3...2020-06-28 12:06:33.712853+002020-06-29 06:26:...235310.02020-07-29 16:10:38+002020-09-01 17:22:40+0020...130344.02020-07-07 22:00:00+002020-07-31 22:00:00+0020...2020-09-042020-10-11 22:00:00+002020-10-11 22:00:00+00...rejectedrejectedconfirmedconfirmedrejectedcanc...rejected_direct_debitrejected_direct_debit30.0Instant Payment Cash Request 12838rejected dir...2020-08-17 19:05:49.830145+002020-09-03 15:45:...2020-10-13 14:25:09.68019+002020-10-13 14:25:0...2020-09-07 14:39:58.670351+002020-09-07 14:39:...00afterafterafterafterafterafter
direct_debit_rejected25727991157959.02020-06-17 11:03:32.61712+002020-06-17 11:03:3...2020-07-21 22:09:32.695508+002020-07-21 22:09:...60544935.02020-06-17 14:52:56.14175+002020-06-17 14:52:5...722081.02020-07-17 11:03:52.469+002020-07-17 11:03:52....2020-06-182020-06-182020-06-182020-06-182020-0...2020-07-02 18:47:17.295625+002020-07-02 18:47:......rejectedrejectedrejectedrejectedcancelledrejec...rejected_direct_debitmonth_delay_on_paymentmon...9290.0rejected direct debitmonth delay on payment - ...2020-07-21 22:09:32.585036+002020-08-20 23:11:...2020-10-13 14:25:00.836605+002020-10-13 14:25:...2020-08-06 08:42:18.59726+002020-07-07 05:35:0...2020-07-30 22:00:00+002020-08-15 05:34:55.649+...2020-08-15 05:34:55.649+002020-08-30 05:34:55....afterafterafterafterafterafterafterafterbefore...
direct_debit_sent12412056710.02020-08-08 18:20:28.454918+002020-08-08 18:20:...2020-09-09 10:07:25.743348+002020-09-09 10:07:...2687797.02020-08-17 07:35:42.551778+002020-08-17 07:35:...0.02020-09-27 22:00:00+002020-09-27 22:00:00+0020...2020-08-112020-08-112020-08-112020-08-182020-0...2020-06-10 03:42:00.436408+002020-12-23 08:21:......rejectedcancelledcancelledcancelledcancelledre...rejected_direct_debitmonth_delay_on_paymentrej...360.0rejected direct debitPostpone Cash Request 115...2020-09-06 22:09:12.979847+002020-08-25 17:18:...2020-10-13 14:25:09.281636+002020-10-13 14:25:...2020-09-18 08:56:59.846076+002021-02-11 04:25:...2020-08-28 23:51:00+002020-08-28 23:51:00+0020...2020-09-27 23:51:00+002020-09-27 23:51:00+0020...afterafterafterafterafterafterafterafteraftera...
money_back3446527981946958.02020-05-23 20:58:55.129432+002020-05-14 21:11:...2020-07-06 03:36:03.023911+002020-06-03 05:11:...759119993.02020-05-24 12:40:33.05491+002020-05-15 09:11:1...17933438.02020-06-06 22:00:00+002020-05-29 21:11:46.695+...2020-05-262020-05-172020-05-272020-05-122020-0...2020-07-06 03:36:03.023521+002020-06-03 05:11:......acceptedacceptedacceptedacceptedcancelledaccep...rejected_direct_debitmonth_delay_on_paymentrej...94595.0Instant Payment Cash Request 23534Postpone Cas...2020-10-23 15:21:35.895711+002020-06-09 11:25:...2020-10-23 15:21:35.89574+002020-10-13 14:25:0...2020-11-06 07:16:22.014422+002020-10-17 05:30:...2020-06-15 02:26:27+002020-10-27 17:05:21.138+...2020-07-15 02:26:27+002020-10-30 23:00:00+0020...afterbeforebeforeafterbeforebeforeafterafteraf...
rejected68269051548101.02019-12-10 19:05:21.596873+002019-12-10 19:50:...2019-12-11 16:47:42.40783+002019-12-11 14:24:2...113094094.02019-12-11 16:47:42.405646+002019-12-11 14:24:...9460686.02020-01-09 19:05:21.596363+002020-01-09 19:50:...2020-06-250...000.00000000
transaction_declined10271604105.02020-10-23 16:32:14.85667+002020-10-13 11:37:3...2020-10-23 16:33:15.530982+002020-10-13 11:38:...2226056.02020-10-12 15:22:44.665209+000.02020-11-05 22:00:00+002020-11-04 22:00:00+0020...02020-11-05 20:31:25+002020-11-08 22:25:14+00...confirmedconfirmedconfirmedconfirmedconfirmedc...0240.0Instant Payment Cash Request 23641Instant Paym...2020-10-23 16:32:34.165305+002020-10-13 11:37:...2020-10-23 16:32:34.165333+002020-10-13 14:25:...2020-11-05 20:31:25.727454+002020-11-05 14:03:...00afterafterafterafterafterafterafterafteraftera...
\n", + "

7 rows × 28 columns

\n", + "
" + ], + "text/plain": [ + " id_x amount \\\n", + "status_x \n", + "active 2284630 13825.0 \n", + "canceled 407411 2721.0 \n", + "direct_debit_rejected 25727991 157959.0 \n", + "direct_debit_sent 1241205 6710.0 \n", + "money_back 344652798 1946958.0 \n", + "rejected 68269051 548101.0 \n", + "transaction_declined 1027160 4105.0 \n", + "\n", + " created_at_x \\\n", + "status_x \n", + "active 2020-07-01 09:30:03.14541+002020-07-01 09:30:0... \n", + "canceled 2020-06-28 12:06:33.71284+002020-06-29 06:26:3... \n", + "direct_debit_rejected 2020-06-17 11:03:32.61712+002020-06-17 11:03:3... \n", + "direct_debit_sent 2020-08-08 18:20:28.454918+002020-08-08 18:20:... \n", + "money_back 2020-05-23 20:58:55.129432+002020-05-14 21:11:... \n", + "rejected 2019-12-10 19:05:21.596873+002019-12-10 19:50:... \n", + "transaction_declined 2020-10-23 16:32:14.85667+002020-10-13 11:37:3... \n", + "\n", + " updated_at_x \\\n", + "status_x \n", + "active 2020-08-11 22:27:58.240406+002020-08-11 22:27:... \n", + "canceled 2020-06-28 12:06:33.712853+002020-06-29 06:26:... \n", + "direct_debit_rejected 2020-07-21 22:09:32.695508+002020-07-21 22:09:... \n", + "direct_debit_sent 2020-09-09 10:07:25.743348+002020-09-09 10:07:... \n", + "money_back 2020-07-06 03:36:03.023911+002020-06-03 05:11:... \n", + "rejected 2019-12-11 16:47:42.40783+002019-12-11 14:24:2... \n", + "transaction_declined 2020-10-23 16:33:15.530982+002020-10-13 11:38:... \n", + "\n", + " user_id \\\n", + "status_x \n", + "active 4929215.0 \n", + "canceled 235310.0 \n", + "direct_debit_rejected 60544935.0 \n", + "direct_debit_sent 2687797.0 \n", + "money_back 759119993.0 \n", + "rejected 113094094.0 \n", + "transaction_declined 2226056.0 \n", + "\n", + " moderated_at \\\n", + "status_x \n", + "active 2020-07-01 16:44:53.070844+002020-07-01 16:44:... \n", + "canceled 2020-07-29 16:10:38+002020-09-01 17:22:40+0020... \n", + "direct_debit_rejected 2020-06-17 14:52:56.14175+002020-06-17 14:52:5... \n", + "direct_debit_sent 2020-08-17 07:35:42.551778+002020-08-17 07:35:... \n", + "money_back 2020-05-24 12:40:33.05491+002020-05-15 09:11:1... \n", + "rejected 2019-12-11 16:47:42.405646+002019-12-11 14:24:... \n", + "transaction_declined 2020-10-12 15:22:44.665209+00 \n", + "\n", + " deleted_account_id \\\n", + "status_x \n", + "active 0.0 \n", + "canceled 130344.0 \n", + "direct_debit_rejected 722081.0 \n", + "direct_debit_sent 0.0 \n", + "money_back 17933438.0 \n", + "rejected 9460686.0 \n", + "transaction_declined 0.0 \n", + "\n", + " reimbursement_date \\\n", + "status_x \n", + "active 2020-08-03 22:00:00+002020-08-03 22:00:00+0020... \n", + "canceled 2020-07-07 22:00:00+002020-07-31 22:00:00+0020... \n", + "direct_debit_rejected 2020-07-17 11:03:52.469+002020-07-17 11:03:52.... \n", + "direct_debit_sent 2020-09-27 22:00:00+002020-09-27 22:00:00+0020... \n", + "money_back 2020-06-06 22:00:00+002020-05-29 21:11:46.695+... \n", + "rejected 2020-01-09 19:05:21.596363+002020-01-09 19:50:... \n", + "transaction_declined 2020-11-05 22:00:00+002020-11-04 22:00:00+0020... \n", + "\n", + " cash_request_received_date \\\n", + "status_x \n", + "active 2020-07-032020-07-032020-07-032020-07-032020-0... \n", + "canceled 2020-09-04 \n", + "direct_debit_rejected 2020-06-182020-06-182020-06-182020-06-182020-0... \n", + "direct_debit_sent 2020-08-112020-08-112020-08-112020-08-182020-0... \n", + "money_back 2020-05-262020-05-172020-05-272020-05-122020-0... \n", + "rejected 2020-06-25 \n", + "transaction_declined 0 \n", + "\n", + " money_back_date ... \\\n", + "status_x ... \n", + "active 2020-06-11 22:37:13.182826+002020-08-06 22:00:... ... \n", + "canceled 2020-10-11 22:00:00+002020-10-11 22:00:00+00 ... \n", + "direct_debit_rejected 2020-07-02 18:47:17.295625+002020-07-02 18:47:... ... \n", + "direct_debit_sent 2020-06-10 03:42:00.436408+002020-12-23 08:21:... ... \n", + "money_back 2020-07-06 03:36:03.023521+002020-06-03 05:11:... ... \n", + "rejected 0 ... \n", + "transaction_declined 2020-11-05 20:31:25+002020-11-08 22:25:14+00 ... \n", + "\n", + " status_y \\\n", + "status_x \n", + "active cancelledcancelledcancelledcancelledcancelledr... \n", + "canceled rejectedrejectedconfirmedconfirmedrejectedcanc... \n", + "direct_debit_rejected rejectedrejectedrejectedrejectedcancelledrejec... \n", + "direct_debit_sent rejectedcancelledcancelledcancelledcancelledre... \n", + "money_back acceptedacceptedacceptedacceptedcancelledaccep... \n", + "rejected 0 \n", + "transaction_declined confirmedconfirmedconfirmedconfirmedconfirmedc... \n", + "\n", + " category \\\n", + "status_x \n", + "active month_delay_on_paymentrejected_direct_debitmon... \n", + "canceled rejected_direct_debitrejected_direct_debit \n", + "direct_debit_rejected rejected_direct_debitmonth_delay_on_paymentmon... \n", + "direct_debit_sent rejected_direct_debitmonth_delay_on_paymentrej... \n", + "money_back rejected_direct_debitmonth_delay_on_paymentrej... \n", + "rejected 0 \n", + "transaction_declined 0 \n", + "\n", + " total_amount \\\n", + "status_x \n", + "active 775.0 \n", + "canceled 30.0 \n", + "direct_debit_rejected 9290.0 \n", + "direct_debit_sent 360.0 \n", + "money_back 94595.0 \n", + "rejected 0.0 \n", + "transaction_declined 240.0 \n", + "\n", + " reason \\\n", + "status_x \n", + "active Postpone Cash Request 6098Postpone Cash Reques... \n", + "canceled Instant Payment Cash Request 12838rejected dir... \n", + "direct_debit_rejected rejected direct debitmonth delay on payment - ... \n", + "direct_debit_sent rejected direct debitPostpone Cash Request 115... \n", + "money_back Instant Payment Cash Request 23534Postpone Cas... \n", + "rejected 0 \n", + "transaction_declined Instant Payment Cash Request 23641Instant Paym... \n", + "\n", + " created_at_y \\\n", + "status_x \n", + "active 2020-08-13 10:58:39.63422+002020-08-13 10:58:5... \n", + "canceled 2020-08-17 19:05:49.830145+002020-09-03 15:45:... \n", + "direct_debit_rejected 2020-07-21 22:09:32.585036+002020-08-20 23:11:... \n", + "direct_debit_sent 2020-09-06 22:09:12.979847+002020-08-25 17:18:... \n", + "money_back 2020-10-23 15:21:35.895711+002020-06-09 11:25:... \n", + "rejected 0 \n", + "transaction_declined 2020-10-23 16:32:34.165305+002020-10-13 11:37:... \n", + "\n", + " updated_at_y \\\n", + "status_x \n", + "active 2020-10-13 14:25:16.660127+002020-10-13 14:25:... \n", + "canceled 2020-10-13 14:25:09.68019+002020-10-13 14:25:0... \n", + "direct_debit_rejected 2020-10-13 14:25:00.836605+002020-10-13 14:25:... \n", + "direct_debit_sent 2020-10-13 14:25:09.281636+002020-10-13 14:25:... \n", + "money_back 2020-10-23 15:21:35.89574+002020-10-13 14:25:0... \n", + "rejected 0 \n", + "transaction_declined 2020-10-23 16:32:34.165333+002020-10-13 14:25:... \n", + "\n", + " paid_at \\\n", + "status_x \n", + "active 2020-06-25 23:41:23.810387+002020-07-12 04:34:... \n", + "canceled 2020-09-07 14:39:58.670351+002020-09-07 14:39:... \n", + "direct_debit_rejected 2020-08-06 08:42:18.59726+002020-07-07 05:35:0... \n", + "direct_debit_sent 2020-09-18 08:56:59.846076+002021-02-11 04:25:... \n", + "money_back 2020-11-06 07:16:22.014422+002020-10-17 05:30:... \n", + "rejected 0 \n", + "transaction_declined 2020-11-05 20:31:25.727454+002020-11-05 14:03:... \n", + "\n", + " from_date \\\n", + "status_x \n", + "active 2020-08-03 22:00:00+002020-08-03 22:00:00+0020... \n", + "canceled 0 \n", + "direct_debit_rejected 2020-07-30 22:00:00+002020-08-15 05:34:55.649+... \n", + "direct_debit_sent 2020-08-28 23:51:00+002020-08-28 23:51:00+0020... \n", + "money_back 2020-06-15 02:26:27+002020-10-27 17:05:21.138+... \n", + "rejected 0 \n", + "transaction_declined 0 \n", + "\n", + " to_date \\\n", + "status_x \n", + "active 2020-09-03 10:58:32.274+002020-09-03 10:58:32.... \n", + "canceled 0 \n", + "direct_debit_rejected 2020-08-15 05:34:55.649+002020-08-30 05:34:55.... \n", + "direct_debit_sent 2020-09-27 23:51:00+002020-09-27 23:51:00+0020... \n", + "money_back 2020-07-15 02:26:27+002020-10-30 23:00:00+0020... \n", + "rejected 0 \n", + "transaction_declined 0 \n", + "\n", + " charge_moment \n", + "status_x \n", + "active afterafterafterafterafterafterafterafteraftera... \n", + "canceled afterafterafterafterafterafter \n", + "direct_debit_rejected afterafterafterafterafterafterafterafterbefore... \n", + "direct_debit_sent afterafterafterafterafterafterafterafteraftera... \n", + "money_back afterbeforebeforeafterbeforebeforeafterafteraf... \n", + "rejected 0 \n", + "transaction_declined afterafterafterafterafterafterafterafteraftera... \n", + "\n", + "[7 rows x 28 columns]" + ] + }, + "execution_count": 364, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "merged_df_clean = merged_df\n", + "\n", + "merged_df_clean\n", + "\n", + "merged_df_clean.groupby(\"status_x\").sum()\n", + "\n", + "#merged_df2_clean[\"reembolsado\"].sum()" + ] + }, + { + "cell_type": "code", + "execution_count": 365, + "id": "54dc0bd8-6957-4a19-8fd2-d7d7fe8bacba", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " Cohorte Total Solicitudes Solicitudes Aprobadas \\\n", + "0 2019-11 1 0.0 \n", + "1 2019-12 289 0.0 \n", + "2 2020-01 223 0.0 \n", + "3 2020-02 184 0.0 \n", + "4 2020-03 244 0.0 \n", + "5 2020-04 473 0.0 \n", + "6 2020-05 997 0.0 \n", + "7 2020-06 3662 0.0 \n", + "8 2020-07 4793 0.0 \n", + "9 2020-08 5250 0.0 \n", + "10 2020-09 6227 0.0 \n", + "11 2020-10 9611 0.0 \n", + "12 2020-11 140 0.0 \n", + "\n", + " Tasa de Solicitudes Aprobadas \n", + "0 0.0 \n", + "1 0.0 \n", + "2 0.0 \n", + "3 0.0 \n", + "4 0.0 \n", + "5 0.0 \n", + "6 0.0 \n", + "7 0.0 \n", + "8 0.0 \n", + "9 0.0 \n", + "10 0.0 \n", + "11 0.0 \n", + "12 0.0 \n" + ] + }, + { + "ename": "TypeError", + "evalue": "Invalid object type at position 0", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)", + "File \u001b[1;32mlib.pyx:2391\u001b[0m, in \u001b[0;36mpandas._libs.lib.maybe_convert_numeric\u001b[1;34m()\u001b[0m\n", + "\u001b[1;31mTypeError\u001b[0m: Invalid object type", + "\nDuring handling of the above exception, another exception occurred:\n", + "\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)", + "Cell \u001b[1;32mIn[365], line 31\u001b[0m\n\u001b[0;32m 27\u001b[0m \u001b[38;5;28mprint\u001b[39m(cohort_approval_rate)\n\u001b[0;32m 30\u001b[0m plt\u001b[38;5;241m.\u001b[39mfigure(figsize\u001b[38;5;241m=\u001b[39m(\u001b[38;5;241m12\u001b[39m, \u001b[38;5;241m6\u001b[39m))\n\u001b[1;32m---> 31\u001b[0m sns\u001b[38;5;241m.\u001b[39mlineplot(data\u001b[38;5;241m=\u001b[39mcohort_approval_rate, x\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mCohorte\u001b[39m\u001b[38;5;124m'\u001b[39m, y\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mTasa de Solicitudes Aprobadas\u001b[39m\u001b[38;5;124m'\u001b[39m, marker\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mo\u001b[39m\u001b[38;5;124m'\u001b[39m, color\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mblue\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m 32\u001b[0m plt\u001b[38;5;241m.\u001b[39mtitle(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mTasa de Solicitudes Aprobadas por Cohorte\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m 33\u001b[0m plt\u001b[38;5;241m.\u001b[39mxlabel(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mCohorte (Mes y Año)\u001b[39m\u001b[38;5;124m'\u001b[39m)\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\seaborn\\relational.py:515\u001b[0m, in \u001b[0;36mlineplot\u001b[1;34m(data, x, y, hue, size, style, units, weights, palette, hue_order, hue_norm, sizes, size_order, size_norm, dashes, markers, style_order, estimator, errorbar, n_boot, seed, orient, sort, err_style, err_kws, legend, ci, ax, **kwargs)\u001b[0m\n\u001b[0;32m 512\u001b[0m color \u001b[38;5;241m=\u001b[39m kwargs\u001b[38;5;241m.\u001b[39mpop(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcolor\u001b[39m\u001b[38;5;124m\"\u001b[39m, kwargs\u001b[38;5;241m.\u001b[39mpop(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mc\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m))\n\u001b[0;32m 513\u001b[0m kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcolor\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m _default_color(ax\u001b[38;5;241m.\u001b[39mplot, hue, color, kwargs)\n\u001b[1;32m--> 515\u001b[0m p\u001b[38;5;241m.\u001b[39mplot(ax, kwargs)\n\u001b[0;32m 516\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m ax\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\seaborn\\relational.py:276\u001b[0m, in \u001b[0;36m_LinePlotter.plot\u001b[1;34m(self, ax, kws)\u001b[0m\n\u001b[0;32m 268\u001b[0m \u001b[38;5;66;03m# TODO How to handle NA? We don't want NA to propagate through to the\u001b[39;00m\n\u001b[0;32m 269\u001b[0m \u001b[38;5;66;03m# estimate/CI when some values are present, but we would also like\u001b[39;00m\n\u001b[0;32m 270\u001b[0m \u001b[38;5;66;03m# matplotlib to show \"gaps\" in the line when all values are missing.\u001b[39;00m\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 273\u001b[0m \n\u001b[0;32m 274\u001b[0m \u001b[38;5;66;03m# Loop over the semantic subsets and add to the plot\u001b[39;00m\n\u001b[0;32m 275\u001b[0m grouping_vars \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhue\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msize\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstyle\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m--> 276\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m sub_vars, sub_data \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39miter_data(grouping_vars, from_comp_data\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m):\n\u001b[0;32m 278\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msort:\n\u001b[0;32m 279\u001b[0m sort_vars \u001b[38;5;241m=\u001b[39m [\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124munits\u001b[39m\u001b[38;5;124m\"\u001b[39m, orient, other]\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\seaborn\\_base.py:902\u001b[0m, in \u001b[0;36mVectorPlotter.iter_data\u001b[1;34m(self, grouping_vars, reverse, from_comp_data, by_facet, allow_empty, dropna)\u001b[0m\n\u001b[0;32m 899\u001b[0m grouping_vars \u001b[38;5;241m=\u001b[39m [var \u001b[38;5;28;01mfor\u001b[39;00m var \u001b[38;5;129;01min\u001b[39;00m grouping_vars \u001b[38;5;28;01mif\u001b[39;00m var \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mvariables]\n\u001b[0;32m 901\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m from_comp_data:\n\u001b[1;32m--> 902\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcomp_data\n\u001b[0;32m 903\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m 904\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mplot_data\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\seaborn\\_base.py:1000\u001b[0m, in \u001b[0;36mVectorPlotter.comp_data\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 995\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m var \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mvar_levels:\n\u001b[0;32m 996\u001b[0m \u001b[38;5;66;03m# TODO this should happen in some centralized location\u001b[39;00m\n\u001b[0;32m 997\u001b[0m \u001b[38;5;66;03m# it is similar to GH2419, but more complicated because\u001b[39;00m\n\u001b[0;32m 998\u001b[0m \u001b[38;5;66;03m# supporting `order` in categorical plots is tricky\u001b[39;00m\n\u001b[0;32m 999\u001b[0m orig \u001b[38;5;241m=\u001b[39m orig[orig\u001b[38;5;241m.\u001b[39misin(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mvar_levels[var])]\n\u001b[1;32m-> 1000\u001b[0m comp \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mto_numeric(converter\u001b[38;5;241m.\u001b[39mconvert_units(orig))\u001b[38;5;241m.\u001b[39mastype(\u001b[38;5;28mfloat\u001b[39m)\n\u001b[0;32m 1001\u001b[0m transform \u001b[38;5;241m=\u001b[39m converter\u001b[38;5;241m.\u001b[39mget_transform()\u001b[38;5;241m.\u001b[39mtransform\n\u001b[0;32m 1002\u001b[0m parts\u001b[38;5;241m.\u001b[39mappend(pd\u001b[38;5;241m.\u001b[39mSeries(transform(comp), orig\u001b[38;5;241m.\u001b[39mindex, name\u001b[38;5;241m=\u001b[39morig\u001b[38;5;241m.\u001b[39mname))\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\pandas\\core\\tools\\numeric.py:232\u001b[0m, in \u001b[0;36mto_numeric\u001b[1;34m(arg, errors, downcast, dtype_backend)\u001b[0m\n\u001b[0;32m 230\u001b[0m coerce_numeric \u001b[38;5;241m=\u001b[39m errors \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m (\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mignore\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mraise\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m 231\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 232\u001b[0m values, new_mask \u001b[38;5;241m=\u001b[39m lib\u001b[38;5;241m.\u001b[39mmaybe_convert_numeric( \u001b[38;5;66;03m# type: ignore[call-overload]\u001b[39;00m\n\u001b[0;32m 233\u001b[0m values,\n\u001b[0;32m 234\u001b[0m \u001b[38;5;28mset\u001b[39m(),\n\u001b[0;32m 235\u001b[0m coerce_numeric\u001b[38;5;241m=\u001b[39mcoerce_numeric,\n\u001b[0;32m 236\u001b[0m convert_to_masked_nullable\u001b[38;5;241m=\u001b[39mdtype_backend \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m lib\u001b[38;5;241m.\u001b[39mno_default\n\u001b[0;32m 237\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(values_dtype, StringDtype)\n\u001b[0;32m 238\u001b[0m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m values_dtype\u001b[38;5;241m.\u001b[39mstorage \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpyarrow_numpy\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m 239\u001b[0m )\n\u001b[0;32m 240\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mValueError\u001b[39;00m, \u001b[38;5;167;01mTypeError\u001b[39;00m):\n\u001b[0;32m 241\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m errors \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mraise\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n", + "File \u001b[1;32mlib.pyx:2433\u001b[0m, in \u001b[0;36mpandas._libs.lib.maybe_convert_numeric\u001b[1;34m()\u001b[0m\n", + "\u001b[1;31mTypeError\u001b[0m: Invalid object type at position 0" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Crear una columna binaria que indique si la solicitud fue aprobada\n", + "merged_df2['aprobada'] = merged_df2['recovery_status'] == 'approved'\n", + "\n", + "# Aseguramos que la columna 'aprobada' solo tenga valores no nulos\n", + "merged_df2['aprobada'] = merged_df2['aprobada'].fillna(False) # Para evitar valores nulos\n", + "\n", + "# Calcular la cantidad total de solicitudes por cohorte\n", + "cohort_counts = merged_df2.groupby('cohort')['id_x'].count().reset_index()\n", + "cohort_counts.columns = ['Cohorte', 'Total Solicitudes']\n", + "\n", + "# Calcular la cantidad de solicitudes aprobadas por cohorte\n", + "approved_requests = merged_df2[merged_df2['aprobada']].groupby('cohort')['id_x'].count().reset_index()\n", + "approved_requests.columns = ['Cohorte', 'Solicitudes Aprobadas']\n", + "\n", + "# Combinar los dos resultados en un dataframe\n", + "cohort_approval_rate = pd.merge(cohort_counts, approved_requests, on='Cohorte', how='left')\n", + "\n", + "# Calcular la tasa de solicitudes aprobadas\n", + "cohort_approval_rate['Tasa de Solicitudes Aprobadas'] = cohort_approval_rate['Solicitudes Aprobadas'] / cohort_approval_rate['Total Solicitudes']\n", + "\n", + "# Llenar valores nulos con 0 para cohortes sin solicitudes aprobadas\n", + "cohort_approval_rate['Solicitudes Aprobadas'] = cohort_approval_rate['Solicitudes Aprobadas'].fillna(0)\n", + "cohort_approval_rate['Tasa de Solicitudes Aprobadas'] = cohort_approval_rate['Tasa de Solicitudes Aprobadas'].fillna(0)\n", + "\n", + "\n", + "# Mostrar los resultados\n", + "print(cohort_approval_rate)\n", + "\n", + "\n", + "plt.figure(figsize=(12, 6))\n", + "sns.lineplot(data=cohort_approval_rate, x='Cohorte', y='Tasa de Solicitudes Aprobadas', marker='o', color='blue')\n", + "plt.title('Tasa de Solicitudes Aprobadas por Cohorte')\n", + "plt.xlabel('Cohorte (Mes y Año)')\n", + "plt.ylabel('Tasa de Solicitudes Aprobadas')\n", + "plt.xticks(rotation=45)\n", + "plt.ylim(0, 1)\n", + "plt.show()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 369, + "id": "8c04e754-602e-4f78-b548-b70630af6dd1", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0\n" + ] + } + ], + "source": [ + "contador = 0\n", + "\n", + "for elements in merged_df['recovery_status']:\n", + " if elements == 'rejected':\n", + " contador += 1\n", + "\n", + "print(contador)" + ] + }, + { + "cell_type": "code", + "execution_count": 375, + "id": "342a826c-58c8-4dfd-ab2a-02e79039a3dc", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0\n" + ] + }, + { + "data": { + "text/plain": [ + "0 False\n", + "1 False\n", + "2 False\n", + "3 False\n", + "4 False\n", + " ... \n", + "32089 False\n", + "32090 False\n", + "32091 False\n", + "32092 False\n", + "32093 False\n", + "Name: aprobada, Length: 32094, dtype: bool" + ] + }, + "execution_count": 375, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Crear una columna binaria que indique si la solicitud fue aprobada\n", + "merged_df2['aprobada'] = merged_df2['recovery_status'] == 'approved'\n", + "\n", + "# Aseguramos que la columna 'aprobada' solo tenga valores no nulos\n", + "merged_df2['aprobada'] = merged_df2['aprobada'].fillna(True) # Para evitar valores nulos\n", + "\n", + "merged_df2['aprobada']" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "c87390ae-9d3d-4198-b30c-8de1933b86ec", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.12.7" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/project_dataset/Untitled.ipynb b/project_dataset/Untitled.ipynb new file mode 100644 index 0000000..ad563f3 --- /dev/null +++ b/project_dataset/Untitled.ipynb @@ -0,0 +1,3359 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "id": "349dbdcc-4061-4b54-babd-7601df74b01b", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "RangeIndex: 32094 entries, 0 to 32093\n", + "Data columns (total 29 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 id_x 32094 non-null int64 \n", + " 1 amount 32094 non-null float64\n", + " 2 status_x 32094 non-null object \n", + " 3 created_at_x 32094 non-null object \n", + " 4 updated_at_x 32094 non-null object \n", + " 5 user_id 29522 non-null float64\n", + " 6 moderated_at 21759 non-null object \n", + " 7 deleted_account_id 2573 non-null float64\n", + " 8 reimbursement_date 32094 non-null object \n", + " 9 cash_request_received_date 24149 non-null object \n", + " 10 money_back_date 23917 non-null object \n", + " 11 transfer_type 32094 non-null object \n", + " 12 send_at 22678 non-null object \n", + " 13 recovery_status 7200 non-null object \n", + " 14 reco_creation 7200 non-null object \n", + " 15 reco_last_update 7200 non-null object \n", + " 16 id_y 21057 non-null float64\n", + " 17 cash_request_id 21057 non-null float64\n", + " 18 type 21057 non-null object \n", + " 19 status_y 21057 non-null object \n", + " 20 category 2196 non-null object \n", + " 21 total_amount 21057 non-null float64\n", + " 22 reason 21057 non-null object \n", + " 23 created_at_y 21057 non-null object \n", + " 24 updated_at_y 21057 non-null object \n", + " 25 paid_at 15531 non-null object \n", + " 26 from_date 7766 non-null object \n", + " 27 to_date 7766 non-null object \n", + " 28 charge_moment 21057 non-null object \n", + "dtypes: float64(6), int64(1), object(22)\n", + "memory usage: 7.1+ MB\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAA2UAAAIlCAYAAABVWVCLAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8hTgPZAAAACXBIWXMAAA9hAAAPYQGoP6dpAACboklEQVR4nOzdd1yVdf/H8ddhD9kIiCJiuXKP3KVmjsr2VlHLX3VnaaZl2VIbeje07vTubqs52mW2LC3Tyq05U8tUxIGKLJEN1++PIwcQVJADF+fwfj4e5+HFdX3POZ8LRHnz/V6fy2IYhoGIiIiIiIiYwsXsAkRERERERGozhTIRERERERETKZSJiIiIiIiYSKFMRERERETERAplIiIiIiIiJlIoExERERERMZFCmYiIiIiIiIkUykREREREREykUCYiIiIiImIihTIRETHN4cOHGTp0KPXr18fFxQWLxWJ2SXY1Z84cLBYLc+bMMbsUEX755RcsFguTJ082uxQROYNCmYjUaPv378disZzzIY5rxIgRLFy4kD59+vD0008zadKk8z7nwIEDjBo1iiZNmuDl5UWdOnVo3Lgx11xzDS+++CKnTp2qhsodS+H3Ue/evSs1prbr3bu37d+dJUuWnHVchw4dbOPWrFlTjRVCo0aNaNSoUbW+p4hUnpvZBYiIlMdFF13E0KFDzS5D7CgnJ4effvqJ/v37M3/+/HI9Z8uWLfTu3ZuUlBR69OjBVVddhYeHB/v27WPDhg1899133HzzzVx88cVVXH353HjjjXTt2pV69eqZXYrYkZubG++//z4DBw4sdWzLli388ccfuLm5kZeXZ0J1IuKIFMpExCFcfPHFWnLjZBISEigoKCAiIqLczxk3bhwpKSl88MEHxMbGljq+evVqQkND7VlmpQQEBBAQEGB2GWJnV111FV999RUnTpwgJCSkxLH33nsPNzc3+vXrx/fff29ShSLiaLR8UUScwuTJk7FYLPzyyy/MnTuXjh074uPjU2Ip1smTJ5k0aRItW7bE29ubwMBABg4cyG+//Vbma+7YsYNBgwbh5+dHQEAAV199Ndu3b2fEiBFYLBb2799f5vuf6VzXFW3dupU77riDevXq4eHhQXR0NKNHj+bEiRMlxhUuLRsxYgR79+7llltuISgoCF9fX6688kq2bNlS5jkcO3aMRx55hGbNmuHl5UVwcDBdu3Zl+vTpAOzduxcXFxeuueaaMp+fnJyMl5cXbdu2LfP4mTIyMpg8eTLNmze3vd8111zDqlWrSozr3bs30dHRAMydO9e21Ot8wXv16tUEBgaWGcgAunXrRmBgYKn9F/J53rVrFzfddBOhoaFYLBb+/PNP/Pz8zjkL17RpU/z8/MjIyADO/bXft28f//rXv4iJicHT05OwsDB69+5d5tiVK1dy7bXXEhoaiqenJ02aNOGpp56yvU9VOnLkCA899BBNmjTB29ub4OBgWrduzahRo0hLSysxNicnhxkzZtChQwd8fX3x8/PjsssuY/HixeV+v+LfS++88w4tW7bEy8uLhg0bMnHiRLKyssp8nj2+xsW/p8/lrrvuIicnhwULFpQ6/4ULF3LNNdcQFhZ21ud/88039OnTh4CAALy9vWnXrh2vvfYa+fn5Z631fN/3hWPj4uKIi4srscS7rO+rTZs2MWDAANu/bzfeeGO5z19E7E+hTEScyssvv8z9999PkyZNGDNmDD179gQgKSmJbt268eyzzxISEsL999/PzTffzIYNG+jTpw+LFi0q8Trbt2+ne/fufP/99wwcOJAHHniAnJwcevTowd69e+1S6+LFi+ncuTNff/01vXv3ZuzYsbRu3ZpZs2bRrVs3kpOTSz1n//79dOnShePHj3P33XfTr18/fvrpJ/r06cPRo0dLjP3777/p0KED06dPJywsjIceeojBgwfj5eXFCy+8AEDjxo258sorWbJkCQcPHiz1fvPmzSM7O5t77rnnvOeTnZ1N3759mTJlCr6+vowdO5YbbriBX375hV69evHFF1/Yxo4YMYKHHnoIgLZt2zJp0iQmTZp03uuZgoODSU9PJyEh4bz1FLqQz/OePXvo2rUrR48eZfjw4YwYMYLAwEBuuukm/vnnH1avXl3qOWvXruXvv//m5ptvxsfH55w1rV69mvbt2/P222/TvHlzxo0bx0033URmZib/+c9/Sox988036d27N6tWrWLQoEGMGTOG+vXr88ILL9CvXz9ycnLK/bmoqIyMDHr06MHMmTO56KKLGD16NMOGDSMmJoY5c+aQlJRkG5udnc2AAQMYP348ACNHjmTo0KHExcVx/fXXM2vWrAq99/Tp0xk3bhzdunXjoYceIiAggH//+9/ccMMNGIZRYqy9vsYeHh7lqq1bt260aNGC2bNnl9i/aNEiTpw4wd13333W5/7nP//h2muvZevWrQwePJgHHniAzMxMHn74YW677bZS5wbl+74PDAxk0qRJttnZwu+psr6vNmzYwGWXXYabmxv33XcfnTp1YtGiRVx55ZVnDb0iUsUMEZEabN++fQZgXHTRRcakSZNKPVavXm0YhmFMmjTJAAxfX19j69atpV5n8ODBBmC8//77JfYnJCQYUVFRRt26dY3MzEzb/l69ehmAMX/+/BLjJ06caAAGYOzbt8+2v/D9ly9fXuq9Z8+ebQDG7NmzbfsSExMNf39/o0GDBkZcXFyJ8QsXLjQA48EHHyz1eQCMf//73yXGP/XUUwZgTJs2rcT+zp07G4Dx9ttvl6opPj7etv3pp58agDFlypRS49q0aWN4eXkZycnJpY6d6dlnnzUAY8iQIUZBQYFt/5YtWwxPT08jKCjISEtLK3VOw4cPP+9rFxo7dqzt78P06dONdevWlfi6nakyn+enn3661OstXbrUAIxRo0aVOvbggw8agLFs2TLbvrK+9llZWUZUVJTh4uJifP/996Vep/jXZseOHYabm5vRvn1748SJEyXGTZs2zQCMV1555aznf+Z59erVq0JjFi9ebADGww8/XGp8WlqakZ2dbfv4iSeeMABj8uTJJb7+aWlpRqdOnQwPDw/j0KFD56218HvJy8vL2L59u21/bm6u0a9fPwMwPvjgA9t+e3+Nz6Xw34UjR44YL730kgEYmzZtsh3v37+/ER4ebuTm5hrDhw83ANu/UYZhGP/884/h5uZmhIWFGQcOHLDtz87Otr32vHnzyqy1vN/30dHRRnR0dJn1L1++3PZ6H330UYljsbGxBmB8+OGHFfqciIh9KJSJSI1W/IeSsh6vvvqqYRhFP8iV9cPj8ePHDVdXV6Nv375lvsfrr79uAMbXX39tGIZhxMXFGYDRpk2bUmNPnjxpBAYGVjqUzZgxo9QPYMV16NDBCA0NLfV5iImJMfLz88v8HN100022fevWrTMA4/LLLy/z9YvLyckxwsPDjUaNGpX4YbrwNYYOHXre1zAMw2jcuLHh7u5eIlQUuu+++876A2dFQllGRoYxbNgww8XFxfZ3wNXV1ejQoYPx3HPPlQqPF/p5joiIKBE4CuXn5xuRkZFGaGiokZOTY9ufm5tr1K1b16hfv36Jr09ZX/tPPvnEAIxhw4ad93zHjBljAMavv/5aZi1169Y1OnbseN7XqWwoe+KJJ875+vn5+UZQUJBx8cUXl/g7dObrzJw587y1Fn4v3XPPPaWOrV+/3gBKfC/b+2t8LsVDWUJCguHm5mYLfAcOHDBcXFyMRx991DAMo8xQVviLixdffLHUa69evbrUuVX0+94wyhfKyvp3ofDYuHHjyvfJEBG7UqMPEXEIAwYMOGcL6kKdO3cutW/9+vXk5+eTlZVV5rUVf//9NwC7du1i0KBBtus0Cpc+FlenTh3atWtX5rVjFVHYJnvNmjXs2bOn1PGsrCwSExNJTEws0biibdu2uLiUXHneoEEDAFJSUmz71q1bB0D//v3PW4u7uzt3330306ZNY+nSpbbnvPfeewD83//933lfIy0tjb1799KiRQtbPcX17t2bt956i82bN1eqi6a3tzdz587lhRde4LvvvmPdunWsW7eOTZs2sWnTJt566y1WrFhB48aNgcp9nstayubi4sLgwYN55ZVXWLJkCddeey0AS5Ys4fjx4zz66KOlvj5nqsjXprD+JUuWsGzZslLH3d3d2bVr13lf50JdfvnlREREMG3aNDZv3sw111xDz549ad26dYnbUezevZvk5GQiIyOZMmVKqdc5fvw4QIVqveyyy0rt69SpE97e3mzevNm2z95f4/IKDw/n6quvZuHChbzyyivMmTOHgoIC7rrrrrM+548//gAoc5lu165dS51b8VrL831fXh06dCi1rzKvJyKVp1AmIk4lPDy81L7C615+//13fv/997M+t/D+VqmpqQBnvVC/rPeoqMKa/vvf/55z3KlTp0r8IFlWJz83N+s/5cWbBBT+YFW/fv1y1XPPPffw73//m3fffZf+/fuTkZHBhx9+SNOmTenVq9d5n1/Y8OFsn5vCDouFn9vKatCgAffeey/33nsvAP/88w933303K1eu5OGHH+arr74CLvzzfK6vcWxsLK+88goLFiywhbLClv5na0BSXEW+NoX1F14DeKEKf6AvKCg465jCY8V/+A8ICGD16tVMmjSJr7/+mu+++w6wfv4nTpzIqFGjStS5Y8cOduzYcdb3qMg95M72/RcWFsahQ4dsH1fF17i87rrrLhYvXsyXX37JnDlz6Nq1Ky1atDjr+PN9n5x5boXK+31fXvZ+PRGpPDX6EBGnUtbNpP39/QEYP348hnXZdpmPwhsXF/7AcuzYsTLf48yGGlD0g2xZ9yUqK4gU1rRt27Zz1lTYobCiCjsQlvUDXlliYmLo168fX331FYmJiXzyySekpaWVa5as+PmU9bkpvr9wnL1ddNFFtq6FP//8c6m6Kvp5PtdNydu0aUObNm1YvHgxJ0+e5OTJkyxevJi2bdvSunXr89Zaka9NYf1paWnnrP98Cv9On9mJsLjExMQSYws1atSIuXPncvz4cf744w9efPFFDMPggQce4MMPPyxR580333zOOs9sjHEuZ/v+O3bsWIkaq+JrXF6DBg0iPDycRx55hL17956zwUfxWs/2fXLs2LEq+x4RkZpNoUxEnN6ll16KxWIps2NeWQrbv5fVKj89Pb3M5UVBQUFA2T9oFy5ZKq5Lly4A5a6pogqXcf7444/lfs69995LTk4OH3zwAe+99x7u7u4MHz68XM/19/encePG7Nmzp8zPwYoVKwBo165dueupKF9f31L7qurzPHToUDIzM/n888/5/PPPyczMLPeyzIp8bQrrL1yid6ECAgJo2LAhf/3111mDWeHnqE2bNmUed3V1pV27dkyYMMEWxgpb3bdo0QJ/f382bNhAbm5upWot9Ouvv5bat2HDBjIzM0v8Parq76VzcXNzY+jQoRw6dAgfHx9uv/32c45v3749QJnLn9etW1fq3C6Eq6urZrtEHJBCmYg4vYiICG677TZWrVrFyy+/XObMwtq1a233fGrYsCGXX345W7duLXUfoqlTp5Z5zUWnTp0A+OCDD0osEVu9enWp1wDrsic/Pz+efPLJMpd7ZWRkVOoH8UsvvZTOnTuzcuVK3nnnnVLHywpO119/PREREUyfPp3ffvuN66677pz3WjrT8OHDyc3NZeLEiSU+x9u3b2f27NkEBARwww03XND5FHr22WeJj48vtd8wDKZNmwaUvBawqj7PQ4YMwcXFhfnz5zNv3jzbtWblcd1119GgQQPmz5/PDz/8UOp48a/NqFGjcHNzY/To0WWed0pKSpmhvyzDhg0jLy+PRx99tNT3wMGDB3n55ZdxdXVlyJAhtv3bt28nLi6u1GsVzvR4e3sD1nBy//33ExcXxyOPPFJmMNu+fftZZ7/KMm/evBJfs7y8PJ544gmAEr8sqOrvpfN59NFH+fLLL/nhhx/OO8s1ePBg3NzcmDFjBocPH7btz83N5fHHHwest4uojODgYBITE9XaXsTB6JoyEakV3njjDXbv3s2ECROYN28e3bp1IyAggPj4eDZu3Mjff//NkSNHbPeX+u9//0uPHj0YNmwYixYtokmTJqxfv55169Zx2WWXlfotfteuXenWrRs///wz3bp14/LLLycuLo7Fixdz7bXX8uWXX5YYX7duXT788ENuvfVW2rZty8CBA2nevDlZWVnExcWxYsUKunfvXq7mJmczf/58evfuzb333ms756ysLHbs2MEff/xRasbEzc2Nu+++m6lTpwLla/BR3IQJE/j222+ZN28eO3fupG/fvhw/fpyPP/6Y3NxcPvjgA/z8/C74fABmzJjB5MmT6dSpEx07diQ4OJgTJ07w888/8/fffxMSEmK7MTZU3ec5MjKSK664wrZUsm/fvkRGRpbruZ6ennzyyScMHDiQq666ioEDB9K2bVvS0tLYvHkzGRkZtqDVqlUr3njjDe6//36aNWvG1VdfzUUXXWRrrLJixQpGjBjBm2++ed73feKJJ1i2bBmzZ89m9erV9OvXD39/f+Li4vjqq69IT09n+vTpNG3a1PacZcuWMX78eHr06EHz5s0JCQlh7969LF68GG9vbx588EHb2ClTprBp0yZef/11vv32W3r16kXdunU5dOgQ27ZtY8uWLaxevbrcQf/KK6+ka9eu3HHHHQQHB/Pdd9+xfft2BgwYUGJWsjq+l84lPDy83L9suOiii3jxxRcZP348bdq04bbbbsPX15dvvvmGXbt2cf3111eqEQ7AFVdcwYYNG7j22mu57LLL8PDwoGfPnmU2LhKRGqQKOjqKiNhNYdvnAQMGnHPcuVrSF8rIyDBeeuklo2PHjoavr6/h7e1txMTEGDfccIPxwQcfGLm5uSXGb9u2zbj66quNOnXqGH5+fsZVV11lbNu2zdbqunhLfMOwtt6PjY01goODDW9vb6Nr167GDz/8UGZb9EK7du0yRo4caURHRxseHh5GUFCQ0bp1a2PMmDHGunXrSn0eztY+nrO0O09ISDAeeugho3HjxoaHh4cRHBxsdOnSxZgxY0aZr7N7924DMBo2bFiqBXd5pKenG08//bTRtGlTw8PDwwgMDDSuuuqqMlu6X0hL/JUrVxqPP/640a1bNyMyMtJwd3c36tSpY7Rp08Z45JFHjMOHD5f5PHt9noubO3eurS3/3Llzyxxzrq/9nj17jJEjRxoNGjQw3N3djbCwMKN3794l7sFVaN26dcYdd9xhO+fQ0FCjQ4cOxuOPP27s3LnzvLUWysrKMqZPn2507tzZ8Pf3N9zc3IyIiAjjhhtuMH7++edS4//880/joYceMtq3b2+EhIQYnp6eRuPGjY0RI0YYf/75Z6nxeXl5xltvvWX06NHD8Pf3Nzw9PY2GDRsaAwcONP73v/8Z6enp562x+PfyW2+9ZVxyySWGp6en0aBBA+Pxxx83MjIyynxeVXyNz1S8Jf75lNUSv9BXX31l9OrVy/Dz8zM8PT2N1q1bG9OnTy/1b9CFfN+fPHnSuOeee4x69erZbh0xadIkwzCK2t4XflyR9xKRqmUxjHJcISwiIjYjRoxg7ty57Nu3j0aNGpldjl198skn3H777UyZMoVnnnnG7HKkFpo8eTJTpkxh+fLlZbaOFxFxRrqmTEREAOt1WTNmzMDNzY2RI0eaXY6IiEitoWvKRERquW3btvHNN9+watUq1q5dy7/+9a9y399MREREKk+hTESkltu4cSNPPPEEgYGBDBs2jJdfftnskkRERGoVXVMmIiIiIiJiIl1TJiIiIiIiYiKFMhERERERERPpmjI7Kygo4PDhw/j5+WGxWMwuR0RERERETGIYBidPniQyMhIXl3PMh5l5kzTDMIwVK1YYgwYNMurVq2cAxpdfflnieEFBgTFp0iSjXr16hpeXl9GrVy9j+/btJcZkZWUZDz74oBESEmL4+PgY1157rREfH19iTFJSkjF06FDD39/f8Pf3N4YOHWokJyeXGBMXF2cMGjTI8PHxMUJCQozRo0cb2dnZFTqf+Ph4281E9dBDDz300EMPPfTQQw89zswmZzJ9puzUqVO0bduWu+66i5tvvrnU8ZdeeokZM2YwZ84cmjZtyvPPP0+/fv3YvXs3fn5+AIwdO5avv/6ajz76iJCQEMaPH8+gQYPYuHEjrq6uAAwePJiDBw+yZMkSAO69915iY2P5+uuvAcjPz+eaa66hbt26/Pbbb5w4cYLhw4djGAYzZ84s9/kU1hQfH4+/v3+lPjciIiIiIuK40tLSiIqKsmWEs6lR3RctFgtffvklN9xwAwCGYRAZGcnYsWN57LHHAMjOziY8PJwXX3yR++67j9TUVOrWrcu8efO4/fbbATh8+DBRUVF89913DBgwgJ07d3LJJZewZs0aunTpAsCaNWvo1q0bu3btolmzZnz//fcMGjSI+Ph4IiMjAfjoo48YMWIEx44dK3fASktLIyAggNTUVIUyEREREZFarLzZoEY3+ti3bx8JCQn079/fts/T05NevXqxatUqwHp/ndzc3BJjIiMjadWqlW3M6tWrCQgIsAUygK5duxIQEFBiTKtWrWyBDGDAgAFkZ2ezcePGs9aYnZ1NWlpaiYeIiIiIiEh51ehQlpCQAEB4eHiJ/eHh4bZjCQkJeHh4EBQUdM4xYWFhpV4/LCysxJgz3ycoKAgPDw/bmLJMmzaNgIAA2yMqKqqCZykiIiIiIrVZjQ5lhc7sYmgYxnk7G545pqzxFzLmTBMnTiQ1NdX2iI+PP2ddIiIiIiIixdXoUBYREQFQaqbq2LFjtlmtiIgIcnJySE5OPueYo0ePlnr948ePlxhz5vskJyeTm5tbagatOE9PT/z9/Us8REREREREyqtGh7KYmBgiIiJYunSpbV9OTg4rVqyge/fuAHTs2BF3d/cSY44cOcL27dttY7p160Zqairr1q2zjVm7di2pqaklxmzfvp0jR47Yxvz44494enrSsWPHKj1PERERERGpvUxviZ+ens6ePXtsH+/bt4/NmzcTHBxMw4YNGTt2LFOnTqVJkyY0adKEqVOn4uPjw+DBgwEICAhg5MiRjB8/npCQEIKDg3nkkUdo3bo1V155JQAtWrRg4MCB3HPPPbz11luAtSX+oEGDaNasGQD9+/fnkksuITY2lpdffpmkpCQeeeQR7rnnHs1+iYiIiIhIlTE9lG3YsIE+ffrYPh43bhwAw4cPZ86cOUyYMIHMzExGjRpFcnIyXbp04ccffyzR6//VV1/Fzc2N2267jczMTPr27cucOXNs9ygDWLBgAWPGjLF1abzuuuuYNWuW7birqyvffvsto0aNokePHnh7ezN48GBeeeWVqv4UiIiIiIhILVaj7lPmDHSfMhERERERASe5T5mIiIiIiIizUygTERERERExkUKZiIiIiIiIiRTKRERERERETKRQJiIiIiIiYiKFMhERERERERMplImIiIiIiJhIoUxERERE5NQpyMmBY8esf546ZXZFUosolImIiIhI7ZaVBS+9BOHhRY+XXrLuF6kGbmYXICIiIiJimlOnrAHs2WeL9qWkFH08YQL4+ppSmtQemikTERERkdrL3R1ef73sY6+/bj0uUsU0UyYiIiLiRF78bajZJVyQx3rON+eNU1Ksj7MdS02FunWrsSCpjTRTJiIiIiK1V2Cg9XG2YwEB1ViM1FYKZSIiIiJSe+XmwujRZR8bM8Z6XKSKafmiiIiIiNReGRnWUGYYMGuWdcliYKA1kE2cCF5eZlcotYBCmYiIiIjUXvPmwTvvwLRpcPAgHD8OYWHWkKZAJtVEoUxEREREaq8PPoBdu+DGGyEmxtr+Pj0d9u41uzKpRRTKRERERKR22rLF+gDo0sXa1OPHH60fnzgBoaHm1Sa1ihp9iIiIiEjtNG9e0fawYdaZskKaKZNqpFAmIiIiIrVPXh4sWGDddneH22+Hxo2Lju/bZ05dUisplImIiIhI7bNsGSQkWLevuQZCQjRTJqZRKBMRERGR2ueDD4q2hw2z/qmZMjGJQpmIiIiI1C5pabBokXU7OBiuvtq6rZkyMYlCmYiIiIjULp9/DpmZ1u077gBPT+t2UJC1AyNopkyqlUKZiIiIiNQuZS1dBLBYimbL4uKszUBEqoFCmYiIiIjUHnFx8Msv1u2mTaFz55LHC68ry8+H+PhqLU1qL4UyEREREak95s8v2h42zDo7VpyafYgJFMpEREREpHYwjJJLF4cOLT1GzT7EBAplIiIiIlI7rFsHf/1l3e7VC6KjS4/RTJmYQKFMRERERGqHszX4KE4zZWIChTIRERERcX45OfDRR9ZtLy+45Zayx0VHF11nppkyqSYKZSIiIiLi/L77DpKSrNs33gj+/mWP8/KCyEjrtmbKpJoolImIiIiI8yvP0sVChdeVHT8O6elVV5PIaQplIiIiIuLcTpyAb76xbkdEwJVXnnt88evKtIRRqoFCmYiIiIg4t48/htxc6/aQIeDmdu7x6sAo1UyhTEREREScW0WWLoI6MEq1UygTEREREee1ezesXWvdbtsW2rQ5/3OKz5QplEk1UCgTEREREec1b17RdnlmyUDLF6XaKZSJiIiIiHMqKCgKZS4ucOed5XteRAR4elq3NVMm1UChTERERESc08qVcOCAdbt/f6hXr3zPc3Epuq5s3z4wjKqpT+Q0hTIRERERcU4XsnSxUGEoy8yEo0ftV5NIGRTKRERERMT5ZGTAp59at/384PrrK/Z8XVcm1UihTEREREScz1dfwcmT1u1bbwUfn4o9X23xpRoplImIiIiI86novcnOpJkyqUYKZSIiIiLiXI4cgR9/tG5HR8Nll1X8NTRTJtVIoUxEREREnMvChdZ2+ACxsdZuihVVPJRppkyqmEKZiIiIiDiX4ksXY2Mv7DUCAiA42LqtmTKpYgplIiIiIuI8tmyBrVut2126QNOmF/5ahdeVxcdDTk7laxM5C4UyEREREXEelW3wUVxhKDOMoptQi1QBhTIRERERcQ55edbryQDc3eH22yv3emr2IdVEoUxEREREnMOyZZCQYN0eNAhCQir3emqLL9VEoUxEREREnIM9ly6CZsqk2iiUiYiIiIjjS0uDL7+0bgcHw9VXV/41NVMm1UShTEREREQc32efQVaWdfvOO8HDo/Kv2bBh0T3ONFMmVUihTEREREQcn72XLoK1WUhUlHVbM2VShRTKRERERMSx7d8PK1ZYt5s1g0svtd9rF15XlpQEKSn2e12RYhTKRERERMSxzZ9ftD1sGFgs9nttXVcm1UChTEREREQcl2GUXLo4ZIh9X1+hTKqBQpmIiIiIOK516+Dvv63bvXtDdLR9X19t8aUaKJSJiIiIiOOqigYfxWmmTKqBQpmIiIiIOKbsbPjoI+u2tzfcfLP930MzZVINFMpERERExDF99521KyLAjTeCv7/93yMsDHx8rNuaKZMqolAmIiIiIo6pqpcugrWTY+Fs2b59UFBQNe8jtZpCmYiIiIg4nsRE+PZb63a9etC3b9W9V+F1ZTk5cORI1b2P1FoKZSIiIiLieD7+GHJzrdtDhoCbW9W9l64rkyqmUCYiIiIijqc6li4WUgdGqWIKZSIiIiLiWHbvtt6fDKBtW2jdumrfTzNlUsUUykRERETEscybV7Rd1bNkUHKmTKFMqoBCmYiIiIg4joKColDm4gKDB1f9exafKdPyRakCCmUiIiIi4jhWroQDB6zbAwZARETVv6evr/V+ZaCZMqkSCmUiIiIi4jiqs8FHcYVLGA8fhqys6ntfqRUUykRERETEMWRkwKefWrf9/eH666vvvYsvYdy/v/reV2oFhTIRERERcQyLFkF6unX71lvB27v63ltt8aUKKZSJiIiIiGMwa+kiqC2+VCmFMhERERGp+Q4fhqVLrduNGkHPntX7/popkyqkUCYiIiIiNd/ChdZ2+ACxsdZ2+NVJM2VShRTKRERERKTmK37D6NjY6n//Bg3Azc26rZkysTOFMhERERGp2bZsga1brdtdu0KTJtVfg5sbREdbt/fuBcOo/hrEaSmUiYiIiEjNZmaDj+IKlzCmpUFSknl1iNNRKBMRERGRmisvDxYssG67u8Ptt5tXi5p9SBVRKBMRERGRmmvpUjh61Lp97bUQHGxeLWr2IVWkxoeyvLw8nnrqKWJiYvD29qZx48Y8++yzFBR23wEMw2Dy5MlERkbi7e1N79692bFjR4nXyc7OZvTo0YSGhuLr68t1113HwYMHS4xJTk4mNjaWgIAAAgICiI2NJSUlpTpOU0RERETKUlOWLoJmyqTK1PhQ9uKLL/Lmm28ya9Ysdu7cyUsvvcTLL7/MzJkzbWNeeuklZsyYwaxZs1i/fj0RERH069ePkydP2saMHTuWL7/8ko8++ojffvuN9PR0Bg0aRH5+vm3M4MGD2bx5M0uWLGHJkiVs3ryZWDO6+4iIiIgIpKbCokXW7ZAQuOoqU8vRTJlUFTezCzif1atXc/3113PNNdcA0KhRIz788EM2bNgAWGfJXnvtNZ588kluuukmAObOnUt4eDgLFy7kvvvuIzU1lffee4958+Zx5ZVXAjB//nyioqJYtmwZAwYMYOfOnSxZsoQ1a9bQpUsXAN555x26devG7t27adasWZn1ZWdnk52dbfs4LS2tyj4XIiIiIrXKZ59BVpZ1+847wcPD3Ho0UyZVpMbPlPXs2ZOffvqJv/76C4AtW7bw22+/cfXVVwOwb98+EhIS6N+/v+05np6e9OrVi1WrVgGwceNGcnNzS4yJjIykVatWtjGrV68mICDAFsgAunbtSkBAgG1MWaZNm2Zb7hgQEEBUVJT9Tl5ERESkNqtJSxfBej2bn591WzNlYkc1PpQ99thj3HnnnTRv3hx3d3fat2/P2LFjufPOOwFISEgAIDw8vMTzwsPDbccSEhLw8PAgKCjonGPCwsJKvX9YWJhtTFkmTpxIamqq7REfH3/hJysiIiIiVvv3w8qV1u1mzaBTJ1PLAcBiKZoti4uDYpfBiFRGjV+++PHHHzN//nwWLlxIy5Yt2bx5M2PHjiUyMpLhw4fbxlkslhLPMwyj1L4znTmmrPHnex1PT088PT3LezoiIiIiUh7z5xdtDxtmDUQ1QUyM9WbWeXlw8GDRDaVFKqHGz5Q9+uijPP7449xxxx20bt2a2NhYHn74YaZNmwZAREQEQKnZrGPHjtlmzyIiIsjJySE5OfmcY44Wtlst5vjx46Vm4URERESkChlGyaWLQ4eaV8uZdF2ZVIEaH8oyMjJwcSlZpqurq60lfkxMDBERESxdutR2PCcnhxUrVtC9e3cAOnbsiLu7e4kxR44cYfv27bYx3bp1IzU1lXXr1tnGrF27ltTUVNsYEREREakGa9fC339bt/v0gYYNza2nuOKhTNeViZ3U+OWL1157LS+88AINGzakZcuW/PHHH8yYMYO7774bsC45HDt2LFOnTqVJkyY0adKEqVOn4uPjw+DBgwEICAhg5MiRjB8/npCQEIKDg3nkkUdo3bq1rRtjixYtGDhwIPfccw9vvfUWAPfeey+DBg06a+dFEREREakCNa3BR3Fqiy9VoMaHspkzZ/L0008zatQojh07RmRkJPfddx/PPPOMbcyECRPIzMxk1KhRJCcn06VLF3788Uf8CrvjAK+++ipubm7cdtttZGZm0rdvX+bMmYOrq6ttzIIFCxgzZoytS+N1113HrFmzqu9kRURERGq77Gz46CPrtrc33HyzufWcScsXpQpYDMMwzC7CmaSlpREQEEBqair+/v5mlyMiIiK1zIu/1aDrryrgsZ6nG3t88UVREBsypGTDj5ogK8saFgG6doXVq82tR2q08maDGn9NmYiIiIjUIjV56SKAlxdERlq3NVMmdqJQJiIiIiI1Q2IifPutdbtePejb19x6zqbwurKjR+HUKXNrEaegUCYiIiIiNcPHH1vv/wXWNvjFrv2vUYpfV7Z/v2lliPNQKBMRERGRmqH40sXYWPPqOB91YBQ7UygTEREREfPt2gWF94tt1w5atza1nHNSB0axM4UyERERETHfvHlF2zWxwUdxmikTO1MoExERERFzFRhFoczVFe6809x6zqf4TJlCmdiBQpmIiIiImKrh5qMQH2/9YMAAiIgwt6DziYwEDw/rtpYvih0olImIiIiIqVotKRZsavrSRQAXF2jUyLq9dy8YhqnliONTKBMRERER07hn5tH0lwPWD/z94brrzC2ovAqXMGZkwPHj5tYiDk+hTERERERM0+TXeDwzT9+b7LbbwNvb3ILKS80+xI4UykRERETENC1/cLCli4XUFl/sSKFMRERERExRJzGDRhsSrB/ExECPHuYWVBGaKRM7UigTEREREVNcsnQ/LgWnm2QMHWptoOEoNFMmduRAf/NFRERExGkYBq2WFJthio01r5YLoZkysSOFMhERERGpdmF7kqm7NxWAQ61CoUkTkyuqoMBACAqybmumTCpJoUxEREREql3xe5NtHxBzjpE1WOESxgMHIDfX3FrEoSmUiYiIiEi1suQVcMnS/QDkubuw64pocwu6UIVLGAsKrMFM5AIplImIiIhItYpZfwTf5CwA/ulenyx/T5MrukBq9iF2olAmIiIiItWqxNLFgY3PMbKGU7MPsROFMhERERGpNh7pOVz820EAMgI82dulnskVVYJmysROFMpEREREpNo0/+UA7jn5APx5ZSMK3F1NrqgSNFMmdqJQJiIiIiLVpmWxpYs7HLXrYqHoaLBYrNuaKZNKUCgTERERkWoRcDidhluOAXAi2p+E5sEmV1RJHh7QoIF1WzNlUgkKZSIiIiJSLVr+eMa9yQpnmRxZ4XVlJ05AWpq5tYjDUigTERERkapnGLT8wRrKDAvs6O/gSxcLFb+uTEsY5QIplImIiIhIlYvckUjwwZMAxLUP52S4r8kV2Yk6MIodKJSJiIiISJUrfm+yHY58b7IzFQ9luq5MLpBCmYiIiIhUKdecfJr/HAdAjpcrf/WKMrkiO1JbfLEDhTIRERERqVIXrT6E98kcAP66PIocH3eTK7IjLV8UO1AoExEREZEq1dJZly4ChIeDt7d1WzNlcoEUykRERESkyninZHHR6kMAnAz1Jq5DuMkV2ZnFUrSEcf9+KCgwtRxxTAplIiIiIlJlWvwUh2u+AcCf/RphuDrhj5+FoSwrCxISzK1FHJITfleIiIiISE1ReG8ygO3OtnSxkK4rk0pSKBMRERGRKhGyP5XInScASGgSRGLjQHMLqirqwCiVpFAmIiIiIlWi+CyZ0zX4KE4zZVJJCmUiIiIiYn8FBi1/tAaUAlcLf14ZbXJBVUgzZVJJCmUiIiIiYncN/ziK/7EMAPZ2rkdGsLfJFVUhhTKpJIUyEREREbG7VrVl6SKAnx/UrWvd1vJFuQAKZSIiIiJiV+6ZeTT95QAAWXXc2dOjvskVVYPC2bJDhyA729xaxOEolImIiIiIXTX5NR7PzDwAdvWJJs/TzeSKqkFhsw/DgLg4c2sRh6NQJiIiIiJ21WpJsaWLA2LOMdKJ6LoyqQSFMhERERGxmzrHM4jemABASr06HGxd1+SKqona4kslKJSJiIiIiN1csnQ/LgUGcHqWzMVickXVRDNlUgl2CWVZWVns2rWL/Px8e7yciIiIiDgiw6DVkqJAsr22LF0EzZRJpVQ4lM2cOZPnnnvO9vHGjRuJioqiZcuWNG3alPj4eLsWKCIiIiKOIezvZOruSwXgYKtQUhr4mVxRNYqKAldX67ZmyqSCKhzK3n33XQIDA20fP/bYYwQHB/Pqq69iGAbPP/+8PesTEREREQdRvMHHdme/N9mZ3NygYUPrtmbKpIIq3J/0wIEDNG/eHICTJ0+ycuVKPvroI2666SaCgoJ45pln7F6kiIiIiNRslrwCLlm2H4A8dxd2XdHQ3ILM0LixNZClpEByMgQFmV2ROIgKz5RlZ2fj7u4OwOrVqykoKODKK68EoFGjRiQkJNi3QhERERGp8WLWH8E3OQuAPT0akO3naXJFJlCzD7lAFQ5lDRs25NdffwXgq6++ol27dvj7+wNw/Phx27aIiIiI1B4lly7WogYfxanZh1ygCi9fHDp0KFOmTGHRokVs2bKFV155xXZsw4YNNG3a1K4FioiIiEjN5nkyhya/WZu9ZQR4sq9LpMkVmUQzZXKBKhzKnnzySdzc3Fi1ahU33ngjY8aMsR3bvn07N910k10LFBEREZGardkvB3DLKQDgzysbUeBWS2+Fq5kyuUAVDmUWi4XHH3+8zGOLFy+udEEiIiIi4lha/VA0K7Sjti5dBM2UyQWr8K8xGjduzJYtW8o8tn37dho3rmXtT0VERERqsYDDJ4nachyAxGh/EpoFm1yRiUJDoU4d67ZmyqQCKhzK9u/fT3Z2dpnHsrKyiIuLq3RRIiIiIuIYWv6w37a9fWBjsFjMK8ZsFkvRbNn+/ZCfb2o54jguaMGv5SzfbHv37sXPrxbduV1ERESkNjMM29JFwwJ/9mtkbj01QeGqsdxcOHzY3FrEYZTrmrK5c+cyd+5c28f3339/qdb3mZmZbNmyhV69etm3QhERERGpkSJ3JBJ0KB2AuA4RnAz3NbmiGuDM68qiosyrRRxGuUJZRkYGx49b1wpbLBZSUlJKLWH09PTk9ttvZ8qUKfavUkRERERqHN2brAxndmDUhIWUQ7lC2f3338/9998PQExMDJ9//jlt27at0sJEREREpOZyzcmnxU/WXgI5Xq78dblmhICSoUwdGKWcKtwSf586yYiIiIjUehetOoRXeg4Af/VqSK6Pu8kV1RBqiy8XoMKNPrZu3crKlSttH6enpzNq1Ci6du3KM888g2EYdi1QRERERGqeVj8U/aJ+xwAtXbRp1KhoW5MZUk4VDmXjxo3jm2++sX385JNP8s4775CTk8O0adOYNWuWXQsUERERkZrFOzmLxqsPAXAy1Ju4DuEmV1SD+PhARIR1WzNlUk4VDmXbt2+ne/fuABiGwYIFC5gyZQqbNm3iscce4/3337d7kSIiIiJSc7T4KQ7XfOvqqB39YzBcL+guS86r8LqyhATIyDC3FnEIFf4OSklJITQ0FIAtW7aQnJzMbbfdBkDfvn3Zq98IiIiIiDi1wnuTgZYulqn4dWX795tWhjiOCoeykJAQ4uPjAVi+fDnh4eFcfPHFAOTk5OiaMhEREREnFrI/lXq7kgBIaBpMYuNAcwuqic5siy9yHhXuvnjZZZcxefJkEhMTefXVV7nmmmtsx/7++2+idIM8EREREafV8gfdm+y81IFRKqjCM2XTpk3DYrHw0EMP4enpyTPPPGM79umnn9K1a1e7FigiIiIiNUSBQcsfraGswNXCzisbmVtPTaWZMqmgCs+UxcTEsGvXLpKSkggODi5xbNasWUQUdpsREREREafS8I+j+B+zNq7Y2yWSjCAvkyuqoXQDaamgCoeyQmcGMoDWrVtXqhgRERERqblaLdHSxXKJjAR3d8jNVSiTcrmg/qW7du3izjvvpF69enh4eLBp0yYApkyZwvLly+1aoIiIiIiYzz/Pm+aJ/hAaSlYdd/Z0b2B2STWXq2vRTaT37QM1wpPzqHAo27x5M5deeikrVqygd+/e5Ofn246lp6fz5ptv2rVAERERETFPiHckt8WM5r4u/8H9ky9g/35ylnxDYKCau51TYbOP9HRITDS3FqnxKhzKHn/8cdq0acOePXuYN29eiRb4nTt3Zv369XYtUERERETMEeIdSWzziUS//S0ukfWt10o1aECdH34jtvlEQrwjzS6x5lKzD6mACoey33//nQkTJuDj44PFYilxLDw8nISEBLsVJyIiIiLm6RtxM+4vvYrLs89BSop1Z0oKLs89h/tLr9I34mZT66vR1BZfKqDCocwwDDw8PMo8lpycjKenZ6WLEhERERFzebv50TC0NS6vzyzzuMvrM2kY2hpvN79qrsxBaKZMKqDC3RfbtGnDl19+yVVXXVXq2JIlS+jYsaNdChMRERGxt7u+H2d2CRdk9lUzqv09fT0CMI4fL5ohO1NKCvnJSfh6BJCZd7Jaa3MImimTCqhwKHvooYcYPHgwvr6+xMbGAnDgwAF+/vln3n//fT777DO7FykiIiIi1cc1O58ub/yM2ztPQ2Bg2cEsMBDXoGBO7U+t7vIcg2bKpAIqHMpuv/12/vnnHyZPnszrr78OwM0334ybmxtTpkzh2muvtXuRIiIiIlI9/I6e4sanVlJvVxLcvgwefBCef77UuIIxozmQuE2zZGcTFAQBAZCaqpkyOa8Lunn0E088wbBhw/jhhx84evQooaGhDBgwgOjoaHvXJyIiIiLVJHpDAtdN/g2f1GwAcp95ElauxNXFYr22LCUFAgMpGDOa3AkP89OuaeYWXNM1bgx//AEHDkBeHrhd0I/eUgtc8N+MBg0aMHLkSHvWIiIiIiJmMAw6L/yTXm9vwaXAeruj5Mg6fPlwNAV7/k3fe2+m4ROPk5+chGtQMAeOb+WnXdM4kXnY5MJruMJQlp8P8fElrzMTKabCoezAgQPnHdOwYcMLKkZEREREqpdHRi5XT11NsxXxtn3/dI3k62e6k+3nCZmH+WTfTLzj/fD1CODU/lQtWSyvM5t9KJTJWVS4JX6jRo2IiYk558PeDh06xNChQwkJCcHHx4d27dqxceNG23HDMJg8eTKRkZF4e3vTu3dvduzYUeI1srOzGT16NKGhofj6+nLddddx8ODBEmOSk5OJjY0lICCAgIAAYmNjSTlbxyERERERBxccl0rsvUtKBLLf7mrNZy/2tgayYjLzTpKYcVCBrCLU7EPKqcIzZe+//36pm0YnJiayePFiDh48yFNPPWW34sAalHr06EGfPn34/vvvCQsL459//iEwMNA25qWXXmLGjBnMmTOHpk2b8vzzz9OvXz92796Nn5/13hljx47l66+/5qOPPiIkJITx48czaNAgNm7ciKurKwCDBw/m4MGDLFmyBIB7772X2NhYvv76a7uek4iIiIjZmqyM55oXVuGZkQdAVh13vnmqO//0aGByZU5EbfGlnCocykaMGFHm/vHjx3PrrbcSHx9f5vEL9eKLLxIVFcXs2bNt+xo1amTbNgyD1157jSeffJKbbroJgLlz5xIeHs7ChQu57777SE1N5b333mPevHlceeWVAMyfP5+oqCiWLVvGgAED2LlzJ0uWLGHNmjV06dIFgHfeeYdu3bqxe/dumjVrZtfzEhERETGDJb+Ay97dSrf5RauKjjcO4IsXepHSQDeCtivNlEk5VXj54rmMGDGCd999154vyeLFi+nUqRO33norYWFhtG/fnnfeecd2fN++fSQkJNC/f3/bPk9PT3r16sWqVasA2LhxI7m5uSXGREZG0qpVK9uY1atXExAQYAtkAF27diUgIMA2pizZ2dmkpaWVeIiIiIjURN4pWdz66PISgezPvtHMe3OgAllViI6GwhVmmimTc7BrKMvLy7P7NVh79+7lf//7H02aNOGHH37gX//6F2PGjOGDDz4AICEhAYDw8PASzwsPD7cdS0hIwMPDg6CgoHOOCQsLK/X+YWFhtjFlmTZtmu0atICAAKKioi78ZEVERESqSPjuJIbfs4SY9dafawpcLfw0uiNfT+pBrrdatVcJT0+oX9+6rZkyOQe7fAfm5uaydetWJk2aRNu2be3xkjYFBQV06tSJqVOnAtC+fXt27NjB//73P4YNG2Ybd+Z1boZhlNp3pjPHlDX+fK8zceJExo0bZ/s4LS1NwUxERERqlFbf/cOA6etwyykA4FSQF19N6Ul8+/DzPFMqLSYGDh6E48chPR3q1DG7IqmBKhzKXFxczhpSgoKC+OGHHypdVHH16tXjkksuKbGvRYsWfP755wBEREQA1pmuevXq2cYcO3bMNnsWERFBTk4OycnJJWbLjh07Rvfu3W1jjh49Wur9jx8/XmoWrjhPT088PT3PelxERETELC65+fR9fSMdFv1t23eoZSiLnruM9Lo+JlZWizRuDL/+at3etw9atza3HqmRKhzKnnnmmVKhzMvLi0aNGnH11Vfbuh3aS48ePdi9e3eJfX/99RfR0dEAxMTEEBERwdKlS2nfvj0AOTk5rFixghdffBGAjh074u7uztKlS7ntttsAOHLkCNu3b+ell14CoFu3bqSmprJu3To6d+4MwNq1a0lNTbUFNxERERFHUed4Bjc8/Sv1dyTa9m26oQk/j+5IvoeriZXVMmd2YFQokzJUOJRNnjy5Cso4u4cffpju3bszdepUbrvtNtatW8fbb7/N22+/DViXHI4dO5apU6fSpEkTmjRpwtSpU/Hx8WHw4MEABAQEMHLkSMaPH09ISAjBwcE88sgjtG7d2taNsUWLFgwcOJB77rmHt956C7C2xB80aJA6L4qIiIhDifrjKNdP+g3f5CwA8jxc+GF8Z7ZffZHJldVC6sAo5VDjr+q89NJL+fLLL5k4cSLPPvssMTExvPbaawwZMsQ2ZsKECWRmZjJq1CiSk5Pp0qULP/74Y4lZu1dffRU3Nzduu+02MjMz6du3L3PmzLHdowxgwYIFjBkzxtal8brrrmPWrFnVd7IiIiIilWEYdPp4J33+9wcu+QYAqRG+fPn8ZRxtFmJycbVU8VCmDoxyFhbDMIyKPOHuu+8u/4tbLLz33nsVLsqRpaWlERAQQGpqKv7+/maXIyIiIsXc9f248w+qgWZfNeP8g06dgv/7P/joI9uufZdG8PUzPcgM9KrC6uzjsZ7zzS6hahw+XNSB8Zpr4JtvzK1HqlV5s0GFZ8qWL19OSkoKqampuLm5ERISwokTJ8jLyyMgIIDAwEDb2PN1PxQRERERO9izB268EbZvt+1aPbQlv/5fGwxXu94BSSoqIgK8vCArS8sX5awq/F36ySefUKdOHRYsWEBmZiZHjhwhMzOT+fPn4+vry8cff8y+ffvYt28fezVFKyIiIlK1vvkGOnWyBbJsHze+eOFyVt7XToGsJnBxgUaNrNv79kHFFqlJLVHh79Tx48fzyCOPcOedd9qux3J1dWXw4MGMHz+ehx9+2O5FioiIiMgZCgpg0iS49lpITbXua96cD94eyN+X656pNUrhdWWZmVDGLZhEKhzKNm7cSKtWrco81rp1azZv3lzZmkRERETkXJKTrWHs2WeL9t18M6xbR1J0gHl1SdnObIsvcoYKhzJ/f3+WLVtW5rFly5apuYWIiIhIVdqyxbpc8bvvrB+7uMCLL8Knn4Kd7xcrdqK2+HIeFW70ERsby8svv0xeXh6DBw8mIiKChIQEFixYwGuvvca4cY7Z1UhERESkxluwAO65x7oMDiA01NptsW9fc+uSc9NMmZxHhUPZ1KlTOXbsGNOnT2fGjKL2rIZhMHToUKZOnWrXAkVERERqvdxceOQReP31on2dOsHnn0PDhubVJeWjmTI5jwqHMjc3N+bMmcPEiRP5+eefSUpKIiQkhN69e9O8efOqqFFERESk1gpISocrroDffivaOXIkzJplbbUuNZ9myuQ8KhzKCjVr1oxmzZrZsxYRERERKebiPw8zauo3kHTKusPDwxrG7rnH3MKkYvz9ISQETpxQKJMyXdDNK7Kzs3nrrbe488476d+/P3///TcAX331le5NJiIiIlJZhsEVX2/mscc+JagwkNWvDytXKpA5qsIljAcPQk6OubVIjVPhmbLExET69OnDjh07iIiI4OjRo5w8eRKARYsW8cMPP/DGG2/YvVARERGR2sA9O4/hs5bR46edRTt794aPP4awMNPqkkqKiYH16603j46LgyZNzK5IapAKz5RNmDCBlJQUNmzYwIEDBzCK3ZW8T58+rFixwq4FioiIiNQWoQmpPDn+oxKBbMlNHWHpUgUyR6dmH3IOFZ4p++abb3jxxRfp0KED+fn5JY41aNCAgwcP2q04ERERkdqi1Yb93PfSd9RJzwYgy8ud98f2Y/3lzRjodsFtAKSmULMPOYcKf4enpaURHR1d5rHc3Fzy8vIqXZSIiIhIbWEpMBj08TpumL8Kl9MLkBIiA5n59LUcjg41tzixH82UyTlUOJTFxMSwevVqrrjiilLH1q1bp46MIiIiIuXkfSqbe6Yvof2aopmTP7o25p3xA8n09TSxMrE7zZTJOVT4mrIhQ4bw4osv8tVXX9muJ7NYLKxfv57//Oc/xMbG2r1IEREREWcTGZfIMw8ttAWyAgt8Pqw7M5+6ToHMGTVsCC6nf/TWTJmcocIzZY899hi///47N954I0FBQQAMGDCAEydOMHDgQB566CG7FykiIiLiTC5duZu7X1uKV1YuAOl1PHlrwtVs79TI3MKk6ri7Q1SUtfOiZsrkDBUOZe7u7nz33Xd8/PHHfPvttxw9epTQ0FAGDRrEHXfcgYvLBd36TERERMTpueQXcOvs3xj4xUbbvrjGdfnvk4M4Xi/QvMKkejRubA1lycmQkgKBgWZXJDXEBbXysVgs3HHHHdxxxx0l9huGwfz58xk6dKhdihMRERFxFn4pGdz/729psbWoU/XvV7Tggwf7kuPlbmJlUm0aN4bly63b+/ZB+/bm1iM1ht2mtT7++GNatmzJ8OHD7fWSIiIiIk6h8a4jTB6zwBbI8lxdmHd/H94dP0CBrDZRsw85i3KHsn//+9/ExMTg4+ND+/btWbJkCQCrVq2iXbt2DB48mOTkZGbNmlVlxYqIiIg4msuXbOPxCZ8SnJgOQHKwLy/++xZ+vrYdWCzmFifVS23x5SzKtXzxv//9L0888QQBAQG0bt2a+Ph4brjhBmbOnMkDDzyAu7s7zzzzDI888gi+vr5VXbOIiIhIjeeWk0fsG8u5/Mfttn1/tYzkjYnXkBpcx8TKxDSaKZOzKFcoe//99+nZsyfffvstfn5+5Ofnc//99/Ovf/2LRo0a8cMPP3DxxRdXda0iIiIiNZKfhy8BHv6k5qRxMucUwcfSePCFb4j5+6htzNLr2vHx/11OvpuriZWKqTRTJmdRrlC2e/du5s+fj5+fHwCurq489dRTvPvuuzz33HMKZCIiIlIr1fMNY0ijATQLa05e8gncgkKI3/MHYc88gO/pQJbt6cbc0Vey+ooWJlcrpqtbF3x8ICNDM2VSQrmuKcvIyCAyMrLEvvr16wPQpEkT+1clIiIiUsPV8w3j6Q7/osW7X+JWLxKvyCjc6kXS6OPv8f3uR2jenGMRAbww/Q4FMrGyWIpmy/bvh4ICU8uRmqPcLfEtZ7kQ1c3tgrrqi4iIiDi0IY0G4PnSDFyee65oZ0oKluefB+Dkf19lSuJiMvy8TKpQaqSYGNi+HXJy4PBhaNDA7IqkBih3oho/fjyBxW5wZxgGAGPHjiUgIMC232Kx8NVXX9mvQhEREZEaxs/Dl2ZhzXGZObPsAbNm4f3kE7j+/jvknKre4qRmO/O6MoUyoZyhrGHDhsTHxxMfH19if3R0NAcOHCix72wzaiIiIlLz9ZzzpNklVNhvI16o1vfzTs/iij0ncbn4KKSklD0oJYX8lCQCPPw5qVAmxRUPZXv3wmWXmVeL1BjlCmX79++v4jJEREREai7XvHxaboqjx087ab/mH9wDgmDMaxAYWHYwCwzENTCY1Jy0aq5UarzibfHVgVFO0wVhIiIiImUxDKL2HqfHT3/S9ZfdBKRkFB1LTIRlyzAefNB2DVlx+WNGs+voLs2SSWlnzpSJoFAmIiIiUkJAUjrdlu+i+087idqfWOp4WoA3a3o356+TvzHysSfxcLHg+vpM64xZYCD5Y0aT8+g4Fm56s/qLl5qvUaOibYUyOU2hTERERGo9j6xc2q/5h+4/7aTVH3G4FBgljue6ubK5a2N+79uC7R0bnb4BdD6HN73J4LtvpPnEieSnJOEaGMyuoztZuOlNjpw6Zs7JSM3m6wvh4XD0qJYvio1CmYiIiNRKlgKDJjsO0eOnnVz66194Z+aUGrOnRT1+v6IF6y5vVmZr+yOnjjH9z3n47fElwMOf1Jw0LVmU84uJsYayw4chMxO8vc2uSEymUCYiIiK1StjhFLr/9Cfdf95J3aOlG3Ekhvnze98WrL6iBUfrB5XrNU/mnFIYk/Jr3BjWrLFux8VB8+bm1iOmK1coGzduHA8//DBRUVEcOHCAevXq4e7uXtW1iYiIiNhHcjJ88glP/Ocjmuw8UupwprcH6y9rwqq+l/BXy/oYLrrFj1Sh4h0Y9+5VKJPyhbLXXnuNO+64g6ioKGJiYli9ejWdO3eu6tpERERELlxuLvzwA3zwASxeDNnZNCl2uMDFwo72DVl1xSVs6nYROV76hbNUkzNvIC21XrlCWVBQEEePHgXAMAzdIFpERERqJsOAzZutQWzhQjhWutnGwegQfu97CWv6NCclpE711yhy5kyZ1HrlCmVdu3Zl5MiRttmx8ePHExgYWOZYi8XCV199ZbcCRURERM7r8GFYsMAaxrZvL328bl0YMoRJFx3nQOO6oF8wi5k0UyZnKFcoe+ONNxg7diw7duzAYrGwZ88ePD09yxyrWTQRERGpDp7ZuVy+6S/4aCAsXQoFBSUHeHjA9dfDsGEwYAC4u3Pg+3HmFCtSXIMG4OYGeXmaKROgnKEsOjqaL7/8EgAXFxcWLVqka8pERESk2lkKDNr+dYCBq7bTZ/1OfLNKt7Gne3drELvtNggqX/dEkWrl6grR0fDPP9ZQZhiava3lKtwSf/ny5VxyySVVUYuIiIhImRokJDFg9TYGrNpOZGJq6QGNGkFsrPXRpEnp4yI1TePG1lB28iQkJUFIiNkViYkqHMp69eoFwJ49e/j55585ceIEoaGh9OnTh4svvtjuBYqIiEjt5HcqkyvW7WTg79to/c+hUsdPeXnw86UtuPb516FnT3BxMaFKkQt0ZrMPhbJarcKhzDAMRo8ezZtvvklBsbXbLi4ujBo1itdff92uBYqIiEjt4ZqXT9ftexn4+zZ6bP4bj7z8EsfzLRbWt4phSffW/Nq+Kdme7lx7+eUmVStSCWc2+7j0UvNqEdNVOJS9+uqrvPHGG9x///2MGDGCyMhIDh8+zNy5c3njjTeIiYnh4YcfropaRURExAEFevoQ7O1HUuZJUrIzSg8wDJrGHWXgqm30W7ODoJOlx/xTvy5LerTmx26tOBGoNvbiBNQWX4qpcCh79913GT16NP/5z39s++rXr8+ll16Kq6sr77zzjkKZiIiIEB1Ql7GtrqBdVBPykk7gFhzCH/F/8Z/ty4lLPU5I8kn6r9nBVb9vpfGhxFLPT/L3YWnXlnzfow17osLUCEGci9riSzEVDmV79+5l0KBBZR4bNGgQb731VqWLEhEREccWHVCXt6+8C6+Xp+M6cybuKSkQGEjH0aN5f9zD7Bp2G62++QlXwyjxvGw3V35r35QlPVqzrmUM+W6u5pyASFXTTJkUU+FQFhAQQFxcXJnH4uLi8Pf3r3RRIiIi4tjGtrrCGsiee65oZ0oKrs89h6th0PbuB+DrZbZDW5s0YEn31vzcuQXpPl4mVCxSzYKDwd8f0tI0UyYVD2X9+vXjqaeeon379nTs2NG2f/PmzUyaNIkBAwbYtUARERFxLIGePrSLaoLrzJllD5g1Cw4eJKFZY75rFskP3VtxKDy4eosUMZvFYp0t27IF4uIgP996/zKplSocyqZNm8Yvv/xC586dueSSS6hXrx5Hjhzhzz//JDIykmnTplVFnSIiIqZr+8oks0uosC2PTKn29wz29iMv6YR1yWJZUlLITknmsWlj+Cf1WLXWJlKjNG5sDWV5eXDwoPWG0lIrVfiGHlFRUWzevJkJEybg6+vLvn378PX15fHHH+ePP/6gQYMGVVGniIiIOIikzJO4B4VAYGDZAwIDcQkJ4URWerXWJVLjFG/2oevKarUKz5QBhIaGakZMREREylR/x18YfsvgwQfh+edLHc8fM5o/4v8quz2+SG1yZrOPPn3Mq0VMdUGhTERERKQsXbfs4fk3vsC98TpYuRIDsMyaBae7L+aPGU3WI+P5z7LZZpcqYj61xZfTKrx8UURERKQsA1Zt49+vf4pXTh7s2sW2u+9k09CbyD1ymMzDB8k9cpiNQ2/i3mWziUs9bna5IuZTW3w5TTNlIiIiUml3LFnLgx//ZPt4WecWvHBdR3JXf0bgJh+Cvf1IyjypJYsixTVqVLStmbJaTaFMRERELpxhcP+nyxny/Rrbrs/6duQ/g/tjuFgASMnOUBgTKYuXF0RGwuHDmimr5Sq8fDEnJwfDMKqiFhEREXEgrvkFTHz/2xKB7J0bL+e1IUWBTETOo/C6smPH4NQpc2sR01QolGVlZeHt7c2iRYuqqBwRERFxBJ7ZuUyd+RnX/LYVgAILvDxsIHOv62m9Ka6IlE/x68q0hLHWqlAo8/LyIiQkBF9f36qqR0RERGo4v1OZvDr9Q3ps2QNAjpsrT4+6ia/6dDC5MhEHpA6MwgUsX7z22mv58ssvq6IWERERqeFCk0/y32nzaPP3QQBOeXkwftztrOjU3OTKRByUbiAtXECjjzvuuIORI0dy9913c9NNN1GvXj0sZyxT6NBBvykTERFxNlFHTvDq9A+JOJEGQJK/D+PH3cHf0REmVybiwLR8UbiAUDZgwAAA5syZw9y5c0scMwwDi8VCfn6+faoTERGRGqH53sO8/OrHBKVnAnCobiDjxt/BofBgkysTcXCaKRMuIJTNnj27KuoQERGRGurS7Xt5Ydbn+GTnAvB3VBjjx99BUkAdkysTcQL16oGnJ2RnK5TVYhUOZcOHD6+KOkRERKQG6rt2B0+98zXu+QUA/NGsIY+PuYVTPl4mVybiJFxcrDeR3r3bunzRMNTBtBaqcKOP4nbv3s3vv//OKd1TQURExOncvGw9k976yhbIVnRoyvjxdyiQidhb4XVlGRnW+5VJrXNBoeyDDz6gQYMGXHLJJVx++eXs3r0bgNtuu4133nnHrgWKiIhINTMM/u+LFTy8YCkuhnXX4l7tePqBm8hxr/AiGxE5H7XFr/UqHMo+/fRTRowYQYcOHZg1axaGYdiOdejQgU8++cSuBYqIiEj1cSko4NG53zPi699t++Zc24OXhl9FgUulFtiIyNkU78Co68pqpQr/6zpt2jTuuusuFi9ezL333lviWIsWLfjzzz/tVpyIiIhUo6wsnvvvF1y/YjMABRZ4dUg/3r2pl65xEalKmimr9Socynbu3Mkdd9xR5rHg4GBOnDhR6aJERESkmqWmwsCB9Nr0FwC5ri5Mue96Pr/yUpMLE6kFNFNW61V4YbiPjw+pqallHjt06BBBQUGVLkpERESqUUICDBwIW7YAkOHpzhOjb2FDy5jzPFFE7EIzZbVehWfKevToUepaskJz5syhd+/e9qhLREREqsM//0CPHrZAllzHmzEThiiQiVSngAAIPn0jds2U1UoVnil75pln6NmzJ507d2bw4MFYLBa++OILJk2axMqVK1m3bl1V1CkiIiL29scf1hmywhbc0dGMum8g8fVCzK1LpDaKiYGkJIiPh9xccHc3uyKpRhWeKevUqRPff/896enpjB8/HsMwmDp1Kn/99RffffcdrVq1qoo6RURExJ6WL4devYoCWatW8PvvCmQiZilcwlhQAAcOmFuLVLsLutlInz592LlzJ//88w9Hjx4lNDSUpk2b2rs2ERERqQqffw6DB0NOjvXjHj3g669B14WLmOfMZh8XXWReLVLtKnUHyIsuuoiL9BdGRETEcbz1Ftx/PxReGz5oEHz8Mfj4mFuXSG2nZh+12gXdBXL//v3cd999NG3alJCQEJo2bcp9993HPv0FEhERqZkMA557Dv71r6JANnw4fPGFAplITaC2+LVahUPZ5s2bad++PXPmzKF+/fr079+f+vXrM2fOHNq3b8/mzZuroEwRERG5YAUFMHo0PPNM0b4JE2D2bDUTEKkpNFNWq1V4+eLYsWOpW7cuy5Yto2HDhrb9cXFx9OvXj4cffpjly5fbtUgRERG5QNnZ1hmxjz8u2vfKKzB+vHk1iUhpDRuCxWKdydZMWa1T4ZmydevWMWXKlBKBDCA6OprJkyezdu1auxUnIiIiF84nK7vomjEAV1eYO1eBTKQm8vCAqCjrtmbKap0Kz5QFBAQQEBBQ5rHAwED8/f0rXZSIiIhUTlD6KWa99yEcPGzd4e0Nn30GV19tbmEicnaNG1vb4Z84AWlpoJ+ra40Kz5QNHjyYd999t8xj77zzDnfeeWelixIREZELF5mUwtz/zqZVYSALCoKfflIgE6npijf70GxZrVKumbIvvvjCtt2xY0c+++wzOnfuzJ133klERAQJCQl8+OGHHDt2jFtvvbXKihUREZFzu/jIUf737gLC0tKtO+rXhx9+gJYtzS1MRM6veLOPvXuhbVvzapFqVa6ZsltuuYVbb72VW265hdjYWOLj49mwYQPjx49nyJAhjB8/ng0bNnDgwAFiY2OrtOBp06ZhsVgYO3asbZ9hGEyePJnIyEi8vb3p3bs3O3bsKPG87OxsRo8eTWhoKL6+vlx33XUcPHiwxJjk5GRiY2NtSzRjY2NJSUmp0vMRERGxl/b7DjD7f3NtgWxvWCisWqVAJuIo1Ba/1irXTFlN6aa4fv163n77bdq0aVNi/0svvcSMGTOYM2cOTZs25fnnn6dfv37s3r0bPz8/wNo18uuvv+ajjz4iJCSE8ePHM2jQIDZu3IirqytgXZp58OBBlixZAsC9995LbGwsX3/9dfWeqIiISAX12rGbl+Z/jldeHgBbG9Zn9N13suKMxlwiUoOpLX6tVa5Q1qtXr6qu47zS09MZMmQI77zzDs8//7xtv2EYvPbaazz55JPcdNNNAMydO5fw8HAWLlzIfffdR2pqKu+99x7z5s3jyiuvBGD+/PlERUWxbNkyBgwYwM6dO1myZAlr1qyhS5cugPUauW7durF7926aNWtW/SctIiJSDtev38wzn32NW4H1ptC/N72I8cNvJdPDw+TKRKRCNFNWa1W40YdZHnjgAa655hpbqCq0b98+EhIS6N+/v22fp6cnvXr1YtWqVQBs3LiR3NzcEmMiIyNp1aqVbczq1asJCAiwBTKArl27EhAQYBtTluzsbNLS0ko8REREqoVhcNfy33n2k8W2QPZt+1aMuesOBTIRRxQebu2UCpopq2Uq3BIfYNGiRSxYsIC4uDiysrJKHLNYLGzZssUuxRX66KOP2LRpE+vXry91LCEhAYDw8PAS+8PDw4mLi7ON8fDwICgoqNSYwucnJCQQFhZW6vXDwsJsY8oybdo0pkyZUrETEhERqSRLgcG4b5cybOUa2755l3Vh+qD+GC4WEysTkQtmsVhny/780xrKCgrAxWHmUKQSKvxVfvnll7nppptYuXIl7u7uhISElHgEBwfbtcD4+Hgeeugh5s+fj5eX11nHWSwl/wMyDKPUvjOdOaas8ed7nYkTJ5Kammp7xMfHn/M9RUREKsstP5/nP15UIpD956oreOVaBTIRh1d4XVl2NpxjYkCcS4Vnyt544w3uvvtu3nrrLVuDjKq0ceNGjh07RseOHW378vPzWblyJbNmzWL37t2AdaarXr16tjHHjh2zzZ5FRESQk5NDcnJyidmyY8eO0b17d9uYo0ePlnr/48ePl5qFK87T0xNPT8/KnaSIiEg5eefk8PK8z7hs1x4A8i0WnrtlEF92bm9yZSJiF2deVxYZaV4tUm0qPFN24sQJBg8eXC2BDKBv375s27aNzZs32x6dOnViyJAhbN68mcaNGxMREcHSpUttz8nJyWHFihW2wNWxY0fc3d1LjDly5Ajbt2+3jenWrRupqamsW7fONmbt2rWkpqbaxoiIiJgp4FQGb701zxbIst1cGTfsNgUyEWeiDoy1UoVnynr06MHOnTu54oorqqKeUvz8/GjVqlWJfb6+voSEhNj2jx07lqlTp9KkSROaNGnC1KlT8fHxYfDgwQAEBAQwcuRIxo8fb1ti+cgjj9C6dWtb45AWLVowcOBA7rnnHt566y3A2hJ/0KBB6rwoIiKmC09J5X/vLOCiY4kApHl58tBdd7CpcbTJlYmIXZ15A2mpFSocyl577TVuvPFGoqKiGDhwIB41oLvThAkTyMzMZNSoUSQnJ9OlSxd+/PFH2z3KAF599VXc3Ny47bbbyMzMpG/fvsyZM6fEjN+CBQsYM2aMrUvjddddx6xZs6r9fERERIqLOXqcN99ZQESqtcPvcb863P9/Q/g78uzL60XEQRVfvqiZslqjwqHs4osv5sorr+TGG2/EYrHg4+NT4rjFYiE1NdVuBZbll19+KfWekydPZvLkyWd9jpeXFzNnzmTmzJlnHRMcHMz8+fPtVKWIiEjltY47yKz3PyQwIxOAuNBg7r9nCIeCg87zTBFxSLpXWa1U4VA2YcIEZs2aRbt27WjRokWNmCkTERFxRj12/c30Dz7DOzcXgD/r1+OB/xtMUh1fkysTkSpTpw7UrQvHjyuU1SIVDmVz5szhscceY9q0aVVRj4iIiABXb9rGsx9/hXtBAQBrL27Ew8Nv55SXOv6KOL3Gja2h7PBhyMqCc9wWSpxDhbsv5ufn069fv6qoRURERIChK9cw7cMvbYHshzaX8MDIwQpkIrVF4RJGw4C4OHNrkWpR4VDWv39/1qxZc/6BIiIiUi5B3j5cHBpGkJc3D323jEe//tF27KNunXh8yE3kulV4cYuIOCq1xa91Kvwv/NNPP83tt9+Or68v11xzDcHBwaXGlLVPRERESooJDuWxrr3pFHMxuUkn8AoKxqVBczgyEXbt4o1+vXir3+VgsZhdqohUJzX7qHUqHMratm0LwLhx4xg3blyZY/Lz8ytXlYiIiJOLCQ5lwS3D8HplOq4zZ+KekgKBgfDggxgrV/Lmc0/zVkO1vBeplTRTVutUOJQ988wzWPQbOxERkUp5rGtvayB77rminSkp8PzzGBYL7f41Cr773LT6RMREmimrdSocys51LzARERE5vyBvHzrFXIzrWe6d6TJzJp0mTiTI24fkzIxqrk5ETBcVBa6ukJ+vmbJaQlcNi4iIXXR88lmzS6iwjS88Y8r7hvjWITfphHXJYllSUshNTiLEt45CmUht5OYG0dHWWbJ//rF2YdRKNadW4VD27LPn/k/XYrHw9NNPX3BBIiIizu7EqXTcg0Os15CVFcwCA3EPCubEqfTqLk1EaoqYGGsoS0uD5GRQIz2nZvfliwplIiIi55acmcGO3X/S7sEH4fnnSx3PHz2aDfv+1iyZSG3WuDH89JN1e98+hTInV+H7lBUUFJR6JCYm8u6779KqVSv2799fBWWKiIg4l8SpL8CYMfDUU9YZM4DAQPKffpqsR8bz4poVptYnIiZTs49apcKhrCzBwcHcfffdDB48mDFjxtjjJUVERJxWWEoavb74Ci6/nNxLLyX38GEyDh0k9/Bh1t5+M0M++4B9SYlmlykiZlJb/FrFro0+OnfuzNSpU+35kiIiIk5n6K9rcM8vgF27mPOfl1kQv5MQ3zqcOJWuJYsiYqWZslrFrqFsy5Yt1KlTx54vKSIi4lT8MjK5Ze0mALLc3FjYszPJmRkKYyJSkmbKapUKh7IPPvig1L7s7Gy2bt3K+++/z9ChQ+1SmIiIiDO6ffUGfLNzAPjq0nYk+emXmSJShpAQqFMH0tM1U1YLVDiUjRgxosz9Xl5eDB06lFdeeaWyNYmIiDglz9xchvy6FoB8i4W5vbqZXJGI1FgWi3W2bOtWiIuz3kja1dXsqqSKVDiU7Stj+tTLy4vw8HC7FCQiIuKsrlu/heBT1mWKS9tcwqGQIJMrEpEarTCU5ebCoUPQsKHZFUkVqXAoi46Oroo6REREnJprfgHDV6y2fTy7T3cTqxERh1C82ce+fQplTswuLfFFRETk3K7ctpOopGQAVjVtzK769UyuSERqvOLNPnRdmVMr10xZmzZtyv2CFouFLVu2XHBBIiIiTscwuHv577YPZ/fpYWIxIuIw1Ba/1ihXKAsODsZisZxzTHp6Ohs3bjzvOBERkdqm2197aX44AYDtDSJZd1EjcwsSEcegtvi1RrlC2S+//HLWY3l5ebz99ts8++yzWCwWBg8ebK/aREREnMJdvxSfJetu7aomInI+jRoVbWumzKlV6pqyTz/9lEsuuYTRo0fTtm1bNm7cyLx58+xVm4iIiMO7JP4wXfbsByAuNJifWzU3tyARcRze3lDv9PWnmilzahcUyn755Re6dOnC7bffjr+/Pz/++CM//PAD7dq1s3N5IiIijq34LNmc3t0pcFGPLRGpgMLryhISICPD3FqkylTof4Zt27Zx9dVX07dvX06cOMHChQvZsGEDffv2rar6REREHFb08RNcuW0nAMf96vBNh/I3zhIRAUpeV7Z/v2llSNUqVyiLj49n+PDhdOjQgY0bN/Laa6+xc+dO7rjjjqquT0RExGENW7EaF8O6veCyLuS4V/j2oCJS26kDY61Qrv8dmjZtSk5ODgMHDmTChAn4+fmxbdu2s47v0KGD3QoUERFxRKFpJ7lug/UWMSe9PPm0a0eTKxIRh6QOjLVCuUJZdnY2AN9//z1Lliw56zjDMLBYLOTn59unOhEREQc15Le1eJz+//DTbh1J9/YyuSIRcUi6gXStUK5QNnv27KquQ0RExGnUyczi1tUbAchxdWVBzy4mVyQiDqv48kXNlDmtcoWy4cOHV3UdIiIiTuPWNRvxy7KuMlncqS2J/n4mVyQiDisyEjw8ICdHM2VOTH15RURE7MgjN48hv64FoMACH/TqZnJFIuLQXF0hOtq6vXcvGIa59UiVUCgTERGxo0GbtlL3ZDoAP7VqQVzdEJMrEhGHV3hd2alTkJhobi1SJRTKRERE7MSloIARv6yyfTy7T3cTqxERp6G2+E5PoUxERMROrti+i+jEJADWXtyIHVH1Ta5IRJyC2uI7PYUyERERezAM7lpebJasdw8TixERp6KZMqenUCYiImIHnf/ZT6uDhwHYWT+C1U0bn+cZIiLlpJkyp6dQJiIiYgd3Lf/dtj2nd3ewWEysRkScim4g7fQUykRERCqp+cEjdP/L+oNSfHAQS1tfYnJFIuJUAgOtD9BMmZNSKBMREamku4p1XJzbqxv5rvrvVUTsrHC27MAByMsztxaxO/2vISIiUgkNEpPot/VPAE7U8WXxpW1NrkhEnFJhs4/8fIiPN7cWsTuFMhERkUoYtnINroYBwMKencl2dze5IhFxSrquzKkplImIiFyg4JPpXL9+MwCnPD34uFsncwsSEeeltvhOTaFMRETkAg3+bR1ep6/t+KxLB076eJtckYg4LbXFd2oKZSIiIhfAJyub21dvACDX1YX5l3c1uSIRcWqaKXNqCmUiIiIX4Ja1m/DPzALg2w5tOBbgb3JFIuLUoqOL7n+omTKno1AmIiJSQe55ecSuXGP7eE6vbiZWIyK1gqcn1K9v3dZMmdNRKBMREamgazZtIyztJAA/t2zGvvC6JlckIrVC4XVliYlw8qS5tYhdKZSJiIhUgKXAYESxm0W/36eHidWISK2iZh9OS6FMRESkAnr/uZuY4ycA2NC4IduiG5hckYjUGsWbfSiUORWFMhERkfIyDO5a/rvtw9m9NUsmItVIN5B2WgplIiIi5dRh3wHaHjgEwF8RYfzW/GKTKxKRWkVt8Z2WQpmIiEg53V18lqxPj6L21CIi1UHXlDkthTIREZHy2LqVy3btAeBQUAA/tG1pckEiUutERICXl3VbM2VORaFMRESkPF56ybY57/Ju5Lvqv1ARqWYWS9ESxn37wDDMrUfsRv+jiIiInM/+/fDRRwAk+3izqHM7U8sRkVqsMJRlZUFCgrm1iN0olImIiJzP9OmQnw/Ahz07k+nhYXJBIlJr6boyp6RQJiIici7Hj8N77wGQ6e7OR90vNbkgEanV1IHRKSmUiYiInMusWZCZCcDnXTqQ6utjckEiUqtppswpKZSJiIiczalT1lAG4ObGvMu7mluPiIhuIO2UFMpERETO5t13ISnJun3nnSQEBZhbj4hI8eWLmilzGgplIiIiZcnNtTb4KDRhgnm1iIgU8vOD0FDrtmbKnIZCmYiISFk+/BDi463bgwZBq1bm1iMiUqhwtuzgQcjONrcWsQuFMhERkTMVFJS4WTSPPWZeLSIiZyq8rsww4MABc2sRu1AoExEROdN338GOHdbt7t2hZ09z6xERKU5t8Z2OQpmIiMiZ/v3vou3HHzevDhGRsqgtvtNRKBMRESnu99+tD4BLLoFrrjG3HhGRM2mmzOkolImIiBT34otF2xMmgIv+qxSRGkYzZU5H/9OIiIgU2rEDvv7aut2gAdx5p7n1iIiUJSoKXF2t25opcwoKZSIiIoVefrloe9w48PAwrxYRkbNxd7cGM9BMmZNQKBMREQFrW+kFC6zbQUFwzz3m1iMici6FSxiTkyElxdRSpPIUykRERABefRXy8qzbDz4IdeqYW4+IyLkUb/ah2TKHp1AmIiKSlATvvGPd9vaG0aPNrUdE5HyKN/vQdWUOT6FMRETkv/+FU6es23ffDXXrmluPiMj5qC2+U1EoExGR2i0jA15/3brt6grjx5tbj4hIeagtvlNRKBMRkdrt/fchMdG6ffvtJX/7LCJSU2mmzKkolImISO2VlwfTpxd9PGGCebWIiFRE3brg62vd1kyZw1MoExGR2uuTT2D/fuv2wIHQtq2p5YiIlJvFUjRbtn8/FBSYWo5UjkKZiIjUToYBL75Y9PFjj5lXi4jIhSi8riwnBw4fNrcWqRSFMhERqZW6790DW7daP+jSBXr1MrcgEZGKUlt8p1HjQ9m0adO49NJL8fPzIywsjBtuuIHdu3eXGGMYBpMnTyYyMhJvb2969+7Njh07SozJzs5m9OjRhIaG4uvry3XXXcfBgwdLjElOTiY2NpaAgAACAgKIjY0lRXdIFxFxSsNX/1b0wWOPWZcCiYg4Et1A2mnU+FC2YsUKHnjgAdasWcPSpUvJy8ujf//+nCq8nwzw0ksvMWPGDGbNmsX69euJiIigX79+nDx50jZm7NixfPnll3z00Uf89ttvpKenM2jQIPLz821jBg8ezObNm1myZAlLlixh8+bNxMbGVuv5iohI1Wt16CCdDuy3ftCsGVx/van1iIhcEM2UOQ03sws4nyVLlpT4ePbs2YSFhbFx40Yuv/xyDMPgtdde48knn+Smm24CYO7cuYSHh7Nw4ULuu+8+UlNTee+995g3bx5XXnklAPPnzycqKoply5YxYMAAdu7cyZIlS1izZg1dunQB4J133qFbt27s3r2bZs2aVe+Ji4hIlSkxS/boo+BS439HKSJSmtriOw2H+18oNTUVgODgYAD27dtHQkIC/fv3t43x9PSkV69erFq1CoCNGzeSm5tbYkxkZCStWrWyjVm9ejUBAQG2QAbQtWtXAgICbGPKkp2dTVpaWomHiIjUXI0Sj9P7r13WDyIjYehQcwsSEblQWr7oNBwqlBmGwbhx4+jZsyetWrUCICEhAYDw8PASY8PDw23HEhIS8PDwICgo6JxjwsLCSr1nWFiYbUxZpk2bZrsGLSAggKioqAs/QRERqXKxa3/HBcP6wcMPg6enuQWJiFwoHx8o/BlYM2UOzaFC2YMPPsjWrVv58MMPSx2znHGBtmEYpfad6cwxZY0/3+tMnDiR1NRU2yM+Pv58pyEiIiapezKNa7ZZOy6e9PSCe+81uSIRkUoqvK7syBHIzDS3FrlgDhPKRo8ezeLFi1m+fDkNGjSw7Y+IiAAoNZt17Ngx2+xZREQEOTk5JCcnn3PM0aNHS73v8ePHS83CFefp6Ym/v3+Jh4iI1EyD163GvcDa4OnTjpeC/s0WEUdXfAnj/v2mlSGVU+NDmWEYPPjgg3zxxRf8/PPPxBT/iwfExMQQERHB0qVLbftycnJYsWIF3bt3B6Bjx464u7uXGHPkyBG2b99uG9OtWzdSU1NZt26dbczatWtJTU21jREREcfll5nJzX9sACDb1Y0PO3U1uSIRETso3oFR15U5rBrfffGBBx5g4cKFfPXVV/j5+dlmxAICAvD29sZisTB27FimTp1KkyZNaNKkCVOnTsXHx4fBgwfbxo4cOZLx48cTEhJCcHAwjzzyCK1bt7Z1Y2zRogUDBw7knnvu4a233gLg3nvvZdCgQeq8KCLiBG7ZtB7fnBwAvm7TjqQ6dUyuSETEDtQW3ynU+FD2v//9D4DevXuX2D979mxGjBgBwIQJE8jMzGTUqFEkJyfTpUsXfvzxR/z8/GzjX331Vdzc3LjtttvIzMykb9++zJkzB1dXV9uYBQsWMGbMGFuXxuuuu45Zs2ZV7QmKiEiV88zN5c71awDIt1iY10UrIETESagDo1Oo8aHMMIzzjrFYLEyePJnJkyefdYyXlxczZ85k5syZZx0THBzM/PnzL6RMERGpwQZt20xIxikAfmp+CQeDQ0yuSETETjRT5hRq/DVlIiIileFSUEDs2qL7Tc7t1tPEakRE7Kx+fXB3t25rpsxhKZSJiIhT67vrT6KSkwBY06gxuyIiTa5IRMSOXF0hOtq6vXcvlGOVmdQ8CmUiIuK8DIMRq3+zfTin22UmFiMiUkUKrys7eRJOnDC3FrkgCmUiIuK0uuzfS/OjRwD4MyKS9Y1izvMMEREHpLb4Dk+hTEREnNbwYrNkc7v1BIvFxGpERKpI8Q6MavbhkBTKRETEKbU4cogu+60/nBwICubnZi1MrkhEpIpopszhKZSJiIhTKn4t2bwu3Slw0X95IuKkNFPm8PQ/lIiIOJ2opBNcsWsnAIm+dfimTTtzCxIRqUqaKXN4CmUiIuJ0Ytf8jgvWttAfXtqVHDd3kysSEalCQUEQEGDd1kyZQ1IoExERpxKSfpJB27YAkO7hyWcdOplckYhIFbNYipYwHjgAeXnm1iMVplAmIiJO5c71a/DMt/5A8nmHTqR7eZtckYhINShcwpiXBwcPmluLVJhCmYiIOI06WVncumk9ADmuriy8tKvJFYmIVJPizT50XZnDUSgTERGncdMfG6iTnQ3At63bkujnb3JFIiLVpHizD11X5nAUykRExCm45+UxeP0aAAqw8EGXHiZXJCJSjdQW36EplImIiFO4ZvsW6qafBGB5s+YcCAk1uSIRkWqktvgOTaFMREQcnktBAcPW/G77eG63niZWIyJigujoom3NlDkchTIREXF4vf/aRXTSCQDWR8ewI7KByRWJiFQzLy+oX9+6rZkyh6NQJiIijs0wGL76N9uHmiUTkVqr8LqyY8cgPd3cWqRCFMpERMShdYrbT6sjhwDYFR7B6piLTK5IRMQkxa8r27/ftDKk4hTKRETEoQ1fUzRL9kHXnmCxmFiNiIiJ1BbfYSmUiYiIw2qWcITue/cAcDAwiGUtLjG5IhERE+kG0g5LoUxERBzWsGKzZPO7dCffxdXEakRETKaZMoelUCYiIg6pfnIS/XbuACDJx5fFbdqbXJGIiMl0A2mHpVAmIiIOaejaVbgaBgAfdepCtru7yRWJiJisXj3w9LRua/miQ1EoExERhxN0Kp3rtv4BQIa7B592vNTkikREagAXF2jUyLq9bx+c/sWV1HwKZSIi4nDuWL8Wr7w8AL5o35E0bx+TKxIRqSEKryvLyLDer0wcgkKZiIg4FJ/sbG7btA6AXBdXFnTuZnJFIiI1iK4rc0gKZSIi4lBu3LwR/6wsAL5v1Zpj/gEmVyQiUoMU78Co68ochkKZiIg4DLf8PIasW237eG7XniZWIyJSA6ktvkNSKBMREYdx1fZthJ9MA+CXJs3YH1rX5IpERGoY3UDaISmUiYiIQ7AYBQwvdrPoOd0uM7EaEZEaSteUOSSFMhERcQiX//0XMScSAdgUFc22BlEmVyQiUgMFBEBwsHVbM2UOQ6FMRERqPsNg+OqiWbK53XQtmYjIWRVeVxYfDzk55tYi5aJQJiIiNV67+AO0PRQPwJ66Yfx2UROTKxIRqcEKlzAWFMCBA+bWIuWiUCYiIjVaoI8PD5w4CqGhwOmOixaLyVWJiNRgaovvcNzMLkBERKQsjeqG8ugVl9GpycW4Db4ZwsLIXr6cv3bvg6Rks8sTEam51OzD4WimTEREapxGdUP54K4hXPrZp7hFRlp/69ugAe7r1vH+/w2jUd1Qs0sUEam5NFPmcBTKRESkxnn0isvwmj4d1+eeg5QU686UFFyeew6v6dN5tI/a4YuInJVmyhyOQpmIiNQogT4+dGpyMa4zZ5Z53HXmTDo2vZhAH59qrkxExEE0bAgup3/M10yZQ9A1ZSIi1aD7g8+ZXcIFWTXr6ep7M8OgXfwBRqYl4Zpwc9EM2ZlSUshLSiLUrw4pGRnVV5+IiKPw8ICoKIiL00yZg1AoExERU3nl5jBwxzZu27COZscSrF0Ww8IgMLDsYBYYiFtwMIkn06u7VBERxxETYw1lSUmQmmq9qbTUWAplIiJiigbJSdyyaT3Xb9mEf1ZW0YHERHJ+Xo7b6NG4PFd6hjF/9Gg2/rVHs2QiIufSuDH88ot1e98+aNfOzGrkPBTKRESk2liMArru/YfbN66jx56/ccEocXxr/QZ80rELe/7ay3vjx+OF9RoyUlIgMJD80aPJGj+el2cvMKV+ERGHUbzZh0JZjadQJiIiVa5OVibXbt3MbRvX0TA5qcSxbFc3frykFR936szOevWtO5NSGDZ7AY/efCsdJ04kLykJt+BgNuz+m1dmL2D/8UQTzkJExIEUb4uv68pqPIUyERGpMhcfO8qtG9dxzfYteOfmljiW4B/Apx0uZVHbDqT4+pZ67v7jiTzwyZcE+vgQ6leHxJPpWrIoIlJeaovvUBTKRETErlwL8un1125u37CWTgf2lzq+tlFjPunYmV+bNCXfxfW8r5eSkaEwJiJSUbqBtENRKBMREbsIOpXOjZs3cvOmDUScTCtx7JSHB9+0bsenHS5lX90wkyoUEalFwsLAxwcyMjRT5gAUykRE5MIZBqxbB7Nm8d2HH+KRn1/i8P7gED7p2Jlv2rTjlKeXSUWKiNRCFot1CeOOHbB/PxQUFN1QWmochTIREam4rCz4+GOYNQs2bADA4/ShAiysbNKUTzp1YV2jGAyLfggQETFF48bWUJadDUeOQP36ZlckZ6FQJiIi5XfgALz5JrzzDiSW7ICY4u3NorYd+KzDpRwJDDKpQBERsTmzLb5CWY2lUCYiIudmGLB8uXVW7KuvrEtgimvfHkaP5uqde8l2dzenRhERKe3Mtvg9e5pXi5yT1pSIiEiZfHKy4Y03oGVL6NsXvvyyKJC5u8PgwbBqFWzcCHfdpUAmIlLTnDlTJjWWZspERKSEhsmJ3LxtLVfv2gy52SUPRkbCv/4F99wDERGm1CciIuWkG0g7DIUyERHBpaCA7nF/ccu2tXSO/6f0gMsugwcfhBtvtM6SiYhIzdeoUdG2QlmNplAmIlKL+WdlcO2fG7lp+3rqnUwpcSzLzR2vu0bAAw9A27am1CciIpVQp471fmXHjmn5Yg2nUCYiUgs1PX6Em7etpf9fW/HMzytx7JB/EJ+37sy3zTvww9tTTapQRETsIibGGsoOHbLezsRL94ysiRTKRERqCbf8PPr88yc3b1tLm4T4UsdXNWzC5627sCb6Yt1bTETEWTRuDGvXWrfj4qBZM3PrkTIplImIOLnQU2lcv30DN+zYQEhmeoljJz28+LZFe75o1ZmDgSEmVSgiIlWmeAfGvXsVymoohTIREQcWWMeHYP86JKWlk5KeUXTAMGh7JI6bt62j994/cTvj3mL/BIfxWesu/Ni0DZkentVctYiIVJviHRh1XVmNpVAmIuKAosNDefiay2jf4iLyEpNwCw3mjz/38N/Fy2n+68/cvHUtTU8klHhOnsWFlY1b8FnrzmyObAQWiznFi4hI9VFbfIegUCYi4mCiw0N5d/RgvGZMx7XvTNxTUiAwkE4PjmbOmNFYPvkfFAtkSd6+fNWyE4taduJ4nQDzChcRkeqnG0g7BIUyEREH8/A1l1kD2XPPFe1MScHl+ecAA6ZNgxtvZHt4Az5r3YXlF7ck11X/3IuI1EoNGoCbG+TlaaasBtP/0iIiNZxrfj7RKYlcnJhAy/wsOjUbh8vMmWUPnjWLgoOHePju8az31qyYiEit5+YGDRtaA9nevWAYWr5eAymUiYjprhzy3PkH1UDLFjxt99f0y8rkohMJNE1M4OLEBC4+kUBM0vGie4m1amW930xKStkvkJJCdnIyJy5qAoeP2b0+ERFxQI0bWwNZWhokJ0NwsNkVyRkUykRETGAxCohMTabJiQSanA5gTRITiEhPPfcTExIgLAwCA8sOZoGBuIUEk5SWXvqYiIjUTme2xVcoq3EUykREqtqpU7RMiLcGr9MhrPGJo/jm5pz3qfkWC/GBIewJieDv0Aj2hEQQ++fftB49uuQ1ZYXjR4/mjz/3lGyPLyIitduZbfE7dTKvFimTQpmIiL0YBhw8CFu2lHz8/TfvGMZ5n37K3ZM9oeG28PV3aAR7g8PIdvcoMe7wktW8O248XoDrzJnWGbPAQPJHjyZr3Hhenbmwas5PREQc05kzZVLjKJSJiFwA9/w82LzZ+igewJKSyvX8w36B7Am1Bq/CEHbEPxDD4nLe58YdTeT/Zi7k4etvpf3EieSdSMItJJhNO/bw2syFxB1NrNzJiYiIc6ktN5A+dQrc3W2/rCQ3F3x9za6qXBTKRETOIyDrFBelJNA4OYGLkhO4KCWBhqnH4eNnz/9kLy9o1YrFpwpsIWxPSASnPL0qVVPc0UTGzl5EYB0fgv3rkJSWriWLIiJSttowU5aVBS+9BK+/XhTKxoyBiROt/xfXcAplIuK0Avx8CA6sQ1JKOqknzx9YXAoKaHDyhDV8pSRwUfIRGqccJTTzZPneMCIC2rWDtm2LHk2bgpsb/36wajpMpqRnKIyJiMi5hYSAnx+cPOmcM2WnTlkD2bPFflmaklL08YQJNX7GTKFMRJxOw8hQHrjlMtq2vojcE0m4hwSzeese3vj8Nw4cti7t883JIiYlgYuSj9pmwWJSjxa1nj+HPIsL8f6hxFzbv2QACwur6lMTERGpOIvFuoRxyxaIi4P8fHB1NbuqC2cYkJhoPZeEBOjb1zpDVpbXX4cnn6ze+i6AQpnImRx4PbJYA9msJwbj9ep0XAbOxO3017HD6NG89fhYtt4yjMj1q6h3Krlcr5fm4c3ewHD+CYrgn6B67A2MIC6gLrmubiybZ//7lImIiADEb+tj19cLCTmED0BuLod/6kl+Pfsv6Ytqvdw+L5STA4cOWUPXgQOl/zxwADIzrWNbtYLFi895/05SU6FuXfvUVkUUykSKc/D1yOXmCMHTMPDKz8UrNwfvvBx88rLxPr3tXca2T14OXnk5dHnjJbxnvILl+eeLXislBZfnnsPFMOj40P/Bjd+WersCLBz2C+afwAj2BoXzT6A1hB338bf+hlFERMSB5Tco+jnG7WBmlYSycktLKztwFW4fPmydDSuPcty/k4AAOxZfNRTKRAqdaz2yYVinxqdNs4azsz28vc99/FwPD4/q+eG/qoJnTo51rXp6etGfZ9s+Y9/09Tvwzs0+HbJybIHLhXL+g1woNBR6doM7bi37+KxZcPAgmRGR7M1zZW9ghHUGLDCcfYHhZLl7Xvj5i4iI1GB59U//Hx8aimduQ3JdXSjIT7X/GxUUWIPS2Wa54uKsM1cXyscHoqOtj4YNrX8eOWL9WebZMhpwjRlj/eWzh0fpYzWIQplIIXf3s69HnjkTHnsMNm60rmGuKmcJeTv3HSfHxZUcFzdyXdzIcXEjx7XYtourddvV7SxjrM8d+eJomvz8NS7PF2s6cTp4FhgG+3pdxefjXsIrLwfv/NMBKT8Hr2Lb3nk5eOXnWmeobB/n4G4UXPBpt638Z84qIgKOHTvnEoaspGTGDHuKfQfVNl5ERGoPo/UlsOgVuPJK/JOO4x8WRlbKelJS3ycv+0D5Xyg7H7cj2bgmZOF2OBvXI1m4HcnC9Ug2nLgI4uOtIehChYcXha2y/gwOLvuX2BMnWv900NVOCmVOrpffNWaXUGErTpZeWlYtUlLOvR75+HHrD/1VGcqysqyPM7Swx2uHhkLn/8FN/cs87DJzJhc99hgTDv9Wted4FvkWFzLcPMh09yDTzZPMM7Yz3D3IdPMgy82DDPfC46f/PL3tFhzM9PAI3M6xhMEtJISkVHUrFBGR2sPNsyGB186AF1+DESOwnA4tXmNGEz7hVY4eetgazAwDl9Q8XA9n4ZaQhevh7NN/ZuGakI3b4Sxck84VuFLOXYi7uzVYnS10NWhg/YX0hfDysnZZfPJJ60xcQIA1HDpAIAOFMnECV7e+v9Kv4R9Uh/nfP3vOH+bz6oZzn/8VZDXrgLuRh4eRj0dBPu5GPh4Fpz828nEvyMfj9HHrtvW4u5Fve87V111aFMAyM4u2z/bIyan0OZZnFqkiwTPD1YMs19OB6PSfxT8ecEsvqFPH2oK3+J9lbF/14OvkurjZZfnmlm3/0G70aFyfK92CPn/0aDZv3VOu9vgiIiLOIjBgJJaXX4Mzrre2PPscGAZhV9xKwcjbcT2ShUvmha98ITDw3LNcERHg4lLZ0zm7wuvjC5t61PAli8UplIkAacnpbFvzJ20eHI3r82X8MP/gaLau3sGRtBxw96n0+109538VGj9owFO4F+RZw11BHh75edZAeHqfR35e0bZtTH7RdkEedTzqMCgsHJdzBM+CumHM82tBcstGpUJWpqt1lirT1YNsV3eM8wSoAa+V/75cua7uFfp8nMt/P/uVWU+MxxNwnTnTtoQhf/Rosh8ezxtTF9rtvURERGo6F9cAvAI7YXn9+jKPW2bOwvWxx3FN84HMs//S0nCB/Lqe5NfzJK+eV7E/i7YbdPu1qk7D6SmUiZz25n++4dXZ46w/zM8q9sP8g6PJHjuOt+76j2m1GRYLOa7u5FQyvET9sYc255hF2rLpbz7xbwb+lXobUx04nMiDUxcy6uZbaff4RHKTknAPPn2fsqkLbfcpExERx/X12p5ml3BBru3yW7W/p6tbMEZyonXJYllOr5QpiI4k3y+DvHqeJYJWfj0v674wT3CvwlmuWk6hTOS0+H0JPHzXf7hvzHW0eXwieSdO4BYSwpZV23n7rv8Qvy/B7BIr7a25vzDjxbPMIo0dz9uPzTW7RLs4cDiRx2cuIsDPh+DAOiSlpGvJooiI1Er5eUlYgkLP2TLeqBfGkbmNKCgIru7y5DSFMpFi4vcl8NTD7+EfVIfgUH+SEtNIS043uyy7iY8/zrjH5nLvsJtPB88k3EKC2brhL95+bC7x8cfNLtGuUk9mKIyJiEitVpCfSlbKBrzGjLZeQ3YGY8xoslLWU1CQZkJ1UkihrAxvvPEGL7/8MkeOHKFly5a89tprXHbZZWaXJdUoLTndqcJYcfHxx3n6hc/wD/AhKMiP5OSTpKkboYiIiNNKSX2P8AmvAmB5vWiljDFmNMaEsaQcetjcAgUtDD3Dxx9/zNixY3nyySf5448/uOyyy7jqqqs4cKAC928QcQBpqRnE7T+qQCYiIuLk8rIPcPTQw2SN6ouRcIiChDiMhENk3X9FUTt8MZVmys4wY8YMRo4cyf/93/8B8Nprr/HDDz/wv//9j2nTpplcnYiIiIhIxeVlHyDx2GRcTgTg6hZM/okkCvJTzS5LTlMoKyYnJ4eNGzfy+OOPl9jfv39/Vq1aVeZzsrOzyc7Otn2cmmr9y52WVjPW5eYZlbijukkq+rnLzbfDPbyqWYXPMS/7/INqmIqcY15u6RtmO4IKnWOO859jfrbjnWNFvxfzs5z7exEgL9O5zzEnw/HODyp2jlmnHO//fqjYOWacyqvCSqpORc7xZHpVneOJ0w/7qyk//9YkhZ8TwzDOOc5inG9ELXL48GHq16/P77//Tvfu3W37p06dyty5c9m9e3ep50yePJkpU6ZUZ5kiIiIiIuJA4uPjadCgwVmPa6asDJYzboprGEapfYUmTpzIuHHjbB8XFBSQlJRESEjIWZ/jDNLS0oiKiiI+Ph5/fwe+qdVZOPv5gc7RWegcnYOzn6Oznx/oHJ2FzlHszTAMTp48SWRk5DnHKZQVExoaiqurKwkJJe9HdezYMcLDw8t8jqenJ56eniX2BQYGVlWJNY6/v79Tf0M7+/mBztFZ6Bydg7Ofo7OfH+gcnYXOUewpICDgvGPUfbEYDw8POnbsyNKlS0vsX7p0aYnljCIiIiIiIvaimbIzjBs3jtjYWDp16kS3bt14++23OXDgAP/617/MLk1ERERERJyQQtkZbr/9dk6cOMGzzz7LkSNHaNWqFd999x3R0dFml1ajeHp6MmnSpFJLN52Fs58f6Bydhc7ROTj7OTr7+YHO0VnoHMUs6r4oIiIiIiJiIl1TJiIiIiIiYiKFMhERERERERMplImIiIiIiJhIoUyknCwWC4sWLTK7DBGpRfTvjohI7aBQJqWMGDGCG264wewyqsSIESOwWCylHnv27DG7NLsoPL+ybuEwatQoLBYLI0aMqP7CqsiqVatwdXVl4MCBZpdiN7Xta+jM/96UxRnP1xm/D4s7duwY9913Hw0bNsTT05OIiAgGDBjA6tWrzS7N7uLj4xk5ciSRkZF4eHgQHR3NQw89xIkTJ8r1/F9++QWLxUJKSkrVFlpBhf+u/vvf/y6xf9GiRVgsFpOqsq/iP9+4u7sTHh5Ov379eP/99ykoKDC7PCkHhTKpdQYOHMiRI0dKPGJiYswuy26ioqL46KOPyMzMtO3Lysriww8/pGHDhpV67dzc3MqWZ1fvv/8+o0eP5rfffuPAgQOVeq38/Pwa8x9XVX4NRezNnt+HNdHNN9/Mli1bmDt3Ln/99ReLFy+md+/eJCUlmV2aXe3du5dOnTrx119/8eGHH7Jnzx7efPNNfvrpJ7p16+bw5+vl5cWLL75IcnKy2aVUmcKfb/bv38/3339Pnz59eOihhxg0aBB5eXlmlyfnoVAm57RkyRJ69uxJYGAgISEhDBo0iH/++cd2fP/+/VgsFr744gv69OmDj48Pbdu2rdG/QSz8TWfxh6urK19//TUdO3bEy8uLxo0bM2XKlFL/iB05coSrrroKb29vYmJi+PTTT006i7Pr0KEDDRs25IsvvrDt++KLL4iKiqJ9+/a2feX92n7yySf07t0bLy8v5s+fX63nci6nTp3ik08+4f7772fQoEHMmTPHdqzwt7Xffvstbdu2xcvLiy5durBt2zbbmDlz5hAYGMg333zDJZdcgqenJ3FxcSacSWn2+hpeccX/t3fnUVFc2R/Avw1KNw3iUZAAioAgCCIyCEZwjLK0RMENBYmgKGIm4HIOGiO4gbgzmjjuogKaIYZRRsQNNSwzJyNRJKIeYZjMDLgMMDFIolFEhfv7Iz9qLNYGoRvj/ZzDOdSrV9X39quq7lfLaw8sWrRItO6qqipIpVJkZ2d3fSLtZG5ujh07dojKHB0dERsbK0xLJBIcOnQI06ZNg1wux+DBg5GRkaHaQDuJMvl2d63thw372KuauzKxYcMGGBoaolevXggLC0NUVBQcHR27Pngl/Pjjj/j666+xdetWuLu7w8zMDCNHjkR0dDR8fHwAAD/99BM+/PBDGBoaQk9PDx4eHrhx44awjtjYWDg6OuLAgQMwNTWFXC6Hv79/t7uatHDhQmhpaeHixYsYO3YsBg4ciAkTJuCrr77Cf/7zH6xatQoAUFtbi08++QSmpqaQSqUYPHgwDh8+jLKyMri7uwMA+vTp0+2u6nt5ecHIyAibN29usU5aWhqGDh0KqVQKc3NzbN++XZgXHR2NUaNGNVnGwcEBMTExXRJzezV8v+nfvz+cnJywcuVKnDp1CufPnxf2zba2VwDIyMiAs7MzZDIZDAwM4Ofnp4Zs3j7cKWOtevLkCZYuXYr8/HxkZWVBQ0MD06ZNa3JFYdWqVfj4449RWFgIa2trfPDBB2/UWZkLFy4gODgYS5YsQVFREQ4cOIDk5GRs3LhRVG/NmjXCWdPg4GB88MEHKC4uVlPULZs3bx6SkpKE6cTERISGhorqKNu2K1aswJIlS1BcXAxvb2+VxK+M1NRU2NjYwMbGBsHBwUhKSkLjn11cvnw5tm3bhvz8fBgaGmLy5Mmiq31Pnz7F5s2bcejQIdy+fRuGhoaqTqNFndGGYWFh+OKLL1BbWyssk5KSAhMTE+HL05to3bp1CAgIwM2bNzFx4kQEBQW98Wfx31TK7IetSUlJwcaNG7F161YUFBRg4MCB2LdvXxdG3D66urrQ1dVFenq6aD9qQETw8fFBZWUlzp07h4KCAjg5OcHT01O0Tf7zn//En/70J5w+fRqZmZkoLCzEwoULVZlKqx4+fIgLFy4gIiIC2traonlGRkYICgpCamoqiAhz5szBl19+iZ07d6K4uBj79++Hrq4uTE1NkZaWBgAoKSlBRUUF/vCHP6gjnWZpampi06ZN2LVrF+7fv99kfkFBAQICAhAYGIhbt24hNjYWa9asETozQUFBuHLliujE1+3bt3Hr1i0EBQWpKo128/DwwPDhw/HnP/9Zqe317Nmz8PPzg4+PD65fv46srCw4OzurOYu3BDHWSEhICE2ZMqXZed9//z0BoFu3bhERUWlpKQGgQ4cOCXVu375NAKi4uFgV4bZLSEgIaWpqko6OjvA3Y8YMGjNmDG3atElU9/PPPydjY2NhGgB99NFHojrvvvsuhYeHqyR2ZTS03YMHD0gqlVJpaSmVlZWRTCajBw8e0JQpUygkJKTZZVtq2x07dqgwA+W5ubkJsb148YIMDAzo0qVLRESUk5NDAOjLL78U6ldVVZG2tjalpqYSEVFSUhIBoMLCQtUH34rObMNnz55R3759hZyJiBwdHSk2NlYVqSjl1eONmZkZffbZZ6L5w4cPp5iYGGEaAK1evVqY/vnnn0kikdD58+dVEO3r60i+J0+eVFl87dXafpiUlES9e/cW1T958iS9+tXj3XffpYULF4rqjB49moYPH96lcbfHiRMnqE+fPiSTycjNzY2io6Ppxo0bRESUlZVFenp69OzZM9EylpaWdODAASIiiomJIU1NTbp3754w//z586ShoUEVFRWqS6QV33zzTavb2qeffkoA6MqVKwRAaOPGGo691dXVXRdsB7y6340aNYpCQ0OJSLw9zpo1ixQKhWi55cuXk52dnTDt4OBAcXFxwnR0dDS5uLh0cfTKae2728yZM8nW1lap7dXV1ZWCgoK6OlzWDL5Sxlr1r3/9C7NmzcKgQYOgp6cnPHvV+LkBBwcH4X9jY2MAvzwc3R25u7ujsLBQ+Nu5cycKCgoQFxcnnBXV1dXFggULUFFRgadPnwrLurq6itbl6uraLa+UGRgYwMfHB0eOHEFSUhJ8fHxgYGAgqqNs23bHM2QlJSW4evUqAgMDAQA9evTAzJkzkZiYKKr3anv17dsXNjY2ovbS0tISbbvdSWe0oVQqRXBwsPC+FBYW4saNG93qlqKOeLXNdHR00KtXr257vPk1U3Y/bGsdI0eOFJU1nla36dOno7y8HBkZGfD29kZubi6cnJyQnJyMgoIC/Pzzz9DX1xd9fpSWloquqAwcOBADBgwQpl1dXVFfX4+SkhJ1pNRu9P9XP0tLS6GpqYmxY8eqOaKO27p1K44cOYKioiJReXFxMUaPHi0qGz16NL777jvU1dUB+OVqWUpKCoBf3pNjx45166tkDYgIEolEqe21sLAQnp6eao747dRD3QGw7m3SpEkwNTXFwYMHYWJigvr6etjb2+P58+eiej179hT+b3heoLsMmtCYjo4OrKysRGX19fVYt25ds/dNy2SyVtfXXUduCg0NFZ4n2rNnT5P5yratjo6OSuJtj8OHD+Ply5fo37+/UEZE6NmzZ5sPcb/aXtra2t22/YDOacOwsDA4Ojri/v37SExMhKenJ8zMzFSWQ3toaGg0ufWtucFlXj3eAL+0aXc93rRG2Xy7q7b2Q2Xza7wPNl6mO5DJZFAoFFAoFFi7di3CwsIQExODiIgIGBsbIzc3t8kyjZ+ne1VDzt3l+GNlZQWJRIKioqJmRwf9+9//jj59+kAul6s+uE723nvvwdvbGytXrhSdoGrouLyq8bY4a9YsREVF4dtvv0VNTQ3u3bsnnJTozoqLi2FhYYH6+vo2t9fGt68y1eFOGWtRVVUViouLceDAAYwZMwYA8PXXX6s5qq7h5OSEkpKSJp21xr755hvMmTNHNP3qwAvdyfvvvy98OW/8LNib3LYvX77E0aNHsX37dowfP140b/r06UhJSYG9vT2AX9qnYbTC6upq/OMf/8CQIUNUHnNHdUYbDhs2DM7Ozjh48CC++OIL7Nq1q+sD76B+/fqhoqJCmH706BFKS0vVGFHXepPzVWY/tLS0xOPHj/HkyRPh5E5hYaGoro2NDa5evYrZs2cLZdeuXevy+F+XnZ0d0tPT4eTkhMrKSvTo0QPm5uYt1r979y7Ky8thYmICAMjLy4OGhgasra1VFHHr9PX1oVAosHfvXkRGRoq+mFdWViIlJQVz5szBsGHDUF9fj7/85S/w8vJqsh4tLS0AEK4sdVdbtmyBo6Oj6P23s7Nrcgy9fPkyrK2toampCQAYMGAA3nvvPaSkpKCmpgZeXl545513VBp7e2VnZ+PWrVuIjIzEgAED2txeHRwckJWVhXnz5qk2UMadMtayPn36QF9fHwkJCTA2Nsbdu3cRFRWl7rC6xNq1a+Hr6wtTU1P4+/tDQ0MDN2/exK1bt7Bhwwah3vHjx+Hs7Izf/va3SElJwdWrV3H48GE1Rt4yTU1N4Va9hg+UBm9y2545cwbV1dWYP38+evfuLZo3Y8YMHD58GJ999hkAIC4uDvr6+njnnXewatUqGBgYvFG/EdVZbRgWFoZFixZBLpdj2rRpXR53R3l4eCA5ORmTJk1Cnz59sGbNmiZ5/5q8yfkqsx9mZWVBLpdj5cqVWLx4Ma5evSoanREAFi9ejAULFsDZ2Rlubm5ITU3FzZs3MWjQIBVm07Kqqir4+/sjNDQUDg4O6NWrF65du4b4+HhMmTIFXl5ecHV1xdSpU7F161bY2NigvLwc586dw9SpU4Xbv2UyGUJCQrBt2zY8evQIS5YsQUBAAIyMjNSc4f/s3r0bbm5u8Pb2xoYNG2BhYYHbt29j+fLl6N+/PzZu3Ii+ffsiJCQEoaGh2LlzJ4YPH447d+7g+++/R0BAAMzMzCCRSHDmzBlMnDgR2tra0NXVVXdqTQwbNgxBQUGik1TLli2Di4sL1q9fj5kzZyIvLw+7d+/G3r17RcsGBQUhNjYWz58/Fz5ruova2lpUVlairq4O//3vf5GZmYnNmzfD19cXc+bMgYaGRpvba0xMDDw9PWFpaYnAwEC8fPkS58+fxyeffKLu9H791PQsG+vGZs+eTdOnTyciokuXLpGtrS1JpVJycHCg3Nxc0cPADYNBXL9+XVi+urqaAFBOTo7qg29Daw/CZmZmkpubG2lra5Oenh6NHDmSEhIShPkAaM+ePaRQKEgqlZKZmRkdO3ZMRZErp7X8iEg0SERH2rY78PX1pYkTJzY7r6CggADQ9u3bCQCdPn2ahg4dSlpaWuTi4iIa1KO5QQi6g85swwaPHz8muVxOERERXRd4B716vPnpp58oICCA9PT0yNTUlJKTk5Ua+KJ3796UlJSkuqBfQ2fk2x0osx8WFBTQyZMnycrKimQyGfn6+lJCQgI1/uoRFxdHBgYGpKurS6GhobRkyRIaNWqUKtJo07NnzygqKoqcnJyod+/eJJfLycbGhlavXk1Pnz4lIqJHjx7R4sWLycTEhHr27EmmpqYUFBREd+/eJaJfBvoYPnw47d27l0xMTEgmk5Gfnx89fPhQnak1q6ysjObOnUtGRkZCLosXL6YffvhBqFNTU0ORkZFkbGxMWlpaZGVlRYmJicL8uLg4MjIyIolE0uKgRKrW3HG1rKyMpFKpaHs8ceIE2dnZUc+ePWngwIH0+9//vsm6qqurSSqVklwup8ePH3d16EoLCQkhAASAevToQf369SMvLy9KTEykuro6oV5b2ysRUVpaGjk6OpKWlhYZGBiQn5+fOlJ660iIuuHN20yt3n//fVhZWWH37t3qDoWxDsnNzYW7uzuqq6tbfa7jbXHv3j2Ym5sjPz8fTk5O6g5H5G073rxt+XaEQqGAkZERPv/8c3WH0iliY2ORnp7e5NZNxhh7Fd++yATV1dW4fPkycnNz8dFHH6k7HMbYa3rx4gUqKioQFRWFUaNGdasO2dt2vHnb8lXW06dPsX//fnh7e0NTUxPHjh3DV199hUuXLqk7NMYYUynulDFBaGgo8vPzsWzZMkyZMkXd4TDGXtPf/vY3uLu7w9raGidOnFB3OCJv2/HmbctXWRKJBOfOncOGDRtQW1sLGxsbpKWlNTuIBGOM/Zrx7YuMMcYYY4wxpkb849GMMcYYY4wxpkbcKWOMMcYYY4wxNeJOGWOMMcYYY4ypEXfKGGOMMcYYY0yNuFPGGGOMMcYYY2rEnTLGGGNqd/PmTcybNw8WFhaQyWTQ1dWFk5MT4uPj8fDhw3avb9y4cbC3t++CSJsqLy9HbGys0j8OnJubC4lEAolEguTk5GbreHh4QCKRwNzcvNPibE5RURFiY2NRVlbWZJ4q30PGGHvbcaeMMcaYWh08eBAjRoxAfn4+li9fjszMTJw8eRL+/v7Yv38/5s+fr+4QW1VeXo5169Yp3Slr0KtXLxw+fLhJeWlpKXJzc6Gnp9dJEbasqKgI69ata7ZTxhhjTHX4x6MZY4ypTV5eHsLDw6FQKJCeng6pVCrMUygUWLZsGTIzM9UYYcvq6urw8uXLDi8/c+ZMHDp0CN999x0GDx4slCcmJqJ///4YNmwYioqKOiNUxhhj3RxfKWOMMaY2mzZtgkQiQUJCgqhD1kBLSwuTJ08Wpuvr6xEfH48hQ4ZAKpXC0NAQc+bMwf3795tdf35+PsaMGQO5XI5BgwZhy5YtqK+vF9W5e/cugoODYWhoCKlUCltbW2zfvl1Ur6ysDBKJBPHx8diwYQMsLCwglUqRk5MDFxcXAMC8efOE2xJjY2PbzF2hUMDU1BSJiYmi/I4cOYKQkBBoaDT9iH727Bmio6NhYWEBLS0t9O/fHwsXLsSPP/4oqmdubg5fX19kZmbCyckJ2traGDJkiOi1kpOT4e/vDwBwd3dv8ZZKZd5Dxhhjr4c7ZYwxxtSirq4O2dnZGDFiBExNTZVaJjw8HCtWrIBCoUBGRgbWr1+PzMxMuLm54YcffhDVraysRFBQEIKDg5GRkYEJEyYgOjoaf/zjH4U6Dx48gJubGy5evIj169cjIyMDXl5e+Pjjj7Fo0aImr79z505kZ2dj27ZtOH/+PExMTJCUlAQAWL16NfLy8pCXl4ewsLA2c9HQ0MDcuXNx9OhR1NXVAQAuXryI+/fvY968eU3qExGmTp2Kbdu2Yfbs2Th79iyWLl2KI0eOwMPDA7W1taL6N27cwLJlyxAZGYlTp07BwcEB8+fPx1//+lcAgI+PDzZt2gQA2LNnjxC7j49Pu95DxhhjnYAYY4wxNaisrCQAFBgYqFT94uJiAkARERGi8itXrhAAWrlypVA2duxYAkBXrlwR1bWzsyNvb29hOioqqtl64eHhJJFIqKSkhIiISktLCQBZWlrS8+fPRXXz8/MJACUlJSmVR05ODgGg48eP07///W+SSCR05swZIiLy9/encePGERGRj48PmZmZCctlZmYSAIqPjxetLzU1lQBQQkKCUGZmZkYymYzu3LkjlNXU1FDfvn3pd7/7nVB2/PhxAkA5OTlN4lT2PWSMMfb6+EoZY4yxN0JOTg4AYO7cuaLykSNHwtbWFllZWaJyIyMjjBw5UlTm4OCAO3fuCNPZ2dmws7NrUm/u3LkgImRnZ4vKJ0+ejJ49e75uKgILCwuMGzcOiYmJqKqqwqlTpxAaGtps3YZYGufv7+8PHR2dJvk7Ojpi4MCBwrRMJoO1tbUo/7Yo8x4yxhh7fdwpY4wxphYGBgaQy+UoLS1Vqn5VVRUAwNjYuMk8ExMTYX4DfX39JvWkUilqampE62xpfa++ZoPm6r6u+fPn4/Tp0/j000+hra2NGTNmNFuvqqoKPXr0QL9+/UTlEokERkZGHcq/LZ2xDsYYY23jThljjDG10NTUhKenJwoKClocqONVDR2EioqKJvPKy8thYGDQ7hj09fVbXB+AJuuUSCTtfo22+Pn5QS6XY8uWLQgMDIS2tnaLsb58+RIPHjwQlRMRKisrO5Q/Y4yx7oE7ZYwxxtQmOjoaRIQFCxbg+fPnTea/ePECp0+fBvDLDyoDaDLIRH5+PoqLi+Hp6dnu1/f09ERRURG+/fZbUfnRo0chkUjg7u7e5joaRo3s6NUjbW1trF27FpMmTUJ4eHirsQJN809LS8OTJ086lP/rxs4YY6xz8O+UMcYYUxtXV1fs27cPERERGDFiBMLDwzF06FC8ePEC169fR0JCAuzt7TFp0iTY2Njgww8/xK5du6ChoYEJEyagrKwMa9asgampKSIjI9v9+pGRkTh69Ch8fHwQFxcHMzMznD17Fnv37kV4eDisra3bXIelpSW0tbWRkpICW1tb6OrqwsTERLgFUhlLly7F0qVLW62jUCjg7e2NFStW4NGjRxg9ejRu3ryJmJgY/OY3v8Hs2bOVfr0G9vb2AICEhAT06tULMpkMFhYWzd62yBhjrOvwlTLGGGNqtWDBAly7dg0jRozA1q1bMX78eEydOhXHjh3DrFmzkJCQINTdt28ftmzZgnPnzsHX1xerVq3C+PHjcfny5Q51JPr164fLly/Dw8MD0dHR8PX1xYULFxAfH49du3YptQ65XC4M1DF+/Hi4uLiIYu4sEokE6enpWLp0KZKSkjBx4kRhePzs7Oxmf+etLRYWFtixYwdu3LiBcePGwcXFRbgyyRhjTHUkRETqDoIxxhhjjDHG3lZ8pYwxxhhjjDHG1Ig7ZYwxxhhjjDGmRtwpY4wxxhhjjDE14k4ZY4wxxhhjjKkRd8oYY4wxxhhjTI24U8YYY4wxxhhjasSdMsYYY4wxxhhTI+6UMcYYY4wxxpgacaeMMcYYY4wxxtSIO2WMMcYYY4wxpkbcKWOMMcYYY4wxNfo/xZDqxgPtHCwAAAAASUVORK5CYII=", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAA2UAAAIlCAYAAABVWVCLAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8hTgPZAAAACXBIWXMAAA9hAAAPYQGoP6dpAACLoElEQVR4nOzdeZxN9R/H8fedfTH7GGMYg0hkKWsoS9YiFaUi0aKdChWpKCGVNvJrsxVS2VqULIVEWUqRpdRgMGOdzRiznt8ft7nmzowxM2bm3Dvzej4e83DuOd977ufce2fcz/18F4thGIYAAAAAAKZwMTsAAAAAAKjMSMoAAAAAwEQkZQAAAABgIpIyAAAAADARSRkAAAAAmIikDAAAAABMRFIGAAAAACYiKQMAAAAAE5GUAQAAAICJSMoAAKiE5syZI4vFojlz5pgdSqXXqVMnWSwWs8MAYCKSMgCQtH//flksFrsfd3d31ahRQ/3799fWrVvNDrHCMQxDX375pfr376+oqCh5e3vL29tbdevW1a233qoFCxYoIyPD7DDLVc77cMiQIWaH4jTWrl1r+5296qqrztvuyy+/tLXr2bNnOUZIAgzgwtzMDgAAHMkll1yiO++8U5KUkpKibdu26fPPP9eyZcu0evVqdejQweQIK4ZTp07ptttu0+rVq+Xv768uXbrokksukYuLi2JiYrR27VotWrRI06ZN06ZNm8wOF07Azc1Nv/zyi3bt2qVGjRrlOz5r1iy5ubkpMzPThOgAoHAkZQCQS7169TR+/Hi7fS+//LLGjBmj5557TuvWrTMnsAokMzNTN910k3788UcNGTJEb775pgICAuzaZGdna+nSpXr33XdNihLOpkePHvr22281a9Ysvfbaa3bHjh07pm+++UbXX3+9vvzyS5MiBIDzo/siAFzAvffeK0natm1bvmPp6el6/fXX1bx5c/n6+srPz0/XXHNNvg9+99xzjywWi3788ccCH2PixImyWCz6+OOP7fb/8ccfuv3221W9enV5eHgoKipKw4YN08mTJ+3a5e729u+//+qWW25RUFCQfH191bVrV/3+++/5HtNisahTp04FxlO7dm3Vrl27xNdbmLlz5+rHH39Uly5dNGvWrHwJmSS5uLioX79++vbbbws8xxdffKEuXbooKChIXl5eaty4sV577TVlZWXZtcvdbWzNmjW6+uqr5evrq5CQEA0ePDjf85ijJM/7nj171LdvX4WGhspisWj//v2SpKVLl+qOO+5QvXr15OPjo4CAAF1zzTVavHhxvljr1Klje45yd6Vdu3atrZ1hGJo1a5bat28vf39/+fj4qGXLlpo1a1aB13Lq1Ck9+OCDqlatmnx8fNSqVSstXbq0wLaFyXm/xMTE6LbbblNISIh8fX3VqVMnbdy4scD7FOf9MmTIEFksFv3777964403dPnll8vT07PIXTlr1qyprl276uOPP85XDfvoo4+UkZGhu++++7z3P3nypJ544gnVqVNHnp6eCgsL02233aZdu3adN9b9+/drxowZatiwoby8vBQVFaUXXnhB2dnZdm1zHvfuu++2e13zyszM1IQJE2wxXHrppZoxY0aRrh+AkzMAAEZ0dLQhyejRo0e+Y8eOHTMkGQEBAXb7z549a3Tq1MmQZFx55ZXGsGHDjAcffNCIjIw0JBnTpk2ztf3+++8NScb9999f4OM3bNjQ8PX1NZKTk237vvjiC8PT09Pw8fExbr/9duPJJ580evXqZUgy6tevb5w6dSpf/B07djRCQ0ONDh06GCNGjDBuvPFGQ5IRFBRkxMXF2T1mTvuCREVFGVFRUSW+3sK0a9fOkGSsWbOmSO3zGjNmjCHJqFmzpnHvvfcaTzzxhNGiRQtDknHLLbfYtZ09e7Yhyejbt6/h4eFh9OvXzxg5cqTRqlUrQ5LRvn37fOcvyfPevn17IyAgwGjXrp0xYsQIY8iQIcbhw4cNwzCMBg0aGE2aNDEGDx5sjB492rj33nuNqlWrGpKMt99+23au3377zXjssccMSUazZs2McePG2X6io6MNwzCM7OxsY8CAAYYk49JLLzUeeOABY9iwYcZll11mSDJGjhxpdy0pKSlGkyZNDElG27ZtjdGjRxsDBw403N3dbdc0e/bsIj3vkoymTZsakZGRRuvWrY3Ro0cbgwYNMjw8PAwPDw/jhx9+sGtf3PfL4MGDDUnG9ddfbwQHBxuDBg0ynnrqKWPq1KmFxvXDDz8YkowHHnjAWLhwoSHJWLZsmV2bRo0aGVdeeeV5f89PnDhh1KtXz5BkdOrUyRg9erRx++23G25uboavr6+xcePGAmO95ZZbjNDQUGPIkCHG8OHDjVq1ahmSjGeeecbWdunSpbbfwxtvvNHudc3RsWNH2/kiIyON+++/33jooYeMkJAQQ5Lx/vvvX+jlAeDkSMoAwCg8KZswYYIhyejVq5fd/meeecaQZIwfP97Izs627U9KSjJatmxpeHh42D6YZ2dnG5GRkUZQUJCRlpZmd56tW7cakow777zTtu/EiROGv7+/UbNmTePAgQN27RcsWGBIMh599NF88UsyXn75Zbv2zz77rCHJmDx5st3+4iZlxbne88nIyDDc3d0Nd3d34+zZs4W2LcjKlSsNScZ1111npKSk2PZnZ2cbDz74oCHJWLRokW1/TlLm5uZmbNiwwbY/MzPTljBs2rTJtv9invfnnnuuwJj/+eeffPuSk5ONJk2aGAEBAXbXkXO+wYMHF3iu999/35Bk3HvvvUZGRoZtf1pamnHDDTcYkoytW7fa9o8bN86QZAwdOtTuPN99950t7uIkZZKMQYMG2b3+a9euNSwWi1GvXj0jKyvLtr+475ecRKeg574wuZOys2fPGsHBwUafPn1sxzdu3GhLAs/3e37PPfcYkowxY8bY7V+xYoUtGc99bTmx1qlTxzhy5Iht//Hjx43AwEDDz8/P7vc85314vuc6Jylr06aNkZiYaNu/Z88ew83NzWjQoEGRnw8AzomkDACMcx+GL7nkEtu32KNGjbJ9WAoLCzN27dpla5+VlWUEBQUZ9erVs/vAmePLL7/MVw14+umnDUnGkiVL7No+/vjjhiRjxYoVtn2vv/66Icn4+OOPC4y3efPmRmhoaL7469SpY/fhMfexvn372u0vTlJWkustyNGjRw1JRnh4eIHHZ86caVdJGDdunBETE2M73qdPH0OScfDgwXz3TUhIMCwWi9GvXz/bvpwPw3fddVe+9jnHclerSvq8h4eH50u2L2Tq1KmGJGPt2rX5zne+pKxp06aGr6+vkZqamu/YH3/8ka9aVqdOHcPDw8OIjY3N175Lly7FTspcXV0LfO5zqm4//vijYRgle7/kJDpvvfVWkeLJkTspMwzDePTRRw03NzdbZfi+++4zPD09jZMnTxaYlKWlpRne3t5GSEiIXYKco0ePHnbXljvWWbNm5Wufc+yPP/6w7StqUvb999+f91hSUlLRnhAATomJPgAgl3/++UcvvPCC3b6wsDD9+OOPuvTSS2379u7dq/j4eEVERORrL0nHjx+XJO3Zs8e2b9CgQZoyZYrmzZunm2++WZKUlZWlTz75ROHh4erataut7c8//2z7d9++ffnOf/bsWZ04cUInTpxQaGiobX+zZs3k4mI/XLhmzZqSpISEhCI9BwUpyfUWxDCMQo/PmjVLP/30k92+nj172q7h559/lq+vr2bOnFng/b29vQuMoXnz5vn2FfS8XMzz7uHhUWBMx44d08svv6xvv/1WBw4cUGpqqt3xI0eOFHi/vM6cOaMdO3YoIiJCL7/8cr7jOcsH5Fx/cnKyoqOj1ahRI4WHh+drf80112jNmjVFeuwcUVFRioyMLPBcy5cv1/bt23X11Vdf1PuldevWxYopr3vuuUfTp0/XRx99pEceeUSfffaZbrrpJgUHByspKSlf+z179ig1NVWdOnWSj49PvuOdOnXSd999Z7u23Ir6viqqC53Pz8+v2OcE4BxIygAglx49emjFihWSrB8c586dq6efflo33XSTNm/erCpVqkiyTp4gSX/++af+/PPP854vJSXFtn355Zfryiuv1PLly5WQkKDAwECtWrVKR48e1YgRI+Tq6mprm3P+d955p9B4U1JS7JKDgibNcHOz/qnPOwlGcZTkegsSEhIiNzc3nThxQmlpafL09LQ7vmHDBtv2kCFDNHfu3HxxZGZmFvhBv7AYivq8lPR5r1atWoHtTp06pVatWungwYNq3769unbtqsDAQLm6umr79u364osvlJaWVuhj5YiPj5dhGDp8+HCRrj8xMVGS9UuFgpwv5sJc6Fw5j3kx75eSxJXblVdeqSuuuEKzZ89WWFiYkpKSCp3gIydRO9/j5iS0OdeWW2n/vpXV7y8Ax8fsiwBwHlWrVtWoUaP0zDPPaPfu3Xr22Wdtx/z9/SVJ/fr1k2HtCl7gz+zZs+3OOWjQIKWlpWnRokWSpHnz5tn255Zz/h07dhR6/qioqBJfn8ViOe+aTXk/gJb0evNyc3NTq1atlJmZaZeAFZW/v79CQkIKjSE6OrrY5819fqn4z3tBM+lJ0syZM3Xw4EG99NJL2rBhg6ZNm6YJEyZo/PjxhS50XFhsLVq0KDS2H374wa79sWPHCjzf0aNHi/X4RTlXTlJxMe+X8z2XxXH33Xdr9+7dGjt2rCIjI9WtW7fzts2J9XzPR87+nHYAUBZIygDgAp555hlFRERoxowZtmnOGzZsKH9/f23dutXWbawo7rjjDrm6umrevHlKSUnRsmXLdPnll+uKK66wa9emTRtJKtOFk4OCgnT48OF8+/fv35+v61VJr7cgOVWLyZMnX7A7Y15t2rTRyZMn9ffff19UDIWdXyq95/2ff/6RJPXp0yffsYKWR8iplhZUFfHz81PDhg21e/fuInWN8/f3V506dbRv3z7FxcUV6fEv5MCBA4qJiTnvuXLex6X5fimJO++8U56enjp8+LAGDx6cr0tvbpdddpm8vLy0ZcsWnTlzJt/xnLUJ8/6OFkdhrysASCRlAHBB3t7eevrpp5WRkaEJEyZIslZ8HnroIR04cECjRo0q8IPnzp0781UWcsaOrV+/Xm+99ZZSUlLyVckka+Li5+ensWPHFtj968yZM7bxTyXVsmVL7d+/324NrPT0dI0YMSJf25Jeb0GGDBmidu3aac2aNbrnnnsKHOdjGEaB+4cPHy7JOm6ooDXG4uLitHv37gvGcD6l/bznVNTyVgUXLFigb775Jl/7oKAgWSwWHTp0qMDzDR8+XGfOnNHQoUML7PoXHR1t++JAslZg09PT9fzzz9u1W7lyZbHHk0nWpGLs2LF2yfS6dev0zTffqF69emrXrp2k0n2/lERwcLC+++47LV26VI899lihbT08PHTHHXfoxIkTmjx5st2x1atX69tvv1W9evXUvn37i4pH0nlfVwBgTBkAFMH999+vKVOm6KOPPtIzzzyjSy65RC+88IJ+/fVXvf3221q+fLk6duyoqlWr6vDhw9qxY4d+//13bdq0Kd84nEGDBum7777T+PHj5eLiooEDB+Z7vKpVq+qTTz7RrbfeqmbNmqlnz5667LLLdPbsWR04cEDr1q1Tu3btbOPfSuKJJ57QypUr1atXL91xxx3y8fHRqlWrFBgYqOrVq+drX9Lrzcvd3V1ffPGF+vfvrzlz5mjJkiXq0qWL6tWrJ4vFori4OK1bt04HDhxQ3bp1FRERYbtvz5499dxzz2nChAmqV6+eevbsqaioKJ08eVL79u3Tjz/+qJdeekkNGzYs0XNS2s97zuQuw4YN0w8//KCoqCj98ccfWr16tfr27aslS5bYta9SpYpatWql9evX6+6771b9+vXl4uKiAQMGqFatWnrggQf0888/a+7cufrpp5/UtWtXRURE6OjRo9qzZ49++eUXLViwwLbw91NPPaUlS5bogw8+0J9//qkOHTooJiZGn332mXr16qXly5cX6/lp2rSp1q5dq6uuukrXXnutjhw5ooULF8rd3V0ffPCBXUWqtN4vJdWxY8cit50yZYrWrVunl156SRs3blSbNm20f/9+LVq0SD4+Ppo9e3ah1bYLadu2rby9vfXmm28qKSlJVatWlSSNHj26xOcEUMGU5lSOAOCsClunLMe0adNs6zTlyMzMNN577z2jffv2hr+/v+Hp6WnUqlXL6Nmzp/G///3POH36dL7zpKSkGFWqVDEkGZ07dy40rj179hj33nuvERUVZXh4eBhBQUFGkyZNjOHDhxubN2/OF//5plLXeaa///TTT40mTZoYHh4eRnh4uDFs2DAjOTm5wHXKSnq955OdnW0sWbLE6Nu3rxEZGWl4enoaXl5eRu3atY2+ffsa8+fPP+8086tWrTJuuOEGo2rVqoa7u7sRHh5utG3b1pgwYYLdlO2FTUWeM5V67kV8c5TW824YhrF9+3aje/fuRlBQkOHn52d07NjRWL169Xlj27t3r3H99dcbgYGBhsViMSTlW5j5008/Nbp27WoEBQUZ7u7uRo0aNYxOnToZU6dONY4fP27X9uTJk8b9999vVK1a1fDy8jJatGhhLFmy5ILTtOeV8x46cOCAceuttxpBQUGGt7e30aFDB7s14HIrzvslZyr5nIWyiyrvlPiFKez3/Pjx48bw4cONqKgow93d3QgNDTVuueUWY8eOHfnaFhZrztpweV+z5cuXG61atTK8vb1ta77lyJn2viAlfV4AOBeLYRSzQz8AAKh0LBaLOnbsaNfdFQBQOhhTBgAAAAAmIikDAAAAABORlAEAAACAiZh9EQAAXBBD0AGg7FApAwAAAAATkZQBAAAAgInovljKsrOzdeTIEfn5+clisZgdDgAAAACTGIah5ORkRUREFLoIPUlZKTty5IgiIyPNDgMAAACAg4iJiVHNmjXPe5ykrJT5+flJsj7x/v7+JkcDAAAAwCxJSUmKjIy05QjnQ1JWynK6LPr7+5OUAQAAALjgsCYm+gAAAAAAE5GUAQAAAICJSMoAAAAAwEQkZQAAAABgIpIyAAAAADARSRkAAAAAmIikDAAAAABMRFIGAAAAACYiKQMAAAAAE5GUAQAAAICJSMoAAAAAwEQkZQAAAABgIpIyAAAAADARSRkAAAAAmIikDAAAAABMRFIGAAAApKRI6enSsWPWf1NSzI4IlQhJGQAAACq3s2elV16RqlU79/PKK9b9QDlwMzsAAAAAwDQpKdYE7MUXz+1LSDh3+6mnJF9fU0JD5UGlDAAAAJWXu7v09tsFH3v7betxoIxRKQMAAKhApmy40+wQSuTpq+eZ88AJCdaf8x1LTJSqVi3HgFAZUSkDAABA5RUYaP0537GAgHIMBpUVSRkAAAAqr4wMadiwgo8NH249DpQxui8CAACg8vL1lZ54QjIMafp0a5fFwEBrQjZmjOTlZXaEqARIygAAAFB5ZWZKPXtaE7BDh6Tjx6WwMGuSRkKGckJSBgAAgMpr61Zp82bp5pul0FApPFw6fVr691+zI0MlQlIGAACAymvVqnPbJ09KJ06c2w4NNScmVDpM9AEAAIDKa+XKc9vdu5/bjo4u/1hQaZGUAQAAoHJKTpZ+/tm6femlUufO547RfRHliKQMAAAAldPatdaJPiSpWzepTp1zx6iUoRwxpgwAAACVU96uixER525TKUM5IikDAABA5ZQzyYerq9Spk/1C0VTKUI5IygAAAFD5HDwo7d1r3b7qKsnf37o2mb+/lJREpQzlijFlAAAAqHxyT4WfM+uixXJuXNnBg+fGmwFljKQMAAAAlU/upKxbt3PbOUlZZqZ06FD5xoRKi6QMAAAAlUt2trR6tXU7IEBq1ercsbp1z20zrgzlhKQMAAAAlctvv0knT1q3r71Wcss1zULuafEZV4ZyQlIGAACAyuV8XRclKmUwBUkZAAAAKpe865PlRqUMJiApAwAAQOVx5oz000/W7Tp1pEsusT9eu/a5bSplKCckZQAAAKg81q+X0tOt23m7LkqSt7dUvbp1m0oZyglJGQAAACqPwrou5sgZV3bsmJSSUvYxodIjKQMAAEDlkTPJh4uLdebFguQeV0YXRpQDkjIAAABUDkeOSDt3WrdbtpSCggpuxwyMKGckZQAAAKgcchaMls7fdVFiBkaUO5IyAAAAVA6FrU+WG5UylDOSMgAAAFR8hnEuKfP1la666vxtGVOGckZSBgAAgIpvxw7p6FHrdufOkofH+dtGRJw7TvdFlAOSMgAAAFR8Re26KEmurlJUlHU7OtpaZQPKEEkZAAAAKr6irE+WW864spQU6fjxsokJ+A9JGQAAACq2s2el9eut2zVrSg0aXPg+jCtDOSIpAwAAQMX200/WxEyydl20WC58n9wzMDKuDGWMpAwAAAAVW3G7LkpUylCuSMoAAABQseWe5KNLl6Ldh0oZypFDJWWTJ0+WxWLR448/bttnGIbGjx+viIgIeXt7q1OnTvrzzz/t7peWlqZhw4YpNDRUvr6+6tOnjw4dOmTXJj4+XoMGDVJAQIACAgI0aNAgJSQk2LU5ePCgbrjhBvn6+io0NFTDhw9Xenp6WV0uAAAAytqxY9Jvv1m3r7xSqlq1aPejUoZy5DBJ2ZYtW/T++++radOmdvtfeeUVvf7665o+fbq2bNmi8PBwdevWTcnJybY2jz/+uJYuXaqFCxdqw4YNOn36tHr37q2srCxbmwEDBmj79u1asWKFVqxYoe3bt2vQoEG241lZWerVq5dSUlK0YcMGLVy4UIsXL9bIkSPL/uIBAABQNtasObdd1K6LkhQUJAUGWreplKGMOURSdvr0aQ0cOFAffPCBgoKCbPsNw9Cbb76psWPHqm/fvmrcuLHmzp2rM2fOaMGCBZKkxMREzZw5U1OnTlXXrl115ZVXat68edqxY4dWr14tSdq9e7dWrFihDz/8UG3btlXbtm31wQcf6Ouvv9bevXslSStXrtSuXbs0b948XXnllerataumTp2qDz74QElJSeX/pAAAAODiFWd9srxyqmUxMVJGRunFBOThEEnZI488ol69eqlr1652+6OjoxUXF6fuub7V8PT0VMeOHbVx40ZJ0rZt25SRkWHXJiIiQo0bN7a12bRpkwICAtSmTRtbm6uuukoBAQF2bRo3bqyIiAhbmx49eigtLU3btm07b+xpaWlKSkqy+wEAAIADMIxzk3x4e0vt2xfv/jnjyrKyrIkZUEZMT8oWLlyoX3/9VZMnT853LC4uTpJUrVo1u/3VqlWzHYuLi5OHh4ddha2gNmFhYfnOHxYWZtcm7+MEBQXJw8PD1qYgkydPto1TCwgIUGRk5IUuGQAAAOVhzx7p8GHrdocOkpdX8e7PuDKUE1OTspiYGD322GOaN2+evAr5JbHkWUvCMIx8+/LK26ag9iVpk9eYMWOUmJho+4nhWxQAAADHcDFdFyVmYES5MTUp27Ztm44dO6YWLVrIzc1Nbm5uWrdund5++225ubnZKld5K1XHjh2zHQsPD1d6erri4+MLbXP06NF8j3/8+HG7NnkfJz4+XhkZGfkqaLl5enrK39/f7gcAAAAOoCTrk+VGpQzlxNSkrEuXLtqxY4e2b99u+2nZsqUGDhyo7du3q27dugoPD9eqXN9ypKena926dWrXrp0kqUWLFnJ3d7drExsbq507d9ratG3bVomJidq8ebOtzS+//KLExES7Njt37lRsbKytzcqVK+Xp6akWLVqU6fMAAACAUpaeLq1da90OD5caNy7+OaiUoZy4mfngfn5+apznF8TX11chISG2/Y8//rgmTZqk+vXrq379+po0aZJ8fHw0YMAASVJAQIDuvfdejRw5UiEhIQoODtaoUaPUpEkT28QhDRs2VM+ePTV06FC99957kqT7779fvXv3VoMGDSRJ3bt3V6NGjTRo0CC9+uqrOnXqlEaNGqWhQ4dS/QIAAHA2mzZJKSnW7a5dpQsMfSlQVJT1foZBpQxlytSkrCieeuoppaam6uGHH1Z8fLzatGmjlStXys/Pz9bmjTfekJubm/r376/U1FR16dJFc+bMkaurq63N/PnzNXz4cNssjX369NH06dNtx11dXbV8+XI9/PDDat++vby9vTVgwAC99tpr5XexAAAAKB25x5OVpOuiJHl6SjVqSIcOUSlDmbIYhmGYHURFkpSUpICAACUmJlJhAwAA5W7KhjvNDqFEnr56XumesE0bKWfoypEjUvXqJTtPhw7Sjz9at5OSpFyFAeBCipobmD4lPgAAAFCqTp2StmyxbjduXPKETLIfV0YXRpQRkjIAAABULN9/bx0HJpW862IOZmBEOSApAwAAQMVyseuT5cYMjCgHJGUAAACoOAzj3PpkHh7WMWEXg0oZygFJGQAAACqOf/6R9u+3bl99teTjc3Hno1KGckBSBgAAgIojp0omXXzXRcm68LSnp3WbShnKCEkZAAAAKo7SWJ8sNxeXc10Yo6PPTSAClCKSMgAAAFQMmZnWmRclKTRUuuKK0jlvTlKWmiodPVo65wRyISkDAABAxbB5s3WBZ0nq0sVa5SoNjCtDGSMpAwAAQMVQ2l0XczADI8oYSRkAAAAqhtJcnyw3KmUoYyRlAAAAcH6JidLPP1u3L7tMiowsvXNTKUMZIykDAACA81u7VsrKsm6XZpVMsk/KqJShDJCUAQAAwPmV9vpkuQUESMHB1m0qZSgDJGUAAABwfjnjydzcpE6dSv/8OePKYmKk9PTSPz8qNZIyAAAAOLf9+6W//7Zut20r+fmV/mPkdGE0DOngwdI/Pyo1kjIAAAA4t7KadTE3ZmBEGSIpAwAAgHMrq/XJcmMGRpQhkjIAAAA4r6wsac0a63ZgoNSyZdk8DjMwogyRlAEAAMB5/fqrdOqUdfvaayVX17J5nNzdF6mUoZSRlAEAAMB5lUfXRUmqVUuyWKzbVMpQykjKAAAA4LzKcn2y3Dw8pMhI6zaVMpQykjIAAAA4p9OnpY0brduXXGLfxbAs5IwrO3VKSkws28dCpUJSBgAAAOe0fr2UkWHdLssqWQ7GlaGMkJQBAADAOZVX18UcTIuPMkJSBgAAAOeUM8mHi4t15sWyxgLSKCMkZQAAAHA+hw9Lu3ZZt1u3tq5RVtaolKGMkJQBAADA+eSeCr88ui5KVMpQZkjKAAAA4HzKa32y3KpVk7y9rdtUylCKSMoAAADgXLKzzyVlfn5Smzbl87gWy7kujNHR1jiAUkBSBgAAAOfyxx/S8ePW7U6dJHf38nvsnKQsLU2Kiyu/x0WFRlIGAAAA52JG18UcjCtDGSApAwAAgHMp7/XJcmMGRpQBkjIAAAA4j9RU6ccfrdu1akmXXlq+j0+lDGWApAwAAADOY8MG63guyVols1jK9/GplKEMkJQBAADAeZjZdVGyT8qolKGUkJQBAADAeeRM8mGxSF26lP/j+/lJoaHWbSplKCUkZQAAAHAOR49Kv/9u3W7e/FxyVN5yxpUdPnyuKyVwEUjKAAAA4BxWrz63bUbXxRw5XRgNQzpwwLw4UGGQlAEAAMA5mLk+WW7MwIhSRlIGAAAAx2cY5yb58PGR2rUzLxZmYEQpIykDAACA49u1S4qNtW537Ch5epoXC5UylDKSMgAAADi+3F0XzRxPJlEpQ6kjKQMAAIDjM3t9stwiIyVXV+s2lTKUApIyAAAAOLa0NGndOut29erS5ZebG4+7uzUxk6iUoVSQlAEAAMCxbdoknTlj3e7WzbpwtNlyxpUlJEjx8aaGAudHUgYAAADH5khdF3MwrgyliKQMAAAAji33JB9du5oXR27MwIhSRFIGAAAAx3XypLRtm3W7aVMpPNzceHJQKUMpIikDAACA41qzxrpwtOQ4XRclKmUoVSRlAAAAcFy5uy52725eHHlRKUMpIikDAACAYzKMc5N8eHpK11xjbjy5Va0q+fpat6mU4SKRlAEAAMAx/f23dPCgdfuaayRvb3Pjyc1iOVctO3BAysoyNx44NZIyAAAAOKbcXRcdaTxZjpxxZenp0pEj5sYCp0ZSBgAAAMfkiOuT5ca4MpQSkjIAAAA4nowM6YcfrNtVq0rNmpkbT0GYgRGlhKQMAAAAjueXX6TkZOt2166SiwN+bKVShlLigO9uAAAAVHqOPp5MolKGUkNSBgAAAMfjDElZ7drntqmU4SKQlAEAAMCxJCRYuy9KUsOGUs2apoZzXr6+UrVq1m0qZbgIJGUAAABwLD/8IGVnW7e7dzc3lgvJGVcWGyulppobC5wWSRkAAAAcizN0XcyRe1zZgQPmxQGnRlIGAAAAx5KzPpm7u9Sxo7mxXEjuGRjpwogSIikDAACA4/j3X+mff6zb7dpJVaqYG8+F5K6UMdkHSoikDAAAAI7DmbouSlTKUCpIygAAAOA4nC0po1KGUkBSBgAAAMeQlSWtWWPdDgqSWrQwN56iqFlTcnOzblMpQwmRlAEAAMAxbN1qXaNMkrp0kVxdTQ2nSFxdpago63Z0tGQY5sYDp0RSBgAAAMfgbF0Xc+SMK0tKkk6dMjcWOCWSMgAAADgGZ0/KJMaVoURIygAAAGC+5GRp40brdr169omOo8s92QfjylACJGUAAAAw37p1Umamdbt7d3NjKS4qZbhIJGUAAAAw38qV57adqeuiRKUMF42kDAAAAObLGU/m6ip17mxuLMVFpQwXiaQMAAAApvI7miLt2WO90aaNFBBgbkDFFRIi+flZt6mUoQRIygAAAGCq2lvjzt1wtq6LkmSxnKuWHThgXQQbKAaSMgAAAJiq9pbYczecMSmTzo0ry8yUDh0yNxY4HZIyAAAAmCfbOFcp8/eXWrc2N56SYlwZLgJJGQAAAExT7e94+SSmWW907iy5u5sbUEkxAyMuAkkZAAAATFN7a66ui862PlluVMpwEUjKAAAAYJramyvAeDKJShkuCkkZAAAATOF2NlM1dxy33oiKkurVMzegi1G79rltKmUoJpIyAAAAmCLy92Nyy8i23uje3Tq1vLPy9paqV7duUylDMZGUAQAAwBQVYir83HLGlR09Kp05Y24scCokZQAAADBF7S3WqfANi6RrrzU3mNKQe1wZXRhRDCRlAAAAKHe+J1IV9m+CJCn2shApJMTcgEoDMzCihEjKAAAAUO5yT4W/v2W4iZGUImZgRAmRlAEAAKDc1d4aZ9ve36q6iZGUIiplKCGSMgAAAJQvw7BN8pHu7aYjl4eaHFApoVKGEiIpAwAAQLkK/TdBVU6dlSTFNAtTloeryRGVkogIyd3duk2lDMVgelL2v//9T02bNpW/v7/8/f3Vtm1bffvtt7bjhmFo/PjxioiIkLe3tzp16qQ///zT7hxpaWkaNmyYQkND5evrqz59+ujQoUN2beLj4zVo0CAFBAQoICBAgwYNUkJCgl2bgwcP6oYbbpCvr69CQ0M1fPhwpaenl9m1AwAAVEZ1tpzruhjduoJ0XZQkV9dzi0j/+69kGKaGA+dhelJWs2ZNvfzyy9q6dau2bt2qa6+9VjfeeKMt8XrllVf0+uuva/r06dqyZYvCw8PVrVs3JScn287x+OOPa+nSpVq4cKE2bNig06dPq3fv3srKyrK1GTBggLZv364VK1ZoxYoV2r59uwYNGmQ7npWVpV69eiklJUUbNmzQwoULtXjxYo0cObL8ngwAAIBKIPf6ZPtbVqCkTDo3riwlRTpxwtxY4DTczA7ghhtusLs9ceJE/e9//9PPP/+sRo0a6c0339TYsWPVt29fSdLcuXNVrVo1LViwQA888IASExM1c+ZMffzxx+rataskad68eYqMjNTq1avVo0cP7d69WytWrNDPP/+sNm3aSJI++OADtW3bVnv37lWDBg20cuVK7dq1SzExMYqIiJAkTZ06VUOGDNHEiRPl7+9fYPxpaWlKS0uz3U5KSir15wgAAKCicE3LUuTvxyRJyaHeOlm74M9YTivvuLKqVc2LBU7D9EpZbllZWVq4cKFSUlLUtm1bRUdHKy4uTt27d7e18fT0VMeOHbVx40ZJ0rZt25SRkWHXJiIiQo0bN7a12bRpkwICAmwJmSRdddVVCggIsGvTuHFjW0ImST169FBaWpq2bdt23pgnT55s6xIZEBCgyMjI0nkyAAAAKqAaO4/LPc3am2l/q+qSxWJyRKWMGRhRAg6RlO3YsUNVqlSRp6enHnzwQS1dulSNGjVSXJy1v3G1atXs2lerVs12LC4uTh4eHgoKCiq0TVhYWL7HDQsLs2uT93GCgoLk4eFha1OQMWPGKDEx0fYTExNTzKsHAACoPOrk6roY3aqCrE+WGzMwogRM774oSQ0aNND27duVkJCgxYsXa/DgwVq3bp3tuCXPNyiGYeTbl1feNgW1L0mbvDw9PeXp6VloLAAAALCqnWuSjwMVbTyZRKUMJeIQlTIPDw/Vq1dPLVu21OTJk9WsWTO99dZbCg+3fnuSt1J17NgxW1UrPDxc6enpio+PL7TN0aNH8z3u8ePH7drkfZz4+HhlZGTkq6ABAACg+Lzjz6ra36ckSUfrB+lMkJfJEZUBKmUoAYdIyvIyDENpaWmqU6eOwsPDtWrVKtux9PR0rVu3Tu3atZMktWjRQu7u7nZtYmNjtXPnTlubtm3bKjExUZs3b7a1+eWXX5SYmGjXZufOnYqNPVdSX7lypTw9PdWiRYsyvV4AAIDKoPa2OFn+myV+f8sK2HVRkoKCpIAA6zaVMhSR6d0Xn3nmGV133XWKjIxUcnKyFi5cqLVr12rFihWyWCx6/PHHNWnSJNWvX1/169fXpEmT5OPjowEDBkiSAgICdO+992rkyJEKCQlRcHCwRo0apSZNmthmY2zYsKF69uypoUOH6r333pMk3X///erdu7caNGggSerevbsaNWqkQYMG6dVXX9WpU6c0atQoDR069LwzLwIAAKDoam891ytpf6sK2HUxR9260m+/SQcPSpmZkpvpH7nh4Ex/hxw9elSDBg1SbGysAgIC1LRpU61YsULdunWTJD311FNKTU3Vww8/rPj4eLVp00YrV66Un5+f7RxvvPGG3Nzc1L9/f6WmpqpLly6aM2eOXF3PrQ4/f/58DR8+3DZLY58+fTR9+nTbcVdXVy1fvlwPP/yw2rdvL29vbw0YMECvvfZaOT0TAAAAFZhh2NYny/Bw1aGmFXiq+Dp1rElZVpYUE2M/zgwogMUwWGq8NCUlJSkgIECJiYlU2AAAQLmbsuFOs0MoUPCBRA2982tJ1lkXP3u9i93xp6+eZ0ZYZePJJ6WcL/ZXr5a6dCm8PSqsouYGDjmmDAAAABVL7lkXK3TXRYkZGFFsJGUAAAAoc/brk1XwpCz3DIwkZSgCkjIAAACUKZfMbEX+Zl2eKCXIS8frBpobUFnLXSljWnwUAUkZAAAAylTEnyfkmZop6b+p8F0sJkdUxqKiJMt/10ilDEVAUgYAAIAylbvrYoUfTyZJXl5SRIR1m0oZioCkDAAAAGWqdu6krKIuGp1Xzriy48el06fNjQUOj6QMAAAAZcYzOU3he05Jko7XCdDpqj4mR1ROmIERxVCipGzPnj264447VL16dXl4eOjXX3+VJL3wwgv64YcfSjVAAAAAOK+obUflkm1dFnd/y0rQdTEHMzCiGIqdlG3fvl2tWrXSunXr1KlTJ2VlZdmOnT59Wu+++26pBggAAADnVXtrrq6LrStJ10WJGRhRLMVOykaPHq2mTZtq3759+vjjj2UYhu1Y69attWXLllINEAAAAM6rzmbrotGZ7i6KaVbN5GjKEZUyFINbce/w008/ad68efLx8bGrkklStWrVFBcXd557AgAAoDIJPJyswFjrJBeHG1dVhnexP3o6LyplKIZiV8oMw5CHh0eBx+Lj4+Xp6XnRQQEAAMD52c262KoSdV2UpOrVpZzPxVTKcAHFTsqaNm2qpUuXFnhsxYoVatGixUUHBQAAAOdXe8u5HlSVYn2y3FxcpNq1rdvR0VKuIT9AXsWuIT/22GMaMGCAfH19NWjQIEnSwYMH9f3332vWrFlatGhRqQcJAAAA52LJzFbUr9akLNXfQ0frB5kckQnq1pX27pXOnJGOHZOqVaIxdSiWYidlt912m/755x+NHz9eb7/9tiSpX79+cnNz0wsvvKAbbrih1IMEAACAc6m+56S8TmdIsi4YbbhWwuVx844rIynDeZRotOUzzzyju+66S999952OHj2q0NBQ9ejRQ1FRUaUdHwAAAJyQXdfFyrQ+WW55Z2Bs29a8WODQSjwFTs2aNXXvvfeWZiwAAACoIOzWJ6tsk3zkYAZGFFGxk7KDBw9esE2tWrVKFAwAAACcn0dKhmr8eUKSdDLST0nhVUyOyCS5kzJmYEQhip2U1a5dWxaLpdA2edcvAwAAQOVR67ejcsmyzjZY6WZdzC1390UqZShEsZOyWbNm5UvKTpw4oS+//FKHDh3Ss88+W2rBAQAAwPnYr09WiZOygAApKEiKj6dShkIVOykbMmRIgftHjhypW2+9VTExMRcbEwAAAJxYTlKW7WrRwSsr+YyDdetK27ZJMTFSRobk7m52RHBApTo36ZAhQ/Thhx+W5ikBAADgRPzjTiskJlmSdKRRqNJ9K3kSkjOuLDtbKsLcDKicSjUpy8zMVEJCQmmeEgAAAE4k91T40ZW562IOxpWhCEo8JX5uGRkZ+uOPPzRu3Dg1a9asNE4JAAAAJ8RU+HkwAyOKoNhJmYuLy3lnXwwKCtJ333130UEBAADA+ViyslV7q7VSdraKu2IvCzE5IgdApQxFUOyk7Pnnn8+XlHl5eal27dq6/vrr5efnV2rBAQAAwHlU+zte3knpkqQDzcNluJXqSBnnRKUMRVDspGz8+PFlEAYAAACcnd1U+C3puihJioqSLBbJMKiU4bz4+gIAAAClIqfroiTtb80kH5IkDw+pZk3rNpUynEeJJvrYsGGDFixYoAMHDig1NdXumMVi0Zo1a0olOAAAADgH99RM1fzjuCQpoXoVJdRgSItN3brWdcpOnpSSkiR/f7MjgoMpdqVs9uzZ6tChgz777DPFx8fLMAy7n+zs7LKIEwAAAA4s8vejcs20fg5k1sU8GFeGCyh2peyVV15R//79NXfuXHl6epZFTAAAAHAytTezPtl55Z2BkSWkkEexK2UHDhzQfffdR0IGAAAAm5z1ybJdLDrQoprJ0TgYKmW4gGInZQ0bNtTRo0fLIhYAAAA4oSonzqhqdKIkKa5BsNL8+PLeDmuV4QKKnZRNmjRJL7/8sg4fPlwW8QAAAMDJ1N7CrIuFolKGCyj2mLJ33nlHiYmJuvTSS3XFFVcoJMR+pXaLxaIvvvii1AIEAACAY8u9Plk065PlFx4ueXlJZ89SKUOBip2U/fHHH3J1dVVYWJiOHDmiI0eO2B23WCylFhwAAAAcXLahqG3WSlm6t5uOXB5qckAOyGKxVst275b275eysyUXlgvGOcVOyvbv318GYQAAAMAZVf03QVVOnZUkHbyymrLdXU2OyEHVrWtNys6eleLipIgIsyOCAyFFBwAAQInVydV1kfXJCsG4MhSiRElZWlqa3nvvPd1xxx3q1q2b/v77b0nSF198oX/pJwsAAFBp5J7kg/XJCsEMjChEsbsvnjhxQp07d9aff/6p8PBwHT16VMnJyZKkZcuW6bvvvtOMGTNKPVAAAAA4Fte0LNX8/ZgkKSnMR6dq+ZsckQOjUoZCFLtS9tRTTykhIUFbt27VwYMHZRiG7Vjnzp21bt26Ug0QAAAAjqnmjmNyT8+SJO1vGW6d0AIFo1KGQhS7Uvb1119rypQpat68ubKysuyO1axZU4cOHSq14AAAAOC46mzOPZ6MrouFolKGQhS7UpaUlKSoqKgCj2VkZCgzM/OigwIAAIDjq70116LRLZjko1B+flLof8sFkJQhj2InZXXq1NGmTZsKPLZ582Y1aNDgooMCAACAY/OJP6tqf8dLkuLqByk1yMvkiJxATrXs0CEpLc3cWOBQip2UDRw4UFOmTNEXX3xhG09msVi0ZcsWvfXWWxo0aFCpBwkAAADHErU1V9fF1nRdLJKccWWGIR08aG4scCjFHlP29NNP66efftLNN9+soKAgSVKPHj108uRJ9ezZU4899lipBwkAAADHUifXVPj7W5KUFUnucWX//ivVr29eLHAoxU7K3N3d9c033+jTTz/V8uXLdfToUYWGhqp37966/fbb5eLCetQAAAAVmmGo9n+VsgxPVx1qUtXkgJxE7hkYGVeGXIqdlEnW7oq33367br/99tKOBwAAAA4uZH+S/I6nSpJimoUpy9PV5IicRN5KGfCfYpe1brnlFn3zzTfKzs4ui3gAAADg4GpvZSr8EqFShvModlK2adMm3XDDDapZs6bGjBmjPXv2lEVcAAAAcFC51yeLbsVU+EUWGSnlDPWhUoZcip2UxcTE6Ouvv9Y111yjN998U5dffrnatWunmTNnKjk5uSxiBAAAgINwychS5O/HJEmng710om6guQE5E3d3qVYt6zaVMuRS7KTMxcVF1113nT799FPFxsZq2rRpysjI0NChQ1W9enUNHjy4LOIEAACAA6ix84Q8UjMlSftbhksWi8kROZmccWXx8VJCgqmhwHFc1FSJgYGBevjhh7VlyxatX79ewcHBmjdvXmnFBgAAAAdTewvjyS4K48pQgIuev37VqlUaMGCAunfvrkOHDqlt27alERcAAAAcUO2trE92UZiBEQUo0ZT4//zzj+bMmaO5c+fq8OHDql69uh577DHdc889qs8ieAAAABWSV1Kaqu85KUk6XjdAKaHeJkfkhKiUoQDFTso6duyoDRs2yN3dXTfccIPuuece9ejRg0WjAQAAKriobXGyGNbtaLoulgyVMhSg2ElZcnKy3nzzTQ0cOFDBwcFlERMAAAAcUO0tuboukpSVDJUyFKDYSdmvv/5aFnEAAADAkRmG6vw3yUemu4timoWZHJCTqlpV8vGRzpyhUgabEvc5/O677zRmzBgNHTpUBw8elCRt2bJFx48fL7XgAAAA4BiqH7coILSOFBqqQ02qKtOrRFMTwGI5Vy3bv1/KzjY1HDiGYv82nTlzRjfeeKPWrFkjy3/rUjz00EOqVauWXnvtNUVGRuq1114r9UABAABQ/kK8I9QlvJ+iWjSRrjwqhYXJf/fPCrF8p5OpR8wOzznVqSPt3Cmlp0tHjkg1a5odEUxW7ErZ2LFjtXXrVi1evFiJiYkyDMN2rHv37lq9enWpBggAAABzhHhHaNBlYxT1/nK5RNSwVnhq1lTgV+s06LIxCvGOMDtE58S4MuRR7KTs888/14QJE3TzzTfL29t+GtRatWrZujICAADAuXUJ7yf3V96Qy4sTpIQE686EBLm8OEHur7yhLuH9TI3PaTEDI/IodlJ2/PhxXX755QWfzMVFqampFx0UAAAAzOXt5qdaoU3k8va0Ao+7vD1NtUKbyNvNr5wjqwColCGPYo8pq1Gjhnbs2KHOnTvnO/bHH3+oTu7MHwAAwIHc/e0Is0MokdnXvV7uj+nrEaCsUyflmlMhyyshQVnxp+TrEaDUzORyjc3pUSlDHsWulPXt21cTJ07Ub7/9ZttnsVh04MABvfHGG7r11ltLNUAAAACUv5T0RLkFhUiBgQU3CAyUa1CwUtITyzWuCiF3UkalDCpBUjZu3DhFRESodevWatmypSwWi+6++241btxYYWFhGj16dFnECQAAgHIUsW63tGqV9OijBR7PHj5MB0/soEpWEr6+Uth/67xRKYNKkJT5+flp48aNmjBhgqpUqaJLLrlEPj4+GjNmjNavX59v8g8AAAA4l8u+P6Cbx66Xy1OjpeHDZTz37LmKWWCgsp9/ThlPPaE1cYtNjdOp5VTLjhyRzp41NxaYrkSr/nl7e2v06NEFVsU2bNigq6+++qIDAwAAQPlrsvwf9XzlF7lkG9KePdr39O1ye3GiIseOUVb8KbkGBevg8T+0Zs9k1im7GHXrSr/8Yt3ev1+67DJTw4G5Sm0p9l9++UXPPfec1qxZo6ysrNI6LQAAAMpJi0V71PWtbbbbv/e+RN8NriZj/3R5H/KTr0eAUvYn0mWxNOQdV0ZSVqkVufviwoUL1blzZzVq1Eg333yztm/fLkn6559/1KdPH7Vr104bNmzQqFGjyipWAAAAlJGrPtppl5BtufUyrXiqjQxX68fF1MxknThziISstOSeFp9xZZVekSplCxcu1IABAyRJVatW1ddff60ffvhBn3zyiW677TalpKTorrvu0oQJE1SzZs0yDRgAAAClyDDU4b3tajt/l23XT4Mba8O9TSWLxcTAKjhmYEQuRaqUTZs2TY0bN9b+/ft19OhRnThxQh07dtTNN98sT09PrVu3TrNnzyYhAwAAcCbZhrq+udUuIfvhoSu14b5mJGRljUoZcilSUrZz504988wzqlWrliQpICBAr732mtLT0zV58mQm9gAAAHAylsxsXT/5Z7VY8pdt33cjWmnzgEYmRlWJ1Kwpubpat6mUVXpFSsqSk5NVJ3eJVbLdbtKkSelHBQAAgDLjkpGlPi/8pCYrrBWabBeLvh7bVttvvtTkyCoRNzcpKsq6/e+/kmGYGw9MVeSJPix5Stg5t93d3Us3IgAAAJQZt7RM9X1mvS5be1CSlOXmoi9evFp/9qx7gXui1OUUPZKSpPh4c2OBqYo8Jf7UqVNVrVo1223DMGSxWPTqq6+qatWqtv0Wi0VvvfVW6UYJAACAi+ZxJkP9nl6rWtuPSZIyPF21dGIHRbeJMDmySqpuXWnNGuv2v/9KwcHmxgPTFDkp+/zzzwvc/+mnn9rdJikDAABwPF5Jabp11A+K2H1SkpTm46ZFUzrp0BXVLnBPlJm8MzC2bGleLDBVkZKy7Ozsso4DAAAAZcTnVKpuG/G9wv5JkCSl+nnos6nXKq5hiLmBVXbMwIj/FLlSBgAAAOfjdzRFtz2xRiEx1kWfTwd76dPXr9WJS4JMjgysVYYcJGUAAAAVVOChZN3+xBoFxKVIkpLCfLTwzS6Kj/Q3OTJIolIGmyLPvggAAADnERqdoAGPrrIlZKdq+mn+O91IyBxJSIhUpYp1m0pZpUZSBgAAUMFU23tSdwxbLb+TqZKk43UDtGBaNyWFVzE5MtixWM5Vyw4ckLKyzI0HpiEpAwAAqEBq/HFMdzy2Rj6JaZKk2MuCteDtbkoJ9TY5MhQoZ1xZRoZ0+LC5scA0JGUAAAAVxapV6j/ye3mmZEiSYppV1cI3u+psgKfJgeG8co8rowtjpUVSBgAAUBF88YXUu7c8zlq7wEW3qq7PXrtW6b7uJgeGQuWegZHJPiqtIs2++OKLLxb5hBaLRc8991yJAwIAAEAxLVgg3XWXbUzS3g6R+mpce2V5uJocGC6IShlUxKRs/PjxRT4hSRkAAEA5ev996cEHJcOQJO3sXlvfjGkrw40OUU6BShlUxKQsOzu7rOMAAABAcb3+ujRy5LnbDz6o5XckSS4W82JC8dSufW6bSlmlxVcoAAAAzsYwpBdesE/IRo2SZswgIXM2Pj5SeLh1m0pZpWV6UjZ58mS1atVKfn5+CgsL00033aS9e/fatTEMQ+PHj1dERIS8vb3VqVMn/fnnn3Zt0tLSNGzYMIWGhsrX11d9+vTRoUOH7NrEx8dr0KBBCggIUEBAgAYNGqSEhAS7NgcPHtQNN9wgX19fhYaGavjw4UpPTy+TawcAACg2w5CefFLKPbzkxRelV16xrnsF55MzriwuTjpzxtxYYIoSJWXr16/XLbfcossvv1x169a1+7nkkkuKda5169bpkUce0c8//6xVq1YpMzNT3bt3V0pKiq3NK6+8otdff13Tp0/Xli1bFB4erm7duik5OdnW5vHHH9fSpUu1cOFCbdiwQadPn1bv3r2VlWsRvgEDBmj79u1asWKFVqxYoe3bt2vQoEG241lZWerVq5dSUlK0YcMGLVy4UIsXL9bI3N9CAQAAmCU7W3roIWnq1HP7Xn9deu45EjJnlntc2f79poUB8xRpTFluGzZsUJcuXdSpUyft3r1bPXv2VHJysjZt2qS6deuqffv2xTrfihUr7G7Pnj1bYWFh2rZtmzp06CDDMPTmm29q7Nix6tu3ryRp7ty5qlatmhYsWKAHHnhAiYmJmjlzpj7++GN17dpVkjRv3jxFRkZq9erV6tGjh3bv3q0VK1bo559/Vps2bSRJH3zwgdq2bau9e/eqQYMGWrlypXbt2qWYmBhFRERIkqZOnaohQ4Zo4sSJ8vf3L+7TBQAAUDoyM6UhQ6T58623LRbpvfekoUNNDQulIO8MjI0amRcLTFHsStm4ceN0991325Kpl156ST/++KN+/fVXnT592pY4lVRiYqIkKTg4WJIUHR2tuLg4de/e3dbG09NTHTt21MaNGyVJ27ZtU0ZGhl2biIgINW7c2NZm06ZNCggIsCVkknTVVVcpICDArk3jxo1tCZkk9ejRQ2lpadq2bVuB8aalpSkpKcnuBwAAoFSlpUm33nouIXN1tW6TkFUMzMBY6RU7Kdu5c6duvvlmWf4rked0D2zatKmee+65Yq1plpdhGBoxYoSuvvpqNW7cWJIUFxcnSapWrZpd22rVqtmOxcXFycPDQ0FBQYW2CQsLy/eYYWFhdm3yPk5QUJA8PDxsbfKaPHmybYxaQECAIiMji3vZAAAA5+VxNkPq00datuy/HR7S4sXSHXeYGhdKEWuVVXrFTsrOnDmjKlWqyMXFRZ6enjpx4oTt2GWXXaZdu3aVOJhHH31Uf/zxhz755JN8xyx5+kkbhpFvX1552xTUviRtchszZowSExNtPzExMYXGBAAAUFTeKWka+dwSaeVK6w4fH+nrr6UbbzQ3MJQuKmWVXrGTslq1auno0aOSpEaNGmn58uW2Y+vWrVNISEiJAhk2bJi+/PJL/fDDD6pZs6Ztf/h/U4TmrVQdO3bMVtUKDw9Xenq64uPjC22TE3dux48ft2uT93Hi4+OVkZGRr4KWw9PTU/7+/nY/AAAAF8s3KVVPjlmkS/88Yt3h729Nzrp1MzcwlL4aNSR3d+s2lbJKqdhJWadOnbR27VpJ0tChQzVjxgx16dJF119/vV566SXdUcxSumEYevTRR7VkyRJ9//33qpP7mwJJderUUXh4uFatWmXbl56ernXr1qldu3aSpBYtWsjd3d2uTWxsrHbu3Glr07ZtWyUmJmrz5s22Nr/88osSExPt2uzcuVOxsbG2NitXrpSnp6datGhRrOsCAAAoqYBTpzX66c9VZ98x646QEOmHH6RiTqgGJ+HqKkVFWbf//de67AEqlWLPvvjCCy/o1KlTkqQHH3xQZ86c0fz582WxWPTss89q7NixxTrfI488ogULFuiLL76Qn5+frVIVEBAgb29vWSwWPf7445o0aZLq16+v+vXra9KkSfLx8dGAAQNsbe+9916NHDlSISEhCg4O1qhRo9SkSRPbbIwNGzZUz549NXToUL333nuSpPvvv1+9e/dWgwYNJEndu3dXo0aNNGjQIL366qs6deqURo0apaFDh1IBAwAA5SLkaJKeHLtY1Y4kSJLig30VtH49M/JVdHXrSvv2SadPSydPSqGhZkeEclTspCw0NFShud4kI0aM0IgRI0ocwP/+9z9J1gpcbrNnz9aQIUMkSU899ZRSU1P18MMPKz4+Xm3atNHKlSvl5+dna//GG2/Izc1N/fv3V2pqqrp06aI5c+bI1dXV1mb+/PkaPny4bZbGPn36aPr06bbjrq6uWr58uR5++GG1b99e3t7eGjBggF577bUSXx8AAEBRVTsUryfHLlbIcetarCfC/PXK5H56hYSs4ss7roykrFKxGEbx6qPXXnutZsyYocsuuyzfsb/++ksPPvigvv/++1IL0NkkJSUpICBAiYmJVNcAAHAwd39b8i+Sy1rN6OMa9ewSBcSfkSTF1gzSq5P6KT7UT7Ove73I55my4c6yCrFMPX31PLNDMNcrr0hPP23dXrhQuu02c+NBqShqblDsStnatWvPuxZXcnKy1q1bV9xTAgAAVGp19sZpxHNLVOV0miTpYN2qeu2lvkoO9DE5MpQbZmCs1IqdlBUmNjZWPj788QAAACiqBjsO6bHxy+SdmiFJ+qdBuF5/8Wad8fMyOTKUK9Yqq9SKlJR98cUX+uKLL2y3J0yYoKpVq9q1SU1N1dq1a3XllVeWboQAAAAVVOOt+zXspS/lkZ4lSdrdtKbefv5GnfXxMDkylDsqZZVakZKyXbt26fPPP5dkXVz5+++/l4uL/Wz6np6eatKkid56663SjxIAAKCCabHhbz34yjdyy8yWJP3eqo7eeaa3MjxLtSMTnEVQkBQQICUmUimrhIr0Wz9mzBiNGTNGkuTi4qIffvhBrVu3LtPAAAAAKqp2a3bp3jdWyiXbOt/a5qvr6/0nr1OWu+sF7okKy2KxVsu2b5cOHJAyMyU3EvTKotivdHZ2dlnEAQAAUCl0/vp33TXj3EzVP3ZtpDmPdVO2q0sh90KlULeuNSnLypIOHZJq1zY7IpSTEqffa9as0Zo1a3Ty5EmFhoaqS5cuuvbaa0szNgAAgArlus+3qP/sDbbbq2+4Qgse6CTDxWJiVHAYeceVkZRVGsVOytLT09WvXz998803MgxDbm5uyszM1Msvv6xevXpp8eLFcnd3L4tYAQAAnJNh6OaPN6nPwl9su77u30qLB7e3dlsDJGZgrMSKXSd/8cUX9d133+nll1/W0aNHlZ6erqNHj2rKlCn67rvv9OKLL5ZFnAAAAM7JMHTH++vsErJFg9tr8ZCrSchgjxkYK61iV8o++eQTPfPMM3ryySdt+6pWrapRo0bp9OnT+uijjzRhwoRSDRIAAMAZWbKyNWTaGnVYudO2b96DnbSmD0sIoQBUyiqtYlfKDh06pGuuuabAY9dcc40OHz580UEBAAA4O9fMLD3w6re2hCzbxaKZj3cnIcP5RUWd26ZSVqkUOymrWrWqduzYUeCxHTt25FtUGgAAoLJxS8/UIxO/Vpv1f0mSMl1d9L+nr9eG7pebHBkcmpeXVKOGdZtKWaVSpKRs/fr1On36tCSpT58+ev7557VkyRK7Nl988YXGjx+vG2+8sfSjBAAAcGB+Hr6qWaW6/Dx85ZmarsfHL9OVv1grHRnurpr23A3aes2lJkcJp5AzruzYMem/z9+o+Io0pqxz587atGmTWrdurYkTJ+qnn37SrbfeKl9fX4WHh+vo0aM6ffq0mjRpookTJ5Z1zAAAAA6hum+YBtbuoQZhlykz/qTcgkKU/uNa+ZxdI0k66+Wut8bdqD3NIs0NFM6jbl1pw3/LJuzfLzVubGo4KB9FqpQZhmHbDgoK0ubNmzVjxgxdf/31ioqK0nXXXad3331Xv/zyiwIDA8sqVgAAAIdR3TdMzzV/UA0/XCq36hHyioiUW/UI+azfKK1frzMtmurVSf1IyFA8zMBYKZVo8WhPT0898MADeuCBB0o7HgAAAKcwsHYPeb7yulxyzzqdkCC99JIMSUfmva9/oz81Kzw4K2ZgrJSKPNGHhXU0AAAAJFnHkDUIu0wu06YVeNwyfbpq124qPw/fco4MTo9KWaVU5EpZ586d5eJy4RzOYrEoMTHxooICAADmuHrOWLNDKLYNQ8p/PHuAh791DFlCQsENEhKUlXBKAR7+Sk5PKdfY4ORyJ2VUyiqNIidlnTp1Yrp7AAAASYnpSXILCpECA61dFvMKDJRrYLAS05PKOzQ4u4gIycNDSk+nUlaJFDkpe/7559W6deuyjAUAAMApJKenKHbvr4p89FHppZfyHc8aPkx7ju6hSobic3GRateW/vrLWikzDIlhRBVesRePBgAAqOxq7D+hsMEPScOHS88+a62YSVJgoLKef07pT47QggPfmRojnFjOZB9nzljXK0OFR1IGAABQDN6nz+rRl76S5+87pA4dFN+tgzJjjygt9pAyY49o9z03acKv7yo2hQ/TKCHGlVU6JZoSHwAAoDKyZBsaOvU7hR9JkCQdSD+piae+ktdP6xXg4a/E9CS6LOLi5Z0W/6qrzIsF5aJISVl2dnZZxwEAAODwei/8RVf+Yp184bSfl6Y/e4MyPN2UkZ5CMobSw7T4lQ7dFwEAAIqg6ZZo3TR/kyQp2yK9+/T1OhEeYHJUqJBYQLrSISkDAAC4gKqxCbr/1W/lYlhvL7mrvf5sHmVuUKi4qJRVOiRlAAAAhfA4m6FhE76S7+k0SdK2dvW0vH8rk6NChRYYKAUFWbeplFUKJGUAAADnYxga8vZqRe4/IUmKrRmkD0d0Z90olL2catnBg1JGhrmxoMyRlAEAAJxHty9+U9u1eyRJqd7umvbsDTrr42lyVKgUcsaVZWdLMTHmxoIyR1IGAABQgAY7Dum2D9fbbs8c0UOxtUJMjAiVCuPKKhWSMgAAgDwCT5zWQ5OXyzXbOrPH8ltbaVv7+iZHhUqFGRgrFZIyAACAXNwyMvXIpK8VkHBGkvTnFbW0+K52JkeFSodKWaVCUgYAAJDLHe+tU709sZKkE2H+evfp62W48pEJ5YxKWaXCXxgAAID/XLNyp6795g9JUrqHq6Y/21unA7xNjgqVUq1a52b5pFJW4ZGUAQAASKr9V5wGvfO97fZHj3bRgXrVTIwIlZqnp1SzpnWbSlmFR1IGAAAqPb/EM3p04tdyz8iSJK3p1Uw/db3c5KhQ6eWMKztxQkpONjcWlCmSMgAAUKm5ZGXrgSnfKOS49UPvvobV9cn9HU2OChDjyioRkjIAAFCp9Zv7ky7fbl2cNzHIR+8801tZ7q4mRwWIGRgrEZIyAABQabX88S9dv2irJCnT1UXvjOmlhJAqJkcF/IdKWaVBUgYAACqliIMnde8bK223Fw7toL8b1zQxIiAPKmWVBkkZAACodLxT0vTohK/kdTZDkrSx82Vac8MV5gYF5EWlrNIgKQMAAJWKJdvQfVO/U/XD8ZKkg3Wrau6wrufWhAIcRXi45OVl3aZSVqGRlAEAgEql12eb1fznfyRJp6t4avrY3kr3cjc5KqAAFsu5LozR0ZJhmBsPygxJGQAAqDQab92vmz/eKEnKtkjvPXW9jlcPNDcooDA5SdnZs1JcnLmxoMyQlAEAgMrh33/1wCvfyOW/YsPSQe20s2VtU0MCLohxZZUCSRkAAKj4zpyR+vZVldNpkqRfr7pEy/u3NjkooAiYgbFSICkDAAAVm2FI998v/f67JCm2RpA+HNlDhgsTe8AJUCmrFEjKAABAxTZ9ujR/viTprJe7pj93g1J9PU0OCigiKmWVAkkZAACouH78URoxwnZz5ojuOlIrxMSAgGLKnZRRKauwSMoAAEDFdOSIdOutUmam9fZTT2nr1ZeaGxNQXP7+Ush/XyRQKauwSMoAAEDFk54u3XKLdPSo9XaXLtLEiebGBJRUzriyQ4es721UOCRlAACg4nniCWnTJut2rVrSJ59Ibm7mxgSUVE4XRsOQDhwwNxaUCZIyAABQscyZI82YYd329JQWL5aqVjU1JOCiMANjhUdSBgAAKo5ff5UefPDc7f/9T2rZ0rx4gNLADIwVHkkZAACoGE6ckPr2ldKsC0TrwQelu+82NyagNFApq/BIygAAgPPLypLuuOPceJurrpLefNPUkIBSQ6WswiMpAwAAzu/ZZ6XVq63bYWHSokXW8WRARVCrluTy38d2KmUVEkkZAABwbosXSy+/bN12dZU+/1yqUcPcmIDS5O4uRUZat6mUVUgkZQAAwGlFHTkhDRlybsfUqVKHDqbFA5SZnHFl8fFSQoKpoaD0kZQBAACn5JOapknTFkmnT1t3DBggDR9ublBAWck9rowujBUOSRkAAHA6lmxDz374laLiTll3NG0qvf++ZLGYGxhQVpiBsUIjKQMAAE5n4Deb1OHXv6w3AgOlJUskX19TYwLKFDMwVmgkZQAAwKm02vmv7l+yVpKUbZG0YIF0ySWmxgSUOSplFRpJGQAAcBrVjydo/LtfyMWw3p55UwfpuuvMDQooD4wpq9BIygAAgFPwTMvQxOmLFZCSKknacEV9fdS7vclRAeUkLEzy8bFu032xwiEpAwAAjs8w9ORH3+rSg0clSTHVgjVh6A0yXJjYA5WExXKuWrZ/v5SdbWo4KF0kZQAAwOH1/X6bem7cKUk64+muZx7tqxQfL5OjAspZTlKWlibFxpobC0oVSRkAAHBoTf6O0fBPVttuv3xPL0XXDDMxIsAkTPZRYZGUAQAAhxWScFoT3lkityxrV60FPdvo+9aNTI4KMAnT4ldYJGUAAMAhuWVmacKMJQpNTJEkbbssSu/d0tnkqAATUSmrsEjKAACAQ3p04Wo1/fuQJOlosL/GPXSTslz56IJKjEpZhcVfNgAA4HB6/rRDt6zZJklKd3PV2Ef6KsHf1+SoAJOxVlmFRVIGAAAcSv0DcXpy7re221MH9dCeuhEmRgQ4iCpVpKpVrdtUyioUkjIAAOAw/E+f0cTpi+WZkSlJ+qLjFVre4QpzgwIcSc64siNHpLNnzY0FpYakDAAAOASX7GyNe/cLRZxIlCTtqhuhNwd2NzkqwMHkdGE0DOnAAXNjQakhKQMAAA7hvqXr1eZP6ziZeD8fjX2krzLc3UyOCnAwzMBYIZGUAQAA03XYtld3fb1RkpTpYtHzD9+s48H+JkcFOCBmYKyQSMoAAICpasWe0NgPv7LdntG/i367LMrEiAAHRqWsQiIpAwAApvFOTdOkaYvlezZdkrS6TSN91r2VyVEBDoxKWYVEUgYAAMxhGBo782vVjj0pSfqnRlW9fPf1ksVicmCAA4uMlFxdrdtUyioMkjIAAGCKgd/8rE7b9kqSkr099cywfjrr6WFyVICDc3OTatWyblMpqzBIygAAQLlr+We07l+81nb7xQdu1OFqweYFBDiTnHFliYlSfLy5saBUkJQBAIByFX4iQePfXSZXw5AkzbzxGm1qVs/kqAAnwriyCoekDAAAlBuP9AxNnL5EgadTJUk/NaunOX2uNjkqwMkwA2OFw4qMAACgTAV6+ijY20+nziTr4Q8/VYMDcZKkQ2FBmnB/HxkuTOwBFAuVsgqHpAwAAJSJqICqerzxtboisr4yT52UR2CwXH0ul06OUeq//+iZR/vptI+X2WECzodKWYVD90UAAFDqogKq6v2ud6v5x4vkXj1C3jUi5VqjhrRtm7R+vT585n79GxlmdpiAc6JSVuGQlAEAgFL3eONr5fXqVLlOmCAlJFh3JiRIL72k7GnT1GbAUDPDA5xbaKhUpYp1m0pZhUBSBgAASlWgp4+ujKwv12nTCjzuMm2aroy8VIGePuUcGVBBWCznqmX790tZWaaGg4tn+piy9evX69VXX9W2bdsUGxurpUuX6qabbrIdNwxDL7zwgt5//33Fx8erTZs2euedd3T55Zfb2qSlpWnUqFH65JNPlJqaqi5dumjGjBmqWbOmrU18fLyGDx+uL7/8UpLUp08fTZs2TYGBgbY2Bw8e1COPPKLvv/9e3t7eGjBggF577TV5eLCQJQBAavbaOLNDKLbfR71Qbo8VGp+stn/sU9fTLnK9Ku5chSyvhARlxp9SsLefEtLOlFt8QIVSt660Y4eUkSEdOSJFRpodES6C6ZWylJQUNWvWTNOnTy/w+CuvvKLXX39d06dP15YtWxQeHq5u3bopOTnZ1ubxxx/X0qVLtXDhQm3YsEGnT59W7969lZXrW4MBAwZo+/btWrFihVasWKHt27dr0KBBtuNZWVnq1auXUlJStGHDBi1cuFCLFy/WyJEjy+7iAQBwYpZsQ43+Oaz7lqzTzHEztWzEND0951u1WPuLLGFhUq4vPu0EBsotKFinUpMLPg7gwhhXVqGYXim77rrrdN111xV4zDAMvfnmmxo7dqz69u0rSZo7d66qVaumBQsW6IEHHlBiYqJmzpypjz/+WF27dpUkzZs3T5GRkVq9erV69Oih3bt3a8WKFfr555/Vpk0bSdIHH3ygtm3bau/evWrQoIFWrlypXbt2KSYmRhEREZKkqVOnasiQIZo4caL8/f3L4dkAAMCx+Z45q9Z/Rqvt7/vU9o9/FJRcQKXrxAmlr/1BbsMelcuEl/Idzho+TL/F/EWVDLgYeWdg7NjRvFhw0UxPygoTHR2tuLg4de/e3bbP09NTHTt21MaNG/XAAw9o27ZtysjIsGsTERGhxo0ba+PGjerRo4c2bdqkgIAAW0ImSVdddZUCAgK0ceNGNWjQQJs2bVLjxo1tCZkk9ejRQ2lpadq2bZs6d+5cYIxpaWlKS0uz3U5KSirNpwAAANNFxp1Uu9/3qe3v+3TFXzFyy8ousN2e2uHa2KyeNjatp7Nn/9Z7T46Sl8Ui17enWbsyBgYqa/gwnR01Um+tnl2+FwFUNFTKKhSHTsri4qyLS1arVs1uf7Vq1XTgwAFbGw8PDwUFBeVrk3P/uLg4hYXln3Y3LCzMrk3exwkKCpKHh4etTUEmT56sF14ov/76AACUNbfMLDX766Da/b5P7bbvU+Sx+ALbnfF019bL6+inZvX0c9N6OhlY5dzB5BO6f/VsPXZnP105Zowy40/JLShYv8Xs1VurZ+tA4vFyuhqggmKtsgrFoZOyHBaLxe62YRj59uWVt01B7UvSJq8xY8ZoxIgRtttJSUmKZKAlAMDZHD0qffONJsxYrNY7o+V7Nr3AZoerBlqrYc3qaXuDWspwP/9HiQOJxzXip88U6OmjYG8/nUpNpssiUFpq1z63TaXM6Tl0UhYeHi7JWsWqXr26bf+xY8dsVa3w8HClp6crPj7erlp27NgxtWvXztbm6NGj+c5//Phxu/P88ssvdsfj4+OVkZGRr4KWm6enpzw9PUt4hQAAmMQwpN9+k77+Wlq+XNq8WZKUt7N+potFO+pHamOzevrpino6GB5inY67GBLSzpCMAaXNx0cKD5fi4qiUVQAOnZTVqVNH4eHhWrVqla688kpJUnp6utatW6cpU6ZIklq0aCF3d3etWrVK/fv3lyTFxsZq586deuWVVyRJbdu2VWJiojZv3qzWrVtLkn755RclJibaEre2bdtq4sSJio2NtSWAK1eulKenp1q0aFGu1w0AQJk4fVpavdqahC1fLsXGFtgsoYq3fm56iTY2rafNTerqtI9XOQcKoEjq1LEmZbGxUmqq5O1tdkQoIdOTstOnT2vfvn2229HR0dq+fbuCg4NVq1YtPf7445o0aZLq16+v+vXra9KkSfLx8dGAAQMkSQEBAbr33ns1cuRIhYSEKDg4WKNGjVKTJk1sszE2bNhQPXv21NChQ/Xee+9Jku6//3717t1bDRo0kCR1795djRo10qBBg/Tqq6/q1KlTGjVqlIYOHcrMiwAA5/Xvv9YE7OuvpbVrpfSCuyWqWTOpVy89YDmk3XUjlO1i+qo5AC6kbl1p0ybr9v79UsOGpoaDkjM9Kdu6davdzIY547MGDx6sOXPm6KmnnlJqaqoefvhh2+LRK1eulJ+fn+0+b7zxhtzc3NS/f3/b4tFz5syRq6urrc38+fM1fPhw2yyNffr0sVsbzdXVVcuXL9fDDz+s9u3b2y0eDQCAs3DLylKz/TG6Zvff6rD7b+nJFwtu6OUlde0q9epl/flvPPSfc8aWY7QALkreGRhJypyW6UlZp06dZBjGeY9bLBaNHz9e48ePP28bLy8vTZs2TdOmTTtvm+DgYM2bN6/QWGrVqqWvv/76gjEDAOBIAlPOqP2efeqw+2+1++sf+aeeLbhhZKTUu7f1p3NnujoBzo4ZGCsM05MyAABQTIah+rHHdM2ev9Vh119qevCwXAv4gjPLYpFru3bWSljv3lLjxsWepAOAA2OtsgqDpAwAAJMFefsoxLeKTqacVnxqwbMUemZkqPW+aF2ze5867P5L1ROSCmyX5O2lnxpcoh8vq6+fLqundeNeLcvQAZiJSlmFQVIGAIBJ6gSH6umrOqllnXrKOHVS7sEh2hr9t6b8vE7Rp06oWkKiOvw3NqzVvmh5Z2QWeJ5/qlXV+svqaX2jS/V7VKSyXJmkA6gUatSQ3N2ljAwqZU6OpAwAABPUCQ7V/FvuktdrU+U6bZrcExKkwEC1HjZMnz3+uA7fdKPq/LihwPumu7pqyyW19WPD+lrfsL4OhwQV2A5ABefqKkVFSfv2WStlhkEXZSdFUgYAgAmevqqTNSGbMOHczoQEuU6YIFfDUJ0RI6VcSdkx/yr68bL6Wt/wUv1Sv45SPT1MiBqAw6lTx5qUJSdLp05JISFmR4QSICkDAKCcBXn7qGWdenI936zB06dLhw5pV7PG+qFaqNY3rK89NcL5BhxAfrnHlf37L0mZkyIpAwCUihZjz7MelgPbNvF5Ux43xLeKdQxZQkLBDRISlJqQoOcef1D7Thwr19gAOJncMzBGR0utWpkXC0qMkcAAAJSzkymn5REcLAUGFtwgMFBuwcE6mXK6XOMC4ITyVsrglEjKAAAoZ96Hj8hYvUZ69NECj2cNG6at0X+fd3p8ALDJWymDU6L7IgAA5cg9M1OvfrxI7ktXSuvXK1uSy/Tp0n+zL2YNG6azo0ZqyqKPzA4VgDOgUlYhUCkDAKAcjfpqlRofOiLt2aPYPjdoa/9+yjhyRGcOH1LGkSP65bZ+GrjoI0WfOmF2qACcQVCQ5O9v3aZS5rSolAEAUE56bP9Tt2/cIklKc3PV41c11Z7vlipovY9CfKvoZMppuiwCKB6LxVot275dOnBAysqyrl8Gp0KlDACAchB17ITGLfrKdnvKjT21p0Z1SVJ86hntO3GMhAxAyeSMK8vMlA4dMjcWlAhJGQAAZcwrPUNTP14k37R0SdLXzZtocZvmJkcFoMJgXJnTIykDAKCMjVn2rerHWdcb+ycsVC/17cVC0ABKDzMwOj2SMgAAytCNW7brpi3bJUmp7u4addetSvX0MDcoABULlTKnR1IGAEAZqX/kqJ5Z8o3t9oR+vfRvtaomRgSgQqJS5vRIygAAKAO+Z9M09ePP5ZWZKUla1Ka5lrdoanJUACqk2rXPbVMpc0okZQAAlDbD0LhFXynqxClJ0u4a4ZpyY0+TgwJQYXl5SRER1m0qZU6JpAwAgFJ2+8Yt6vH7LklSspenRt15i9LdWRoUQBnK6cJ49KiUkmJuLCg2kjIAAErR5TGHNeqrlbbb4/r30aHQYBMjAlAp5J7sY/9+08JAyZCUAQBQSvzPpOrVjxfJPStbkvTxNW20pklDk6MCUCnknuyDcWVOh6QMAIBSYMk29NLCZaoRnyhJ2h5VU2/26mpyVAAqjdyVMsaVOR2SMgAASsHgdRvVcfffkqR4H289dWc/Zbq6mhwVgEqDSplTIykDAOAiNf/3gIat+F6SlG2RnrnjZh0NDDA5KgCVCpUyp0ZSBgDARQhOPq0p8xfLLduQJH147TXaeFk9k6MCUOlEREgeHtZtKmVOh6QMAIAScsnO1uQFSxWWdFqStPmS2vpf944mRwWgUnJxObeIdHS0ZBimhoPiISkDAKCEHli1Xlfts3YTOu5XRaMH9FW2C/+1AjBJzriylBTp+HFzY0Gx8D8HAAAl0HbvP7p/zXpJUpbFoqcH9tVJ/yomRwWgUmNcmdMiKQMAoJjCEpI06ZOlcvmvd9D0np217ZLapsYEAMzA6LxIygAAKAa3rCy9Mm+RglPOSJLWX1ZPszu1NzkqABCVMidGUgYAQDEM/2aNrjxwSJJ0JDBAz95+kwwXi8lRAYColDkxkjIAAIqo8849Grz+Z0lShquLnhrUT4m+PiZHBQD/oVLmtEjKAAAoin//1YuffmG7+XrvbtpRq6aJAQFAHoGB1h+JSpmTISkDAOBCzp6Vbr1V/mfTJEnfNW2kBe1bmxwUABQgp1oWEyNlZJgbC4qMpAwAgAt54gnp118lSQdCg/XCrTdIFsaRAXBAOePKsrKsiRmcAkkZAACFWbBAevddSdJZNzeNGnSLUrw8TQ4KAM6DcWVOiaQMAIDz2b1buv9+282Xb75Of0WEmxgQAFwAMzA6JTezAwAAwCGlpEi33GL9V5IGD9bSy2uZGxMAXAiVMqdEpQwAgLwMQ3roIWnXLuvtyy+X3nmHcWQAHB+VMqdEUgYAQF4zZ0off2zdrlJFWrRI8vU1NyYAKIqoqHNfIFEpcxokZQAA5LZ9u/Too+duv/++dNllpoUDAMXi6SnVqGHdplLmNEjKAADIkZgo3XqrlGZdj0wPPSTdcYe5MQFAceWMKztxQjp92txYUCQkZQAASNZxZPfeK+3bZ73dooX0xhvmxgQAJZF7XBldGJ0CSRkAAJL09tvS4sXW7YAA6fPPrd2AAMDZ5J6BkS6MToGkDACAn3+WRo06d3vuXPtvmgHAmVApczokZQCAyu3kSal/fykz03p71CjpxhvNjQkALgaVMqdDUgYAqLyys6VBg6SYGOvt9u2lSZPMjQkALhaVMqdDUgYAqLymTJG+/da6HRoqLVwoububGxMAXKzwcMnLy7pNpcwpkJQBACqlFgeipWeftd6wWKQFC6SaNc0NCgBKg4uLVLu2dTs62jq7LBwaSRkAoNIJOZ2sScsWWbsvStLzz0vdupkbFACUppxxZamp0tGj5saCCyIpAwBUKi7Z2Zq0bJFCU/5bULVrV+m558wNCgBKG+PKnApJGQCgUnlg/Q9qeXC/9UZEhDR/vuTqampMAFDqmIHRqZCUAQAqjXb//K37Nq6XJGVaXKRPP5XCwkyOCgDKAJUyp0JSBgCoFKolJWrCl4ttt6d37iJdfbWJEQFAGaJS5lRIygAAFZ5bVqZeXvqZAlNTJUnr6jfQvDbtTI4KAMoQlTKnQlIGAKjwhn+/Sk0PH5IkHQ4I1LjeN8uw8F8ggArM318KCbFuUylzePyPBACo0Drv2aWBW36WJKW7uurpvv2V7O1tclQAUA5yqmWHDknp6ebGgkKRlAEAKqyap05q/PJlttuvd+mh3dVrmBcQAJSnnHFl2dnSwYPmxoJCkZQBACokz4wMTVn6maqkpUmSVjRqrM9btDY5KgAoR4wrcxokZQCACmnUqm912dE4SdL+4BBNvK6PZLGYHBUAlCNmYHQaJGUAgArn+h2/q+/2bZKks27uerrvbTrj6WlyVABQzqiUOQ2SMgBAhVL3+DE9s+Ir2+2Xe/bSvrBqJkYEACahUuY0SMoAABWGd3qapiz5TN4ZGZKkZc2u1FdNrzQ5KgAwSa1akst/H/eplDk0kjIAQMVgGBr77Veqe/K4JOnvqtX0avfrTQ4KAEzk7i5FRlq3qZQ5NJIyAECF0Pe3rbruzx2SpNMennqqb3+ddfcwOSoAMFnOuLJTp6TERHNjwXmRlAEAnN5lcUf05Kpvbbdfur6PDoaEmhgRADgIJvtwCiRlAACnVuVsqqYs+UweWVmSpIUtWmtVo8YmRwUADiL3ZB8kZQ6LpAwA4LwMQ+O/XqaaCfGSpJ3Va+jNLj1MDgoAHEjuShnjyhwWSRkAwGkN3LxJnf/aI0lK9PLW6JtvVYabm8lRAYADoVLmFEjKAABOqemhgxr+wyrb7XE33KzYwCATIwIAB0SlzCmQlAEAnE7gmRRNXvq53LKzJUlz2l6tH+s3MDkqAHBA1apJ3t7WbSplDoukDADgVCxGtiZ8uUThyUmSpG2RUZrR8VqTowIAB2WxnKuWRUdL/32ZBcdCUgYAcCr3/PSj2v27T5J00sdXz9x0i7JcXE2OCgAcWM64srQ0KS7O3FhQIJIyAIDTaLX/Xz3w4w+SpGxZNPbGW3TCz9/kqADAwTGuzOGRlAEAnEJocpImLlskV8OQJL3XoZO21Kl7gXsBAJiB0fExbzAAwKEF+vgozNdbo5cvU8iZFEnSxrr1NLN9B5MjAwAnQaXM4ZGUAQAcUu2qoXry2mvUon496dgxuQ8dIq1apRMvTdRzV18rw0JnDwAoEiplDo//0QAADqd21VB9dPdAtVr0udwjIuReu7ZUs6aMbdvku2qVAmtHmR0iADgPKmUOj6QMAOBwnrz2GnlPnSrXCROkhATrzoQEWV56SR5vvK4nO19janwA4FSqVJGqVrVuUylzSCRlAADTuWVlqdGRw7pj8ya9tnaV2lxSVy7TphXY1nXaNLW4tJ4CfXzKOUoAcGI51bLDh61T48OhMKYMAMpBu0cnmB1CiWyc/lyZnDfwTIqaHD6kZocOqumhGF0ee0RemRnWg40bS8eOnauQ5ZWQoMxTpxTqV0UJZ86USXwAUOHUrStt3iwZhnTggHTppWZHhFxIygAAZcpiZKvu8eNqejjG+nMoRrVPnTz/HeLiZISFyRIYWHBiFhgot+BgnUg+XVYhA0DFk3dcGUmZQyEpAwCUKp+0NDU+ckjNDlmTsCaHD8kv7Wyh9zkUGKQ/akTqj5qR+r1mpB7f969aDhtmHVOWR9awYdr21z6qZABQHDkzMIaGSomJ5saCfEjKAAAlZxjWQeMbN2r0iq/V9FCM6h0/alvguSDprq7aHR5hTcBqRGpHzUidqOJn1+aVH37URyNHykvWMWRKSJACA5U1bJjOjhypV2fPL9vrAoCK5vLLpWXLpK5dpfh4KT1dysiQfH3NjgwiKQMAFMfZs9K2bdLGjdKmTdZ/jx6VJN16nruc8K2i32tGakcNaxVsT3h1pbu5F/ow+4+f0F2z5+vJfreqxZgxyjx1Sm7Bwdq692+9Nnu+9h8/UcoXBgAVXLNm0uTJ0pAhti+6NHy4NGaM5OVlcnAgKQMAnF9srDXxyvnZts36zep5ZFks+jus2n9dEWvp95qROhIQKFksxX7o/cdP6JHPlirQx0ehflV0Ivk0XRYBoCRSUqRXXpFeeuncvoQE6cUXrdtPPUXFzGQkZQAASZJrdpYuOXlMjeMOqklsjJrEHZTeeb7wOwUESG3bSu3a6cHd/+jPiBo64+lZqnElnDlDMgYAF8PdXXr77YKPvf22NSm74QbJx0eqXl2KiLD+5GxXr279e1+CL9hQNCRlAFBJ+Z09o8Zxh9T4aIyaxB5Uo6OH5ZOZXvidGjSQ2rWz/rRtKzVsKLlYl7zcMvbFcogaAKSvfrna7BBK5IY2G8x54ISEQpcZ0fHj0v790s6d5z+Ht7d9klZQ4hYRQfJWQiRlAODEAqv4KNi/ik4lnVbC6UKqSYahqIQTavxfBaxJXIzqxB8v9Nxn3dzl1b7duSTsqquss3YBAJxLYKD15zzLjKhqVSkurvBzpKZap9L/99/C23l5FZys5d0XGEjylgtJWQFmzJihV199VbGxsbr88sv15ptv6pprrjE7LJSXlBRrmT9nEGxFnJmIa3R6UdVC9USva3Rlw0uUeeKU3EKD9duufXrjmw06cPSEvDLS1fDYYTWJtSZgjeNiFJCWWug546oEaGd4pHaE19KO6pH6OyRcP/5vfPlcEACg7GRkWCf1eLGAHg3Dh1v/PXjQOo44NlY6cuT8/8bHF/5YZ88WPXkrSuWtOMmbE//fT1KWx6effqrHH39cM2bMUPv27fXee+/puuuu065du1SrVi2zw0NZO3vWOhD27bcr7sxEXKPZ0V20qGqh+nDYAHm9PlWuXabJ/b9rbDlsmD567DEd7NNXUZs2yM3IPu85Ml1ctDe0unZUr6Ud4ZHaGR6p41UCyu8iAADlx9fX+n+gVPj/jXXrnlvP7HxSU61VtYIStuImb9HR1p/CeHpeuPJWo4b1Gpz4/36Ssjxef/113XvvvbrvvvskSW+++aa+++47/e9//9PkyZNNjg5lKmdmotzfIuXMTGQY0nXXSa+/blp4pWLECOnbb6XcC/JWtmvs2VOaOtX+PgWtqZV3X1HaFLLvlZ1/2W5aCmhiUUH3K7hdw/dnyGfqa7LkmUXLZcIEuRiGLnnyCenm9Xb3i/fy0c7/KmA7wiO1O6zGBaelBwBUIF5e1gk9xo61Lh4dEGCtJBU3YfH2lurUsf4U5uxZ+8rb+apvp04Vfp60tAsnb8uWSVu3OvXskiRluaSnp2vbtm0aPXq03f7u3btr48aNBd4nLS1NaWlpttuJ/62QnpSUVHaBomykp0tvvVXwsbfflh56SPr++wv/8XBUwcHW6yhs9qXKco1r15b7NTYtrRMFB0tNGyv5tvOsCjZtmozdu3Wg7qXa6e6rP8NraFe1mjrsH2Tf/SM7S0rPuuDDFedvWVba2SK3dRTF/VuddTbtwo0cTHGvMTO1Yl9j+hnnuz6peNd4NuX8y1Y4suJc45mUzDKMpOw4xOfDrCxr9ensf3+zyzKmkBDrT+PG529z9qy18nb0qDVJi4sr+Od8lbfgYKl1a2nw4IKPv/WWNGyY9bpNkPOaGwV9aZuLxbhQi0rkyJEjqlGjhn766Se1a9fOtn/SpEmaO3eu9u7dm+8+48eP1wsvvFCeYQIAAABwIjExMapZs+Z5j1MpK4Alz2BCwzDy7csxZswYjRgxwnY7Oztbp06dUkhIyHnvUxEkJSUpMjJSMTEx8vf3NzucUlfRr0/iGisKrrFiqOjXWNGvT+IaKwquEaXNMAwlJycrIiKi0HYkZbmEhobK1dVVcXmmBD127JiqVatW4H08PT3lmWeh1MDAwLIK0eH4+/tX6F/oin59EtdYUXCNFUNFv8aKfn0S11hRcI0oTQEBF55Iy6Uc4nAaHh4eatGihVatWmW3f9WqVXbdGQEAAACgtFApy2PEiBEaNGiQWrZsqbZt2+r999/XwYMH9eCDD5odGgAAAIAKiKQsj9tuu00nT57Uiy++qNjYWDVu3FjffPONoqKizA7NoXh6emrcuHH5um5WFBX9+iSusaLgGiuGin6NFf36JK6xouAaYRZmXwQAAAAAEzGmDAAAAABMRFIGAAAAACYiKQMAAAAAE5GUAUVksVi0bNkys8MAUInwdwcAKgeSMuQzZMgQ3XTTTWaHUSaGDBkii8WS72ffvn1mh1Yqcq6voCUcHn74YVksFg0ZMqT8AysjGzdulKurq3r27Gl2KKWmsr2GFfnvTUEq4vVWxN/D3I4dO6YHHnhAtWrVkqenp8LDw9WjRw9t2rTJ7NBKXUxMjO69915FRETIw8NDUVFReuyxx3Ty5Mki3X/t2rWyWCxKSEgo20CLKefv6ssvv2y3f9myZbJYLCZFVbpyf75xd3dXtWrV1K1bN82aNUvZ2dlmh4ciIClDpdOzZ0/Fxsba/dSpU8fssEpNZGSkFi5cqNTUVNu+s2fP6pNPPlGtWrUu6twZGRkXG16pmjVrloYNG6YNGzbo4MGDF3WurKwsh/mPqyxfQ6C0lebvoSPq16+ffv/9d82dO1d//fWXvvzyS3Xq1EmnTp0yO7RS9e+//6ply5b666+/9Mknn2jfvn169913tWbNGrVt29bpr9fLy0tTpkxRfHy82aGUmZzPN/v379e3336rzp0767HHHlPv3r2VmZlpdni4AJIyFGrFihW6+uqrFRgYqJCQEPXu3Vv//POP7fj+/ftlsVi0ZMkSde7cWT4+PmrWrJlDf4OY801n7h9XV1d99dVXatGihby8vFS3bl298MIL+f6IxcbG6rrrrpO3t7fq1Kmjzz//3KSrOL/mzZurVq1aWrJkiW3fkiVLFBkZqSuvvNK2r6iv7WeffaZOnTrJy8tL8+bNK9drKUxKSoo+++wzPfTQQ+rdu7fmzJljO5bzbe3y5cvVrFkzeXl5qU2bNtqxY4etzZw5cxQYGKivv/5ajRo1kqenpw4cOGDCleRXWq/htddeq0cffdTu3CdPnpSnp6e+//77sr+QYqpdu7befPNNu31XXHGFxo8fb7ttsVj04Ycf6uabb5aPj4/q16+vL7/8snwDLSVFuV5HV9jvYc7vWG4FVSZeeuklhYWFyc/PT/fdd59Gjx6tK664ouyDL4KEhARt2LBBU6ZMUefOnRUVFaXWrVtrzJgx6tWrlyQpMTFR999/v8LCwuTv769rr71Wv//+u+0c48eP1xVXXKH33ntPkZGR8vHx0a233upw1aRHHnlEHh4eWrlypTp27KhatWrpuuuu0+rVq3X48GGNHTtWkpSWlqannnpKkZGR8vT0VP369TVz5kzt379fnTt3liQFBQU5XFW/a9euCg8P1+TJk8/bZvHixbr88svl6emp2rVra+rUqbZjY8aM0VVXXZXvPk2bNtW4cePKJObiyvl8U6NGDTVv3lzPPPOMvvjiC3377be2380LvV8l6csvv1TLli3l5eWl0NBQ9e3b14SrqXxIylColJQUjRgxQlu2bNGaNWvk4uKim2++OV9FYezYsRo1apS2b9+uSy+9VHfccYdTfSvz3Xff6c4779Tw4cO1a9cuvffee5ozZ44mTpxo1+65556zfWt655136o477tDu3btNivr87r77bs2ePdt2e9asWbrnnnvs2hT1tX366ac1fPhw7d69Wz169CiX+Ivi008/VYMGDdSgQQPdeeedmj17tvIuu/jkk0/qtdde05YtWxQWFqY+ffrYVfvOnDmjyZMn68MPP9Sff/6psLCw8r6M8yqN1/C+++7TggULlJaWZrvP/PnzFRERYfvw5IxeeOEF9e/fX3/88Yeuv/56DRw40Om/xXdWRfk9LMz8+fM1ceJETZkyRdu2bVOtWrX0v//9rwwjLp4qVaqoSpUqWrZsmd3vUQ7DMNSrVy/FxcXpm2++0bZt29S8eXN16dLF7j25b98+ffbZZ/rqq6+0YsUKbd++XY888kh5XkqhTp06pe+++04PP/ywvL297Y6Fh4dr4MCB+vTTT2UYhu666y4tXLhQb7/9tnbv3q13331XVapUUWRkpBYvXixJ2rt3r2JjY/XWW2+ZcTkFcnV11aRJkzRt2jQdOnQo3/Ft27apf//+uv3227Vjxw6NHz9ezz33nC2ZGThwoH755Re7L77+/PNP7dixQwMHDiyvyyi2a6+9Vs2aNdOSJUuK9H5dvny5+vbtq169eum3337TmjVr1LJlS5OvopIwgDwGDx5s3HjjjQUeO3bsmCHJ2LFjh2EYhhEdHW1IMj788ENbmz///NOQZOzevbs8wi2WwYMHG66uroavr6/t55ZbbjGuueYaY9KkSXZtP/74Y6N69eq225KMBx980K5NmzZtjIceeqhcYi+KnNfu+PHjhqenpxEdHW3s37/f8PLyMo4fP27ceOONxuDBgwu87/le2zfffLMcr6Do2rVrZ4stIyPDCA0NNVatWmUYhmH88MMPhiRj4cKFtvYnT540vL29jU8//dQwDMOYPXu2IcnYvn17+QdfiNJ8Dc+ePWsEBwfbrtkwDOOKK64wxo8fXx6XUiS5/95ERUUZb7zxht3xZs2aGePGjbPdlmQ8++yzttunT582LBaL8e2335ZDtBevJNe7dOnScouvuAr7PZw9e7YREBBg137p0qVG7o8ebdq0MR555BG7Nu3btzeaNWtWpnEXx6JFi4ygoCDDy8vLaNeunTFmzBjj999/NwzDMNasWWP4+/sbZ8+etbvPJZdcYrz33nuGYRjGuHHjDFdXVyMmJsZ2/NtvvzVcXFyM2NjY8ruQQvz888+Fvtdef/11Q5Lxyy+/GJJsr3FeOX974+Pjyy7YEsj9e3fVVVcZ99xzj2EY9u/HAQMGGN26dbO735NPPmk0atTIdrtp06bGiy++aLs9ZswYo1WrVmUcfdEU9tnttttuMxo2bFik92vbtm2NgQMHlnW4KACVMhTqn3/+0YABA1S3bl35+/vbxl7lHTfQtGlT23b16tUlWQdHO6LOnTtr+/bttp+3335b27Zt04svvmj7VrRKlSoaOnSoYmNjdebMGdt927Zta3eutm3bOmSlLDQ0VL169dLcuXM1e/Zs9erVS6GhoXZtivraOuI3ZHv37tXmzZt1++23S5Lc3Nx02223adasWXbtcr9ewcHBatCggd3r5eHhYffedSSl8Rp6enrqzjvvtD0v27dv1++//+5QXYpKIvdr5uvrKz8/P4f9e1ORFfX38ELnaN26td2+vLfN1q9fPx05ckRffvmlevToobVr16p58+aaM2eOtm3bptOnTyskJMTu/4/o6Gi7ikqtWrVUs2ZN2+22bdsqOztbe/fuNeOSis34r/oZHR0tV1dXdezY0eSISm7KlCmaO3eudu3aZbd/9+7dat++vd2+9u3b6++//1ZWVpYka7Vs/vz5kqzPySeffOLQVbIchmHIYrEU6f26fft2denSxeSIKyc3swOAY7vhhhsUGRmpDz74QBEREcrOzlbjxo2Vnp5u187d3d22nTNewFEmTcjL19dX9erVs9uXnZ2tF154ocB+015eXoWez1Fnbrrnnnts44neeeedfMeL+tr6+vqWS7zFMXPmTGVmZqpGjRq2fYZhyN3d/YKDuHO/Xt7e3g77+kml8xred999uuKKK3To0CHNmjVLXbp0UVRUVLldQ3G4uLjk6/pW0OQyuf/eSNbX1FH/3hSmqNfrqC70e1jU68v7O5j3Po7Ay8tL3bp1U7du3fT888/rvvvu07hx4/Twww+revXqWrt2bb775B1Pl1vONTvK35969erJYrFo165dBc4OumfPHgUFBcnHx6f8gytlHTp0UI8ePfTMM8/YfUGVk7jklve9OGDAAI0ePVq//vqrUlNTFRMTY/tSwpHt3r1bderUUXZ29gXfr3m7r6L8kJThvE6ePKndu3frvffe0zXXXCNJ2rBhg8lRlY3mzZtr7969+ZK1vH7++WfddddddrdzT7zgSHr27Gn7cJ53LJgzv7aZmZn66KOPNHXqVHXv3t3uWL9+/TR//nw1btxYkvX1yZmtMD4+Xn/99Zcuu+yyco+5pErjNWzSpIlatmypDz74QAsWLNC0adPKPvASqlq1qmJjY223k5KSFB0dbWJEZcuZr7cov4eXXHKJkpOTlZKSYvtyZ/v27XZtGzRooM2bN2vQoEG2fVu3bi3z+C9Wo0aNtGzZMjVv3lxxcXFyc3NT7dq1z9v+4MGDOnLkiCIiIiRJmzZtkouLiy699NJyirhwISEh6tatm2bMmKEnnnjC7oN5XFyc5s+fr7vuuktNmjRRdna21q1bp65du+Y7j4eHhyTZKkuO6uWXX9YVV1xh9/w3atQo39/QjRs36tJLL5Wrq6skqWbNmurQoYPmz5+v1NRUde3aVdWqVSvX2Ivr+++/144dO/TEE0+oZs2aF3y/Nm3aVGvWrNHdd99dvoGCpAznFxQUpJCQEL3//vuqXr26Dh48qNGjR5sdVpl4/vnn1bt3b0VGRurWW2+Vi4uL/vjjD+3YsUMvvfSSrd3nn3+uli1b6uqrr9b8+fO1efNmzZw508TIz8/V1dXWVS/nP5Qczvzafv3114qPj9e9996rgIAAu2O33HKLZs6cqTfeeEOS9OKLLyokJETVqlXT2LFjFRoa6lRrRJXWa3jffffp0UcflY+Pj26++eYyj7ukrr32Ws2ZM0c33HCDgoKC9Nxzz+W77orEma+3KL+Ha9askY+Pj5555hkNGzZMmzdvtpudUZKGDRumoUOHqmXLlmrXrp0+/fRT/fHHH6pbt245Xs35nTx5UrfeeqvuueceNW3aVH5+ftq6dateeeUV3Xjjjeratavatm2rm266SVOmTFGDBg105MgRffPNN7rpppts3b+9vLw0ePBgvfbaa0pKStLw4cPVv39/hYeHm3yF50yfPl3t2rVTjx499NJLL6lOnTr6888/9eSTT6pGjRqaOHGigoODNXjwYN1zzz16++231axZMx04cEDHjh1T//79FRUVJYvFoq+//lrXX3+9vL29VaVKFbMvLZ8mTZpo4MCBdl9SjRw5Uq1atdKECRN02223adOmTZo+fbpmzJhhd9+BAwdq/PjxSk9Pt/1f4yjS0tIUFxenrKwsHT16VCtWrNDkyZPVu3dv3XXXXXJxcbng+3XcuHHq0qWLLrnkEt1+++3KzMzUt99+q6eeesrsy6v4TBrLBgc2aNAgo1+/foZhGMaqVauMhg0bGp6enkbTpk2NtWvX2g0GzpkM4rfffrPdPz4+3pBk/PDDD+Uf/AUUNhB2xYoVRrt27Qxvb2/D39/faN26tfH+++/bjksy3nnnHaNbt26Gp6enERUVZXzyySflFHnRFHZ9hmHYTRJRktfWEfTu3du4/vrrCzy2bds2Q5IxdepUQ5Lx1VdfGZdffrnh4eFhtGrVym5Sj4ImIXAEpfka5khOTjZ8fHyMhx9+uOwCL6Hcf28SExON/v37G/7+/kZkZKQxZ86cIk18ERAQYMyePbv8gr4IpXG9jqAov4fbtm0zli5datSrV8/w8vIyevfubbz//vtG3o8eL774ohEaGmpUqVLFuOeee4zhw4cbV111VXlcxgWdPXvWGD16tNG8eXMjICDA8PHxMRo0aGA8++yzxpkzZwzDMIykpCRj2LBhRkREhOHu7m5ERkYaAwcONA4ePGgYhnWij2bNmhkzZswwIiIiDC8vL6Nv377GqVOnzLy0Au3fv98YMmSIER4ebruWYcOGGSdOnLC1SU1NNZ544gmjevXqhoeHh1GvXj1j1qxZtuMvvviiER4eblgslvNOSlTeCvq7un//fsPT09Pu/bho0SKjUaNGhru7u1GrVi3j1VdfzXeu+Ph4w9PT0/Dx8TGSk5PLOvQiGzx4sCHJkGS4ubkZVatWNbp27WrMmjXLyMrKsrW70PvVMAxj8eLFxhVXXGF4eHgYoaGhRt++fc24pErHYhgO2HkbpurZs6fq1aun6dOnmx0KUCJr165V586dFR8fX+i4jsoiJiZGtWvX1pYtW9S8eXOzw7FT2f7eVLbrLYlu3bopPDxcH3/8sdmhlIrx48dr2bJl+bpuAkBudF+ETXx8vDZu3Ki1a9fqwQcfNDscABcpIyNDsbGxGj16tK666iqHSsgq29+byna9RXXmzBm9++676tGjh1xdXfXJJ59o9erVWrVqldmhAUC5IimDzT333KMtW7Zo5MiRuvHGG80OB8BF+umnn9S5c2ddeumlWrRokdnh2Klsf28q2/UWlcVi0TfffKOXXnpJaWlpatCggRYvXlzgJBIAUJHRfREAAAAATMTi0QAAAABgIpIyAAAAADARSRkAAAAAmIikDAAAAABMRFIGAAAAACYiKQMAmO6PP/7Q3XffrTp16sjLy0tVqlRR8+bN9corr+jUqVPFPl+nTp3UuHHjMog0vyNHjmj8+PFFXhx47dq1slgsslgsmjNnToFtrr32WlksFtWuXbvU4izIrl27NH78eO3fvz/fsfJ8DgGgsiMpAwCY6oMPPlCLFi20ZcsWPfnkk1qxYoWWLl2qW2+9Ve+++67uvfdes0Ms1JEjR/TCCy8UOSnL4efnp5kzZ+bbHx0drbVr18rf37+UIjy/Xbt26YUXXigwKQMAlB8WjwYAmGbTpk166KGH1K1bNy1btkyenp62Y926ddPIkSO1YsUKEyM8v6ysLGVmZpb4/rfddps+/PBD/f3336pfv75t/6xZs1SjRg01adJEu3btKo1QAQAOjkoZAMA0kyZNksVi0fv/b+/uQqLq1jiA/7eV40x1kx+YYdMkmJpINShkROo0IzYqEglSWppZjHUzU2DTNxkxDRaRlDAXTkoRIUFqlgnNQBeK2Ad2kXSTGlKCCRGEpek6Fwc37z6j74zaOfsczv93t5/9zFrr2TfDw9qs7fEoGrJZ4eHhKCwslK9nZmbgdruRlJQEjUaDmJgYHDx4ECMjI3OO39fXh507d0Kn02Hjxo1wuVyYmZlR5Hz69AmlpaWIiYmBRqNBcnIyrl+/rsgbGhqCJElwu924cuUKDAYDNBoN/H4/0tPTAQAVFRXya4mXLl0KWrvZbEZ8fDwaGxsV9TU1NeHQoUMICwv8i/758yecTicMBgPCw8Oxbt06HD9+HN++fVPkbdiwAfn5+ejs7MS2bdug1WqRlJSkmOvu3bsoLi4GAGRnZ8/7SmUoz5CIiJaGTRkREalienoaPp8PRqMR8fHxIf3GZrOhpqYGZrMZbW1tqK2tRWdnJzIzM/H161dF7ujoKA4cOIDS0lK0tbUhLy8PTqcT9+7dk3PGxsaQmZmJrq4u1NbWoq2tDbt378apU6dw4sSJgPlv3boFn8+Huro6PHv2DHFxcfB6vQCAc+fOoaenBz09PThy5EjQWsLCwlBeXo7m5mZMT08DALq6ujAyMoKKioqAfCEEioqKUFdXh7KyMnR0dMDhcKCpqQk5OTn49euXIr+/vx8nT56E3W5Ha2sr0tLSUFlZiZcvXwIArFYrrl69CgC4ffu2vHar1bqgZ0hERH+AICIiUsHo6KgAIEpKSkLKHxgYEABEdXW1It7b2ysAiDNnzsixXbt2CQCit7dXkZuSkiJyc3Pl69OnT8+ZZ7PZhCRJ4sOHD0IIIQYHBwUAkZCQICYnJxW5fX19AoDwer0h1eH3+wUA0dLSIj5+/CgkSRJPnjwRQghRXFwssrKyhBBCWK1Wodfr5d91dnYKAMLtdivGe/jwoQAgPB6PHNPr9SIiIkIMDw/LsYmJCbFmzRpx7NgxOdbS0iIACL/fH7DOUJ8hEREtHXfKiIjof4Lf7wcAlJeXK+IZGRlITk7GixcvFPHY2FhkZGQoYmlpaRgeHpavfT4fUlJSAvLKy8shhIDP51PECwsLsWLFiqWWIjMYDMjKykJjYyPGx8fR2tqKw4cPz5k7u5Z/rb+4uBgrV64MqH/Lli1Yv369fB0REYHExERF/cGE8gyJiGjp2JQREZEqoqKioNPpMDg4GFL++Pg4AGDt2rUB9+Li4uT7syIjIwPyNBoNJiYmFGPON95f55w1V+5SVVZWor29HTdu3IBWq8W+ffvmzBsfH8fy5csRHR2tiEuShNjY2EXVH8yfGIOIiIJjU0ZERKpYtmwZTCYTXr9+Pe9BHX812yB8+fIl4N7nz58RFRW14DVERkbOOx6AgDElSVrwHMHs3bsXOp0OLpcLJSUl0Gq186719+/fGBsbU8SFEBgdHV1U/URE9N+BTRkREanG6XRCCIGqqipMTk4G3J+amkJ7ezuAf35QGUDAIRN9fX0YGBiAyWRa8Pwmkwnv37/HmzdvFPHm5mZIkoTs7OygY8yeGrnY3SOtVosLFy6goKAANpvtb9cKBNb/6NEj/PjxY1H1L3XtRET0Z/A7ZUREpJrt27ejoaEB1dXVMBqNsNls2Lx5M6ampvD27Vt4PB6kpqaioKAAmzZtwtGjR1FfX4+wsDDk5eVhaGgI58+fR3x8POx2+4Lnt9vtaG5uhtVqxeXLl6HX69HR0YE7d+7AZrMhMTEx6BgJCQnQarW4f/8+kpOTsWrVKsTFxcmvQIbC4XDA4XD8bY7ZbEZubi5qamrw/ft37NixA+/evcPFixexdetWlJWVhTzfrNTUVACAx+PB6tWrERERAYPBMOdri0RE9O/DnTIiIlJVVVUVXr16BaPRiGvXrsFisaCoqAgPHjzA/v374fF45NyGhga4XC48ffoU+fn5OHv2LCwWC7q7uxfVSERHR6O7uxs5OTlwOp3Iz8/H8+fP4Xa7UV9fH9IYOp1OPqjDYrEgPT1dseY/RZIkPH78GA6HA16vF3v27JGPx/f5fHN+5y0Yg8GAmzdvor+/H1lZWUhPT5d3JomI6D9HEkIItRdBRERERET0/4o7ZURERERERCpiU0ZERERERKQiNmVEREREREQqYlNGRERERESkIjZlREREREREKmJTRkREREREpCI2ZURERERERCpiU0ZERERERKQiNmVEREREREQqYlNGRERERESkIjZlREREREREKvoHnExobLIvPTMAAAAASUVORK5CYII=", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Frequency of service use by cohort:\n", + "month\n", + "1 223\n", + "2 184\n", + "3 244\n", + "4 473\n", + "5 997\n", + "6 3662\n", + "7 4793\n", + "8 5250\n", + "9 6227\n", + "10 9611\n", + "11 141\n", + "12 289\n", + "Name: id_x, dtype: int64\n", + "Revenue generated by cohort:\n", + "month\n", + "1 0.0\n", + "2 0.0\n", + "3 0.0\n", + "4 5.0\n", + "5 1285.0\n", + "6 8725.0\n", + "7 10395.0\n", + "8 17565.0\n", + "9 22935.0\n", + "10 43815.0\n", + "11 565.0\n", + "12 0.0\n", + "Name: total_amount, dtype: float64\n", + "Incident rate by cohort:\n", + "month\n", + "1 0.107623\n", + "2 0.032609\n", + "3 0.061475\n", + "4 0.095137\n", + "5 0.183551\n", + "6 0.188422\n", + "7 0.151888\n", + "8 0.201905\n", + "9 0.177774\n", + "10 0.132660\n", + "11 0.141844\n", + "12 0.048443\n", + "Name: id_x, dtype: float64\n", + "None\n", + "None\n", + "Values of 'time_to_reimbursement' after calculation:\n", + "0 30.0\n", + "1 30.0\n", + "2 30.0\n", + "3 30.0\n", + "4 NaN\n", + "Name: time_to_reimbursement, dtype: float64\n", + "Null values in 'time_to_reimbursement': 28033\n", + "None\n", + "None\n", + "Values of 'time_to_reimbursement' after calculation:\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# %% [markdown]\n", + "# Business Understanding\n", + "# %%\n", + "# objective\n", + "\"\"\" 1. how often users from different cohorts use the cash advance services.(Frequency of service usage over the time - trend analysis - bar chart)\n", + " 2. Incident rate for payment-related issues across cohorts (trend variation to understand in which periods this appear and for each cohort)\n", + " 3. Revenue Analysis over the time: total revenue generated by each cohort over months to assess the financial impact of user behavior (trend)\n", + "4.New Metric to track this:\n", + "- how long time to happen the first incident rate / min and max\n", + "- avg of users that need the cash advance\n", + "-measure of insights into user behavior or the performance of IronHack Payments' services.\n", + "Columns_to_use:\n", + " track the data of first request - [id,amount,created_at,updated_at,user_id,status]\n", + " revenue analysis = transfer_type,cash_request_received_date,\n", + " incident rate = [deleted_account_i, reimbursement_date (charge_date),recovery_status,reco_last_update]\n", + "\"\"\"\n", + "# %% [markdown]\n", + "# Data Mining\n", + "# %%\n", + "#Libraries used for this project\n", + "import pandas as pd # painel data, dataframes\n", + "import numpy as np # numerical data\n", + "import os # manage directories folders\n", + "import seaborn as sns # visualization\n", + "from datetime import datetime # format dates\n", + "from openpyxl import load_workbook # excel file with folders/tabs\n", + "# %% [markdown]\n", + "# Data Collection\n", + "# %%\n", + "#dataset1\n", + "cash_req = pd.read_csv(\"extract - cash request - data analyst.csv\")\n", + "df1 = cash_req.copy()\n", + "df1 = pd.DataFrame(df1)\n", + "df1\n", + "# %%\n", + "#dataset2\n", + "fee = pd.read_csv(\"extract - fees - data analyst - .csv\")\n", + "df2 = fee.copy()\n", + "df2 = pd.DataFrame(df2)\n", + "df2\n", + "# %%\n", + "df3_path = \"Lexique - Data Analyst.xlsx\" # sourcefile\n", + "df3 = pd.read_excel(df3_path) # coverting into dataframe\n", + "df3_workbook = load_workbook(df3_path) # open the workbook\n", + "cash_request_workbook = df3_workbook.worksheets[1] # acessing to the second folder of the workbook\n", + "cash_request_workbook\n", + "fees_workbook = df3_workbook.worksheets[0] # acessing to the first folder of the workbook\n", + "fees_workbook\n", + "df3_cash_request = []\n", + "for row in cash_request_workbook.iter_rows(values_only=True):\n", + " df3_cash_request.append(row) # junta todas as rows ao dicionario vazio\n", + "df3_cash_request = pd.DataFrame(df3_cash_request)\n", + "df3_cash_request\n", + "df3_fees = []\n", + "for row in fees_workbook.iter_rows(values_only=True):\n", + " df3_fees.append(row)\n", + "df3_fees = pd.DataFrame(df3_fees)\n", + "df3_fees.head(13)\n", + "df3\n", + "# %%\n", + "merged_df = pd.merge(df1,df2,how='left',left_on='id',right_on='cash_request_id')\n", + "merged_df # left join based on the id\n", + "merged_df.head()\n", + "merged_df2 = merged_df.copy()\n", + "# %%\n", + "merged_df2.info()\n", + "merged_df2.isnull().mean()\n", + "# %%\n", + "merged_df.isnull().mean()\n", + "merged_df.duplicated().sum()\n", + "(merged_df =='').sum() # no spaces on the dataframe\n", + "# %%\n", + "import matplotlib.pyplot as plt # review\n", + "import seaborn as sns\n", + "plt.figure(figsize=(10, 6))\n", + "sns.histplot(merged_df['amount'], kde=True, bins=50)\n", + "plt.title('Distribution of the value of advance requests')\n", + "plt.show()\n", + "# %%\n", + "merged_df2 = merged_df2[['id_x','created_at_x', 'total_amount', 'recovery_status', 'reimbursement_date']]\n", + "merged_df2.head() # columns to keep\n", + "merged_df2.isnull().mean()\n", + "#merged_df2.dtypes\n", + "# %%\n", + "merged_df2['total_amount'] = merged_df2['total_amount'].fillna(0)\n", + "merged_df2['total_amount'].isnull().mean()\n", + "merged_df2['recovery_status'] = merged_df2['recovery_status'].fillna(\"Not Aplicable\")\n", + "merged_df2['recovery_status'].isnull().mean()\n", + "merged_df2['created_at_x'] = pd.to_datetime(merged_df2['created_at_x'], errors='coerce')\n", + "merged_df2['created_at_x'] = merged_df2['created_at_x'].dt.strftime(\"%Y/%m/%d\")\n", + "merged_df2['created_at_x'] = pd.to_datetime(merged_df2['created_at_x'],format=\"%Y/%m/%d\")\n", + "merged_df2['reimbursement_date'] = pd.to_datetime(merged_df2['reimbursement_date'], errors='coerce')\n", + "merged_df2['reimbursement_date'] = merged_df2['reimbursement_date'].dt.strftime('%Y/%m/%d')\n", + "merged_df2['reimbursement_date'] = pd.to_datetime(merged_df2['reimbursement_date'], format='%Y/%m/%d')\n", + "merged_df2.dtypes\n", + "merged_df2.isnull().mean()\n", + "# alternative way\n", + "# merged_df2['reimbursement_date'] = merged_df2['reimbursement_date'].apply(lambda x:x.date().strftime(\"%Y/%m/%d\"))\n", + "# %%\n", + "# Month Column\n", + "merged_df2['month'] = merged_df2['created_at_x'].dt.month\n", + "merged_df2\n", + "cohort_counts = merged_df2.groupby('month')['id_x'].count()\n", + "cohort_counts\n", + "plt.figure(figsize=(10, 6))\n", + "# Criando o barplot para cohort_counts\n", + "sns.barplot(x=cohort_counts.index, y=cohort_counts.values,\n", + " palette='viridis', hue=cohort_counts.index, legend=False)\n", + "# Criando a linha de tendência para cohort_counts\n", + "sns.lineplot(x=cohort_counts.index, y=cohort_counts.values, color='red', marker='o', linewidth=2)\n", + "# Adicionando títulos e rótulos\n", + "plt.title('Frequency of Service Use per Month', fontsize=14)\n", + "plt.xlabel('Cohort Month', fontsize=12)\n", + "plt.ylabel('Number of Requests', fontsize=12)\n", + "# Personalizando os rótulos do eixo x para meses\n", + "plt.xticks(ticks=range(len(cohort_counts.index)), labels=['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'])\n", + "# Exibindo o gráfico\n", + "plt.show()\n", + "# %%\n", + "cohort_revenue = merged_df2.groupby('month')['total_amount'].sum()\n", + "cohort_revenue\n", + "cohort_revenue = merged_df2.groupby('month')['total_amount'].sum()\n", + "# Visualização do cohort_revenue\n", + "plt.figure(figsize=(10, 6))\n", + "# Criando o barplot para cohort_revenue\n", + "sns.barplot(x=cohort_revenue.index, y=cohort_revenue.values,\n", + " palette='viridis', hue=cohort_revenue.index, legend=False)\n", + "# Criando a linha de tendência para cohort_revenue\n", + "sns.lineplot(x=cohort_revenue.index, y=cohort_revenue.values, color='red', marker='o', linewidth=2)\n", + "# Adicionando títulos e rótulos\n", + "plt.title('Revenue Generated per Month', fontsize=14)\n", + "plt.xlabel('Cohort Month', fontsize=12)\n", + "plt.ylabel('Total Revenue', fontsize=12)\n", + "# Personalizando os rótulos do eixo x para meses\n", + "plt.xticks(ticks=range(len(cohort_revenue.index)), labels=['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'])\n", + "# Exibindo o gráfico\n", + "plt.show()\n", + "# %%\n", + "merged_df.isnull().mean()\n", + "# merged_clean_df_cohort_analysis = merged_df[['created_at_x', 'paid_at', 'total_amount', 'recovery_status'])\n", + "# %%\n", + "merged_df2\n", + "# %%\n", + "\"\"\" # Convert 'paid_at' to datetime if not already\n", + "merged_df2['paid_at'] = pd.to_datetime(merged_df2['paid_at'])\n", + "# Extract the year, quarter, month, and bi-annual period from 'paid_at'\n", + "merged_df2['year'] = merged_df2['paid_at'].dt.year\n", + "merged_df2['quarter'] = merged_df2['paid_at'].dt.to_period('Q')\n", + "merged_df2['semester'] = (merged_df2['paid_at'].dt.month - 1) // 6 + 1\n", + "merged_df2['month'] = merged_df2['paid_at'].dt.month\n", + "# Calculate total revenue per cohort for each period type\n", + "monthly_revenue = merged_df2.groupby(['month', 'month']).agg({'total_amount': 'sum'}).reset_index()\n", + "quarterly_revenue = merged_df2.groupby(['quarter']).agg({'total_amount': 'sum'}).reset_index()\n", + "semester_revenue = merged_df2.groupby(['semester']).agg({'total_amount': 'sum'}).reset_index()\n", + "annual_revenue = merged_df2.groupby(['year']).agg({'total_amount': 'sum'}).reset_index()\n", + "# Plotting the cohort revenue\n", + "plt.figure(figsize=(12, 6))\n", + "# Plot monthly revenue\n", + "sns.barplot(x='month', y='total_amount', data=monthly_revenue, color='blue', label='Monthly Revenue')\n", + "# Plot quarterly revenue\n", + "sns.barplot(x='quarter', y='total_amount', data=quarterly_revenue, color='green', label='Quarterly Revenue')\n", + "# Plot semester revenue\n", + "sns.barplot(x='semester', y='total_amount', data=semester_revenue, color='orange', label='Semester Revenue')\n", + "# Plot annual revenue\n", + "sns.barplot(x='year', y='total_amount', data=annual_revenue, color='purple', label='Annual Revenue')\n", + "# Customize plot\n", + "plt.title('Cohort Revenue per Time Period', fontsize=14)\n", + "plt.xlabel('Time Period', fontsize=12)\n", + "plt.ylabel('Total Revenue (in currency)', fontsize=12)\n", + "plt.legend()\n", + "plt.show()\"\"\"\n", + "# %%\n", + "# Calculate the incident rate\n", + "incident_rate = merged_df2[merged_df2['recovery_status'] == 'completed'].groupby('month')['id_x'].count() / cohort_counts\n", + "# Create the plot\n", + "plt.figure(figsize=(10, 6))\n", + "sns.barplot(x=incident_rate.index, y=incident_rate.values,\n", + " hue=incident_rate.index, palette='viridis', legend=False)\n", + "sns.lineplot(x=incident_rate.index, y=incident_rate.values, color='red', marker='o', linewidth=2)\n", + "plt.title('Incident Rate by Cohort', fontsize=14)\n", + "plt.xlabel('Cohort Month', fontsize=12)\n", + "plt.ylabel('Incident Rate', fontsize=12)\n", + "# Customize x-axis labels for months\n", + "plt.xticks(ticks=range(len(incident_rate.index)), labels=['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'])\n", + "# Display the plot\n", + "plt.show()\n", + "# %%\n", + "print(\"Frequency of service use by cohort:\")\n", + "print(cohort_counts)\n", + "print(\"Revenue generated by cohort:\")\n", + "print(cohort_revenue)\n", + "print(\"Incident rate by cohort:\")\n", + "print(incident_rate)\n", + "# %%\n", + "print(merged_df2['created_at_x'].dt.tz)\n", + "print(merged_df2['reimbursement_date'].dt.tz)\n", + "# %%\n", + "# Calcular a diferença entre 'reimbursement_date' e 'created_at_x'\n", + "merged_df2['time_to_reimbursement'] = (merged_df2['reimbursement_date'] - merged_df2['created_at_x']).dt.days\n", + "# Verificar os valores da coluna 'time_to_reimbursement'\n", + "print(\"Values of 'time_to_reimbursement' after calculation:\")\n", + "print(merged_df2['time_to_reimbursement'].head())\n", + "# Checar valores nulos na coluna 'time_to_reimbursement'\n", + "print(\"Null values in 'time_to_reimbursement':\", merged_df2['time_to_reimbursement'].isnull().sum())\n", + "plt.show()\n", + "# %%\n", + "print(merged_df2['created_at_x'].dt.tz)\n", + "print(merged_df2['reimbursement_date'].dt.tz)\n", + "# %%\n", + "# Remover linhas com valores nulos nas colunas 'created_at_x' e 'reimbursement_date'\n", + "merged_df2_clean = merged_df2.dropna(subset=['created_at_x', 'reimbursement_date'])\n", + "merged_df2_clean\n", + "(merged_df2_clean['reimbursement_date'] - merged_df2_clean['created_at_x']).dt.days\n", + "print(\"Values of 'time_to_reimbursement' after calculation:\")\n", + "merged_df2_clean['time_to_reimbursement'].head(20)\n", + "plt.figure(figsize=(10, 6))\n", + "sns.boxplot(x=merged_df2_clean['time_to_reimbursement'], color='green')\n", + "plt.title('Time to Refund Boxplot', fontsize=14)\n", + "plt.xlabel('Time until Refund (days)', fontsize=12)\n", + "plt.show()\n", + "# %%\n", + "import matplotlib.pyplot as plt\n", + "import seaborn as sns\n", + "plt.figure(figsize=(10, 6))\n", + "sns.histplot(merged_df2_clean['time_to_reimbursement'], kde=True, color='blue', bins=30)\n", + "plt.title('Distribution of Time until Reimbursement', fontsize=14)\n", + "plt.xlabel('Time until Refund (days)', fontsize=12)\n", + "plt.ylabel('Frequency', fontsize=12)\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 409, + "id": "f2824fa0-41b4-43da-baca-c63f4da6414a", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "RangeIndex: 32094 entries, 0 to 32093\n", + "Data columns (total 29 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 id_x 32094 non-null int64 \n", + " 1 amount 32094 non-null float64\n", + " 2 status_x 32094 non-null object \n", + " 3 created_at_x 32094 non-null object \n", + " 4 updated_at_x 32094 non-null object \n", + " 5 user_id 29522 non-null float64\n", + " 6 moderated_at 21759 non-null object \n", + " 7 deleted_account_id 2573 non-null float64\n", + " 8 reimbursement_date 32094 non-null object \n", + " 9 cash_request_received_date 24149 non-null object \n", + " 10 money_back_date 23917 non-null object \n", + " 11 transfer_type 32094 non-null object \n", + " 12 send_at 22678 non-null object \n", + " 13 recovery_status 7200 non-null object \n", + " 14 reco_creation 7200 non-null object \n", + " 15 reco_last_update 7200 non-null object \n", + " 16 id_y 21057 non-null float64\n", + " 17 cash_request_id 21057 non-null float64\n", + " 18 type 21057 non-null object \n", + " 19 status_y 21057 non-null object \n", + " 20 category 2196 non-null object \n", + " 21 total_amount 21057 non-null float64\n", + " 22 reason 21057 non-null object \n", + " 23 created_at_y 21057 non-null object \n", + " 24 updated_at_y 21057 non-null object \n", + " 25 paid_at 15531 non-null object \n", + " 26 from_date 7766 non-null object \n", + " 27 to_date 7766 non-null object \n", + " 28 charge_moment 21057 non-null object \n", + "dtypes: float64(6), int64(1), object(22)\n", + "memory usage: 7.1+ MB\n" + ] + }, + { + "data": { + "text/plain": [ + "id_x 0.000000\n", + "created_at_x 0.000000\n", + "total_amount 0.343896\n", + "recovery_status 0.775659\n", + "reimbursement_date 0.000000\n", + "dtype: float64" + ] + }, + "execution_count": 409, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import pandas as pd # painel data, dataframes\n", + "import numpy as np # numerical data\n", + "import os # manage directories folders\n", + "import seaborn as sns # visualization\n", + "from datetime import datetime # format dates\n", + "from openpyxl import load_workbook # excel file with folders/tabs\n", + "\n", + "# %% [markdown]\n", + "# Data Collection\n", + "# %%\n", + "\n", + "#dataset1\n", + "\n", + "#Se lee un archivo CSV con datos relacionados con solicitudes de efectivo\n", + "cash_req = pd.read_csv(\"extract - cash request - data analyst.csv\")\n", + "\n", + "#Se copia el dataframe para trabajar sin modificar el original:\n", + "df1 = cash_req.copy()\n", + "df1 = pd.DataFrame(df1)\n", + "df1\n", + "\n", + "# %%\n", + "#dataset2\n", + "\n", + "#Se lee otro archivo CSV con información sobre tarifas:\n", + "fee = pd.read_csv(\"extract - fees - data analyst - .csv\")\n", + "\n", + "#Se convierte a un dataframe y se almacena en df2.\n", + "df2 = fee.copy()\n", + "df2 = pd.DataFrame(df2)\n", + "df2\n", + "\n", + "\"\"\"\n", + "# %%\n", + "df3_path = \"Lexique - Data Analyst.xlsx\" # sourcefile\n", + "df3 = pd.read_excel(df3_path) # coverting into dataframe\n", + "df3_workbook = load_workbook(df3_path) # open the workbook\n", + "cash_request_workbook = df3_workbook.worksheets[1] # acessing to the second folder of the workbook\n", + "cash_request_workbook\n", + "fees_workbook = df3_workbook.worksheets[0] # acessing to the first folder of the workbook\n", + "fees_workbook\n", + "df3_cash_request = []\n", + "for row in cash_request_workbook.iter_rows(values_only=True):\n", + " df3_cash_request.append(row) # junta todas as rows ao dicionario vazio\n", + "df3_cash_request = pd.DataFrame(df3_cash_request)\n", + "df3_cash_request\n", + "df3_fees = []\n", + "for row in fees_workbook.iter_rows(values_only=True):\n", + " df3_fees.append(row)\n", + "df3_fees = pd.DataFrame(df3_fees)\n", + "df3_fees.head(13)\n", + "df3\n", + "\"\"\"\n", + "\n", + "# %% Se realiza un merge (combinación de tablas) entre df1 y df2, usando una \"unión izquierda\" basada en las claves id y cash_request_id:\n", + "merged_df = pd.merge(df1,df2,how='left',left_on='id',right_on='cash_request_id')\n", + "merged_df # left join based on the id\n", + "merged_df.head()\n", + "merged_df2 = merged_df.copy()\n", + "\n", + "# %%\n", + "\n", + "merged_df2.info() # Información básica del dataframe combinado:\n", + "merged_df2.isnull().mean() # Proporción de valores nulos en cada columna:\n", + "\n", + "# %%\n", + "merged_df.isnull().mean()\n", + "merged_df.duplicated().sum() # Detección de duplicados:\n", + "(merged_df =='').sum() # Revisión de espacios vacíos: no spaces on the dataframe\n", + "\n", + "# %%\n", + "\"\"\"\n", + "import matplotlib.pyplot as plt # review\n", + "import seaborn as sns\n", + "plt.figure(figsize=(10, 6))\n", + "sns.histplot(merged_df['amount'], kde=True, bins=50)\n", + "plt.title('Distribuição do valor das solicitações de adiantamento')\n", + "plt.show()\n", + "\"\"\"\n", + "\n", + "# %%\n", + "merged_df2 = merged_df2[['id_x','created_at_x', 'total_amount', 'recovery_status', 'reimbursement_date']]\n", + "merged_df2.head() # columns to keep\n", + "merged_df2.isnull().mean()\n", + "#merged_df2.dtypes\n", + "#merged_df2\n" + ] + }, + { + "cell_type": "code", + "execution_count": 413, + "id": "8c8babdf-c9c1-4c14-97bb-3d58ebded186", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
id_xcreated_at_xtotal_amountrecovery_statusreimbursement_date
052019-12-10 19:05:21.596873+00NaNNaN2020-01-09 19:05:21.596363+00
1702019-12-10 19:50:12.34778+00NaNNaN2020-01-09 19:50:12.34778+00
272019-12-10 19:13:35.82546+00NaNNaN2020-01-09 19:13:35.825041+00
3102019-12-10 19:16:10.880172+00NaNNaN2020-01-09 19:16:10.879606+00
415942020-05-06 09:59:38.877376+00NaNNaN2020-06-05 22:00:00+00
..................
32089223572020-10-20 07:58:04.006937+005.0NaN2021-02-05 11:00:00+00
32090202562020-10-10 05:40:55.700422+005.0NaN2021-02-05 11:00:00+00
32091202562020-10-10 05:40:55.700422+005.0NaN2021-02-05 11:00:00+00
32092198862020-10-08 14:16:52.155661+005.0NaN2021-02-05 11:00:00+00
32093198862020-10-08 14:16:52.155661+005.0NaN2021-02-05 11:00:00+00
\n", + "

32094 rows × 5 columns

\n", + "
" + ], + "text/plain": [ + " id_x created_at_x total_amount recovery_status \\\n", + "0 5 2019-12-10 19:05:21.596873+00 NaN NaN \n", + "1 70 2019-12-10 19:50:12.34778+00 NaN NaN \n", + "2 7 2019-12-10 19:13:35.82546+00 NaN NaN \n", + "3 10 2019-12-10 19:16:10.880172+00 NaN NaN \n", + "4 1594 2020-05-06 09:59:38.877376+00 NaN NaN \n", + "... ... ... ... ... \n", + "32089 22357 2020-10-20 07:58:04.006937+00 5.0 NaN \n", + "32090 20256 2020-10-10 05:40:55.700422+00 5.0 NaN \n", + "32091 20256 2020-10-10 05:40:55.700422+00 5.0 NaN \n", + "32092 19886 2020-10-08 14:16:52.155661+00 5.0 NaN \n", + "32093 19886 2020-10-08 14:16:52.155661+00 5.0 NaN \n", + "\n", + " reimbursement_date \n", + "0 2020-01-09 19:05:21.596363+00 \n", + "1 2020-01-09 19:50:12.34778+00 \n", + "2 2020-01-09 19:13:35.825041+00 \n", + "3 2020-01-09 19:16:10.879606+00 \n", + "4 2020-06-05 22:00:00+00 \n", + "... ... \n", + "32089 2021-02-05 11:00:00+00 \n", + "32090 2021-02-05 11:00:00+00 \n", + "32091 2021-02-05 11:00:00+00 \n", + "32092 2021-02-05 11:00:00+00 \n", + "32093 2021-02-05 11:00:00+00 \n", + "\n", + "[32094 rows x 5 columns]" + ] + }, + "execution_count": 413, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "merged_df2" + ] + }, + { + "cell_type": "code", + "execution_count": 431, + "id": "7caf7124-1c58-4f60-a0d0-3587836c67bc", + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\EliteBook\\AppData\\Local\\Temp\\ipykernel_26244\\2759623616.py:7: UserWarning: Converting to PeriodArray/Index representation will drop timezone information.\n", + " merged_df2['cohort'] = merged_df2['created_at_x'].dt.to_period('M')\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Cohorte2019-112019-122020-012020-022020-032020-042020-052020-062020-072020-082020-092020-102020-11
Ingresos Totales0.00.00.00.00.05.01285.08725.010395.017565.022935.043815.0565.0
\n", + "
" + ], + "text/plain": [ + "Cohorte 2019-11 2019-12 2020-01 2020-02 2020-03 2020-04 \\\n", + "Ingresos Totales 0.0 0.0 0.0 0.0 0.0 5.0 \n", + "\n", + "Cohorte 2020-05 2020-06 2020-07 2020-08 2020-09 2020-10 \\\n", + "Ingresos Totales 1285.0 8725.0 10395.0 17565.0 22935.0 43815.0 \n", + "\n", + "Cohorte 2020-11 \n", + "Ingresos Totales 565.0 " + ] + }, + "execution_count": 431, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#Calcular ingresos generados por cohortes\n", + "\n", + "# Convertir la columna de fechas a tipo datetime\n", + "merged_df2['created_at_x'] = pd.to_datetime(merged_df2['created_at_x'])\n", + "\n", + "# Crear una columna de cohorte basada en el mes y año de registro\n", + "merged_df2['cohort'] = merged_df2['created_at_x'].dt.to_period('M')\n", + "\n", + "# Calcular los ingresos totales generados por cohorte\n", + "cohort_revenue = merged_df2.groupby('cohort')['total_amount'].sum().reset_index()\n", + "\n", + "# Renombrar columnas\n", + "cohort_revenue.columns = ['Cohorte', 'Ingresos Totales']\n", + "\n", + "# Convertirlo a Dataframe\n", + "df_cohort_revenue = pd.DataFrame(cohort_revenue)\n", + "df_cohort_revenue = df_cohort_revenue.set_index(\"Cohorte\")\n", + "\n", + "# Mostrar los resultados\n", + "df_cohort_revenue.T\n" + ] + }, + { + "cell_type": "code", + "execution_count": 421, + "id": "c704625d-3021-4387-aa84-838f7d5b6b32", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Visualización de resultados\n", + "\n", + "import matplotlib.pyplot as plt\n", + "\n", + "\n", + "plt.figure(figsize=(12, 6))\n", + "sns.barplot(data=cohort_revenue, x='Cohorte', y='Ingresos Totales', color='blue')\n", + "plt.title('Ingresos Totales por Cohorte')\n", + "plt.xlabel('Cohorte (Mes y Año)')\n", + "plt.ylabel('Ingresos Totales')\n", + "plt.xticks(rotation=45)\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 407, + "id": "4d774073-670d-4865-a5d4-a8454599787d", + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\EliteBook\\AppData\\Local\\Temp\\ipykernel_26244\\2138421487.py:19: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n", + "The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n", + "\n", + "For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n", + "\n", + "\n", + " cohort_metrics['Recuperaciones Exitosas'].fillna(0, inplace=True)\n", + "C:\\Users\\EliteBook\\AppData\\Local\\Temp\\ipykernel_26244\\2138421487.py:20: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n", + "The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n", + "\n", + "For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n", + "\n", + "\n", + " cohort_metrics['Tasa de Recuperación Exitosa'].fillna(0, inplace=True)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
CohorteTotal SolicitudesRecuperaciones ExitosasTasa de Recuperación Exitosa
\n", + "
" + ], + "text/plain": [ + "Empty DataFrame\n", + "Columns: [Cohorte, Total Solicitudes, Recuperaciones Exitosas, Tasa de Recuperación Exitosa]\n", + "Index: []" + ] + }, + "execution_count": 407, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Proponer y calcular un nuevo métrico relevante\n", + "# Nuevo métrica: Tasa de recuperación exitosa\n", + "\n", + "# Calcular la cantidad total de solicitudes por cohorte\n", + "cohort_counts = merged_df2.groupby('cohort')['id_x'].count().reset_index()\n", + "cohort_counts.columns = ['Cohorte', 'Total Solicitudes']\n", + "\n", + "# Calcular la cantidad de solicitudes recuperadas con éxito por cohorte\n", + "successful_recoveries = merged_df2[merged_df2['recovery_status'] == 'successful'].groupby('cohort')['id_x'].count().reset_index()\n", + "successful_recoveries.columns = ['Cohorte', 'Recuperaciones Exitosas']\n", + "\n", + "# Combinar los dos resultados en un dataframe\n", + "cohort_metrics = pd.merge(cohort_counts, successful_recoveries, on='Cohorte')\n", + "\n", + "# Calcular la tasa de recuperación exitosa\n", + "cohort_metrics['Tasa de Recuperación Exitosa'] = cohort_metrics['Recuperaciones Exitosas'] / cohort_metrics['Total Solicitudes']\n", + "\n", + "# Llenar valores nulos con 0 para cohortes sin recuperaciones exitosas\n", + "cohort_metrics['Recuperaciones Exitosas'].fillna(0, inplace=True)\n", + "cohort_metrics['Tasa de Recuperación Exitosa'].fillna(0, inplace=True)\n", + "cohort_metrics['Recuperaciones Exitosas'] = cohort_metrics['Recuperaciones Exitosas'].fillna(0)\n", + "cohort_metrics['Tasa de Recuperación Exitosa'] = cohort_metrics['Tasa de Recuperación Exitosa'].fillna(0)\n", + "\n", + "df_cohort_metrics = pd.DataFrame(cohort_metrics)\n", + "\n", + "# Mostrar los resultados\n", + "df_cohort_metrics\n" + ] + }, + { + "cell_type": "code", + "execution_count": 385, + "id": "c9b54b38-f287-4eeb-a64d-261976c23796", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " cohort total_solicitado total_reembolsado tasa_reembolso_promedio\n", + "0 2019-11 0.0 0.0 NaN\n", + "1 2019-12 0.0 0.0 NaN\n", + "2 2020-01 0.0 0.0 NaN\n", + "3 2020-02 0.0 0.0 NaN\n", + "4 2020-03 0.0 0.0 NaN\n", + "5 2020-04 5.0 5.0 1.0\n", + "6 2020-05 1285.0 1285.0 1.0\n", + "7 2020-06 8725.0 8725.0 1.0\n", + "8 2020-07 10395.0 10395.0 1.0\n", + "9 2020-08 17565.0 17565.0 1.0\n", + "10 2020-09 22935.0 22935.0 1.0\n", + "11 2020-10 43815.0 43815.0 1.0\n", + "12 2020-11 565.0 565.0 1.0\n" + ] + }, + { + "ename": "TypeError", + "evalue": "Invalid object type at position 0", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)", + "File \u001b[1;32mlib.pyx:2391\u001b[0m, in \u001b[0;36mpandas._libs.lib.maybe_convert_numeric\u001b[1;34m()\u001b[0m\n", + "\u001b[1;31mTypeError\u001b[0m: Invalid object type", + "\nDuring handling of the above exception, another exception occurred:\n", + "\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)", + "Cell \u001b[1;32mIn[385], line 24\u001b[0m\n\u001b[0;32m 19\u001b[0m \u001b[38;5;28mprint\u001b[39m(cohort_reimbursement)\n\u001b[0;32m 23\u001b[0m plt\u001b[38;5;241m.\u001b[39mfigure(figsize\u001b[38;5;241m=\u001b[39m(\u001b[38;5;241m12\u001b[39m, \u001b[38;5;241m6\u001b[39m))\n\u001b[1;32m---> 24\u001b[0m sns\u001b[38;5;241m.\u001b[39mlineplot(data\u001b[38;5;241m=\u001b[39mcohort_reimbursement, x\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mcohort\u001b[39m\u001b[38;5;124m'\u001b[39m, y\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtasa_reembolso_promedio\u001b[39m\u001b[38;5;124m'\u001b[39m, marker\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mo\u001b[39m\u001b[38;5;124m'\u001b[39m, color\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mpurple\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m 25\u001b[0m plt\u001b[38;5;241m.\u001b[39mtitle(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mTasa de Reembolso Promedio por Cohorte\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m 26\u001b[0m plt\u001b[38;5;241m.\u001b[39mxlabel(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mCohorte (Mes y Año)\u001b[39m\u001b[38;5;124m'\u001b[39m)\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\seaborn\\relational.py:515\u001b[0m, in \u001b[0;36mlineplot\u001b[1;34m(data, x, y, hue, size, style, units, weights, palette, hue_order, hue_norm, sizes, size_order, size_norm, dashes, markers, style_order, estimator, errorbar, n_boot, seed, orient, sort, err_style, err_kws, legend, ci, ax, **kwargs)\u001b[0m\n\u001b[0;32m 512\u001b[0m color \u001b[38;5;241m=\u001b[39m kwargs\u001b[38;5;241m.\u001b[39mpop(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcolor\u001b[39m\u001b[38;5;124m\"\u001b[39m, kwargs\u001b[38;5;241m.\u001b[39mpop(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mc\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m))\n\u001b[0;32m 513\u001b[0m kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcolor\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m _default_color(ax\u001b[38;5;241m.\u001b[39mplot, hue, color, kwargs)\n\u001b[1;32m--> 515\u001b[0m p\u001b[38;5;241m.\u001b[39mplot(ax, kwargs)\n\u001b[0;32m 516\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m ax\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\seaborn\\relational.py:276\u001b[0m, in \u001b[0;36m_LinePlotter.plot\u001b[1;34m(self, ax, kws)\u001b[0m\n\u001b[0;32m 268\u001b[0m \u001b[38;5;66;03m# TODO How to handle NA? We don't want NA to propagate through to the\u001b[39;00m\n\u001b[0;32m 269\u001b[0m \u001b[38;5;66;03m# estimate/CI when some values are present, but we would also like\u001b[39;00m\n\u001b[0;32m 270\u001b[0m \u001b[38;5;66;03m# matplotlib to show \"gaps\" in the line when all values are missing.\u001b[39;00m\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 273\u001b[0m \n\u001b[0;32m 274\u001b[0m \u001b[38;5;66;03m# Loop over the semantic subsets and add to the plot\u001b[39;00m\n\u001b[0;32m 275\u001b[0m grouping_vars \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhue\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msize\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstyle\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m--> 276\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m sub_vars, sub_data \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39miter_data(grouping_vars, from_comp_data\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m):\n\u001b[0;32m 278\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msort:\n\u001b[0;32m 279\u001b[0m sort_vars \u001b[38;5;241m=\u001b[39m [\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124munits\u001b[39m\u001b[38;5;124m\"\u001b[39m, orient, other]\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\seaborn\\_base.py:902\u001b[0m, in \u001b[0;36mVectorPlotter.iter_data\u001b[1;34m(self, grouping_vars, reverse, from_comp_data, by_facet, allow_empty, dropna)\u001b[0m\n\u001b[0;32m 899\u001b[0m grouping_vars \u001b[38;5;241m=\u001b[39m [var \u001b[38;5;28;01mfor\u001b[39;00m var \u001b[38;5;129;01min\u001b[39;00m grouping_vars \u001b[38;5;28;01mif\u001b[39;00m var \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mvariables]\n\u001b[0;32m 901\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m from_comp_data:\n\u001b[1;32m--> 902\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcomp_data\n\u001b[0;32m 903\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m 904\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mplot_data\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\seaborn\\_base.py:1000\u001b[0m, in \u001b[0;36mVectorPlotter.comp_data\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 995\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m var \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mvar_levels:\n\u001b[0;32m 996\u001b[0m \u001b[38;5;66;03m# TODO this should happen in some centralized location\u001b[39;00m\n\u001b[0;32m 997\u001b[0m \u001b[38;5;66;03m# it is similar to GH2419, but more complicated because\u001b[39;00m\n\u001b[0;32m 998\u001b[0m \u001b[38;5;66;03m# supporting `order` in categorical plots is tricky\u001b[39;00m\n\u001b[0;32m 999\u001b[0m orig \u001b[38;5;241m=\u001b[39m orig[orig\u001b[38;5;241m.\u001b[39misin(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mvar_levels[var])]\n\u001b[1;32m-> 1000\u001b[0m comp \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mto_numeric(converter\u001b[38;5;241m.\u001b[39mconvert_units(orig))\u001b[38;5;241m.\u001b[39mastype(\u001b[38;5;28mfloat\u001b[39m)\n\u001b[0;32m 1001\u001b[0m transform \u001b[38;5;241m=\u001b[39m converter\u001b[38;5;241m.\u001b[39mget_transform()\u001b[38;5;241m.\u001b[39mtransform\n\u001b[0;32m 1002\u001b[0m parts\u001b[38;5;241m.\u001b[39mappend(pd\u001b[38;5;241m.\u001b[39mSeries(transform(comp), orig\u001b[38;5;241m.\u001b[39mindex, name\u001b[38;5;241m=\u001b[39morig\u001b[38;5;241m.\u001b[39mname))\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\pandas\\core\\tools\\numeric.py:232\u001b[0m, in \u001b[0;36mto_numeric\u001b[1;34m(arg, errors, downcast, dtype_backend)\u001b[0m\n\u001b[0;32m 230\u001b[0m coerce_numeric \u001b[38;5;241m=\u001b[39m errors \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m (\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mignore\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mraise\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m 231\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 232\u001b[0m values, new_mask \u001b[38;5;241m=\u001b[39m lib\u001b[38;5;241m.\u001b[39mmaybe_convert_numeric( \u001b[38;5;66;03m# type: ignore[call-overload]\u001b[39;00m\n\u001b[0;32m 233\u001b[0m values,\n\u001b[0;32m 234\u001b[0m \u001b[38;5;28mset\u001b[39m(),\n\u001b[0;32m 235\u001b[0m coerce_numeric\u001b[38;5;241m=\u001b[39mcoerce_numeric,\n\u001b[0;32m 236\u001b[0m convert_to_masked_nullable\u001b[38;5;241m=\u001b[39mdtype_backend \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m lib\u001b[38;5;241m.\u001b[39mno_default\n\u001b[0;32m 237\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(values_dtype, StringDtype)\n\u001b[0;32m 238\u001b[0m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m values_dtype\u001b[38;5;241m.\u001b[39mstorage \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpyarrow_numpy\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m 239\u001b[0m )\n\u001b[0;32m 240\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mValueError\u001b[39;00m, \u001b[38;5;167;01mTypeError\u001b[39;00m):\n\u001b[0;32m 241\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m errors \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mraise\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n", + "File \u001b[1;32mlib.pyx:2433\u001b[0m, in \u001b[0;36mpandas._libs.lib.maybe_convert_numeric\u001b[1;34m()\u001b[0m\n", + "\u001b[1;31mTypeError\u001b[0m: Invalid object type at position 0" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Crear una columna binaria que indique si la solicitud fue reembolsada\n", + "merged_df2['reembolsado'] = ~merged_df2['reimbursement_date'].isnull()\n", + "\n", + "# Asumimos que el monto total reembolsado es igual a `total_amount` para solicitudes con reembolso\n", + "merged_df2['monto_reembolsado'] = merged_df2['total_amount'] * merged_df2['reembolsado']\n", + "\n", + "\n", + "\n", + "# Calcular la suma del monto reembolsado y el total solicitado por cohorte\n", + "cohort_reimbursement = merged_df2.groupby('cohort').agg(\n", + " total_solicitado=('total_amount', 'sum'),\n", + " total_reembolsado=('monto_reembolsado', 'sum')\n", + ").reset_index()\n", + "\n", + "# Calcular la tasa de reembolso promedio\n", + "cohort_reimbursement['tasa_reembolso_promedio'] = cohort_reimbursement['total_reembolsado'] / cohort_reimbursement['total_solicitado']\n", + "\n", + "# Mostrar los resultados\n", + "print(cohort_reimbursement)" + ] + }, + { + "cell_type": "code", + "execution_count": 348, + "id": "3c5f9ee8-735a-47e7-af7f-fa0172e07637", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " cohort total_solicitado total_reembolsado tasa_reembolso_promedio\n", + "5 NaT 5.0 5.0 1.0\n", + "6 NaT 1285.0 1285.0 1.0\n", + "7 NaT 8725.0 8725.0 1.0\n", + "8 NaT 10395.0 10395.0 1.0\n", + "9 NaT 17565.0 17565.0 1.0\n", + "10 NaT 22935.0 22935.0 1.0\n", + "11 NaT 43815.0 43815.0 1.0\n", + "12 NaT 565.0 565.0 1.0\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "import seaborn as sns\n", + "import matplotlib.pyplot as plt\n", + "import pandas as pd\n", + "\n", + "# Crear una columna binaria que indique si la solicitud fue reembolsada\n", + "merged_df2['reembolsado'] = ~merged_df2['reimbursement_date'].isnull()\n", + "\n", + "# Asumimos que el monto total reembolsado es igual a `total_amount` para solicitudes con reembolso\n", + "merged_df2['monto_reembolsado'] = merged_df2['total_amount'] * merged_df2['reembolsado']\n", + "\n", + "# Calcular la suma del monto reembolsado y el total solicitado por cohorte\n", + "cohort_reimbursement = merged_df2.groupby('cohort').agg(\n", + " total_solicitado=('total_amount', 'sum'),\n", + " total_reembolsado=('monto_reembolsado', 'sum')\n", + ").reset_index()\n", + "\n", + "# Calcular la tasa de reembolso promedio\n", + "cohort_reimbursement['tasa_reembolso_promedio'] = cohort_reimbursement['total_reembolsado'] / cohort_reimbursement['total_solicitado']\n", + "\n", + "# Verifica y convierte tipos de datos si es necesario\n", + "cohort_reimbursement['cohort'] = pd.to_datetime(cohort_reimbursement['cohort'], errors='coerce')\n", + "cohort_reimbursement['tasa_reembolso_promedio'] = pd.to_numeric(cohort_reimbursement['tasa_reembolso_promedio'], errors='coerce')\n", + "\n", + "# Eliminar filas con valores nulos en 'tasa_reembolso_promedio'\n", + "cohort_reimbursement = cohort_reimbursement.dropna(subset=['tasa_reembolso_promedio'])\n", + "\n", + "# Mostrar los resultados\n", + "print(cohort_reimbursement)\n", + "\n", + "# Graficar\n", + "plt.figure(figsize=(12, 6))\n", + "sns.lineplot(data=cohort_reimbursement, x='cohort', y='tasa_reembolso_promedio', marker='o', color='purple')\n", + "plt.title('Tasa de Reembolso Promedio por Cohorte')\n", + "plt.xlabel('Cohorte (Mes y Año)')\n", + "plt.ylabel('Tasa de Reembolso Promedio')\n", + "plt.xticks(rotation=45)\n", + "plt.ylim(0, 1)\n", + "plt.show()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 350, + "id": "86457065-0242-4727-9da6-5ff9c2a472ff", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAA/4AAAJHCAYAAAApLo3EAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8hTgPZAAAACXBIWXMAAA9hAAAPYQGoP6dpAABxsElEQVR4nO3dd3RU5fr28WtSSEJJCCWEIEKCgvQqSJDeVYoNBAUBpYogSBEsIKIIR4XjoSmCimBHkSOIoPQjIAihBpQaWkBaEmlpz/sHb+bHkMyQgSQTdr6ftbIWeebZe+65sifknt1sxhgjAAAAAABgSV6eLgAAAAAAAGQfGn8AAAAAACyMxh8AAAAAAAuj8QcAAAAAwMJo/AEAAAAAsDAafwAAAAAALIzGHwAAAAAAC6PxBwAAAADAwmj8AQAAAACwMBp/AACQbYYOHapSpUrpyJEjni4FAIA8i8YfACzCZrNl6mvVqlWeLtWpsWPHymazZdn6PvnkE4fX7uPjo5IlS+qJJ57QX3/9lWXPk1fd6Of1/fffa86cOfrpp59UunTpLH3usmXLOt3GmzRp4vb6Mnot06dP1yeffJI1BVvclStXNHXqVN1///0KDg5Wvnz5VKpUKXXq1EmrV692e32rVq2SzWbTt99+mw3Vpvf5559rypQpOfJcAOAJPp4uAACQNdavX+/w/RtvvKGVK1dqxYoVDuOVKlXKybJyhY8//lj33HOPLl++rP/973968803tXLlSu3Zs0fBwcGeLu+29eyzz6pNmzYZPnbgwAH17dtXCxYsULVq1bLl+Rs0aKB33nkn3XhgYKDb68rotUyfPl3FihVTjx49brbEPOH06dNq06aNtm/frl69emn48OEqUqSIjh07ph9++EHNmzfXH3/8oerVq3u6VKc+//xz7dy5Uy+88IKnSwGAbEHjDwAWcd999zl8X7x4cXl5eaUbz4uqVKmiOnXqSJKaNGmilJQUjRkzRgsXLlTPnj09XF3OuHTpkgICArJ0nXfccYfuuOOODB+LiIjQqVOnsvT5rle4cOEs275dvZa8LiUlRcnJyfLz88vw8e7du2vbtm36+eef1axZM4fHnnjiCQ0dOjTXfsB28eJF5c+f39NlAEC241B/AMhDpk2bpkaNGikkJEQFChRQ1apVNWnSJCUlJTnM27p1qx566CGFhITIz89PYWFhevDBB3X06FG31+XM4sWLVaNGDfn5+Sk8PDzDPbeSZIzR9OnTVaNGDQUEBCg4OFiPPfaYDhw4cNM5pH0IcPLkSYfxzZs3q3379ipSpIj8/f1Vs2ZNff311+mWP3bsmPr06aPSpUsrX758CgsL02OPPWZfX9opBocOHXJYLu3w5WtPt2jSpImqVKmitWvX6r777lNAQIBKlSqlV199VSkpKQ7LJyYmavz48brnnnvk5+en4sWLq2fPnvr7778d5pUtW1YPPfSQvvvuO9WsWVP+/v56/fXXJbn3c1u6dKmaN2+uoKAg5c+fXxUrVtSECRPsj2d0eHxqaqomTZpkrzEkJETdu3d32Haufd2bNm1Sw4YNlT9/fkVEROjtt99WampqulpuxuXLl1WzZk3dddddiouLs4/HxsYqNDTU/iFQRq+lbNmy2rVrl1avXm0/haBs2bL2x2NiYvTUU0/Z3yMVK1bUu+++m672GTNmqHr16ipYsKAKFSqke+65R6NHj7Y//vfff2vAgAGqVKmSChYsqJCQEDVr1kxr167N1GtM+1l///33qlatmvz9/RUREaH3338/3dzM1Hzo0CHZbDZNmjRJ48ePV3h4uPz8/LRy5coMn/+PP/7QTz/9pGeeeSZd05/m3nvv1Z133mn/fufOnerQoYOCg4Pl7++vGjVq6NNPP81w2aSkJL388ssKCwtTYGCgWrRoob1796abN2fOHFWvXl3+/v4qUqSIHn74YUVHRzvM6dGjhwoWLKgdO3aoVatWKlSokJo3b64mTZpo8eLFOnz4sMMpI2ky+74DgNyMPf4AkIfs379fXbt2VXh4uPLly6dt27bpzTff1J49ezRnzhxJ0oULF9SyZUuFh4dr2rRpKlGihGJjY7Vy5UolJCS4tS5nfv31V3Xo0EH169fXl19+qZSUFE2aNCldIy5Jffv21SeffKJBgwZp4sSJOnv2rMaNG6fIyEht27ZNJUqUcDuHgwcPSpLKly9vH1u5cqXatGmjevXqaebMmQoKCtKXX36pzp076+LFi/bDvY8dO6Z7771XSUlJGj16tKpVq6YzZ87o559/1rlz526qntjYWD3xxBN66aWXNG7cOC1evFjjx4/XuXPnNHXqVElXG+oOHTpo7dq1GjFihCIjI3X48GGNGTNGTZo00ebNmx326G/ZskXR0dF65ZVXFB4ergIFCkjK/M9t9uzZ6t27txo3bqyZM2cqJCREf/75p3bu3OnytfTv318ffvihBg4cqIceekiHDh3Sq6++qlWrVmnLli0qVqyYw+t+8skn9eKLL2rMmDH6/vvvNWrUKIWFhal79+43zM0Yo+Tk5HTj3t7estls8vf319dff63atWurV69eWrBggVJTU/Xkk0/KGKMvvvhC3t7eGa77+++/12OPPaagoCBNnz5dkux7vP/++29FRkYqMTFRb7zxhsqWLasff/xRw4YN0/79++3zv/zySw0YMEDPP/+83nnnHXl5eWnfvn3avXu3/XnOnj0rSRozZoxCQ0P1zz//6Pvvv1eTJk3066+/Zup6BVFRUXrhhRc0duxYhYaGav78+Ro8eLASExM1bNgwt2pO8/7776t8+fJ65513FBgYqLvvvjvD5162bJkkqWPHjjesU5L27t2ryMhIhYSE6P3331fRokU1b9489ejRQydPntSIESMc5o8ePVoNGjTQRx99pPj4eI0cOVLt2rVTdHS0/Wc3YcIEjR49Wl26dNGECRN05swZjR07VvXr19emTZscak9MTFT79u3Vt29fvfTSS0pOTtYdd9yhPn36aP/+/fr+++8dnt/d9x0A5FoGAGBJTz/9tClQoIDTx1NSUkxSUpKZO3eu8fb2NmfPnjXGGLN582YjySxcuDDTz+VsXc7Uq1fPhIWFmUuXLtnH4uPjTZEiRcy1/zWtX7/eSDLvvvuuw/JHjhwxAQEBZsSIES6f5+OPPzaSzIYNG0xSUpJJSEgwS5cuNaGhoaZRo0YmKSnJPveee+4xNWvWdBgzxpiHHnrIlCxZ0qSkpBhjjOnVq5fx9fU1u3fvvuHzHjx40GF85cqVRpJZuXKlfaxx48ZGkvnhhx8c5vbu3dt4eXmZw4cPG2OM+eKLL4wks2DBAod5mzZtMpLM9OnT7WNlypQx3t7eZu/evS7zcfZzS0hIMIGBgeb+++83qampTpcfM2aMw88rOjraSDIDBgxwmLdx40YjyYwePTrd6964caPD3EqVKpnWrVu7rDvtNUrK8OuNN95wmPvVV18ZSWbKlCnmtddeM15eXmbZsmUuX4sxxlSuXNk0btw43XO/9NJLGdbev39/Y7PZ7LkPHDjQFC5c+Iav5VrJyckmKSnJNG/e3Dz88MM3nF+mTBljs9lMVFSUw3jLli1NYGCguXDhgls1Hzx40Egy5cqVM4mJiTd8/n79+hlJZs+ePZl6fU888YTx8/MzMTExDuNt27Y1+fPnN+fPnzfG/N975YEHHnCY9/XXXxtJZv369cYYY86dO2cCAgLSzYuJiTF+fn6ma9eu9rGnn37aSDJz5sxJV9eDDz5oypQpk27cnfcdAORmHOoPAHnI1q1b1b59exUtWlTe3t7y9fVV9+7dlZKSoj///FOSdNdddyk4OFgjR47UzJkzHfZOuruujFy4cEGbNm3SI488In9/f/t4oUKF1K5dO4e5P/74o2w2m5566iklJyfbv0JDQ1W9evVM36Hgvvvuk6+vrwoVKqQ2bdooODhYP/zwg3x8rh74tm/fPu3Zs0dPPvmkJDk81wMPPKATJ07YDy/+6aef1LRpU1WsWDFTz50ZhQoVUvv27R3GunbtqtTUVK1Zs0bS1SwKFy6sdu3aOdRXo0YNhYaGpsuiWrVqDkc0pMnMz+23335TfHy8BgwY4NZdFtIOB7/+Ynh169ZVxYoV9euvvzqMh4aGqm7duunqPnz4cKae7/7779emTZvSfT3zzDMO8zp16qT+/ftr+PDhGj9+vEaPHq2WLVtm+nVdb8WKFapUqVK62nv06CFjjP2CmnXr1tX58+fVpUsX/fDDDzp9+nSG65s5c6Zq1aolf39/+fj4yNfXV7/++mu6Q9WdqVy5croL53Xt2lXx8fHasmWLWzWnad++vXx9fTP1/O5YsWKFmjdvnu4uDz169NDFixfTXaT0+vdF2oUi07aR9evX69KlS+m2udKlS6tZs2bptjlJevTRRzNdr7vvOwDIrWj8ASCPiImJUcOGDXXs2DH9+9//1tq1a7Vp0yZNmzZN0tWLv0lSUFCQVq9erRo1amj06NGqXLmywsLCNGbMGPt54JldV0bOnTun1NRUhYaGpnvs+rGTJ0/KGKMSJUrI19fX4WvDhg1OG6nrzZ07V5s2bdKKFSvUt29fRUdHq0uXLg7PI0nDhg1L9zwDBgyQJPtz/f3331l+EbiMTg9Iy+LMmTP2Gs+fP698+fKlqzE2NjZdFiVLlky3zsz+3NLOXXb3dabVmtFzh4WF2R9PU7Ro0XTz/Pz8XG4/1woKClKdOnXSfWX0/L169VJSUpJ8fHw0aNCgTK3fmTNnzjh9jWmPS1K3bt00Z84cHT58WI8++qhCQkJUr149LV++3L7Me++9p/79+6tevXpasGCBNmzYoE2bNqlNmzaZzsHVeymtlszWnCajuRlJO3c/7fSZG3G3juu3kbTTLdKycXeby58/v1t3fXD3fQcAuRXn+ANAHrFw4UJduHBB3333ncqUKWMfj4qKSje3atWq+vLLL2WM0fbt2/XJJ59o3LhxCggI0EsvveTWuq4XHBwsm82m2NjYdI9dP1asWDHZbDatXbs2wyuKO7vK+PUqVqxov6Bf06ZNlZKSoo8++kjffvutHnvsMft556NGjdIjjzyS4ToqVKgg6erdEq6/UN310o5kuHLlisO4syYho2sbpGWR1vgUK1ZMRYsW1dKlSzNcR6FChRy+z2hPfWZ/bsWLF5ekG77O66XVeuLEiXQfGhw/ftzh/P6cdOHCBXXr1k3ly5fXyZMn9eyzz+qHH3646fUVLVpUJ06cSDd+/PhxSXJ4nT179lTPnj114cIFrVmzRmPGjNFDDz2kP//8U2XKlNG8efPUpEkTzZgxw2Fd115P40ZcvZfSfibu1CxlvP1kpHXr1ho9erQWLlzo9NaO13K3jsysT5LTdd7s60rj7vsOAHIr9vgDQB6R9gfvtc2yMUazZs1yuUz16tU1efJkFS5c2H7Y8M2sK02BAgVUt25dfffdd7p8+bJ9PCEhQf/9738d5j700EMyxujYsWMZ7tmtWrVqJl55epMmTVJwcLBee+01paamqkKFCrr77ru1bdu2DJ+nTp069j/w27Ztq5UrV2Z4ZfE0aVd/3759u8P4okWLMpyfkJCQ7rHPP/9cXl5eatSokT2LM2fOKCUlJcP60j6YcCWzP7fIyEgFBQVp5syZMsbccL1p0q7qPm/ePIfxTZs2KTo6Ws2bN8/0urJSv379FBMTo++++06zZ8/WokWLNHny5Bsu5+zog+bNm2v37t3290OauXPnymazqWnTpumWKVCggNq2bauXX35ZiYmJ2rVrl6SrP5PrP8Davn17ukPeXdm1a5e2bdvmMPb555+rUKFCqlWr1k3XnBm1atVS27ZtNXv27HSnC6TZvHmzYmJi7HWsWLHC3uhfW0f+/Pndvj1j/fr1FRAQkG6bO3r0qP20gsxw9rPOivcdAOQG7PEHgDyiZcuWypcvn7p06aIRI0bo8uXLmjFjhs6dO+cw78cff9T06dPVsWNHRUREyBij7777TufPn7efF53ZdTnzxhtvqE2bNmrZsqVefPFFpaSkaOLEiSpQoID9KueS1KBBA/Xp00c9e/bU5s2b1ahRIxUoUEAnTpzQunXrVLVqVfXv39/tLIKDgzVq1CiNGDFCn3/+uZ566il98MEHatu2rVq3bq0ePXqoVKlSOnv2rKKjo7VlyxZ98803kqRx48bpp59+UqNGjTR69GhVrVpV58+f19KlSzV06FDdc889uvfee1WhQgUNGzZMycnJCg4O1vfff69169ZlWE/RokXVv39/xcTEqHz58lqyZIlmzZql/v372w+lfuKJJzR//nw98MADGjx4sOrWrStfX18dPXpUK1euVIcOHfTwww+7fN2Z/bkVLFhQ7777rp599lm1aNFCvXv3VokSJbRv3z5t27bNfqeB61WoUEF9+vTRf/7zH3l5ealt27b2q/qXLl1aQ4YMcfdH5dL58+e1YcOGdON+fn6qWbOmJOmjjz7SvHnz9PHHH6ty5cqqXLmyBg4cqJEjR6pBgwbpznm/VtqRL1999ZUiIiLk7++vqlWrasiQIZo7d64efPBBjRs3TmXKlNHixYs1ffp09e/f335thd69eysgIEANGjRQyZIlFRsbqwkTJigoKEj33nuvpKuN5RtvvKExY8aocePG2rt3r8aNG6fw8PAM71iQkbCwMLVv315jx45VyZIlNW/ePC1fvlwTJ06036M+szXfjLlz56pNmzZq27atevXqpbZt2yo4OFgnTpzQf//7X33xxRf6448/dOedd2rMmDH68ccf1bRpU7322msqUqSI5s+fr8WLF2vSpEkKCgpy67kLFy6sV199VaNHj1b37t3VpUsXnTlzRq+//rr8/f01ZsyYTK2natWq+u677zRjxgzVrl1bXl5eqlOnTpa87wAgV/DUVQUBANkro6v6//e//zXVq1c3/v7+plSpUmb48OHmp59+crjS/J49e0yXLl1MuXLlTEBAgAkKCjJ169Y1n3zyidvrcmXRokWmWrVqJl++fObOO+80b7/9doZXVjfGmDlz5ph69eqZAgUKmICAAFOuXDnTvXt3s3nzZpfPkXZ1/U2bNqV77NKlS+bOO+80d999t0lOTjbGGLNt2zbTqVMnExISYnx9fU1oaKhp1qyZmTlzpsOyR44cMb169TKhoaHG19fXhIWFmU6dOpmTJ0/a5/z555+mVatWJjAw0BQvXtw8//zzZvHixRle1b9y5cpm1apVpk6dOsbPz8+ULFnSjB49Ot0dBpKSksw777xjz71gwYLmnnvuMX379jV//fWXfV6ZMmXMgw8+mGEm7vzclixZYho3bmwKFChg8ufPbypVqmQmTpxofzyjn1dKSoqZOHGiKV++vPH19TXFihUzTz31lDly5IjDvLTXfb2nn346w6urX8/VVf1LlSpljDFm+/btJiAgwDz99NMOy16+fNnUrl3blC1b1pw7d87pazl06JBp1aqVKVSokJHkUNfhw4dN165dTdGiRY2vr6+pUKGC+de//mW/+4Mxxnz66aemadOmpkSJEiZfvnz27WT79u32OVeuXDHDhg0zpUqVMv7+/qZWrVpm4cKFbuXw4IMPmm+//dZUrlzZ5MuXz5QtW9a899576eZmpua0q/r/61//uuFzX+vSpUvm/fffN/Xr1zeBgYHGx8fHhIWFmUceecQsXrzYYe6OHTtMu3btTFBQkMmXL5+pXr26+fjjjx3mpF3V/5tvvnEYT6vv+vkfffSR/fdJUFCQ6dChg9m1a5fDHFd3Ojl79qx57LHHTOHChY3NZnPYFjL7vgOA3MxmjBvH8AEAgCzVpEkTnT59Wjt37vR0KbgNlS1bVlWqVNGPP/7o6VIAALkY5/gDAAAAAGBhNP4AAAAAAFgYh/oDAAAAAGBh7PEHAAAAAMDCaPwBAAAAALAwGn8AAAAAACzMx9MFWEFqaqqOHz+uQoUKyWazebocAAAAAIDFGWOUkJCgsLAweXm53qdP458Fjh8/rtKlS3u6DAAAAABAHnPkyBHdcccdLufQ+GeBQoUKSboaeGBgoIerAQAAAABYXXx8vEqXLm3vR12h8c8CaYf3BwYG0vgDAAAAAHJMZk435+J+AAAAAABYGI0/AAAAAAAWRuMPAAAAAICF0fgDAAAAAGBhNP4AAAAAAFgYjT8AAAAAABZG4w8AAAAAgIXR+AMAAAAAYGE0/gAAAAAAWBiNPwAAAAAAFkbjDwAAAACAhdH4AwAAAABgYTT+AAAAAABYGI0/AAAAAAAWRuMPAAAAAICF0fgDAAAAAGBhNP4AAAAAAFgYjT8AAAAAABZG4w8AAAAAgIXR+AMAAAAAYGE0/gAAAAAAWBiNPwAAAAAAFkbjDwAAAACAhdH4AwAAAABgYTT+AAAAAABYGI0/AAAAAAAWRuMPAAAAAICF0fgDAAAAAGBhNP4AAAAAAFgYjT8AAAAAABZG4w8AAAAAgIXR+AMAAAAAYGE0/gAAAAAAWBiNPwAAAAAAFkbjDwAAAACAhdH4AwAAAABgYTT+AAAAAABYGI0/AAAAAAAWRuMPAAAAAICF0fgDAAAAAGBhNP4AAAAAAFgYjT8AAAAAABZG4w8AAAAAgIXR+AMAAAAAYGE0/gAAAAAAWBiNPwAAAAAAFkbjDwAAAACAhdH4AwAAAABgYTT+AAAAAABYGI0/AAAAAAAWRuMPAAAAAICF0fgDAAAAAGBhNP4AAAAAAFgYjT8AAAAAABZG4w8AAAAAgIXR+AMAAAAAYGG3ZeM/ffp0hYeHy9/fX7Vr19batWtdzl+9erVq164tf39/RUREaObMmU7nfvnll7LZbOrYsWMWVw0AAAAAQM677Rr/r776Si+88IJefvllbd26VQ0bNlTbtm0VExOT4fyDBw/qgQceUMOGDbV161aNHj1agwYN0oIFC9LNPXz4sIYNG6aGDRtm98sAAAAAACBH2IwxxtNFuKNevXqqVauWZsyYYR+rWLGiOnbsqAkTJqSbP3LkSC1atEjR0dH2sX79+mnbtm1av369fSwlJUWNGzdWz549tXbtWp0/f14LFy7MVE3x8fEKCgpSXFycAgMDb/7FAQAAAACQCe70obfVHv/ExET98ccfatWqlcN4q1at9Ntvv2W4zPr169PNb926tTZv3qykpCT72Lhx41S8eHE988wzN6zjypUrio+Pd/gCAAAAACA3uq0a/9OnTyslJUUlSpRwGC9RooRiY2MzXCY2NjbD+cnJyTp9+rQk6X//+59mz56tWbNmZaqOCRMmKCgoyP5VunTpm3g1AAAAAABkv9uq8U9js9kcvjfGpBu70fy08YSEBD311FOaNWuWihUrlqnnHzVqlOLi4uxfR44ccfMVAAAAAACQM3w8XYA7ihUrJm9v73R790+dOpVur36a0NDQDOf7+PioaNGi2rVrlw4dOqR27drZH09NTZUk+fj4aO/evSpXrpzD8n5+fvLz88uKlwQAAAAAQLa6rfb458uXT7Vr19by5csdxpcvX67IyMgMl6lfv366+cuWLVOdOnXk6+ure+65Rzt27FBUVJT9q3379mratKmioqI4jB8AAAAAcFu7rfb4S9LQoUPVrVs31alTR/Xr19eHH36omJgY9evXT9LVw/CPHTumuXPnSrp6Bf+pU6dq6NCh6t27t9avX6/Zs2friy++kCT5+/urSpUqDs9RuHBhSUo3DgAAAADA7ea2a/w7d+6sM2fOaNy4cTpx4oSqVKmiJUuWqEyZMpKkEydOKCYmxj4/PDxcS5Ys0ZAhQzRt2jSFhYXp/fff16OPPuqplwAAAAAAQI6xmbQr3eGmuXP/RAAAAAAAbpU7fehtdY4/AAAAAABwD40/AAAAAAAWRuMPAAAAAICF0fgDAAAAAGBhNP4AAAAAAFgYjT8AAAAAABZG4w8AAAAAgIXR+AMAAAAAYGE0/gAAAAAAWBiNPwAAAAAAFkbjDwAAAACAhdH4AwAAAABgYTT+AAAAAABYGI0/AAAAAAAWRuMPAAAAAICF0fgDAAAAAGBhNP4AAAAAAFgYjT8AAAAAABZG4w8AAAAAgIXR+AMAAAAAYGE0/gAAAAAAWBiNPwAAAAAAFkbjDwAAAACAhdH4AwAAAABgYTT+AAAAAABYGI0/AAAAAAAWRuMPAAAAAICF0fgDAAAAAGBhNP4AAAAAAFgYjT8AAAAAABZG4w8AAAAAgIXR+AMAAAAAYGE0/gAAAAAAWBiNPwAAAAAAFkbjDwAAAACAhdH4AwAAAABgYTT+AAAAAABYGI0/AAAAAAAWRuMPAAAAAICF0fgDAAAAAGBhNP4AAAAAAFgYjT8AAAAAABZG4w8AAAAAgIXR+AMAAAAAYGE0/gAAAAAAWBiNPwAAAAAAFkbjDwAAAACAhdH4AwAAAABgYTT+AAAAAABYGI0/AAAAAAAWRuMPAAAAAICF0fgDAAAAAGBhNP4AAAAAAFgYjT8AAAAAABZG4w8AAAAAgIXR+AMAAAAAYGE0/gAAAAAAWBiNPwAAAAAAFkbjDwAAAACAhdH4AwAAAABgYT63svClS5eUlJTkMBYYGHhLBQEAAAAAgKzj9h7/ixcvauDAgQoJCVHBggUVHBzs8AUAAAAAAHIPtxv/4cOHa8WKFZo+fbr8/Pz00Ucf6fXXX1dYWJjmzp2bHTUCAAAAAICb5Pah/v/97381d+5cNWnSRL169VLDhg111113qUyZMpo/f76efPLJ7KgTAAAAAADcBLf3+J89e1bh4eGSrp7Pf/bsWUnS/fffrzVr1mRtdQAAAAAA4Ja43fhHRETo0KFDkqRKlSrp66+/lnT1SIDChQtnZW0AAAAAAOAWud349+zZU9u2bZMkjRo1yn6u/5AhQzR8+PAsLxAAAAAAANw8mzHG3MoKYmJitHnzZpUrV07Vq1fPqrpuK/Hx8QoKClJcXBy3MwQAAAAAZDt3+lC3L+53vTvvvFOBgYEc5g8AAAAAQC7k9qH+EydO1FdffWX/vlOnTipatKhKlSplPwUAAAAAAADkDm43/h988IFKly4tSVq+fLmWL1+un376SW3btuUcfwAAAAAAchm3D/U/ceKEvfH/8ccf1alTJ7Vq1Uply5ZVvXr1srxAAAAAAABw89ze4x8cHKwjR45IkpYuXaoWLVpIkowxSklJydrqAAAAAADALXG78X/kkUfUtWtXtWzZUmfOnFHbtm0lSVFRUbrrrruyvMCMTJ8+XeHh4fL391ft2rW1du1al/NXr16t2rVry9/fXxEREZo5c6bD47NmzVLDhg0VHBys4OBgtWjRQr///nt2vgQAAAAAAHKE243/5MmTNXDgQFWqVEnLly9XwYIFJV09BWDAgAFZXuD1vvrqK73wwgt6+eWXtXXrVjVs2FBt27ZVTExMhvMPHjyoBx54QA0bNtTWrVs1evRoDRo0SAsWLLDPWbVqlbp06aKVK1dq/fr1uvPOO9WqVSsdO3Ys218PAAAAAADZyWaMMZ4uwh316tVTrVq1NGPGDPtYxYoV1bFjR02YMCHd/JEjR2rRokWKjo62j/Xr10/btm3T+vXrM3yOlJQUBQcHa+rUqerevfsNa3Ln/okAAAAAANwqd/pQt/f4S9L+/fv1/PPPq0WLFmrZsqUGDRqkAwcO3FSx7khMTNQff/yhVq1aOYy3atVKv/32W4bLrF+/Pt381q1ba/PmzUpKSspwmYsXLyopKUlFihTJ8PErV64oPj7e4QsAAAAAgNzI7cb/559/VqVKlfT777+rWrVqqlKlijZu3Gg/9D87nT59WikpKSpRooTDeIkSJRQbG5vhMrGxsRnOT05O1unTpzNc5qWXXlKpUqXsFy683oQJExQUFGT/SrvLAQAAAAAAuY3bt/N76aWXNGTIEL399tvpxkeOHKmWLVtmWXHO2Gw2h++NMenGbjQ/o3FJmjRpkr744gutWrVK/v7+Ga5v1KhRGjp0qP37+Ph4mn8AAAAAQK7k9h7/6OhoPfPMM+nGe/Xqpd27d2dJUc4UK1ZM3t7e6fbunzp1Kt1e/TShoaEZzvfx8VHRokUdxt955x299dZbWrZsmapVq+a0Dj8/PwUGBjp8AQAAAACQG7nd+BcvXlxRUVHpxqOiohQSEpIVNTmVL18+1a5dO90pBcuXL1dkZGSGy9SvXz/d/GXLlqlOnTry9fW1j/3rX//SG2+8oaVLl6pOnTpZXzwAAAAAAB7g9qH+vXv3Vp8+fXTgwAFFRkbKZrNp3bp1mjhxol588cXsqNHB0KFD1a1bN9WpU0f169fXhx9+qJiYGPXr10/S1cPwjx07prlz50q6egX/qVOnaujQoerdu7fWr1+v2bNn64svvrCvc9KkSXr11Vf1+eefq2zZsvYjBAoWLGi/XSEAAAAAALcjt2/nZ4zRlClT9O677+r48eOSpLCwMA0fPlyDBg1yea59Vpk+fbomTZqkEydOqEqVKpo8ebIaNWokSerRo4cOHTqkVatW2eevXr1aQ4YM0a5duxQWFqaRI0faPyiQpLJly+rw4cPpnmfMmDEaO3bsDevhdn4AAAAAgJzkTh/qduN/rYSEBElSoUKFbnYVlkDjDwAAAADISe70oW6f49+sWTOdP39e0tWGP63pj4+PV7NmzdyvFgAAAAAAZBu3G/9Vq1YpMTEx3fjly5e1du3aLCkKAAAAAABkjUxf3G/79u32f+/evdvhFnkpKSlaunSpSpUqlbXVAQAAAACAW5Lpxr9GjRqy2Wyy2WwZHtIfEBCg//znP1laHAAAAAAAuDWZbvwPHjwoY4wiIiL0+++/q3jx4vbH8uXLp5CQEHl7e2dLkQAAAAAA4OZkuvEvU6aMJCk1NTXbigEAAAAAAFkrU43/okWL1LZtW/n6+mrRokUu57Zv3z5LCgMAAAAAALfOZowxN5rk5eWl2NhYhYSEyMvL+Y0AbDabUlJSsrTA24E7908EAAAAAOBWudOHZmqP/7WH93OoPwAAAAAAtw/nu+9vwsWLF7NydQAAAAAA4Ba53fg3adJER48eTTe+ceNG1ahRIytqAgAAAAAAWcTtxj8wMFDVqlXTl19+Kenqof9jx45Vo0aNuLAfAAAAAAC5TKZv55dm0aJFmjlzpp599lktWrRIhw4dUkxMjBYvXqwWLVpkR40AAAAAAOAmud34S1K/fv10+PBhTZw4UT4+Plq1apUiIyOzujYAAAAAAHCL3D7U/9y5c3r00Uc1Y8YMffDBB+rUqZNatWql6dOnZ0d9AAAAAADgFri9x79KlSoKDw/X1q1bFR4ert69e+urr77SgAEDtHjxYi1evDg76gQAAAAAADfB7T3+/fr105o1axQeHm4f69y5s7Zt26bExMQsLQ4AAAAAANwamzHGeLqI2118fLyCgoIUFxenwMBAT5cDAAAAALA4d/rQTO/xnzRpki5dumT/fs2aNbpy5Yr9+4SEBA0YMOAmygUAAAAAANkl03v8vb29deLECYWEhEiSAgMDFRUVpYiICEnSyZMnFRYWppSUlOyrNpdijz8AAAAAICdlyx7/6z8f4AwBAAAAAAByP7cv7gcAAAAAAG4fNP4AAAAAAFiYjzuTP/roIxUsWFCSlJycrE8++UTFihWTdPXifgAAAAAAIHfJ9MX9ypYtK5vNdsN5Bw8evOWibjdc3A8AAAAAkJPc6UMzvcf/0KFDt1oXAAAAAADIYZzjDwAAAACAhdH4AwAAAABgYTT+AAAAAABYGI0/AAAAAAAWRuMPAAAAAICFZfqq/tdKTU3Vvn37dOrUKaWmpjo81qhRoywpDAAAAAAA3Dq3G/8NGzaoa9euOnz4sIwxDo/ZbDalpKRkWXEAAAAAAODWuN349+vXT3Xq1NHixYtVsmRJ2Wy27KgLAAAAAABkAbcb/7/++kvffvut7rrrruyoBwAAAAAAZCG3L+5Xr1497du3LztqAQAAAAAAWcztPf7PP/+8XnzxRcXGxqpq1ary9fV1eLxatWpZVhwAAAAAALg1NnP9FfpuwMsr/UECNptNxpg8e3G/+Ph4BQUFKS4uToGBgZ4uBwAAAABgce70oW7v8T948OBNFwYAAAAAAHKW241/mTJlsqMOAAAAAACQDdxu/CVp//79mjJliqKjo2Wz2VSxYkUNHjxY5cqVy+r6AAAAAADALbjhVf23bt3qcN7+zz//rEqVKun3339XtWrVVKVKFW3cuFGVK1fW8uXLs7VYAAAAAADgnhte3G/y5Mn6+eeftWDBAhUoUEA1a9ZU69at9fbbbzvMe+mll7Rs2TJt2bIlWwvOjbi4HwAAAAAgJ7nTh95wj/+QIUPUuHFjNWnSRJIUHR2tZ555Jt28Xr16affu3TdXMQAAAAAAyBaZOsd/1KhRaty4sSSpePHiioqK0t133+0wJyoqSiEhIVlfIQAAAAAAuGmZvrhfZGSkJKl3797q06ePDhw4oMjISNlsNq1bt04TJ07Uiy++mG2FAgAAAAAA993wHP/rGWM0ZcoUvfvuuzp+/LgkKSwsTMOHD9egQYNks9mypdDcjHP8AQAAAAA5yZ0+1O3G/1oJCQmSpEKFCt3sKiyBxh8AAAAAkJPc6UMzfah/RvJ6ww8AAAAAQG6Xqca/Vq1a+vXXXxUcHKyaNWu6PJw/L97ODwAAAACA3CpTjX+HDh3k5+cnSerYsWN21gMAAAAAALLQLZ3jj6s4xx8AAAAAkJPc6UO93F35pk2btHHjxnTjGzdu1ObNm91dHQAAAAAAyEZuN/7PPfecjhw5km782LFjeu6557KkKAAAAAAAkDXcbvx3796tWrVqpRuvWbOmdu/enSVFAQAAAACArOF24+/n56eTJ0+mGz9x4oR8fG7p7oAAAAAAACCLud34t2zZUqNGjVJcXJx97Pz58xo9erRatmyZpcUBAAAAAIBb4/Yu+nfffVeNGjVSmTJlVLNmTUlSVFSUSpQooc8++yzLCwQAAAAAADfP7ca/VKlS2r59u+bPn69t27YpICBAPXv2VJcuXeTr65sdNQIAAAAAgJt0UyflFyhQQH369MnqWgAAAAAAQBa76avx7d69WzExMUpMTHQYb9++/S0XBQAAAAAAsobbjf+BAwf08MMPa8eOHbLZbDLGSJJsNpskKSUlJWsrBAAAAAAAN83tq/oPHjxY4eHhOnnypPLnz69du3ZpzZo1qlOnjlatWpUNJQIAAAAAgJvl9h7/9evXa8WKFSpevLi8vLzk5eWl+++/XxMmTNCgQYO0devW7KgTAAAAAADcBLf3+KekpKhgwYKSpGLFiun48eOSpDJlymjv3r1ZWx0AAAAAALglbu/xr1KlirZv366IiAjVq1dPkyZNUr58+fThhx8qIiIiO2oEAAAAAAA3ye3G/5VXXtGFCxckSePHj9dDDz2khg0bqmjRovrqq6+yvEAAAAAAAHDzbCbtsvy34OzZswoODrZf2T+viY+PV1BQkOLi4hQYGOjpcgAAAAAAFudOH+rWOf7Jycny8fHRzp07HcaLFCmSZ5t+AAAAAAByM7cafx8fH5UpU0YpKSnZVQ8AAAAAAMhCbl/V/5VXXtGoUaN09uzZ7KgHAAAAAABkIbcv7vf+++9r3759CgsLU5kyZVSgQAGHx7ds2ZJlxQEAAAAAgFvjduPfsWPHbCgDAAAAAABkhyy5qn9Omz59uv71r3/pxIkTqly5sqZMmaKGDRs6nb969WoNHTpUu3btUlhYmEaMGKF+/fo5zFmwYIFeffVV7d+/X+XKldObb76phx9+OFP1cFV/AAAAAEBOyrar+qc5f/68PvroI4dz/bds2aJjx47dzOrc8tVXX+mFF17Qyy+/rK1bt6phw4Zq27atYmJiMpx/8OBBPfDAA2rYsKG2bt2q0aNHa9CgQVqwYIF9zvr169W5c2d169ZN27ZtU7du3dSpUydt3Lgx218PAAAAAADZye09/tu3b1eLFi0UFBSkQ4cOae/evYqIiNCrr76qw4cPa+7cudlVqySpXr16qlWrlmbMmGEfq1ixojp27KgJEyakmz9y5EgtWrRI0dHR9rF+/fpp27ZtWr9+vSSpc+fOio+P108//WSf06ZNGwUHB+uLL764YU3s8QcAAAAA5KRs3eM/dOhQ9ejRQ3/99Zf8/f3t423bttWaNWvcr9YNiYmJ+uOPP9SqVSuH8VatWum3337LcJn169enm9+6dWtt3rxZSUlJLuc4W+eVK1cUHx/v8AUAAAAAQG7kduO/adMm9e3bN914qVKlFBsbmyVFOXP69GmlpKSoRIkSDuMlSpRw+tyxsbEZzk9OTtbp06ddznG2zgkTJigoKMj+Vbp06Zt9SQAAAAAAZCu3G39/f/8M93Dv3btXxYsXz5KibsRmszl8b4xJN3aj+dePu7POUaNGKS4uzv515MgRt+oHAAAAACCnuN34d+jQQePGjbMfJm+z2RQTE6OXXnpJjz76aJYXeK1ixYrJ29s73Z74U6dOpdtjnyY0NDTD+T4+PipatKjLOc7W6efnp8DAQIcvAAAAAAByI7cb/3feeUd///23QkJCdOnSJTVu3Fh33XWXChUqpDfffDM7arTLly+fateureXLlzuML1++XJGRkRkuU79+/XTzly1bpjp16sjX19flHGfrBAAAAADgduHj7gKBgYFat26dVqxYoS1btig1NVW1atVSixYtsqO+dIYOHapu3bqpTp06ql+/vj788EPFxMSoX79+kq4ehn/s2DH73QX69eunqVOnaujQoerdu7fWr1+v2bNnO1ytf/DgwWrUqJEmTpyoDh066IcfftAvv/yidevW5chrAgAAAAAgu7jd+Kdp1qyZmjVrlpW1ZErnzp115swZjRs3TidOnFCVKlW0ZMkSlSlTRpJ04sQJxcTE2OeHh4dryZIlGjJkiKZNm6awsDC9//77DqclREZG6ssvv9Qrr7yiV199VeXKldNXX32levXq5fjrAwAAAAAgK9lM2pXu3PDrr79q8uTJio6Ols1m0z333KMXXnghx/b65zbu3D8RAAAAAIBb5U4f6vY5/lOnTlWbNm1UqFAhDR48WIMGDVJgYKAeeOABTZ069aaLBgAAAAAAWc/tPf6lSpXSqFGjNHDgQIfxadOm6c0339Tx48eztMDbAXv8AQAAAAA5KVv3+MfHx6tNmzbpxlu1aqX4+Hh3VwcAAAAAALKR241/+/bt9f3336cb/+GHH9SuXbssKQoAAAAAAGQNt6/qX7FiRb355ptatWqV6tevL0nasGGD/ve//+nFF1/U+++/b587aNCgrKsUAAAAAAC4ze1z/MPDwzO3YptNBw4cuKmibjec4w8AAAAAyEnu9KFu7/E/ePDgTRcGAAAAAAByltvn+AMAAAAAgNuH23v8e/Xq5fLxOXPm3HQxAAAAAAAga7nd+J87d87h+6SkJO3cuVPnz59Xs2bNsqwwAAAAAABw69xu/DO6lV9qaqoGDBigiIiILCkKAAAAAABkjSw5x9/Ly0tDhgzR5MmTs2J1AAAAAAAgi2TZxf3279+v5OTkrFodAAAAAADIAm4f6j906FCH740xOnHihBYvXqynn346ywoDAAAAAAC3zu3Gf+vWrQ7fe3l5qXjx4nr33XdveMV/AAAAAACQs9xu/FeuXJkddQAAAAAAgGzg9jn+Bw8e1F9//ZVu/K+//tKhQ4eyoiYAAAAAAJBF3G78e/Tood9++y3d+MaNG9WjR4+sqAkAAAAAAGQRtxv/rVu3qkGDBunG77vvPkVFRWVFTQAAAAAAIIu43fjbbDYlJCSkG4+Li1NKSkqWFAUAAAAAALKG241/w4YNNWHCBIcmPyUlRRMmTND999+fpcUBAAAAAIBb4/ZV/SdNmqRGjRqpQoUKatiwoSRp7dq1io+P14oVK7K8QAAAAAAAcPPc3uNfqVIlbd++XZ06ddKpU6eUkJCg7t27a8+ePapSpUp21AgAAAAAAG6SzRhjPF3E7S4+Pl5BQUGKi4tTYGCgp8sBAAAAAFicO32o23v8pauH9j/11FOKjIzUsWPHJEmfffaZ1q1bdzOrAwAAAAAA2cTtxn/BggVq3bq1AgICtGXLFl25ckWSlJCQoLfeeivLCwQAAAAAADfP7cZ//PjxmjlzpmbNmiVfX1/7eGRkpLZs2ZKlxQEAAAAAgFvjduO/d+9eNWrUKN14YGCgzp8/nxU1AQAAAACALOJ241+yZEnt27cv3fi6desUERGRJUUBAAAAAICs4Xbj37dvXw0ePFgbN26UzWbT8ePHNX/+fA0bNkwDBgzIjhoBAAAAAMBN8nF3gREjRiguLk5NmzbV5cuX1ahRI/n5+WnYsGEaOHBgdtQIAAAAAABuks0YY25mwYsXL2r37t1KTU1VpUqVVLBgQV28eFH58+fP6hpzPXfunwgAAAAAwK1ypw91+1D/NPnz51edOnVUt25d+fj46L333uMcfwAAAAAAcplMN/6JiYl6+eWXde+99yoyMlILFy6UJH388ceKiIjQu+++q8GDB2dXnQAAAAAA4CZk+hz/sWPHatq0aWrZsqX+97//6fHHH1evXr20atUqTZgwQV27dpWvr2921goAAAAAANyU6cb/66+/1ieffKKHH35Y27ZtU82aNRUfH69du3bJx8ftawQCAAAAAIAckOlD/Y8cOaJ7771XklS9enXly5dPI0eOpOkHAAAAACAXy3Tjn5SUpHz58tm/9/X1VVBQULYUBQAAAAAAsoZbu+tfe+01++36EhMTNX78+HTN/3vvvZd11QEAAAAAgFuS6ca/UaNG2rt3r/37yMhIHThwwGGOzWbLusoAAAAAAMAty3Tjv2rVqmwsAwAAAAAAZIdMn+MPAAAAAABuPzT+AAAAAABYGI0/AAAAAAAWRuMPAAAAAICF0fgDAAAAAGBhN9X4r127Vk899ZTq16+vY8eOSZI+++wzrVu3LkuLAwAAAAAAt8btxn/BggVq3bq1AgICtHXrVl25ckWSlJCQoLfeeivLCwQAAAAAADfP7cZ//PjxmjlzpmbNmiVfX1/7eGRkpLZs2ZKlxQEAAAAAgFvjduO/d+9eNWrUKN14YGCgzp8/nxU1AQAAAACALOJ241+yZEnt27cv3fi6desUERGRJUUBAAAAAICs4Xbj37dvXw0ePFgbN26UzWbT8ePHNX/+fA0bNkwDBgzIjhoBAAAAAMBN8nF3gREjRiguLk5NmzbV5cuX1ahRI/n5+WnYsGEaOHBgdtQIAAAAAABuks0YY25mwYsXL2r37t1KTU1VpUqVVLBgwayu7bYRHx+voKAgxcXFKTAw0NPlAAAAAAAszp0+1O09/mny58+vOnXq3OziAAAAAAAgB2Sq8X/kkUcyvcLvvvvuposBAAAAAABZK1MX9wsKCrJ/BQYG6tdff9XmzZvtj//xxx/69ddfFRQUlG2FAgAAAAAA92Vqj//HH39s//fIkSPVqVMnzZw5U97e3pKklJQUDRgwgPPbAQAAAADIZdy+uF/x4sW1bt06VahQwWF87969ioyM1JkzZ7K0wNsBF/cDAAAAAOQkd/rQTB3qf63k5GRFR0enG4+OjlZqaqq7qwMAAAAAANnI7av69+zZU7169dK+fft03333SZI2bNigt99+Wz179szyAgEAAAAAwM1zu/F/5513FBoaqsmTJ+vEiROSpJIlS2rEiBF68cUXs7xAAAAAAABw89w+x/9a8fHxkpTnz2vnHH8AAAAAQE5ypw91e4//tWhyAQAAAADI3dy+uB8AAAAAALh90PgDAAAAAGBhNP4AAAAAAFgYjT8AAAAAABZ2Uxf3u3DhglavXq2YmBglJiY6PDZo0KAsKQwAAAAAANw6txv/rVu36oEHHtDFixd14cIFFSlSRKdPn1b+/PkVEhJC4w8AAAAAQC7i9qH+Q4YMUbt27XT27FkFBARow4YNOnz4sGrXrq133nknO2oEAAAAAAA3ye3GPyoqSi+++KK8vb3l7e2tK1euqHTp0po0aZJGjx6dHTUCAAAAAICb5Hbj7+vrK5vNJkkqUaKEYmJiJElBQUH2fwMAAAAAgNzB7ca/Zs2a2rx5sySpadOmeu211zR//ny98MILqlq1apYXeK1z586pW7duCgoKUlBQkLp166bz58+7XMYYo7FjxyosLEwBAQFq0qSJdu3aZX/87Nmzev7551WhQgXlz59fd955pwYNGqS4uLhsfS0AAAAAAOQEtxv/t956SyVLlpQkvfHGGypatKj69++vU6dO6cMPP8zyAq/VtWtXRUVFaenSpVq6dKmioqLUrVs3l8tMmjRJ7733nqZOnapNmzYpNDRULVu2VEJCgiTp+PHjOn78uN555x3t2LFDn3zyiZYuXapnnnkmW18LAAAAAAA5wWaMMZ4uIjOio6NVqVIlbdiwQfXq1ZMkbdiwQfXr19eePXtUoUKFdMsYYxQWFqYXXnhBI0eOlCRduXJFJUqU0MSJE9W3b98Mn+ubb77RU089pQsXLsjH58Y3PoiPj1dQUJDi4uIUGBh4C68SAAAAAIAbc6cPdXuP/6VLl3Tx4kX794cPH9aUKVO0bNky9yt1w/r16xUUFGRv+iXpvvvuU1BQkH777bcMlzl48KBiY2PVqlUr+5ifn58aN27sdBlJ9uCcNf1XrlxRfHy8wxcAAAAAALmR241/hw4dNHfuXEnS+fPnVbduXb377rvq0KGDZsyYkeUFpomNjVVISEi68ZCQEMXGxjpdRrp6EcJrlShRwukyZ86c0RtvvOH0aABJmjBhgv06A0FBQSpdunRmXwYAAAAAADnK7cZ/y5YtatiwoSTp22+/VWhoqA4fPqy5c+fq/fffd7uAsWPHymazufxKu5hg2t0ErmWMyXD8Wtc/7myZ+Ph4Pfjgg6pUqZLGjBnjdH2jRo1SXFyc/evIkSOZeakAAAAAAOS4G5/Afp2LFy+qUKFCkqRly5bpkUcekZeXl+677z4dPnzY7QIGDhyoJ554wuWcsmXLavv27Tp58mS6x/7+++90e/TThIaGSrq65z/tgoSSdOrUqXTLJCQkqE2bNipYsKC+//57+fr6Oq3Hz89Pfn5+LmsGAAAAACA3cLvxv+uuu7Rw4UI9/PDD+vnnnzVkyBBJV5vpm7mwXbFixVSsWLEbzqtfv77i4uL0+++/q27dupKkjRs3Ki4uTpGRkRkuEx4ertDQUC1fvlw1a9aUJCUmJmr16tWaOHGifV58fLxat24tPz8/LVq0SP7+/m6/DgAAAAAAciO3D/V/7bXXNGzYMJUtW1b16tVT/fr1JV3d+5/WXGeHihUrqk2bNurdu7c2bNigDRs2qHfv3nrooYccruh/zz336Pvvv5d09RD/F154QW+99Za+//577dy5Uz169FD+/PnVtWtXSVf39Ldq1UoXLlzQ7NmzFR8fr9jYWMXGxiolJSXbXg8AAAAAADnB7T3+jz32mO6//36dOHFC1atXt483b95cDz/8cJYWd7358+dr0KBB9qv0t2/fXlOnTnWYs3fvXsXFxdm/HzFihC5duqQBAwbo3LlzqlevnpYtW2Y/XeGPP/7Qxo0bJV09muFaBw8eVNmyZbPxFQEAAAAAkL1sxhjj6SJud+7cPxEAAAAAgFvlTh/q9h5/Sdq0aZO++eYbxcTEKDEx0eGx77777mZWCQAAAAAAsoHb5/h/+eWXatCggXbv3q3vv/9eSUlJ2r17t1asWKGgoKDsqBEAAAAAANwktxv/t956S5MnT9aPP/6ofPny6d///reio6PVqVMn3XnnndlRIwAAAAAAuEluN/779+/Xgw8+KOnq/ewvXLggm82mIUOG6MMPP8zyAgEAAAAAwM1zu/EvUqSIEhISJEmlSpXSzp07JUnnz5/XxYsXs7Y6AAAAAABwSzLd+Pfq1UsJCQlq2LChli9fLknq1KmTBg8erN69e6tLly5q3rx5thUKAAAAAADcl+nb+Xl7e+vEiRPy8fHR5cuXFRYWptTUVL3zzjtat26d7rrrLr366qsKDg7O7ppzHW7nBwAAAADISe70oZlu/L28vBQbG6uQkJAsKdJKaPwBAAAAADnJnT7UrXP8bTbbLRUGAAAAAABylo87k8uXL3/D5v/s2bO3VBAAAAAAAMg6bjX+r7/+uoKCgrKrFgAAAAAAkMXcavyfeOIJzvEHAAAAAOA2kulz/Dm/HwAAAACA20+mG/9MXvwfAAAAAADkIpk+1D81NTU76wAAAAAAANnArdv5AQAAAACA2wuNPwAAAAAAFkbjDwAAAACAhdH4AwAAAABgYTT+AAAAAABYGI0/AAAAAAAWRuMPAAAAAICF0fgDAAAAAGBhNP4AAAAAAFgYjT8AAAAAABZG4w8AAAAAgIXR+AMAAAAAYGE0/gAAAAAAWBiNPwAAAAAAFkbjDwAAAACAhdH4AwAAAABgYTT+AAAAAABYGI0/AAAAAAAWRuMPAAAAAICF0fgDAAAAAGBhNP4AAAAAAFgYjT8AAAAAABZG4w8AAAAAgIXR+AMAAAAAYGE0/gAAAAAAWBiNPwAAAAAAFkbjDwAAAACAhdH4AwAAAABgYTT+AAAAAABYGI0/AAAAAAAWRuMPAAAAAICF0fgDAAAAAGBhNP4AAAAAAFgYjT8AAAAAABZG4w8AAAAAgIXR+AMAAAAAYGE0/gAAAAAAWBiNPwAAAAAAFkbjDwAAAACAhdH4AwAAAABgYTT+AAAAAABYGI0/AAAAAAAWRuMPAAAAAICF0fgDAAAAAGBhNP4AAAAAAFgYjT8AAAAAABZG4w8AAAAAgIXR+AMAAAAAYGE0/gAAAAAAWBiNPwAAAAAAFkbjDwAAAACAhdH4AwAAAABgYTT+AAAAAABYGI0/AAAAAAAWRuMPAAAAAICF0fgDAAAAAGBhNP4AAAAAAFgYjT8AAAAAABZ2WzX+586dU7du3RQUFKSgoCB169ZN58+fd7mMMUZjx45VWFiYAgIC1KRJE+3atcvp3LZt28pms2nhwoVZ/wIAAAAAAMhht1Xj37VrV0VFRWnp0qVaunSpoqKi1K1bN5fLTJo0Se+9956mTp2qTZs2KTQ0VC1btlRCQkK6uVOmTJHNZsuu8gEAAAAAyHE+ni4gs6Kjo7V06VJt2LBB9erVkyTNmjVL9evX1969e1WhQoV0yxhjNGXKFL388st65JFHJEmffvqpSpQooc8//1x9+/a1z922bZvee+89bdq0SSVLlsyZFwUAAAAAQDa7bfb4r1+/XkFBQfamX5Luu+8+BQUF6bfffstwmYMHDyo2NlatWrWyj/n5+alx48YOy1y8eFFdunTR1KlTFRoaesNarly5ovj4eIcvAAAAAAByo9um8Y+NjVVISEi68ZCQEMXGxjpdRpJKlCjhMF6iRAmHZYYMGaLIyEh16NAhU7VMmDDBfp2BoKAglS5dOrMvAwAAAACAHOXxxn/s2LGy2WwuvzZv3ixJGZ5/b4y54Xn51z9+7TKLFi3SihUrNGXKlEzXPGrUKMXFxdm/jhw5kullAQAAAADISR4/x3/gwIF64oknXM4pW7astm/frpMnT6Z77O+//063Rz9N2mH7sbGxDuftnzp1yr7MihUrtH//fhUuXNhh2UcffVQNGzbUqlWr0q3Xz89Pfn5+LmsGAAAAACA38HjjX6xYMRUrVuyG8+rXr6+4uDj9/vvvqlu3riRp48aNiouLU2RkZIbLhIeHKzQ0VMuXL1fNmjUlSYmJiVq9erUmTpwoSXrppZf07LPPOixXtWpVTZ48We3atbuVlwYAAAAAgMd5vPHPrIoVK6pNmzbq3bu3PvjgA0lSnz599NBDDzlc0f+ee+7RhAkT9PDDD8tms+mFF17QW2+9pbvvvlt333233nrrLeXPn19du3aVdPWogIwu6HfnnXcqPDw8Z14cAAAAAADZ5LZp/CVp/vz5GjRokP0q/e3bt9fUqVMd5uzdu1dxcXH270eMGKFLly5pwIABOnfunOrVq6dly5apUKFCOVo7AAAAAACeYDPGGE8XcbuLj49XUFCQ4uLiFBgY6OlyAAAAAAAW504f6vGr+gMAAAAAgOxD4w8AAAAAgIXR+AMAAAAAYGE0/gAAAAAAWBiNPwAAAAAAFkbjDwAAAACAhdH4AwAAAABgYTT+AAAAAABYGI0/AAAAAAAWRuMPAAAAAICF0fgDAAAAAGBhNP4AAAAAAFgYjT8AAAAAABZG4w8AAAAAgIXR+AMAAAAAYGE0/gAAAAAAWBiNPwAAAAAAFkbjDwAAAACAhdH4AwAAAABgYTT+AAAAAABYGI0/AAAAAAAWRuMPAAAAAICF0fgDAAAAAGBhNP4AAAAAAFgYjT8AAAAAABZG4w8AAAAAgIXR+AMAAAAAYGE0/gAAAAAAWBiNPwAAAAAAFkbjDwAAAACAhdH4AwAAAABgYTT+AAAAAABYGI0/AAAAAAAWRuMPAAAAAICF0fgDAAAAAGBhNP4AAAAAAFgYjT8AAAAAABZG4w8AAAAAgIXR+AMAAAAAYGE0/gAAAAAAWBiNPwAAAAAAFkbjDwAAAACAhdH4AwAAAABgYTT+AAAAAABYGI0/AAAAAAAWRuMPAAAAAICF0fgDAAAAAGBhNP4AAAAAAFgYjT8AAAAAABZG4w8AAAAAgIXR+AMAAAAAYGE0/gAAAAAAWBiNPwAAAAAAFkbjDwAAAACAhdH4AwAAAABgYT6eLsAKjDGSpPj4eA9XAgAAAADIC9L6z7R+1BUa/yyQkJAgSSpdurSHKwEAAAAA5CUJCQkKCgpyOcdmMvPxAFxKTU3V8ePHVahQIdlsNk+Xo/j4eJUuXVpHjhxRYGCgp8vJdcjHObJxjXycIxvXyMc5snGNfJwjG9fIxzXycY5sXMtN+RhjlJCQoLCwMHl5uT6Lnz3+WcDLy0t33HGHp8tIJzAw0OMbY25GPs6RjWvk4xzZuEY+zpGNa+TjHNm4Rj6ukY9zZONabsnnRnv603BxPwAAAAAALIzGHwAAAAAAC6PxtyA/Pz+NGTNGfn5+ni4lVyIf58jGNfJxjmxcIx/nyMY18nGObFwjH9fIxzmyce12zYeL+wEAAAAAYGHs8QcAAAAAwMJo/AEAAAAAsDAafwAAAAAALIzGHwAAAAAAC6PxBwAAAADAwmj8AQC4DXATHrjrypUrni4hVzt16pSnS7gtpKamerqEXI3fzc6RTe5C4490+AWfsZSUFCUmJnq6jFyP7Sc9th3X/vnnH509e1bnzp3zdCm5zsGDB7Vp0yZJks1m83A1uc/WrVs1bdo0T5eRK+3Zs0djxozRli1bPF1KrrRnzx5Vr15d//73vz1dSq5z6tQpbd++Xb/99pskycvLiwbuGpcvX9Y///yj5ORkSVd/N/O3z1UXL15UXFyc/W8essmYpzKh8Yck6dChQ5o7d65SUlLk5eXFm/Q6e/bsUd++fdWsWTP1799fy5cv93RJuQrbj3NsO67t2rVLjz/+uBo0aKDHHntMs2bN8nRJucapU6d09913q3379vrll188XU6us337dtWuXVuHDx/2dCm5zo4dO3TffffpypUrCg4OdniMBk6KiopSnTp1dPLkST4Yuc6OHTvUsmVLPf7443r00UfVq1cvSXzwmGbnzp16/PHH1bBhQz3++ON65ZVXJF39cCSv27lzpx5++GHdd9996tChg15++WVJZJMmN/ytzE8C+vPPP1WrVi2NGzdOH330Ec3bdXbt2qVGjRopOTlZDRo00O+//64pU6ZwiOD/x/bjHNuOazt37lTDhg1VoUIFjR49WiVKlNDXX3+thIQET5eWa4SHh6tp06YaOnQoHxpdY9u2bapfv76GDx+uSZMmebqcXOXMmTN65pln9Oyzz2ry5MkKDw9XXFycjh07JokGbtu2bWrQoIHGjh2rlStXat68eVq2bJmny8oV/vrrLzVr1kwdOnTQvHnzNH78eG3YsEExMTH2OXn5g6O9e/eqcePGuvvuuzV06FBVqlRJM2fOVMeOHRUXFycp7+azf/9+NW7cWBUqVNALL7ygypUra+7cuWrSpIni4+Ml5d1spFz0t7JBnnb27FnTtm1b88gjj5jHHnvMREZGmhkzZpjk5GRjjDEpKSkertCzYmNjzb333muGDh1qHztw4IApWLCg+eabbzxYWe7A9uMc245rx44dM5UqVTIjR460j61Zs8a0bt3aHDx40MTGxnqwutzh8uXLpk6dOmbatGnmySefNJUrVzarV682xhizb9++PPv+Onz4sLHZbOall14yxhiTmJhoJk6caLp162b69+9vZs+e7eEKPeuvv/4yNWrUMEePHjWJiYmmW7duplatWubuu+827du3N+fPnzfGGJOamurhSnPe9u3bjZeXlxk9erQxxphTp06ZZs2amX79+pnExMQ8+54y5ur2MHbsWNOpUyf72PHjx03jxo3NunXrzM8//5yn80lOTjZDhw41ffr0sY9dvHjRdOzY0dhsNtOsWTP7eF58b82YMcM0adLEXLlyxRhjTFJSklm/fr25++67TWRkpH1eXtyGctPfyuzxz+OSk5NVrlw59e7dW7NmzVLZsmX12WefadasWfZPo0we/oRu27ZtuuOOO9SjRw9JUlJSksLDw9WoUSP7+ch5OR+2H+fYdlw7evSo2rdvrz59+tjHli1bpq1bt+r+++9Xu3bt9NRTT3mwQs9KTk6Wr6+vSpUqpbp162r06NGqWbOmBg8ebN/TffnyZU+X6RFHjx5V4cKF7Xuw27Rpo++++06XLl3Snj17NGnSJA0cONDDVXrOsWPH9M8//6hUqVLq1q2bzpw5o2HDhumVV17R3r171bx5c0l5b89/UlKS/vOf/2js2LF68803JUnFixdX06ZN9cUXX+j8+fN5+v8sm82mgwcP6siRI/axTz/9VJs2bVLfvn31zDPPqHbt2vYjsvJaTt7e3tq3b58uXLgg6eo52gEBAWrcuLH69OmjP//8Uz179pSU995bknT48GEdPXpU+fLlkyT5+Pjovvvu09dff61jx47p4YcflpQ3D/vPVX8r59hHDMi1Tp48af908syZM6Zr164mMjLSTJ8+3f4pVGJioidL9Jj9+/ebadOmpRt/4IEHzJgxY3K+oFwkbZth+8nYvn372HZcuHDhgjl06JD9+7ffftsEBASYTz/91Kxevdp89tlnpkyZMmbmzJkerDLnXb+naNCgQWbChAnGGGN27dplIiIiTL58+cz777/vifJyheTkZLNmzRoTGhpqbDabefTRR82xY8eMMcb8888/5t133zUVKlQwa9eu9XClOStt24mLizMRERFm4MCBpm3btiYqKso+JyYmxtxxxx159nfQ6dOn7f9O+//p0qVLpnLlyub555/Pk3sjjTH2PY/ffPONCQ8PN82bNze9evUyfn5+5scffzSHDx82x48fN+XLlzdPP/20Z4v1gOTkZJOUlGSGDRtm2rVrZ7Zs2WKMMebgwYOmSJEi5sMPPzT/+c9/TI0aNfLs0Wpr1qwxZcuWNV9//bXDeEpKivnuu+/MPffcY1atWuWh6jwvt/ytnPc+doEkx09qQ0JCZLPZlJSUpCJFimjq1KkqU6aM5s2bpw8//FCXLl3S8OHDNXz4cA9WnLNSU1NljFFERIQGDBggyTEzb29vh6u0z5gxQ/PmzcvxOj3h+vORihYtyvbz/6Vlk5qaqnLlyqlfv34O4xLbjnT1vZQ/f37dcccd9sfCw8P1ww8/qHv37mrUqJHatWun/Pnz68SJE54qN0dd/75KSkqSJBUqVEh//vmnJOmdd95RfHy8mjVrpo8//lhLlizJ8To95dptx9vbW/fdd5+++OILde7cWQMHDlRYWJiMMSpQoIA6deqkQ4cOad++fR6uOmdcv+34+vqqa9euWrNmjbZu3arSpUtLurrXqVSpUqpVq1aeuoPGtb+XixYtqpSUFEn/t+fRx8dHjRs31saNG3Xx4kVJeWdvdlo2aVncf//9eu+991S/fn2lpqZq2LBhevDBB1W6dGmVLFlSTZo00ZkzZzxZco66Nh8fHx898sgjOnjwoHr27KkWLVqoUqVKevzxx9W7d289+OCD2rVrlw4ePOjhqnPOte+T8PBwVaxYUV988YU2bNhgH/fy8lJkZKTOnj2rvXv3eqJMj8mNvZZPtq4duc6JEyeUkpKiO+64Q8YYh8ORfH19lZqaquDgYE2fPl3PPfec5s+fr08++UTbt2/XunXrPFh5zrg2n9TUVId8bDabPbMiRYqocOHCkqTRo0fr3XffVVRUlGeKzkF79+7VRx99pHPnzunOO+9U3759VaJECUlXt5+UlJQ8u/1cm03p0qXVr18/ezZpF3Dx8vJi28lg25GkTp062f9tjJGPj4/Cw8MVHh5uH7Pq4ZOusunQoYPmzJmjLl26aNWqVVq9erUuX76sMWPG6M0331Tjxo2VP39+y2Yjpc+nT58+Cg0N1f3336+yZcuqZMmS9rlpf2hVr15dZcuW9VDFOcdZNk8++aQ2bdqkHTt26N1339Wbb74pH5+rf/Llz59fhQoVkmTt95V04987ab9rhg0bpipVqujDDz/U0KFDLZ1Jmuv/z+rbt69CQ0PVsWNHdezYUZ06ddLJkycl/d+h6xcuXFBoaKhSUlLk7e3tyfKz3fX59OnTR/Xr19fnn3+u5cuX68yZM3r66afVrVs3GWN0+vRpVapUSWFhYZ4uPdtl9LfyHXfcoddee03du3fXe++9pwEDBqhJkyaSrja9lSpVkr+/v2cLzyG5utfK9mMKkGtER0eb0qVLmwceeMDs37/fGJPxBUjSDjmJjY01YWFhJjg42Gzbti1Ha/WEzOZjjDGdOnUykyZNMm+88YYJCAgwmzdvzslSPWLXrl0mKCjIdO7c2TRv3tzUrVvXFCtWzPz0008OOeXF7Sez2RjDtuMsn+tzeuWVV0xERITD6QBW5CobY4yJiooyNpvNhIaGmj/++MO+3KZNm8zRo0c9VXaOySifokWL2vPJyCuvvGIqVqxoP/zfqpxls3jxYmOMMXv27DEPP/ywKVasmHnqqafMnDlzzIABA0yRIkXM3r17PVx99nO17Vz/f1ZycrIZNGiQady4cZ44VNtVNmmH/U+ZMsU0a9bMzJ071+zevduMHDnSFCtWzERHR3u4+uyXUT5FihSxv7cyMnz4cFOzZk2H00msKKO/lZOTk+1/+61Zs8bUrFnTNGrUyLz22mvml19+MYMGDTLBwcH2+VaW23stGv884ujRo6ZBgwamRo0apkmTJqZz584uN8jLly+b3r17m4IFC5odO3bkdLk5zt18OnfubHx8fEz+/PnzROOWnJxsnnjiCdOlSxdjzNVMYmNjTa9evUz+/PnNt99+ax83Jm9tP5nNJg3bjut8Nm3aZAYPHmyCg4PN1q1bPVBxznGVTUBAgP1cyV9++cWeRV66WvSN8rl+29m4caN57rnnTOHChR3Oa7ciV9n4+/vbt50DBw6YmTNnmmrVqpm6deuaFi1aWD4bY9z/P8sYYz799FMTEhJizpw545Gac0pms4mKijKPPPKIKV68uClfvrypWrWq5X8nG5P53ztpjduWLVvM008/bQoXLmz5fFz9rXxt879t2zYzfPhwc+edd5rKlSubWrVqWT4bY26PXotD/fOIbdu2ycfHRzNnztSuXbv06aefavTo0XrrrbcUERFhPww5jZ+fn44dO6bly5erSpUqHqw8Z7iTjzFGRYoUUdGiRfXrr7+qcuXKHq4++9lsNv3999+6//777WMlSpTQ7Nmz5e/vrx49eigiIkI1a9ZUampqntp+3MkmOTmZbUfO8zl58qSWLFmiAwcOaPXq1apataoHK89+N8qmZ8+eKleunJo3b24/hD0vHIKcxp1tJzY2VgsXLtTevXu1evVqVatWzYOVZ7/MbDsRERGqXbu2+vbtq759+yoxMVGpqal54nBbd38v+/j4qHv37mrbtq2KFCniwcqz342yefrpp1W2bFnVrl1b//nPf3TixAklJiaqXLlyCgkJ8WDlOcOdbefKlSvy8fGRn5+f1qxZY/n/s270t3JycrIkqVq1apo4caLGjh2rf/75R/7+/goMDPRw9dnvtui1cuTjBeQKK1eutP971qxZplGjRqZz585m3759xpi8tScpI5nJJy2jrVu35olDlq7VtWtXU7t2bXsG195/tGPHjqZWrVrm4sWLnizRYzKTzYULF4wxxuzcuZNtx0U+p0+fNufOnfNUqTnuRtnUrFkzz76vjHFv2zl16pTl99ZeKzPbTlo2eRH/Zzl3o2xq1Khh/vnnH0+W6FHu/N4xJm/duehGfyunpKTYc8uLd8nI7b0WV/XPQ9IusiFJzz77rLp3767jx4/r5Zdf1oEDB2Sz2TR27Fj9/fffnivSgzKbz8mTJ1WjRg1FRER4rtgcZP7/nsYnn3xSqampGj9+vJKSkuTt7a3k5GR5eXmpd+/eOnv2rGJiYjxcbc66mWwqV67MtuMin6JFi9ovfmhlmc3m3Llzee59Jd3ctlO8eHHL762V3Nt2rr0ne17B/1nOZTab8+fP6+jRox6uNue5s+1c+97y9fX1VMk57kZ/K3t5een111/X33//7bB3O6/I7b0Wh/rnQWmHmjzzzDOy2Wz69NNP9fLLL8vX11fz5s3T448/ruLFi3u6TI+5UT6dOnVyuCqw1aUdWtysWTPdf//9+u9//6v8+fPrueeesx8yWqZMGUnSlStXPFanJ7iTzbW38MsryMc53leuse04x7bjGvk4RzaukU/m0Uu4lmvz8dixBshRaYcppUlKSrL/+8MPPzQFChTIExcmcYZ8XLty5Yoxxph//vnH9OvXz9StW9f07t3bnD9/3hw7dsyMHj3alC9f3pw6dcrDleY8snGNfJwjG9fIxzmycY18nCMb18jHOf5Wdu12yIfG34KuP38kbUM8evSomTVrln087dybQYMGmcDAQLNz586cK9KDyMc1Z/kcOnTIfPPNN+bKlStmwoQJpkaNGsbb29tUrVrVlCxZ0uFWY1ZFNq6Rj3Nk4xr5OEc2rpGPc2TjGvk4x9/Krt2u+dD4W0jahUbi4uLsY2kb5qFDh0ypUqXMSy+95LDMr7/+agoVKpQnfomRj2v//POPSU5OdpnPsGHDjDFXf8ElJCSY77//3qxdu9bExMR4pOacQjaukY9zZOMa+ThHNq6Rj3Nk4xr5OJeZbPhb+fbNh8bfInbs2GHatGljmjZtamrWrGlmzZplPwzp1KlTpnjx4qZfv34ZXk0yLxyuRD6u7dixwzRr1szce++9pnLlyuaDDz4wsbGxxhhj/v77b5f5WB3ZuEY+zpGNa+TjHNm4Rj7OkY1r5OPcrWTD38q3Rz40/hawd+9eU6xYMfPiiy+aOXPmmNdff93YbDbTvXt388cff5jz58+b9957L91tNdK+t/ovN/Jxbf/+/SY4ONgMGjTI/Oc//zEvv/yy8fPzM08//bTZvHmziYuLM++99166c5fyArJxjXycIxvXyMc5snGNfJwjG9fIx7mbzYa/lW+vfGj8LWDw4MGma9euDmNPPvmkyZcvn+natavlD0u6EfJx7d133zUNGjRwGPv5559N+fLlTadOncyBAwc8VJnnkY1r5OMc2bhGPs6RjWvk4xzZuEY+zpGNa1bJJ+/dYNFijDHat2+fihYtKkm6ePGiJKlChQpq27atFi9erFmzZtnn5jXkc2MXLlxQYmKiUlNTlZKSopSUFLVq1UpTp07VunXrNHXqVEl5Mx+ycY18nCMb18jHObJxjXycIxvXyMc5snHNMvl44MMGZLGRI0ea8PBwc/z4cWPM1StKBgYGmjVr1pjZs2ebAgUKmMOHD3u4Ss8hH9e++eYb4+3tbTZt2mSMuXr7kbRDkr7++mvj5eVl1q9f78kSPYZsXCMf58jGNfJxjmxcIx/nyMY18nGObFyzSj40/repa88V2bRpk2ndurUpWLCgad++vcmfP7/p27evMcaYffv25Zlbj1yLfDIvKSnJdOrUyZQvX95ER0cbY/7vPraJiYmmUqVKZurUqZ4s0WPIxjXycY5sXCMf58jGNfJxjmxcIx/nyMY1q+TDof63mZMnT0qSbDabUlNTJUl16tTRtGnT9Prrr6tWrVr64IMPNHPmTElSfHy8ChcurPz583us5pxEPq4dOnRI//73vzV27FjNmzdPkuTj46MBAwaobNmyeuqpp7Rnzx7ly5dP0tUcAwICFBAQ4MmycwTZuEY+zpGNa+TjHNm4Rj7OkY1r5OMc2bhm5Xx8PF0AMi86OlqVK1fWQw89pEWLFsnLy0vJycny8fFRuXLlNHTo0HTLzJ8/XwEBAQoJCfFAxTmLfFzbsWOH2rZtq4oVKyouLk7bt2/XgQMH9Nprr6lx48a6cuWKpkyZosjISL3zzjsKDAzUH3/8oYMHD6pJkyaeLj9bkY1r5OMc2bhGPs6RjWvk4xzZuEY+zpGNa5bPx9OHHCBzTpw4YRo0aGAaN25sQkNDTceOHe2PXX8bOmOM+eWXX0z//v1NYGCg2bp1aw5W6hnk49qhQ4dMuXLlzIgRI0xqaqqJj483H3zwgalUqZL566+/7PP27dtnRowYYcLCwkylSpXMvffea7Zs2eLByrMf2bhGPs6RjWvk4xzZuEY+zpGNa+TjHNm4lhfyofG/TSxcuNA88cQTZs2aNWbFihUmJCTEZXO7ceNG061bN7Nz586cLtUjyMe5lJQUM3HiRNOmTRsTFxdnH9+8ebMpXry42b17d7pljhw5Ys6dO2fOnTuXg5XmPLJxjXycIxvXyMc5snGNfJwjG9fIxzmycS2v5MOh/reJxo0by8/PTw0bNpQkffnll3riiSfUsWNHLVy4UF5eXvZbSNhsNtWtW1ezZs2Sn5+fJ8vOMeTjnJeXl+rUqaPU1FQFBgZKunq7kWrVqqlQoUI6d+5cumXCwsLk5WX9S4CQjWvk4xzZuEY+zpGNa+TjHNm4Rj7OkY1reSYfj3zcgFuWmppqVq5caUJCQkyHDh3s4zNnzjT/+9//7HPyKvJxlJiYaP/3ta+7XLly5pdffrF/v3z58gxPjbAysnGNfJwjG9fIxzmycY18nCMb18jHObJxLS/kc5t9TJF3xMTEaPHixfroo4904sQJXbx4UZLsV6q32Wxq1KiRvvrqK61fv16PPPKIBg4cqP79+ys0NNQ+x6rIx7W0fGbNmqUTJ04oMTFRkpSSkiKbzabk5GRduHBBycnJ9quQvvLKK2rVqpViY2M9WXq2IxvXyMc5snGNfJwjG9fIxzmycY18nCMb1/JkPp7+5AHpbdu2zZQoUcLUrFnTFC5c2JQuXdoMGzbMHDhwwBiT/nz15cuXG5vNZooUKWI2b97siZJzFPm4dqN8UlNTTVJSkrlw4YIpU6aM2bp1q3nrrbdMwYIFzaZNmzxcffYiG9fIxzmycY18nCMb18jHObJxjXycIxvX8mo+NP65zLlz50zt2rXN8OHDzdmzZ40xxrz++uumYcOGpn379varSqYdgpKSkmJ69+5tChQoYHbt2uWxunMK+biW2XzS1KpVy9x7770mX758t/UvsswgG9fIxzmycY18nCMb18jHObJxjXycIxvX8nI+NP65zOHDh02ZMmXMzz//7DD+6aefmkaNGpmuXbua48eP28dXrVplqlWrdttviJlFPq5lJp8TJ04YY4w5e/asCQoKMj4+Pmb79u2eKDdHkY1r5OMc2bhGPs6RjWvk4xzZuEY+zpGNa3k5H87xz2W8vb0VEBCg48ePS5KSk5MlSd27d9eTTz6pnTt3avny5fb5tWvX1i+//KI6dep4pN6cRj6uZSafZcuWSZKCg4M1bdo07dixQ1WrVvVYzTmFbFwjH+fIxjXycY5sXCMf58jGNfJxjmxcy8v52Iz5//c4Q67Rvn17HTlyRCtXrlThwoWVnJwsH5+rd158/PHHdezYMf32228yxlj6AnXOkI9rmc1HunoxxNvuViS3gGxcIx/nyMY18nGObFwjH+fIxjXycY5sXMur+VjjVdzGLly4oISEBMXHx9vH5syZo7i4OHXq1EmJiYn2DVGSWrduLWOMEhMT80RTSz6u3Ww+V65ckSTL/CLLCNm4Rj7OkY1r5OMc2bhGPs6RjWvk4xzZuEY+/8c6r+Q2tHv3bj3yyCNq3LixKlasqPnz5ys1NVXFihXT559/rj179qhVq1bau3evLl++LEn6/fffVahQIeWFAzXIx7VbycfqyMY18nGObFwjH+fIxjXycY5sXCMf58jGNfK5Tg5fUwD/365du0zRokXNkCFDzOeff26GDh1qfH19zZYtW+xzduzYYapWrWrKlStn6tSpY9q1a2cKFSpkoqKiPFh5ziAf18jHObJxjXycIxvXyMc5snGNfJwjG9fIxzmycY180uMcfw84e/asunTponvuuUf//ve/7ePNmjVT1apV9e9//9vh/PRp06bp6NGjCggIUOfOnVWhQgVPlZ4jyMc18nGObFwjH+fIxjXycY5sXCMf58jGNfJxjmxcI5+M+dx4CrJaUlKSzp8/r8cee0zS/100IiIiQmfOnJEk2Ww2paSkyNvbW88995wny81x5OMa+ThHNq6Rj3Nk4xr5OEc2rpGPc2TjGvk4RzaukU/GOMffA0qUKKF58+apYcOGkqSUlBRJUqlSpRwuIOHt7a2EhAT793nl4AzycY18nCMb18jHObJxjXycIxvXyMc5snGNfJwjG9fIJ2M0/h5y9913S7r6CZSvr6+kqxvlyZMn7XMmTJigWbNm2e8vmReuUp+GfFwjH+fIxjXycY5sXCMf58jGNfJxjmxcIx/nyMY18kmPQ/09zMvLy36Oic1mk7e3tyTptdde0/jx47V161aHW0zkNeTjGvk4RzaukY9zZOMa+ThHNq6Rj3Nk4xr5OEc2rpHP/2GPfy6QdliJt7e3SpcurXfeeUeTJk3S5s2bVb16dQ9X53nk4xr5OEc2rpGPc2TjGvk4RzaukY9zZOMa+ThHNq6Rz1V54+ONXC7tXBNfX1/NmjVLgYGBWrdunWrVquXhynIH8nGNfJwjG9fIxzmycY18nCMb18jHObJxjXycIxvXyOcq9vjnIq1bt5Yk/fbbb6pTp46Hq8l9yMc18nGObFwjH+fIxjXycY5sXCMf58jGNfJxjmxcy+v52IzVL194m7lw4YIKFCjg6TJyLfJxjXycIxvXyMc5snGNfJwjG9fIxzmycY18nCMb1/JyPjT+AAAAAABYGIf6AwAAAABgYTT+AAAAAABYGI0/AAAAAAAWRuMPAAAAAICF0fgDAAAAAGBhNP4AAAAAAFgYjT8AALeZsWPHqkaNGp4uI1Nmz56tVq1aebqMHHHs2DGVKVNGLVu21PHjx1WpUiW3lt+xY4fuuOMOXbhwIZsqBADkVTT+AADkoNjYWD3//POKiIiQn5+fSpcurXbt2unXX3/1dGmSsvZDhStXrui1117Tq6++6rB+m82mNm3apJs/adIk2Ww2NWnSJEueP6u99dZb8vb21ttvv53h4ytWrFC3bt3UoUMHNWjQQM8884xb669atarq1q2ryZMnZ0W5AADY+Xi6AAAA8opDhw6pQYMGKly4sCZNmqRq1aopKSlJP//8s5577jnt2bPHY7UZY5SSkpKl61ywYIEKFiyohg0bOoyXLFlSK1eu1NGjR3XHHXfYxz/++GPdeeedWVpDVvr44481YsQIzZkzRy+99FK6x7t162b/98CBA2/qOXr27Kl+/fpp1KhR8vb2vulaAQC4Fnv8AQDIIQMGDJDNZtPvv/+uxx57TOXLl1flypU1dOhQbdiwwT4vJiZGHTp0UMGCBRUYGKhOnTrp5MmT6db32WefqWzZsgoKCtITTzyhhIQE+2NXrlzRoEGDFBISIn9/f91///3atGmT/fFVq1bJZrPp559/Vp06deTn56fPPvtMr7/+urZt2yabzSabzaZPPvlEkhQXF6c+ffooJCREgYGBatasmbZt2+by9X755Zdq3759uvGQkBC1atVKn376qX3st99+0+nTp/Xggw+mm//xxx+rYsWK8vf31z333KPp06fbH0tMTNTAgQNVsmRJ+fv7q2zZspowYUKG9axZs0a+vr6KjY11GH/xxRfVqFEjl69l9erVunTpksaNG6cLFy5ozZo1Do+nHSlxKz8TSWrdurXOnDmj1atXu6wHAAB30PgDAJADzp49q6VLl+q5555TgQIF0j1euHBhSVf3vHfs2FFnz57V6tWrtXz5cu3fv1+dO3d2mL9//34tXLhQP/74o3788UetXr3a4RD0ESNGaMGCBfr000+1ZcsW3XXXXWrdurXOnj3rsJ4RI0ZowoQJio6OVqtWrfTiiy+qcuXKOnHihE6cOKHOnTvLGKMHH3xQsbGxWrJkif744w/VqlVLzZs3T7e+a61du1Z16tTJ8LFevXrZP1SQpDlz5ujJJ59Uvnz5HObNmjVLL7/8st58801FR0frrbfe0quvvmr/0OD999/XokWL9PXXX2vv3r2aN2+eypYtm+FzNmrUSBEREfrss8/sY8nJyZo3b5569uzp9HVIV69V0KVLF/n6+qpLly6aPXt2ujlZ8TPJly+fqlevrrVr17qsBwAAtxgAAJDtNm7caCSZ7777zuW8ZcuWGW9vbxMTE2Mf27Vrl5Fkfv/9d2OMMWPGjDH58+c38fHx9jnDhw839erVM8YY888//xhfX18zf/58++OJiYkmLCzMTJo0yRhjzMqVK40ks3DhQofnHzNmjKlevbrD2K+//moCAwPN5cuXHcbLlStnPvjggwxfx7lz54wks2bNmgzXn5iYaEJCQszq1avNP//8YwoVKmS2bdtmBg8ebBo3bmyfX7p0afP55587rOONN94w9evXN8YY8/zzz5tmzZqZ1NTUDOu43sSJE03FihXt3y9cuNAULFjQ/PPPP06XiYuLM/nz5zdRUVHGGGO2bt1q8ufPb+Li4hxe163+TNI8/PDDpkePHpl6PQAAZAZ7/AEAyAHGGEmSzWZzOS86OlqlS5dW6dKl7WOVKlVS4cKFFR0dbR8rW7asChUqZP++ZMmSOnXqlKSre56TkpLUoEED++O+vr6qW7euwzokOd0jf60//vhD//zzj4oWLaqCBQvavw4ePKj9+/dnuMylS5ckSf7+/hk+7uvrq6eeekoff/yxvvnmG5UvX17VqlVzmPP333/ryJEjeuaZZxyed/z48fbn7dGjh6KiolShQgUNGjRIy5Ytc/laevTooX379tlPrZgzZ446deqU4VEYaT7//HNFRESoevXqkqQaNWooIiJCX375pcO8rPqZBAQE6OLFiy5fBwAA7uDifgAA5IC7775bNptN0dHR6tixo9N5xpgMPxy4ftzX19fhcZvNptTUVPvctLEbrdtVw5smNTVVJUuW1KpVq9I9lnaKwvWKFi0qm82mc+fOOV1vr169VK9ePe3cuVO9evXK8Hmlq4f716tXz+GxtAvf1apVSwcPHtRPP/2kX375RZ06dVKLFi307bffZvicISEhateunT7++GNFRERoyZIlGb6ua82ZM0e7du2Sj8///dmUmpqq2bNnq0+fPvaxrPqZnD17VuXKlXNZEwAA7mCPPwAAOaBIkSJq3bq1pk2bluF92s+fPy/p6t79mJgYHTlyxP7Y7t27FRcXp4oVK2bque666y7ly5dP69ats48lJSVp8+bNN1xHvnz50l3dv1atWoqNjZWPj4/uuusuh69ixYo5XU+lSpW0e/dup89VuXJlVa5cWTt37lTXrl3TPV6iRAmVKlVKBw4cSPe84eHh9nmBgYHq3LmzZs2apa+++koLFixwee2BZ599Vl9++aU++OADlStXzmEv/PV27NihzZs3a9WqVYqKirJ/rVmzRps2bdLOnTudLnstd34mO3fuVM2aNTO1XgAAMoM9/gAA5JDp06crMjJSdevW1bhx41StWjUlJydr+fLlmjFjhqKjo9WiRQtVq1ZNTz75pKZMmaLk5GQNGDBAjRs3ztRh+dLVvfj9+/fX8OHDVaRIEd15552aNGmSLl68eMN7y5ctW1YHDx5UVFSU7rjjDhUqVEgtWrRQ/fr11bFjR02cOFEVKlTQ8ePHtWTJEnXs2NFpXa1bt9a6dev0wgsvOH2+FStWKCkpyemRA2PHjtWgQYMUGBiotm3b6sqVK9q8ebPOnTunoUOHavLkySpZsqRq1KghLy8vffPNNwoNDXW6vrS6goKCNH78eI0bN85lHrNnz1bdunUzvOp//fr1NXv2bE2ePNnlOqTM/0wOHTqkY8eOqUWLFjdcJwAAmcUefwAAckh4eLi2bNmipk2b6sUXX1SVKlXUsmVL/frrr5oxY4akq4eCL1y4UMHBwWrUqJFatGihiIgIffXVV24919tvv61HH31U3bp1U61atbRv3z79/PPPCg4Odrnco48+qjZt2qhp06YqXry4vvjiC9lsNi1ZskSNGjVSr169VL58eT3xxBM6dOiQSpQo4XRdvXv31pIlSxQXF+d0ToECBVw26c8++6w++ugjffLJJ6pataoaN26sTz75xL7Hv2DBgpo4caLq1Kmje++9V4cOHdKSJUvk5eX8TxwvLy/16NFDKSkp6t69u9N5iYmJmjdvnh599NEMH3/00Uc1b948JSYmOl3HtTLzM/niiy/UqlUrlSlTJlPrBAAgM2wm7aQzAACALNapUyfVrFlTo0aN8nQpDnr37q2TJ09q0aJFni7F7sqVK7r77rv1xRdfuDz9AAAAd7HHHwAAZJt//etfKliwoKfLsIuLi9Mvv/yi+fPn6/nnn/d0OQ4OHz6sl19+maYfAJDl2OMPAADyjCZNmuj3339X3759M3VuPgAAVkDjDwAAAACAhXGoPwAAAAAAFkbjDwAAAACAhdH4AwAAAABgYTT+AAAAAABYGI0/AAAAAAAWRuMPAAAAAICF0fgDAAAAAGBhNP4AAAAAAFjY/wN1GC4FVgM7ZAAAAABJRU5ErkJggg==", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Visualización de resultados\n", + "\n", + "import matplotlib.pyplot as plt\n", + "\n", + "\n", + "plt.figure(figsize=(12, 6))\n", + "sns.barplot(data=cohort_revenue, x='Cohorte', y='Ingresos Totales', color='blue')\n", + "plt.title('Ingresos Totales por Cohorte')\n", + "plt.xlabel('Cohorte (Mes y Año)')\n", + "plt.ylabel('Ingresos Totales')\n", + "plt.xticks(rotation=45)\n", + "plt.show()\n", + "\n", + "plt.figure(figsize=(12, 6))\n", + "sns.barplot(data=cohort_metrics, x='Cohorte', y='Tasa de Recuperación Exitosa', color='green')\n", + "plt.title('Tasa de Recuperación Exitosa por Cohorte')\n", + "plt.xlabel('Cohorte (Mes y Año)')\n", + "plt.ylabel('Tasa de Recuperación Exitosa')\n", + "plt.xticks(rotation=45)\n", + "plt.show()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 352, + "id": "099099eb-f333-4f78-b678-4ff55423cc2b", + "metadata": {}, + "outputs": [], + "source": [ + "# Puesto que todas las " + ] + }, + { + "cell_type": "code", + "execution_count": 354, + "id": "4df8bdeb-2513-469e-b25d-af7382c428c7", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idamountstatuscreated_atupdated_atuser_idmoderated_atdeleted_account_idreimbursement_datecash_request_received_datemoney_back_datetransfer_typesend_atrecovery_statusreco_creationreco_last_update
05100.0rejected2019-12-10 19:05:21.596873+002019-12-11 16:47:42.40783+00804.02019-12-11 16:47:42.405646+00NaN2020-01-09 19:05:21.596363+00NaNNaNregularNaNNaNNaNNaN
170100.0rejected2019-12-10 19:50:12.34778+002019-12-11 14:24:22.900054+00231.02019-12-11 14:24:22.897988+00NaN2020-01-09 19:50:12.34778+00NaNNaNregularNaNNaNNaNNaN
27100.0rejected2019-12-10 19:13:35.82546+002019-12-11 09:46:59.779773+00191.02019-12-11 09:46:59.777728+00NaN2020-01-09 19:13:35.825041+00NaNNaNregularNaNNaNNaNNaN
31099.0rejected2019-12-10 19:16:10.880172+002019-12-18 14:26:18.136163+00761.02019-12-18 14:26:18.128407+00NaN2020-01-09 19:16:10.879606+00NaNNaNregularNaNNaNNaNNaN
41594100.0rejected2020-05-06 09:59:38.877376+002020-05-07 09:21:55.34008+007686.02020-05-07 09:21:55.320193+00NaN2020-06-05 22:00:00+00NaNNaNregularNaNNaNNaNNaN
...................................................
2396520616100.0money_back2020-10-12 13:54:11.686225+002021-02-06 20:17:49.292493+0013681.0NaNNaN2021-02-06 11:00:00+002020-10-132021-02-06 20:17:49.257521+00instant2020-10-12 13:54:24.352856+00NaNNaNNaN
239662524350.0money_back2020-10-27 14:41:25.73491+002020-12-18 13:15:40.843946+00NaNNaN30367.02020-11-03 22:00:00+002020-10-282020-12-01 13:26:53.787672+00instant2020-10-27 14:41:57.901946+00completed2020-11-12 23:20:41.928788+002020-12-01 13:26:53.815504+00
2396722357100.0money_back2020-10-20 07:58:04.006937+002021-02-05 12:19:30.656816+0082122.0NaNNaN2021-02-05 11:00:00+002020-10-212021-02-05 12:19:30.626289+00instant2020-10-20 07:58:14.171553+00NaNNaNNaN
2396820256100.0money_back2020-10-10 05:40:55.700422+002021-02-05 13:14:19.707627+0064517.0NaNNaN2021-02-05 11:00:00+002020-10-122021-02-05 13:14:19.689906+00instant2020-10-10 05:41:23.368363+00NaNNaNNaN
2396919886100.0direct_debit_sent2020-10-08 14:16:52.155661+002021-01-05 15:45:52.645536+0044867.0NaNNaN2021-02-05 11:00:00+002020-10-10NaNinstant2020-10-08 14:17:04.526139+00NaNNaNNaN
\n", + "

23970 rows × 16 columns

\n", + "
" + ], + "text/plain": [ + " id amount status created_at \\\n", + "0 5 100.0 rejected 2019-12-10 19:05:21.596873+00 \n", + "1 70 100.0 rejected 2019-12-10 19:50:12.34778+00 \n", + "2 7 100.0 rejected 2019-12-10 19:13:35.82546+00 \n", + "3 10 99.0 rejected 2019-12-10 19:16:10.880172+00 \n", + "4 1594 100.0 rejected 2020-05-06 09:59:38.877376+00 \n", + "... ... ... ... ... \n", + "23965 20616 100.0 money_back 2020-10-12 13:54:11.686225+00 \n", + "23966 25243 50.0 money_back 2020-10-27 14:41:25.73491+00 \n", + "23967 22357 100.0 money_back 2020-10-20 07:58:04.006937+00 \n", + "23968 20256 100.0 money_back 2020-10-10 05:40:55.700422+00 \n", + "23969 19886 100.0 direct_debit_sent 2020-10-08 14:16:52.155661+00 \n", + "\n", + " updated_at user_id moderated_at \\\n", + "0 2019-12-11 16:47:42.40783+00 804.0 2019-12-11 16:47:42.405646+00 \n", + "1 2019-12-11 14:24:22.900054+00 231.0 2019-12-11 14:24:22.897988+00 \n", + "2 2019-12-11 09:46:59.779773+00 191.0 2019-12-11 09:46:59.777728+00 \n", + "3 2019-12-18 14:26:18.136163+00 761.0 2019-12-18 14:26:18.128407+00 \n", + "4 2020-05-07 09:21:55.34008+00 7686.0 2020-05-07 09:21:55.320193+00 \n", + "... ... ... ... \n", + "23965 2021-02-06 20:17:49.292493+00 13681.0 NaN \n", + "23966 2020-12-18 13:15:40.843946+00 NaN NaN \n", + "23967 2021-02-05 12:19:30.656816+00 82122.0 NaN \n", + "23968 2021-02-05 13:14:19.707627+00 64517.0 NaN \n", + "23969 2021-01-05 15:45:52.645536+00 44867.0 NaN \n", + "\n", + " deleted_account_id reimbursement_date \\\n", + "0 NaN 2020-01-09 19:05:21.596363+00 \n", + "1 NaN 2020-01-09 19:50:12.34778+00 \n", + "2 NaN 2020-01-09 19:13:35.825041+00 \n", + "3 NaN 2020-01-09 19:16:10.879606+00 \n", + "4 NaN 2020-06-05 22:00:00+00 \n", + "... ... ... \n", + "23965 NaN 2021-02-06 11:00:00+00 \n", + "23966 30367.0 2020-11-03 22:00:00+00 \n", + "23967 NaN 2021-02-05 11:00:00+00 \n", + "23968 NaN 2021-02-05 11:00:00+00 \n", + "23969 NaN 2021-02-05 11:00:00+00 \n", + "\n", + " cash_request_received_date money_back_date transfer_type \\\n", + "0 NaN NaN regular \n", + "1 NaN NaN regular \n", + "2 NaN NaN regular \n", + "3 NaN NaN regular \n", + "4 NaN NaN regular \n", + "... ... ... ... \n", + "23965 2020-10-13 2021-02-06 20:17:49.257521+00 instant \n", + "23966 2020-10-28 2020-12-01 13:26:53.787672+00 instant \n", + "23967 2020-10-21 2021-02-05 12:19:30.626289+00 instant \n", + "23968 2020-10-12 2021-02-05 13:14:19.689906+00 instant \n", + "23969 2020-10-10 NaN instant \n", + "\n", + " send_at recovery_status \\\n", + "0 NaN NaN \n", + "1 NaN NaN \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "... ... ... \n", + "23965 2020-10-12 13:54:24.352856+00 NaN \n", + "23966 2020-10-27 14:41:57.901946+00 completed \n", + "23967 2020-10-20 07:58:14.171553+00 NaN \n", + "23968 2020-10-10 05:41:23.368363+00 NaN \n", + "23969 2020-10-08 14:17:04.526139+00 NaN \n", + "\n", + " reco_creation reco_last_update \n", + "0 NaN NaN \n", + "1 NaN NaN \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "... ... ... \n", + "23965 NaN NaN \n", + "23966 2020-11-12 23:20:41.928788+00 2020-12-01 13:26:53.815504+00 \n", + "23967 NaN NaN \n", + "23968 NaN NaN \n", + "23969 NaN NaN \n", + "\n", + "[23970 rows x 16 columns]" + ] + }, + "execution_count": 354, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df1" + ] + }, + { + "cell_type": "code", + "execution_count": 356, + "id": "da10a2b4-4f88-4777-9584-745ad4581b0e", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idcash_request_idtypestatuscategorytotal_amountreasoncreated_atupdated_atpaid_atfrom_dateto_datecharge_moment
0653714941.0instant_paymentrejectedNaN5.0Instant Payment Cash Request 149412020-09-07 10:47:27.42315+002020-10-13 14:25:09.396112+002020-12-17 14:50:07.47011+00NaNNaNafter
1696111714.0incidentacceptedrejected_direct_debit5.0rejected direct debit2020-09-09 20:51:17.998653+002020-10-13 14:25:15.537063+002020-12-08 17:13:10.45908+00NaNNaNafter
21629623371.0instant_paymentacceptedNaN5.0Instant Payment Cash Request 233712020-10-23 10:10:58.352972+002020-10-23 10:10:58.352994+002020-11-04 19:34:37.43291+00NaNNaNafter
32077526772.0instant_paymentacceptedNaN5.0Instant Payment Cash Request 267722020-10-31 15:46:53.643958+002020-10-31 15:46:53.643982+002020-11-19 05:09:22.500223+00NaNNaNafter
41124219350.0instant_paymentacceptedNaN5.0Instant Payment Cash Request 193502020-10-06 08:20:17.170432+002020-10-13 14:25:03.267983+002020-11-02 14:45:20.355598+00NaNNaNafter
..........................................
210561237220262.0instant_paymentrejectedNaN5.0Instant Payment Cash Request 202622020-10-10 06:42:22.822743+002020-10-13 14:25:04.18049+002020-11-17 05:14:00.080854+00NaNNaNafter
210572076826764.0instant_paymentrejectedNaN5.0Instant Payment Cash Request 267642020-10-31 15:24:18.680694+002020-10-31 15:24:18.680715+002020-12-16 07:10:54.697639+00NaNNaNafter
210581877925331.0instant_paymentrejectedNaN5.0Instant Payment Cash Request 253312020-10-27 17:28:51.749177+002020-10-27 17:28:51.7492+002020-11-18 04:35:42.915511+00NaNNaNafter
210591654223628.0instant_paymentrejectedNaN5.0Instant Payment Cash Request 236282020-10-23 16:27:52.047457+002020-10-23 16:27:52.047486+002020-12-18 05:18:01.465317+00NaNNaNafter
210601330120982.0instant_paymentacceptedNaN5.0Instant Payment Cash Request 209822020-10-14 07:12:43.958192+002020-10-14 07:12:43.958219+002021-02-12 13:02:46.95022+00NaNNaNafter
\n", + "

21061 rows × 13 columns

\n", + "
" + ], + "text/plain": [ + " id cash_request_id type status \\\n", + "0 6537 14941.0 instant_payment rejected \n", + "1 6961 11714.0 incident accepted \n", + "2 16296 23371.0 instant_payment accepted \n", + "3 20775 26772.0 instant_payment accepted \n", + "4 11242 19350.0 instant_payment accepted \n", + "... ... ... ... ... \n", + "21056 12372 20262.0 instant_payment rejected \n", + "21057 20768 26764.0 instant_payment rejected \n", + "21058 18779 25331.0 instant_payment rejected \n", + "21059 16542 23628.0 instant_payment rejected \n", + "21060 13301 20982.0 instant_payment accepted \n", + "\n", + " category total_amount \\\n", + "0 NaN 5.0 \n", + "1 rejected_direct_debit 5.0 \n", + "2 NaN 5.0 \n", + "3 NaN 5.0 \n", + "4 NaN 5.0 \n", + "... ... ... \n", + "21056 NaN 5.0 \n", + "21057 NaN 5.0 \n", + "21058 NaN 5.0 \n", + "21059 NaN 5.0 \n", + "21060 NaN 5.0 \n", + "\n", + " reason created_at \\\n", + "0 Instant Payment Cash Request 14941 2020-09-07 10:47:27.42315+00 \n", + "1 rejected direct debit 2020-09-09 20:51:17.998653+00 \n", + "2 Instant Payment Cash Request 23371 2020-10-23 10:10:58.352972+00 \n", + "3 Instant Payment Cash Request 26772 2020-10-31 15:46:53.643958+00 \n", + "4 Instant Payment Cash Request 19350 2020-10-06 08:20:17.170432+00 \n", + "... ... ... \n", + "21056 Instant Payment Cash Request 20262 2020-10-10 06:42:22.822743+00 \n", + "21057 Instant Payment Cash Request 26764 2020-10-31 15:24:18.680694+00 \n", + "21058 Instant Payment Cash Request 25331 2020-10-27 17:28:51.749177+00 \n", + "21059 Instant Payment Cash Request 23628 2020-10-23 16:27:52.047457+00 \n", + "21060 Instant Payment Cash Request 20982 2020-10-14 07:12:43.958192+00 \n", + "\n", + " updated_at paid_at from_date \\\n", + "0 2020-10-13 14:25:09.396112+00 2020-12-17 14:50:07.47011+00 NaN \n", + "1 2020-10-13 14:25:15.537063+00 2020-12-08 17:13:10.45908+00 NaN \n", + "2 2020-10-23 10:10:58.352994+00 2020-11-04 19:34:37.43291+00 NaN \n", + "3 2020-10-31 15:46:53.643982+00 2020-11-19 05:09:22.500223+00 NaN \n", + "4 2020-10-13 14:25:03.267983+00 2020-11-02 14:45:20.355598+00 NaN \n", + "... ... ... ... \n", + "21056 2020-10-13 14:25:04.18049+00 2020-11-17 05:14:00.080854+00 NaN \n", + "21057 2020-10-31 15:24:18.680715+00 2020-12-16 07:10:54.697639+00 NaN \n", + "21058 2020-10-27 17:28:51.7492+00 2020-11-18 04:35:42.915511+00 NaN \n", + "21059 2020-10-23 16:27:52.047486+00 2020-12-18 05:18:01.465317+00 NaN \n", + "21060 2020-10-14 07:12:43.958219+00 2021-02-12 13:02:46.95022+00 NaN \n", + "\n", + " to_date charge_moment \n", + "0 NaN after \n", + "1 NaN after \n", + "2 NaN after \n", + "3 NaN after \n", + "4 NaN after \n", + "... ... ... \n", + "21056 NaN after \n", + "21057 NaN after \n", + "21058 NaN after \n", + "21059 NaN after \n", + "21060 NaN after \n", + "\n", + "[21061 rows x 13 columns]" + ] + }, + "execution_count": 356, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df2" + ] + }, + { + "cell_type": "code", + "execution_count": 358, + "id": "f41eed0d-5916-410a-b048-75af28accc5f", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
id_xamountstatus_xcreated_at_xupdated_at_xuser_idmoderated_atdeleted_account_idreimbursement_datecash_request_received_date...status_ycategorytotal_amountreasoncreated_at_yupdated_at_ypaid_atfrom_dateto_datecharge_moment
05100.0rejected2019-12-10 19:05:21.596873+002019-12-11 16:47:42.40783+00804.02019-12-11 16:47:42.405646+00NaN2020-01-09 19:05:21.596363+00NaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
170100.0rejected2019-12-10 19:50:12.34778+002019-12-11 14:24:22.900054+00231.02019-12-11 14:24:22.897988+00NaN2020-01-09 19:50:12.34778+00NaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
27100.0rejected2019-12-10 19:13:35.82546+002019-12-11 09:46:59.779773+00191.02019-12-11 09:46:59.777728+00NaN2020-01-09 19:13:35.825041+00NaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
31099.0rejected2019-12-10 19:16:10.880172+002019-12-18 14:26:18.136163+00761.02019-12-18 14:26:18.128407+00NaN2020-01-09 19:16:10.879606+00NaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
41594100.0rejected2020-05-06 09:59:38.877376+002020-05-07 09:21:55.34008+007686.02020-05-07 09:21:55.320193+00NaN2020-06-05 22:00:00+00NaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
..................................................................
3208922357100.0money_back2020-10-20 07:58:04.006937+002021-02-05 12:19:30.656816+0082122.0NaNNaN2021-02-05 11:00:00+002020-10-21...acceptedNaN5.0Instant Payment Cash Request 223572020-10-20 07:58:19.637461+002020-10-20 07:58:19.637491+002021-02-05 12:19:30.685779+00NaNNaNafter
3209020256100.0money_back2020-10-10 05:40:55.700422+002021-02-05 13:14:19.707627+0064517.0NaNNaN2021-02-05 11:00:00+002020-10-12...acceptedNaN5.0Postpone Cash Request 202562020-10-30 17:08:16.906449+002020-10-30 17:08:21.967966+002020-10-30 17:08:21.416796+002020-11-06 11:00:00+002020-12-07 11:00:00+00before
3209120256100.0money_back2020-10-10 05:40:55.700422+002021-02-05 13:14:19.707627+0064517.0NaNNaN2021-02-05 11:00:00+002020-10-12...acceptedNaN5.0Instant Payment Cash Request 202562020-10-10 05:42:11.679401+002020-10-13 14:25:03.460352+002021-02-05 13:14:19.731397+00NaNNaNafter
3209219886100.0direct_debit_sent2020-10-08 14:16:52.155661+002021-01-05 15:45:52.645536+0044867.0NaNNaN2021-02-05 11:00:00+002020-10-10...acceptedNaN5.0Postpone Cash Request 198862020-10-10 21:22:00.083739+002020-10-13 14:25:18.501716+002020-10-10 21:22:04.456828+002020-11-06 22:00:00+002020-12-06 11:00:00+00before
3209319886100.0direct_debit_sent2020-10-08 14:16:52.155661+002021-01-05 15:45:52.645536+0044867.0NaNNaN2021-02-05 11:00:00+002020-10-10...acceptedNaN5.0Instant Payment Cash Request 198862020-10-08 14:17:09.126909+002020-10-13 14:25:16.470702+002021-02-11 04:24:07.529815+00NaNNaNafter
\n", + "

32094 rows × 29 columns

\n", + "
" + ], + "text/plain": [ + " id_x amount status_x created_at_x \\\n", + "0 5 100.0 rejected 2019-12-10 19:05:21.596873+00 \n", + "1 70 100.0 rejected 2019-12-10 19:50:12.34778+00 \n", + "2 7 100.0 rejected 2019-12-10 19:13:35.82546+00 \n", + "3 10 99.0 rejected 2019-12-10 19:16:10.880172+00 \n", + "4 1594 100.0 rejected 2020-05-06 09:59:38.877376+00 \n", + "... ... ... ... ... \n", + "32089 22357 100.0 money_back 2020-10-20 07:58:04.006937+00 \n", + "32090 20256 100.0 money_back 2020-10-10 05:40:55.700422+00 \n", + "32091 20256 100.0 money_back 2020-10-10 05:40:55.700422+00 \n", + "32092 19886 100.0 direct_debit_sent 2020-10-08 14:16:52.155661+00 \n", + "32093 19886 100.0 direct_debit_sent 2020-10-08 14:16:52.155661+00 \n", + "\n", + " updated_at_x user_id moderated_at \\\n", + "0 2019-12-11 16:47:42.40783+00 804.0 2019-12-11 16:47:42.405646+00 \n", + "1 2019-12-11 14:24:22.900054+00 231.0 2019-12-11 14:24:22.897988+00 \n", + "2 2019-12-11 09:46:59.779773+00 191.0 2019-12-11 09:46:59.777728+00 \n", + "3 2019-12-18 14:26:18.136163+00 761.0 2019-12-18 14:26:18.128407+00 \n", + "4 2020-05-07 09:21:55.34008+00 7686.0 2020-05-07 09:21:55.320193+00 \n", + "... ... ... ... \n", + "32089 2021-02-05 12:19:30.656816+00 82122.0 NaN \n", + "32090 2021-02-05 13:14:19.707627+00 64517.0 NaN \n", + "32091 2021-02-05 13:14:19.707627+00 64517.0 NaN \n", + "32092 2021-01-05 15:45:52.645536+00 44867.0 NaN \n", + "32093 2021-01-05 15:45:52.645536+00 44867.0 NaN \n", + "\n", + " deleted_account_id reimbursement_date \\\n", + "0 NaN 2020-01-09 19:05:21.596363+00 \n", + "1 NaN 2020-01-09 19:50:12.34778+00 \n", + "2 NaN 2020-01-09 19:13:35.825041+00 \n", + "3 NaN 2020-01-09 19:16:10.879606+00 \n", + "4 NaN 2020-06-05 22:00:00+00 \n", + "... ... ... \n", + "32089 NaN 2021-02-05 11:00:00+00 \n", + "32090 NaN 2021-02-05 11:00:00+00 \n", + "32091 NaN 2021-02-05 11:00:00+00 \n", + "32092 NaN 2021-02-05 11:00:00+00 \n", + "32093 NaN 2021-02-05 11:00:00+00 \n", + "\n", + " cash_request_received_date ... status_y category total_amount \\\n", + "0 NaN ... NaN NaN NaN \n", + "1 NaN ... NaN NaN NaN \n", + "2 NaN ... NaN NaN NaN \n", + "3 NaN ... NaN NaN NaN \n", + "4 NaN ... NaN NaN NaN \n", + "... ... ... ... ... ... \n", + "32089 2020-10-21 ... accepted NaN 5.0 \n", + "32090 2020-10-12 ... accepted NaN 5.0 \n", + "32091 2020-10-12 ... accepted NaN 5.0 \n", + "32092 2020-10-10 ... accepted NaN 5.0 \n", + "32093 2020-10-10 ... accepted NaN 5.0 \n", + "\n", + " reason created_at_y \\\n", + "0 NaN NaN \n", + "1 NaN NaN \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "... ... ... \n", + "32089 Instant Payment Cash Request 22357 2020-10-20 07:58:19.637461+00 \n", + "32090 Postpone Cash Request 20256 2020-10-30 17:08:16.906449+00 \n", + "32091 Instant Payment Cash Request 20256 2020-10-10 05:42:11.679401+00 \n", + "32092 Postpone Cash Request 19886 2020-10-10 21:22:00.083739+00 \n", + "32093 Instant Payment Cash Request 19886 2020-10-08 14:17:09.126909+00 \n", + "\n", + " updated_at_y paid_at \\\n", + "0 NaN NaN \n", + "1 NaN NaN \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "... ... ... \n", + "32089 2020-10-20 07:58:19.637491+00 2021-02-05 12:19:30.685779+00 \n", + "32090 2020-10-30 17:08:21.967966+00 2020-10-30 17:08:21.416796+00 \n", + "32091 2020-10-13 14:25:03.460352+00 2021-02-05 13:14:19.731397+00 \n", + "32092 2020-10-13 14:25:18.501716+00 2020-10-10 21:22:04.456828+00 \n", + "32093 2020-10-13 14:25:16.470702+00 2021-02-11 04:24:07.529815+00 \n", + "\n", + " from_date to_date charge_moment \n", + "0 NaN NaN NaN \n", + "1 NaN NaN NaN \n", + "2 NaN NaN NaN \n", + "3 NaN NaN NaN \n", + "4 NaN NaN NaN \n", + "... ... ... ... \n", + "32089 NaN NaN after \n", + "32090 2020-11-06 11:00:00+00 2020-12-07 11:00:00+00 before \n", + "32091 NaN NaN after \n", + "32092 2020-11-06 22:00:00+00 2020-12-06 11:00:00+00 before \n", + "32093 NaN NaN after \n", + "\n", + "[32094 rows x 29 columns]" + ] + }, + "execution_count": 358, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "merged_df" + ] + }, + { + "cell_type": "code", + "execution_count": 360, + "id": "2037d717-919a-4601-8d44-4dbe0a37b6a4", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
id_xcreated_at_xtotal_amountrecovery_statusreimbursement_datecohortreembolsadomonto_reembolsado
052019-12-10 19:05:21.596873+00:00NaNNaN2020-01-09 19:05:21.596363+002019-12TrueNaN
1702019-12-10 19:50:12.347780+00:00NaNNaN2020-01-09 19:50:12.34778+002019-12TrueNaN
272019-12-10 19:13:35.825460+00:00NaNNaN2020-01-09 19:13:35.825041+002019-12TrueNaN
3102019-12-10 19:16:10.880172+00:00NaNNaN2020-01-09 19:16:10.879606+002019-12TrueNaN
415942020-05-06 09:59:38.877376+00:00NaNNaN2020-06-05 22:00:00+002020-05TrueNaN
...........................
32089223572020-10-20 07:58:04.006937+00:005.0NaN2021-02-05 11:00:00+002020-10True5.0
32090202562020-10-10 05:40:55.700422+00:005.0NaN2021-02-05 11:00:00+002020-10True5.0
32091202562020-10-10 05:40:55.700422+00:005.0NaN2021-02-05 11:00:00+002020-10True5.0
32092198862020-10-08 14:16:52.155661+00:005.0NaN2021-02-05 11:00:00+002020-10True5.0
32093198862020-10-08 14:16:52.155661+00:005.0NaN2021-02-05 11:00:00+002020-10True5.0
\n", + "

32094 rows × 8 columns

\n", + "
" + ], + "text/plain": [ + " id_x created_at_x total_amount recovery_status \\\n", + "0 5 2019-12-10 19:05:21.596873+00:00 NaN NaN \n", + "1 70 2019-12-10 19:50:12.347780+00:00 NaN NaN \n", + "2 7 2019-12-10 19:13:35.825460+00:00 NaN NaN \n", + "3 10 2019-12-10 19:16:10.880172+00:00 NaN NaN \n", + "4 1594 2020-05-06 09:59:38.877376+00:00 NaN NaN \n", + "... ... ... ... ... \n", + "32089 22357 2020-10-20 07:58:04.006937+00:00 5.0 NaN \n", + "32090 20256 2020-10-10 05:40:55.700422+00:00 5.0 NaN \n", + "32091 20256 2020-10-10 05:40:55.700422+00:00 5.0 NaN \n", + "32092 19886 2020-10-08 14:16:52.155661+00:00 5.0 NaN \n", + "32093 19886 2020-10-08 14:16:52.155661+00:00 5.0 NaN \n", + "\n", + " reimbursement_date cohort reembolsado monto_reembolsado \n", + "0 2020-01-09 19:05:21.596363+00 2019-12 True NaN \n", + "1 2020-01-09 19:50:12.34778+00 2019-12 True NaN \n", + "2 2020-01-09 19:13:35.825041+00 2019-12 True NaN \n", + "3 2020-01-09 19:16:10.879606+00 2019-12 True NaN \n", + "4 2020-06-05 22:00:00+00 2020-05 True NaN \n", + "... ... ... ... ... \n", + "32089 2021-02-05 11:00:00+00 2020-10 True 5.0 \n", + "32090 2021-02-05 11:00:00+00 2020-10 True 5.0 \n", + "32091 2021-02-05 11:00:00+00 2020-10 True 5.0 \n", + "32092 2021-02-05 11:00:00+00 2020-10 True 5.0 \n", + "32093 2021-02-05 11:00:00+00 2020-10 True 5.0 \n", + "\n", + "[32094 rows x 8 columns]" + ] + }, + "execution_count": 360, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "merged_df2" + ] + }, + { + "cell_type": "code", + "execution_count": 362, + "id": "0a6faf49-b336-478b-8d83-58df39a3250d", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
id_xcreated_at_xtotal_amountrecovery_statusreimbursement_datecohortreembolsadomonto_reembolsadoaprobada
052019-12-10 19:05:21.596873+00:00NaNNaN2020-01-09 19:05:21.596363+002019-12TrueNaNFalse
1702019-12-10 19:50:12.347780+00:00NaNNaN2020-01-09 19:50:12.34778+002019-12TrueNaNFalse
272019-12-10 19:13:35.825460+00:00NaNNaN2020-01-09 19:13:35.825041+002019-12TrueNaNFalse
3102019-12-10 19:16:10.880172+00:00NaNNaN2020-01-09 19:16:10.879606+002019-12TrueNaNFalse
415942020-05-06 09:59:38.877376+00:00NaNNaN2020-06-05 22:00:00+002020-05TrueNaNFalse
..............................
32089223572020-10-20 07:58:04.006937+00:005.0NaN2021-02-05 11:00:00+002020-10True5.0False
32090202562020-10-10 05:40:55.700422+00:005.0NaN2021-02-05 11:00:00+002020-10True5.0False
32091202562020-10-10 05:40:55.700422+00:005.0NaN2021-02-05 11:00:00+002020-10True5.0False
32092198862020-10-08 14:16:52.155661+00:005.0NaN2021-02-05 11:00:00+002020-10True5.0False
32093198862020-10-08 14:16:52.155661+00:005.0NaN2021-02-05 11:00:00+002020-10True5.0False
\n", + "

32094 rows × 9 columns

\n", + "
" + ], + "text/plain": [ + " id_x created_at_x total_amount recovery_status \\\n", + "0 5 2019-12-10 19:05:21.596873+00:00 NaN NaN \n", + "1 70 2019-12-10 19:50:12.347780+00:00 NaN NaN \n", + "2 7 2019-12-10 19:13:35.825460+00:00 NaN NaN \n", + "3 10 2019-12-10 19:16:10.880172+00:00 NaN NaN \n", + "4 1594 2020-05-06 09:59:38.877376+00:00 NaN NaN \n", + "... ... ... ... ... \n", + "32089 22357 2020-10-20 07:58:04.006937+00:00 5.0 NaN \n", + "32090 20256 2020-10-10 05:40:55.700422+00:00 5.0 NaN \n", + "32091 20256 2020-10-10 05:40:55.700422+00:00 5.0 NaN \n", + "32092 19886 2020-10-08 14:16:52.155661+00:00 5.0 NaN \n", + "32093 19886 2020-10-08 14:16:52.155661+00:00 5.0 NaN \n", + "\n", + " reimbursement_date cohort reembolsado monto_reembolsado \\\n", + "0 2020-01-09 19:05:21.596363+00 2019-12 True NaN \n", + "1 2020-01-09 19:50:12.34778+00 2019-12 True NaN \n", + "2 2020-01-09 19:13:35.825041+00 2019-12 True NaN \n", + "3 2020-01-09 19:16:10.879606+00 2019-12 True NaN \n", + "4 2020-06-05 22:00:00+00 2020-05 True NaN \n", + "... ... ... ... ... \n", + "32089 2021-02-05 11:00:00+00 2020-10 True 5.0 \n", + "32090 2021-02-05 11:00:00+00 2020-10 True 5.0 \n", + "32091 2021-02-05 11:00:00+00 2020-10 True 5.0 \n", + "32092 2021-02-05 11:00:00+00 2020-10 True 5.0 \n", + "32093 2021-02-05 11:00:00+00 2020-10 True 5.0 \n", + "\n", + " aprobada \n", + "0 False \n", + "1 False \n", + "2 False \n", + "3 False \n", + "4 False \n", + "... ... \n", + "32089 False \n", + "32090 False \n", + "32091 False \n", + "32092 False \n", + "32093 False \n", + "\n", + "[32094 rows x 9 columns]" + ] + }, + "execution_count": 362, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "merged_df2_clean" + ] + }, + { + "cell_type": "code", + "execution_count": 364, + "id": "e6bcb820-75f0-4c90-8423-7bfdd347edf6", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
id_xamountcreated_at_xupdated_at_xuser_idmoderated_atdeleted_account_idreimbursement_datecash_request_received_datemoney_back_date...status_ycategorytotal_amountreasoncreated_at_yupdated_at_ypaid_atfrom_dateto_datecharge_moment
status_x
active228463013825.02020-07-01 09:30:03.14541+002020-07-01 09:30:0...2020-08-11 22:27:58.240406+002020-08-11 22:27:...4929215.02020-07-01 16:44:53.070844+002020-07-01 16:44:...0.02020-08-03 22:00:00+002020-08-03 22:00:00+0020...2020-07-032020-07-032020-07-032020-07-032020-0...2020-06-11 22:37:13.182826+002020-08-06 22:00:......cancelledcancelledcancelledcancelledcancelledr...month_delay_on_paymentrejected_direct_debitmon...775.0Postpone Cash Request 6098Postpone Cash Reques...2020-08-13 10:58:39.63422+002020-08-13 10:58:5...2020-10-13 14:25:16.660127+002020-10-13 14:25:...2020-06-25 23:41:23.810387+002020-07-12 04:34:...2020-08-03 22:00:00+002020-08-03 22:00:00+0020...2020-09-03 10:58:32.274+002020-09-03 10:58:32....afterafterafterafterafterafterafterafteraftera...
canceled4074112721.02020-06-28 12:06:33.71284+002020-06-29 06:26:3...2020-06-28 12:06:33.712853+002020-06-29 06:26:...235310.02020-07-29 16:10:38+002020-09-01 17:22:40+0020...130344.02020-07-07 22:00:00+002020-07-31 22:00:00+0020...2020-09-042020-10-11 22:00:00+002020-10-11 22:00:00+00...rejectedrejectedconfirmedconfirmedrejectedcanc...rejected_direct_debitrejected_direct_debit30.0Instant Payment Cash Request 12838rejected dir...2020-08-17 19:05:49.830145+002020-09-03 15:45:...2020-10-13 14:25:09.68019+002020-10-13 14:25:0...2020-09-07 14:39:58.670351+002020-09-07 14:39:...00afterafterafterafterafterafter
direct_debit_rejected25727991157959.02020-06-17 11:03:32.61712+002020-06-17 11:03:3...2020-07-21 22:09:32.695508+002020-07-21 22:09:...60544935.02020-06-17 14:52:56.14175+002020-06-17 14:52:5...722081.02020-07-17 11:03:52.469+002020-07-17 11:03:52....2020-06-182020-06-182020-06-182020-06-182020-0...2020-07-02 18:47:17.295625+002020-07-02 18:47:......rejectedrejectedrejectedrejectedcancelledrejec...rejected_direct_debitmonth_delay_on_paymentmon...9290.0rejected direct debitmonth delay on payment - ...2020-07-21 22:09:32.585036+002020-08-20 23:11:...2020-10-13 14:25:00.836605+002020-10-13 14:25:...2020-08-06 08:42:18.59726+002020-07-07 05:35:0...2020-07-30 22:00:00+002020-08-15 05:34:55.649+...2020-08-15 05:34:55.649+002020-08-30 05:34:55....afterafterafterafterafterafterafterafterbefore...
direct_debit_sent12412056710.02020-08-08 18:20:28.454918+002020-08-08 18:20:...2020-09-09 10:07:25.743348+002020-09-09 10:07:...2687797.02020-08-17 07:35:42.551778+002020-08-17 07:35:...0.02020-09-27 22:00:00+002020-09-27 22:00:00+0020...2020-08-112020-08-112020-08-112020-08-182020-0...2020-06-10 03:42:00.436408+002020-12-23 08:21:......rejectedcancelledcancelledcancelledcancelledre...rejected_direct_debitmonth_delay_on_paymentrej...360.0rejected direct debitPostpone Cash Request 115...2020-09-06 22:09:12.979847+002020-08-25 17:18:...2020-10-13 14:25:09.281636+002020-10-13 14:25:...2020-09-18 08:56:59.846076+002021-02-11 04:25:...2020-08-28 23:51:00+002020-08-28 23:51:00+0020...2020-09-27 23:51:00+002020-09-27 23:51:00+0020...afterafterafterafterafterafterafterafteraftera...
money_back3446527981946958.02020-05-23 20:58:55.129432+002020-05-14 21:11:...2020-07-06 03:36:03.023911+002020-06-03 05:11:...759119993.02020-05-24 12:40:33.05491+002020-05-15 09:11:1...17933438.02020-06-06 22:00:00+002020-05-29 21:11:46.695+...2020-05-262020-05-172020-05-272020-05-122020-0...2020-07-06 03:36:03.023521+002020-06-03 05:11:......acceptedacceptedacceptedacceptedcancelledaccep...rejected_direct_debitmonth_delay_on_paymentrej...94595.0Instant Payment Cash Request 23534Postpone Cas...2020-10-23 15:21:35.895711+002020-06-09 11:25:...2020-10-23 15:21:35.89574+002020-10-13 14:25:0...2020-11-06 07:16:22.014422+002020-10-17 05:30:...2020-06-15 02:26:27+002020-10-27 17:05:21.138+...2020-07-15 02:26:27+002020-10-30 23:00:00+0020...afterbeforebeforeafterbeforebeforeafterafteraf...
rejected68269051548101.02019-12-10 19:05:21.596873+002019-12-10 19:50:...2019-12-11 16:47:42.40783+002019-12-11 14:24:2...113094094.02019-12-11 16:47:42.405646+002019-12-11 14:24:...9460686.02020-01-09 19:05:21.596363+002020-01-09 19:50:...2020-06-250...000.00000000
transaction_declined10271604105.02020-10-23 16:32:14.85667+002020-10-13 11:37:3...2020-10-23 16:33:15.530982+002020-10-13 11:38:...2226056.02020-10-12 15:22:44.665209+000.02020-11-05 22:00:00+002020-11-04 22:00:00+0020...02020-11-05 20:31:25+002020-11-08 22:25:14+00...confirmedconfirmedconfirmedconfirmedconfirmedc...0240.0Instant Payment Cash Request 23641Instant Paym...2020-10-23 16:32:34.165305+002020-10-13 11:37:...2020-10-23 16:32:34.165333+002020-10-13 14:25:...2020-11-05 20:31:25.727454+002020-11-05 14:03:...00afterafterafterafterafterafterafterafteraftera...
\n", + "

7 rows × 28 columns

\n", + "
" + ], + "text/plain": [ + " id_x amount \\\n", + "status_x \n", + "active 2284630 13825.0 \n", + "canceled 407411 2721.0 \n", + "direct_debit_rejected 25727991 157959.0 \n", + "direct_debit_sent 1241205 6710.0 \n", + "money_back 344652798 1946958.0 \n", + "rejected 68269051 548101.0 \n", + "transaction_declined 1027160 4105.0 \n", + "\n", + " created_at_x \\\n", + "status_x \n", + "active 2020-07-01 09:30:03.14541+002020-07-01 09:30:0... \n", + "canceled 2020-06-28 12:06:33.71284+002020-06-29 06:26:3... \n", + "direct_debit_rejected 2020-06-17 11:03:32.61712+002020-06-17 11:03:3... \n", + "direct_debit_sent 2020-08-08 18:20:28.454918+002020-08-08 18:20:... \n", + "money_back 2020-05-23 20:58:55.129432+002020-05-14 21:11:... \n", + "rejected 2019-12-10 19:05:21.596873+002019-12-10 19:50:... \n", + "transaction_declined 2020-10-23 16:32:14.85667+002020-10-13 11:37:3... \n", + "\n", + " updated_at_x \\\n", + "status_x \n", + "active 2020-08-11 22:27:58.240406+002020-08-11 22:27:... \n", + "canceled 2020-06-28 12:06:33.712853+002020-06-29 06:26:... \n", + "direct_debit_rejected 2020-07-21 22:09:32.695508+002020-07-21 22:09:... \n", + "direct_debit_sent 2020-09-09 10:07:25.743348+002020-09-09 10:07:... \n", + "money_back 2020-07-06 03:36:03.023911+002020-06-03 05:11:... \n", + "rejected 2019-12-11 16:47:42.40783+002019-12-11 14:24:2... \n", + "transaction_declined 2020-10-23 16:33:15.530982+002020-10-13 11:38:... \n", + "\n", + " user_id \\\n", + "status_x \n", + "active 4929215.0 \n", + "canceled 235310.0 \n", + "direct_debit_rejected 60544935.0 \n", + "direct_debit_sent 2687797.0 \n", + "money_back 759119993.0 \n", + "rejected 113094094.0 \n", + "transaction_declined 2226056.0 \n", + "\n", + " moderated_at \\\n", + "status_x \n", + "active 2020-07-01 16:44:53.070844+002020-07-01 16:44:... \n", + "canceled 2020-07-29 16:10:38+002020-09-01 17:22:40+0020... \n", + "direct_debit_rejected 2020-06-17 14:52:56.14175+002020-06-17 14:52:5... \n", + "direct_debit_sent 2020-08-17 07:35:42.551778+002020-08-17 07:35:... \n", + "money_back 2020-05-24 12:40:33.05491+002020-05-15 09:11:1... \n", + "rejected 2019-12-11 16:47:42.405646+002019-12-11 14:24:... \n", + "transaction_declined 2020-10-12 15:22:44.665209+00 \n", + "\n", + " deleted_account_id \\\n", + "status_x \n", + "active 0.0 \n", + "canceled 130344.0 \n", + "direct_debit_rejected 722081.0 \n", + "direct_debit_sent 0.0 \n", + "money_back 17933438.0 \n", + "rejected 9460686.0 \n", + "transaction_declined 0.0 \n", + "\n", + " reimbursement_date \\\n", + "status_x \n", + "active 2020-08-03 22:00:00+002020-08-03 22:00:00+0020... \n", + "canceled 2020-07-07 22:00:00+002020-07-31 22:00:00+0020... \n", + "direct_debit_rejected 2020-07-17 11:03:52.469+002020-07-17 11:03:52.... \n", + "direct_debit_sent 2020-09-27 22:00:00+002020-09-27 22:00:00+0020... \n", + "money_back 2020-06-06 22:00:00+002020-05-29 21:11:46.695+... \n", + "rejected 2020-01-09 19:05:21.596363+002020-01-09 19:50:... \n", + "transaction_declined 2020-11-05 22:00:00+002020-11-04 22:00:00+0020... \n", + "\n", + " cash_request_received_date \\\n", + "status_x \n", + "active 2020-07-032020-07-032020-07-032020-07-032020-0... \n", + "canceled 2020-09-04 \n", + "direct_debit_rejected 2020-06-182020-06-182020-06-182020-06-182020-0... \n", + "direct_debit_sent 2020-08-112020-08-112020-08-112020-08-182020-0... \n", + "money_back 2020-05-262020-05-172020-05-272020-05-122020-0... \n", + "rejected 2020-06-25 \n", + "transaction_declined 0 \n", + "\n", + " money_back_date ... \\\n", + "status_x ... \n", + "active 2020-06-11 22:37:13.182826+002020-08-06 22:00:... ... \n", + "canceled 2020-10-11 22:00:00+002020-10-11 22:00:00+00 ... \n", + "direct_debit_rejected 2020-07-02 18:47:17.295625+002020-07-02 18:47:... ... \n", + "direct_debit_sent 2020-06-10 03:42:00.436408+002020-12-23 08:21:... ... \n", + "money_back 2020-07-06 03:36:03.023521+002020-06-03 05:11:... ... \n", + "rejected 0 ... \n", + "transaction_declined 2020-11-05 20:31:25+002020-11-08 22:25:14+00 ... \n", + "\n", + " status_y \\\n", + "status_x \n", + "active cancelledcancelledcancelledcancelledcancelledr... \n", + "canceled rejectedrejectedconfirmedconfirmedrejectedcanc... \n", + "direct_debit_rejected rejectedrejectedrejectedrejectedcancelledrejec... \n", + "direct_debit_sent rejectedcancelledcancelledcancelledcancelledre... \n", + "money_back acceptedacceptedacceptedacceptedcancelledaccep... \n", + "rejected 0 \n", + "transaction_declined confirmedconfirmedconfirmedconfirmedconfirmedc... \n", + "\n", + " category \\\n", + "status_x \n", + "active month_delay_on_paymentrejected_direct_debitmon... \n", + "canceled rejected_direct_debitrejected_direct_debit \n", + "direct_debit_rejected rejected_direct_debitmonth_delay_on_paymentmon... \n", + "direct_debit_sent rejected_direct_debitmonth_delay_on_paymentrej... \n", + "money_back rejected_direct_debitmonth_delay_on_paymentrej... \n", + "rejected 0 \n", + "transaction_declined 0 \n", + "\n", + " total_amount \\\n", + "status_x \n", + "active 775.0 \n", + "canceled 30.0 \n", + "direct_debit_rejected 9290.0 \n", + "direct_debit_sent 360.0 \n", + "money_back 94595.0 \n", + "rejected 0.0 \n", + "transaction_declined 240.0 \n", + "\n", + " reason \\\n", + "status_x \n", + "active Postpone Cash Request 6098Postpone Cash Reques... \n", + "canceled Instant Payment Cash Request 12838rejected dir... \n", + "direct_debit_rejected rejected direct debitmonth delay on payment - ... \n", + "direct_debit_sent rejected direct debitPostpone Cash Request 115... \n", + "money_back Instant Payment Cash Request 23534Postpone Cas... \n", + "rejected 0 \n", + "transaction_declined Instant Payment Cash Request 23641Instant Paym... \n", + "\n", + " created_at_y \\\n", + "status_x \n", + "active 2020-08-13 10:58:39.63422+002020-08-13 10:58:5... \n", + "canceled 2020-08-17 19:05:49.830145+002020-09-03 15:45:... \n", + "direct_debit_rejected 2020-07-21 22:09:32.585036+002020-08-20 23:11:... \n", + "direct_debit_sent 2020-09-06 22:09:12.979847+002020-08-25 17:18:... \n", + "money_back 2020-10-23 15:21:35.895711+002020-06-09 11:25:... \n", + "rejected 0 \n", + "transaction_declined 2020-10-23 16:32:34.165305+002020-10-13 11:37:... \n", + "\n", + " updated_at_y \\\n", + "status_x \n", + "active 2020-10-13 14:25:16.660127+002020-10-13 14:25:... \n", + "canceled 2020-10-13 14:25:09.68019+002020-10-13 14:25:0... \n", + "direct_debit_rejected 2020-10-13 14:25:00.836605+002020-10-13 14:25:... \n", + "direct_debit_sent 2020-10-13 14:25:09.281636+002020-10-13 14:25:... \n", + "money_back 2020-10-23 15:21:35.89574+002020-10-13 14:25:0... \n", + "rejected 0 \n", + "transaction_declined 2020-10-23 16:32:34.165333+002020-10-13 14:25:... \n", + "\n", + " paid_at \\\n", + "status_x \n", + "active 2020-06-25 23:41:23.810387+002020-07-12 04:34:... \n", + "canceled 2020-09-07 14:39:58.670351+002020-09-07 14:39:... \n", + "direct_debit_rejected 2020-08-06 08:42:18.59726+002020-07-07 05:35:0... \n", + "direct_debit_sent 2020-09-18 08:56:59.846076+002021-02-11 04:25:... \n", + "money_back 2020-11-06 07:16:22.014422+002020-10-17 05:30:... \n", + "rejected 0 \n", + "transaction_declined 2020-11-05 20:31:25.727454+002020-11-05 14:03:... \n", + "\n", + " from_date \\\n", + "status_x \n", + "active 2020-08-03 22:00:00+002020-08-03 22:00:00+0020... \n", + "canceled 0 \n", + "direct_debit_rejected 2020-07-30 22:00:00+002020-08-15 05:34:55.649+... \n", + "direct_debit_sent 2020-08-28 23:51:00+002020-08-28 23:51:00+0020... \n", + "money_back 2020-06-15 02:26:27+002020-10-27 17:05:21.138+... \n", + "rejected 0 \n", + "transaction_declined 0 \n", + "\n", + " to_date \\\n", + "status_x \n", + "active 2020-09-03 10:58:32.274+002020-09-03 10:58:32.... \n", + "canceled 0 \n", + "direct_debit_rejected 2020-08-15 05:34:55.649+002020-08-30 05:34:55.... \n", + "direct_debit_sent 2020-09-27 23:51:00+002020-09-27 23:51:00+0020... \n", + "money_back 2020-07-15 02:26:27+002020-10-30 23:00:00+0020... \n", + "rejected 0 \n", + "transaction_declined 0 \n", + "\n", + " charge_moment \n", + "status_x \n", + "active afterafterafterafterafterafterafterafteraftera... \n", + "canceled afterafterafterafterafterafter \n", + "direct_debit_rejected afterafterafterafterafterafterafterafterbefore... \n", + "direct_debit_sent afterafterafterafterafterafterafterafteraftera... \n", + "money_back afterbeforebeforeafterbeforebeforeafterafteraf... \n", + "rejected 0 \n", + "transaction_declined afterafterafterafterafterafterafterafteraftera... \n", + "\n", + "[7 rows x 28 columns]" + ] + }, + "execution_count": 364, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "merged_df_clean = merged_df\n", + "\n", + "merged_df_clean\n", + "\n", + "merged_df_clean.groupby(\"status_x\").sum()\n", + "\n", + "#merged_df2_clean[\"reembolsado\"].sum()" + ] + }, + { + "cell_type": "code", + "execution_count": 365, + "id": "54dc0bd8-6957-4a19-8fd2-d7d7fe8bacba", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " Cohorte Total Solicitudes Solicitudes Aprobadas \\\n", + "0 2019-11 1 0.0 \n", + "1 2019-12 289 0.0 \n", + "2 2020-01 223 0.0 \n", + "3 2020-02 184 0.0 \n", + "4 2020-03 244 0.0 \n", + "5 2020-04 473 0.0 \n", + "6 2020-05 997 0.0 \n", + "7 2020-06 3662 0.0 \n", + "8 2020-07 4793 0.0 \n", + "9 2020-08 5250 0.0 \n", + "10 2020-09 6227 0.0 \n", + "11 2020-10 9611 0.0 \n", + "12 2020-11 140 0.0 \n", + "\n", + " Tasa de Solicitudes Aprobadas \n", + "0 0.0 \n", + "1 0.0 \n", + "2 0.0 \n", + "3 0.0 \n", + "4 0.0 \n", + "5 0.0 \n", + "6 0.0 \n", + "7 0.0 \n", + "8 0.0 \n", + "9 0.0 \n", + "10 0.0 \n", + "11 0.0 \n", + "12 0.0 \n" + ] + }, + { + "ename": "TypeError", + "evalue": "Invalid object type at position 0", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)", + "File \u001b[1;32mlib.pyx:2391\u001b[0m, in \u001b[0;36mpandas._libs.lib.maybe_convert_numeric\u001b[1;34m()\u001b[0m\n", + "\u001b[1;31mTypeError\u001b[0m: Invalid object type", + "\nDuring handling of the above exception, another exception occurred:\n", + "\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)", + "Cell \u001b[1;32mIn[365], line 31\u001b[0m\n\u001b[0;32m 27\u001b[0m \u001b[38;5;28mprint\u001b[39m(cohort_approval_rate)\n\u001b[0;32m 30\u001b[0m plt\u001b[38;5;241m.\u001b[39mfigure(figsize\u001b[38;5;241m=\u001b[39m(\u001b[38;5;241m12\u001b[39m, \u001b[38;5;241m6\u001b[39m))\n\u001b[1;32m---> 31\u001b[0m sns\u001b[38;5;241m.\u001b[39mlineplot(data\u001b[38;5;241m=\u001b[39mcohort_approval_rate, x\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mCohorte\u001b[39m\u001b[38;5;124m'\u001b[39m, y\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mTasa de Solicitudes Aprobadas\u001b[39m\u001b[38;5;124m'\u001b[39m, marker\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mo\u001b[39m\u001b[38;5;124m'\u001b[39m, color\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mblue\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m 32\u001b[0m plt\u001b[38;5;241m.\u001b[39mtitle(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mTasa de Solicitudes Aprobadas por Cohorte\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m 33\u001b[0m plt\u001b[38;5;241m.\u001b[39mxlabel(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mCohorte (Mes y Año)\u001b[39m\u001b[38;5;124m'\u001b[39m)\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\seaborn\\relational.py:515\u001b[0m, in \u001b[0;36mlineplot\u001b[1;34m(data, x, y, hue, size, style, units, weights, palette, hue_order, hue_norm, sizes, size_order, size_norm, dashes, markers, style_order, estimator, errorbar, n_boot, seed, orient, sort, err_style, err_kws, legend, ci, ax, **kwargs)\u001b[0m\n\u001b[0;32m 512\u001b[0m color \u001b[38;5;241m=\u001b[39m kwargs\u001b[38;5;241m.\u001b[39mpop(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcolor\u001b[39m\u001b[38;5;124m\"\u001b[39m, kwargs\u001b[38;5;241m.\u001b[39mpop(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mc\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m))\n\u001b[0;32m 513\u001b[0m kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcolor\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m _default_color(ax\u001b[38;5;241m.\u001b[39mplot, hue, color, kwargs)\n\u001b[1;32m--> 515\u001b[0m p\u001b[38;5;241m.\u001b[39mplot(ax, kwargs)\n\u001b[0;32m 516\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m ax\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\seaborn\\relational.py:276\u001b[0m, in \u001b[0;36m_LinePlotter.plot\u001b[1;34m(self, ax, kws)\u001b[0m\n\u001b[0;32m 268\u001b[0m \u001b[38;5;66;03m# TODO How to handle NA? We don't want NA to propagate through to the\u001b[39;00m\n\u001b[0;32m 269\u001b[0m \u001b[38;5;66;03m# estimate/CI when some values are present, but we would also like\u001b[39;00m\n\u001b[0;32m 270\u001b[0m \u001b[38;5;66;03m# matplotlib to show \"gaps\" in the line when all values are missing.\u001b[39;00m\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 273\u001b[0m \n\u001b[0;32m 274\u001b[0m \u001b[38;5;66;03m# Loop over the semantic subsets and add to the plot\u001b[39;00m\n\u001b[0;32m 275\u001b[0m grouping_vars \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhue\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msize\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstyle\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m--> 276\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m sub_vars, sub_data \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39miter_data(grouping_vars, from_comp_data\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m):\n\u001b[0;32m 278\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msort:\n\u001b[0;32m 279\u001b[0m sort_vars \u001b[38;5;241m=\u001b[39m [\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124munits\u001b[39m\u001b[38;5;124m\"\u001b[39m, orient, other]\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\seaborn\\_base.py:902\u001b[0m, in \u001b[0;36mVectorPlotter.iter_data\u001b[1;34m(self, grouping_vars, reverse, from_comp_data, by_facet, allow_empty, dropna)\u001b[0m\n\u001b[0;32m 899\u001b[0m grouping_vars \u001b[38;5;241m=\u001b[39m [var \u001b[38;5;28;01mfor\u001b[39;00m var \u001b[38;5;129;01min\u001b[39;00m grouping_vars \u001b[38;5;28;01mif\u001b[39;00m var \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mvariables]\n\u001b[0;32m 901\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m from_comp_data:\n\u001b[1;32m--> 902\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcomp_data\n\u001b[0;32m 903\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m 904\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mplot_data\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\seaborn\\_base.py:1000\u001b[0m, in \u001b[0;36mVectorPlotter.comp_data\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 995\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m var \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mvar_levels:\n\u001b[0;32m 996\u001b[0m \u001b[38;5;66;03m# TODO this should happen in some centralized location\u001b[39;00m\n\u001b[0;32m 997\u001b[0m \u001b[38;5;66;03m# it is similar to GH2419, but more complicated because\u001b[39;00m\n\u001b[0;32m 998\u001b[0m \u001b[38;5;66;03m# supporting `order` in categorical plots is tricky\u001b[39;00m\n\u001b[0;32m 999\u001b[0m orig \u001b[38;5;241m=\u001b[39m orig[orig\u001b[38;5;241m.\u001b[39misin(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mvar_levels[var])]\n\u001b[1;32m-> 1000\u001b[0m comp \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mto_numeric(converter\u001b[38;5;241m.\u001b[39mconvert_units(orig))\u001b[38;5;241m.\u001b[39mastype(\u001b[38;5;28mfloat\u001b[39m)\n\u001b[0;32m 1001\u001b[0m transform \u001b[38;5;241m=\u001b[39m converter\u001b[38;5;241m.\u001b[39mget_transform()\u001b[38;5;241m.\u001b[39mtransform\n\u001b[0;32m 1002\u001b[0m parts\u001b[38;5;241m.\u001b[39mappend(pd\u001b[38;5;241m.\u001b[39mSeries(transform(comp), orig\u001b[38;5;241m.\u001b[39mindex, name\u001b[38;5;241m=\u001b[39morig\u001b[38;5;241m.\u001b[39mname))\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\pandas\\core\\tools\\numeric.py:232\u001b[0m, in \u001b[0;36mto_numeric\u001b[1;34m(arg, errors, downcast, dtype_backend)\u001b[0m\n\u001b[0;32m 230\u001b[0m coerce_numeric \u001b[38;5;241m=\u001b[39m errors \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m (\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mignore\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mraise\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m 231\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 232\u001b[0m values, new_mask \u001b[38;5;241m=\u001b[39m lib\u001b[38;5;241m.\u001b[39mmaybe_convert_numeric( \u001b[38;5;66;03m# type: ignore[call-overload]\u001b[39;00m\n\u001b[0;32m 233\u001b[0m values,\n\u001b[0;32m 234\u001b[0m \u001b[38;5;28mset\u001b[39m(),\n\u001b[0;32m 235\u001b[0m coerce_numeric\u001b[38;5;241m=\u001b[39mcoerce_numeric,\n\u001b[0;32m 236\u001b[0m convert_to_masked_nullable\u001b[38;5;241m=\u001b[39mdtype_backend \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m lib\u001b[38;5;241m.\u001b[39mno_default\n\u001b[0;32m 237\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(values_dtype, StringDtype)\n\u001b[0;32m 238\u001b[0m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m values_dtype\u001b[38;5;241m.\u001b[39mstorage \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpyarrow_numpy\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m 239\u001b[0m )\n\u001b[0;32m 240\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mValueError\u001b[39;00m, \u001b[38;5;167;01mTypeError\u001b[39;00m):\n\u001b[0;32m 241\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m errors \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mraise\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n", + "File \u001b[1;32mlib.pyx:2433\u001b[0m, in \u001b[0;36mpandas._libs.lib.maybe_convert_numeric\u001b[1;34m()\u001b[0m\n", + "\u001b[1;31mTypeError\u001b[0m: Invalid object type at position 0" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Crear una columna binaria que indique si la solicitud fue aprobada\n", + "merged_df2['aprobada'] = merged_df2['recovery_status'] == 'approved'\n", + "\n", + "# Aseguramos que la columna 'aprobada' solo tenga valores no nulos\n", + "merged_df2['aprobada'] = merged_df2['aprobada'].fillna(False) # Para evitar valores nulos\n", + "\n", + "# Calcular la cantidad total de solicitudes por cohorte\n", + "cohort_counts = merged_df2.groupby('cohort')['id_x'].count().reset_index()\n", + "cohort_counts.columns = ['Cohorte', 'Total Solicitudes']\n", + "\n", + "# Calcular la cantidad de solicitudes aprobadas por cohorte\n", + "approved_requests = merged_df2[merged_df2['aprobada']].groupby('cohort')['id_x'].count().reset_index()\n", + "approved_requests.columns = ['Cohorte', 'Solicitudes Aprobadas']\n", + "\n", + "# Combinar los dos resultados en un dataframe\n", + "cohort_approval_rate = pd.merge(cohort_counts, approved_requests, on='Cohorte', how='left')\n", + "\n", + "# Calcular la tasa de solicitudes aprobadas\n", + "cohort_approval_rate['Tasa de Solicitudes Aprobadas'] = cohort_approval_rate['Solicitudes Aprobadas'] / cohort_approval_rate['Total Solicitudes']\n", + "\n", + "# Llenar valores nulos con 0 para cohortes sin solicitudes aprobadas\n", + "cohort_approval_rate['Solicitudes Aprobadas'] = cohort_approval_rate['Solicitudes Aprobadas'].fillna(0)\n", + "cohort_approval_rate['Tasa de Solicitudes Aprobadas'] = cohort_approval_rate['Tasa de Solicitudes Aprobadas'].fillna(0)\n", + "\n", + "\n", + "# Mostrar los resultados\n", + "print(cohort_approval_rate)\n", + "\n", + "\n", + "plt.figure(figsize=(12, 6))\n", + "sns.lineplot(data=cohort_approval_rate, x='Cohorte', y='Tasa de Solicitudes Aprobadas', marker='o', color='blue')\n", + "plt.title('Tasa de Solicitudes Aprobadas por Cohorte')\n", + "plt.xlabel('Cohorte (Mes y Año)')\n", + "plt.ylabel('Tasa de Solicitudes Aprobadas')\n", + "plt.xticks(rotation=45)\n", + "plt.ylim(0, 1)\n", + "plt.show()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 369, + "id": "8c04e754-602e-4f78-b548-b70630af6dd1", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0\n" + ] + } + ], + "source": [ + "contador = 0\n", + "\n", + "for elements in merged_df['recovery_status']:\n", + " if elements == 'rejected':\n", + " contador += 1\n", + "\n", + "print(contador)" + ] + }, + { + "cell_type": "code", + "execution_count": 375, + "id": "342a826c-58c8-4dfd-ab2a-02e79039a3dc", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0\n" + ] + }, + { + "data": { + "text/plain": [ + "0 False\n", + "1 False\n", + "2 False\n", + "3 False\n", + "4 False\n", + " ... \n", + "32089 False\n", + "32090 False\n", + "32091 False\n", + "32092 False\n", + "32093 False\n", + "Name: aprobada, Length: 32094, dtype: bool" + ] + }, + "execution_count": 375, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Crear una columna binaria que indique si la solicitud fue aprobada\n", + "merged_df2['aprobada'] = merged_df2['recovery_status'] == 'approved'\n", + "\n", + "# Aseguramos que la columna 'aprobada' solo tenga valores no nulos\n", + "merged_df2['aprobada'] = merged_df2['aprobada'].fillna(True) # Para evitar valores nulos\n", + "\n", + "merged_df2['aprobada']" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "c87390ae-9d3d-4198-b30c-8de1933b86ec", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.12.7" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +}