diff --git a/PerformanceOfAlgorithms.xlsx b/ClassificationCharacteristicsOfAlgorithms.xlsx
similarity index 100%
rename from PerformanceOfAlgorithms.xlsx
rename to ClassificationCharacteristicsOfAlgorithms.xlsx
diff --git a/Jupyter Notebooks/PredictionScoreSheet.ipynb b/Jupyter Notebooks/PredictionScoreSheet.ipynb
new file mode 100644
index 0000000..1cac366
--- /dev/null
+++ b/Jupyter Notebooks/PredictionScoreSheet.ipynb
@@ -0,0 +1,277 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Functions to Create Prediction Score Sheet\n",
+ "\n",
+ "This jupyter notebook was created for the purpose of querying the REST API programmatically and obtain results of the predction since there were a lot of Quarter's to be analyzed."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "import matplotlib.pyplot as plt\n",
+ "import seaborn as sns\n",
+ "import datetime"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 20,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "linearregoutfile=r\"C:\\Users\\Manasi\\Desktop\\linearregoutfile.csv\"\n",
+ "neuralnetworksoutfile=r\"C:\\Users\\Manasi\\Desktop\\neuralnetwokoutfile.csv\"\n",
+ "boosteddecisiontreeoutfiler=r\"C:\\Users\\Manasi\\Desktop\\boosteddecisiontree.csv\""
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 21,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "df=pd.read_csv(r\"C:\\Users\\Manasi\\Desktop\\predictionTestCases.csv\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 22,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "
\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " OG_QUARTER_YEAR | \n",
+ " CREDITSCORE | \n",
+ " FIRST_HOME_BUYER_FLAG | \n",
+ " OG_UPB | \n",
+ " OG_LOANTERM | \n",
+ " SELLER_NAME | \n",
+ " SERVICE_NAME | \n",
+ " ORIGINAL_INTERESTRATE | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " 0 | \n",
+ " Q1 1999 | \n",
+ " 615 | \n",
+ " Y | \n",
+ " 48000 | \n",
+ " 360 | \n",
+ " Other sellers | \n",
+ " Other servicers | \n",
+ " 5.375 | \n",
+ "
\n",
+ " \n",
+ " 1 | \n",
+ " Q1 1999 | \n",
+ " 791 | \n",
+ " N | \n",
+ " 284000 | \n",
+ " 312 | \n",
+ " Other sellers | \n",
+ " Other servicers | \n",
+ " 5.750 | \n",
+ "
\n",
+ " \n",
+ " 2 | \n",
+ " Q2 1999 | \n",
+ " 574 | \n",
+ " N | \n",
+ " 162000 | \n",
+ " 325 | \n",
+ " Other sellers | \n",
+ " Other servicers | \n",
+ " 6.875 | \n",
+ "
\n",
+ " \n",
+ " 3 | \n",
+ " Q2 1999 | \n",
+ " 716 | \n",
+ " Y | \n",
+ " 70000 | \n",
+ " 360 | \n",
+ " NORWEST MORTGAGE, IN | \n",
+ " WELLSFARGOHOMEMORTGA | \n",
+ " 7.125 | \n",
+ "
\n",
+ " \n",
+ " 4 | \n",
+ " Q3 1999 | \n",
+ " 642 | \n",
+ " N | \n",
+ " 178000 | \n",
+ " 329 | \n",
+ " Other sellers | \n",
+ " Other servicers | \n",
+ " 7.125 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
"
+ ],
+ "text/plain": [
+ " OG_QUARTER_YEAR CREDITSCORE FIRST_HOME_BUYER_FLAG OG_UPB OG_LOANTERM \\\n",
+ "0 Q1 1999 615 Y 48000 360 \n",
+ "1 Q1 1999 791 N 284000 312 \n",
+ "2 Q2 1999 574 N 162000 325 \n",
+ "3 Q2 1999 716 Y 70000 360 \n",
+ "4 Q3 1999 642 N 178000 329 \n",
+ "\n",
+ " SELLER_NAME SERVICE_NAME ORIGINAL_INTERESTRATE \n",
+ "0 Other sellers Other servicers 5.375 \n",
+ "1 Other sellers Other servicers 5.750 \n",
+ "2 Other sellers Other servicers 6.875 \n",
+ "3 NORWEST MORTGAGE, IN WELLSFARGOHOMEMORTGA 7.125 \n",
+ "4 Other sellers Other servicers 7.125 "
+ ]
+ },
+ "execution_count": 22,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df.head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "import os\n",
+ "import json\n",
+ "import requests\n",
+ "from flask import Flask, render_template, request, jsonify"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 35,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "def get_prediction(og_quarter_year,credit_score,og_first_time_home_buyer,og_upb,og_loan_term,og_seller_name,og_servicer_name,algoType):\n",
+ "\n",
+ " #print(str(algoType)+\"\\t\"+str(credit_score)+\"\\t\"+str(og_first_time_home_buyer)+\"\\t\"+str(og_upb)+\"\\t\"+str(og_loan_term)+\"\\t\"+str(og_quarter_year)+\"\\t\"+str(og_seller_name)+\"\\t\"+str(og_servicer_name))\n",
+ " #make ai call\n",
+ " if algoType==\"pred_df\":\n",
+ " url=\"https://ussouthcentral.services.azureml.net/workspaces/43247f6706b64e68a8b7d22ff16a2a4f/services/89403771d86f46e887c4d27b6eb80908/execute?api-version=2.0&details=true\"\n",
+ " api_key='4/1AxmSvNJyjoFfc1SRtNHf8Znsr7/51JGIcH4Pxb7tI+1NEWrXlXzwUwy5/k5rBDz9kLENVEpt/iY2E/Tkt3g=='\n",
+ " elif algoType==\"pred_nn\":\n",
+ " url=\"https://ussouthcentral.services.azureml.net/workspaces/43247f6706b64e68a8b7d22ff16a2a4f/services/964b03c9c6fa480ca1156bd093eb9ff4/execute?api-version=2.0&details=true\"\n",
+ " api_key=\"A2fylieTrkGctlekKOCkblCgcEZkxq06AHi8fuE69A9MFfVeKHfVj2uMftzuN+utNqV3Wfuyhj1HmM8F4Fj/8g==\"\n",
+ " elif algoType==\"pred_lr\":\n",
+ " url=\"https://ussouthcentral.services.azureml.net/workspaces/43247f6706b64e68a8b7d22ff16a2a4f/services/1f553c369b314b9dad2097ff5c012200/execute?api-version=2.0&details=true\"\n",
+ " api_key=\"cz3t27xidE9ehvF8jtVhP0+s97DKnKqOLaodqaXC8I3Vmn844xIqjoAN8Q/enkiA1HXaOIvSLZQgi/SjaXfX2Q==\"\n",
+ " \n",
+ " \n",
+ " data = {\n",
+ " \n",
+ " \"Inputs\": {\n",
+ " \n",
+ " \"input1\":\n",
+ " {\n",
+ " \"ColumnNames\": [\"CREDIT_SCORE\", \"FIRST_HOME_BUYER_FLAG\", \"OG_UPB\", \"OG_LOANTERM\", \"SELLER_NAME\", \"SERVICE_NAME\", \"OG_QUARTERYEAR\"],\n",
+ " \"Values\": [ [credit_score,og_first_time_home_buyer,og_upb,og_loan_term,og_seller_name,og_servicer_name,og_quarter_year]]\n",
+ " }, },\n",
+ " \"GlobalParameters\": {\n",
+ " }\n",
+ " }\n",
+ " \n",
+ " body = str.encode(json.dumps(data))\n",
+ " \n",
+ " #url = 'https://ussouthcentral.services.azureml.net/workspaces/5de0e8bd28f74cf9a40babb3f1799a53/services/300d6267d2f843c9a5975621ff077a09/execute?api-version=2.0&details=true'\n",
+ " #api_key = 'wQWgTpa3GyVACzg7Q6jVDdwt5JEDnfdvqqG21PKDr+UHmZWRQJh1XfrtLVON846vEDEXoDgnruZ1s9zd4Drzyw==' # Replace this with the API key for the web service\n",
+ " headers = {'Content-Type':'application/json', 'Authorization':('Bearer '+ api_key)}\n",
+ " \n",
+ " response = requests.post(url, data=body,headers=headers)\n",
+ " #print(response.content)\n",
+ " \n",
+ " response_json=json.loads(response.content)\n",
+ " predicted_interest_rate=response_json['Results']['output1']['value']['Values'][0][7]\n",
+ " \n",
+ " return_dict = {\"predicted_interest_rate\":predicted_interest_rate}\n",
+ " return predicted_interest_rate\n",
+ " "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 36,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "\n",
+ "def writePredOutputToFile(outfile,algo_type):\n",
+ " with open(outfile,\"w\") as fil:\n",
+ " for index, row in df.iterrows():\n",
+ " fil.write(get_prediction(row.OG_QUARTER_YEAR,row.CREDITSCORE,row.FIRST_HOME_BUYER_FLAG,row.OG_UPB,row.OG_LOANTERM,row.SELLER_NAME,row.SERVICE_NAME,algo_type))\n",
+ " fil.write(\"\\n\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 38,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "writePredOutputToFile(linearregoutfile,'pred_lr')\n",
+ "writePredOutputToFile(neuralnetworksoutfile,'pred_nn')\n",
+ "writePredOutputToFile(boosteddecisiontreeoutfiler,'pred_df')"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3",
+ "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": "3.6.0"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/PredictionModelErrorMetrics.xlsx b/PredictionModelErrorMetrics.xlsx
new file mode 100644
index 0000000..19c9b29
Binary files /dev/null and b/PredictionModelErrorMetrics.xlsx differ
diff --git a/Team1_Assignment3_Report.docx b/Team1_Assignment3_Report.docx
new file mode 100644
index 0000000..67928f3
Binary files /dev/null and b/Team1_Assignment3_Report.docx differ
diff --git a/Team1_Assignment3_Report.pdf b/Team1_Assignment3_Report.pdf
new file mode 100644
index 0000000..2bdde7e
Binary files /dev/null and b/Team1_Assignment3_Report.pdf differ
diff --git a/Test Cases/ClassificationTestCases.xlsx b/Test Cases/ClassificationTestCases.xlsx
new file mode 100644
index 0000000..0054217
Binary files /dev/null and b/Test Cases/ClassificationTestCases.xlsx differ
diff --git a/Test Cases/PredictionTestCases.xlsx b/Test Cases/PredictionTestCases.xlsx
new file mode 100644
index 0000000..3f796b6
Binary files /dev/null and b/Test Cases/PredictionTestCases.xlsx differ