coursera_assignment.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "<a href=\"https://www.bigdatauniversity.com\"><img src=\"https://ibm.box.com/shared/static/cw2c7r3o20w9zn8gkecaeyjhgw3xdgbj.png\" width=\"400\" align=\"center\"></a>\n",
    "\n",
    "<h1 align=\"center\"><font size=\"5\">Classification with Python</font></h1>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "In this notebook we try to practice all the classification algorithms that we learned in this course.\n",
    "\n",
    "We load a dataset using Pandas library, and apply the following algorithms, and find the best one for this specific dataset by accuracy evaluation methods.\n",
    "\n",
    "Lets first load required libraries:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "outputs": [],
   "source": [
    "import itertools\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from matplotlib.ticker import NullFormatter\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.ticker as ticker\n",
    "from sklearn import preprocessing\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "### About dataset"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "This dataset is about past loans. The __Loan_train.csv__ data set includes details of 346 customers whose loan are already paid off or defaulted. It includes following fields:\n",
    "\n",
    "| Field          | Description                                                                           |\n",
    "|----------------|---------------------------------------------------------------------------------------|\n",
    "| Loan_status    | Whether a loan is paid off on in collection                                           |\n",
    "| Principal      | Basic principal loan amount at the                                                    |\n",
    "| Terms          | Origination terms which can be weekly (7 days), biweekly, and monthly payoff schedule |\n",
    "| Effective_date | When the loan got originated and took effects                                         |\n",
    "| Due_date       | Since it’s one-time payoff schedule, each loan has one single due date                |\n",
    "| Age            | Age of applicant                                                                      |\n",
    "| Education      | Education of applicant                                                                |\n",
    "| Gender         | The gender of applicant                                                               |"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "Lets download the dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "--2019-11-22 10:37:01--  https://s3-api.us-geo.objectstorage.softlayer.net/cf-courses-data/CognitiveClass/ML0101ENv3/labs/loan_train.csv\n",
      "Resolving s3-api.us-geo.objectstorage.softlayer.net (s3-api.us-geo.objectstorage.softlayer.net)... 67.228.254.196\n",
      "Connecting to s3-api.us-geo.objectstorage.softlayer.net (s3-api.us-geo.objectstorage.softlayer.net)|67.228.254.196|:443... connected.\n",
      "HTTP request sent, awaiting response... 200 OK\n",
      "Length: 23101 (23K) [text/csv]\n",
      "Saving to: ‘loan_train.csv’\n",
      "\n",
      "100%[======================================>] 23,101      --.-K/s   in 0.002s  \n",
      "\n",
      "2019-11-22 10:37:01 (14.2 MB/s) - ‘loan_train.csv’ saved [23101/23101]\n",
      "\n"
     ]
    }
   ],
   "source": [
    "!wget -O loan_train.csv https://s3-api.us-geo.objectstorage.softlayer.net/cf-courses-data/CognitiveClass/ML0101ENv3/labs/loan_train.csv"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "### Load Data From CSV File  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Unnamed: 0</th>\n",
       "      <th>Unnamed: 0.1</th>\n",
       "      <th>loan_status</th>\n",
       "      <th>Principal</th>\n",
       "      <th>terms</th>\n",
       "      <th>effective_date</th>\n",
       "      <th>due_date</th>\n",
       "      <th>age</th>\n",
       "      <th>education</th>\n",
       "      <th>Gender</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>9/8/2016</td>\n",
       "      <td>10/7/2016</td>\n",
       "      <td>45</td>\n",
       "      <td>High School or Below</td>\n",
       "      <td>male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>9/8/2016</td>\n",
       "      <td>10/7/2016</td>\n",
       "      <td>33</td>\n",
       "      <td>Bechalor</td>\n",
       "      <td>female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>1000</td>\n",
       "      <td>15</td>\n",
       "      <td>9/8/2016</td>\n",
       "      <td>9/22/2016</td>\n",
       "      <td>27</td>\n",
       "      <td>college</td>\n",
       "      <td>male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>9/9/2016</td>\n",
       "      <td>10/8/2016</td>\n",
       "      <td>28</td>\n",
       "      <td>college</td>\n",
       "      <td>female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6</td>\n",
       "      <td>6</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>9/9/2016</td>\n",
       "      <td>10/8/2016</td>\n",
       "      <td>29</td>\n",
       "      <td>college</td>\n",
       "      <td>male</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Unnamed: 0  Unnamed: 0.1 loan_status  Principal  terms effective_date  \\\n",
       "0           0             0     PAIDOFF       1000     30       9/8/2016   \n",
       "1           2             2     PAIDOFF       1000     30       9/8/2016   \n",
       "2           3             3     PAIDOFF       1000     15       9/8/2016   \n",
       "3           4             4     PAIDOFF       1000     30       9/9/2016   \n",
       "4           6             6     PAIDOFF       1000     30       9/9/2016   \n",
       "\n",
       "    due_date  age             education  Gender  \n",
       "0  10/7/2016   45  High School or Below    male  \n",
       "1  10/7/2016   33              Bechalor  female  \n",
       "2  9/22/2016   27               college    male  \n",
       "3  10/8/2016   28               college  female  \n",
       "4  10/8/2016   29               college    male  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('loan_train.csv')\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(346, 10)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "### Convert to date time object "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Unnamed: 0</th>\n",
       "      <th>Unnamed: 0.1</th>\n",
       "      <th>loan_status</th>\n",
       "      <th>Principal</th>\n",
       "      <th>terms</th>\n",
       "      <th>effective_date</th>\n",
       "      <th>due_date</th>\n",
       "      <th>age</th>\n",
       "      <th>education</th>\n",
       "      <th>Gender</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>2016-09-08</td>\n",
       "      <td>2016-10-07</td>\n",
       "      <td>45</td>\n",
       "      <td>High School or Below</td>\n",
       "      <td>male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>2016-09-08</td>\n",
       "      <td>2016-10-07</td>\n",
       "      <td>33</td>\n",
       "      <td>Bechalor</td>\n",
       "      <td>female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>1000</td>\n",
       "      <td>15</td>\n",
       "      <td>2016-09-08</td>\n",
       "      <td>2016-09-22</td>\n",
       "      <td>27</td>\n",
       "      <td>college</td>\n",
       "      <td>male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>2016-09-09</td>\n",
       "      <td>2016-10-08</td>\n",
       "      <td>28</td>\n",
       "      <td>college</td>\n",
       "      <td>female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6</td>\n",
       "      <td>6</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>2016-09-09</td>\n",
       "      <td>2016-10-08</td>\n",
       "      <td>29</td>\n",
       "      <td>college</td>\n",
       "      <td>male</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Unnamed: 0  Unnamed: 0.1 loan_status  Principal  terms effective_date  \\\n",
       "0           0             0     PAIDOFF       1000     30     2016-09-08   \n",
       "1           2             2     PAIDOFF       1000     30     2016-09-08   \n",
       "2           3             3     PAIDOFF       1000     15     2016-09-08   \n",
       "3           4             4     PAIDOFF       1000     30     2016-09-09   \n",
       "4           6             6     PAIDOFF       1000     30     2016-09-09   \n",
       "\n",
       "    due_date  age             education  Gender  \n",
       "0 2016-10-07   45  High School or Below    male  \n",
       "1 2016-10-07   33              Bechalor  female  \n",
       "2 2016-09-22   27               college    male  \n",
       "3 2016-10-08   28               college  female  \n",
       "4 2016-10-08   29               college    male  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['due_date'] = pd.to_datetime(df['due_date'])\n",
    "df['effective_date'] = pd.to_datetime(df['effective_date'])\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "# Data visualization and pre-processing\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "Let’s see how many of each class is in our data set "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 340,
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "PAIDOFF       260\n",
       "COLLECTION     86\n",
       "Name: loan_status, dtype: int64"
      ]
     },
     "execution_count": 340,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['loan_status'].value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "260 people have paid off the loan on time while 86 have gone into collection \n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Lets plot some columns to underestand data better:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Solving environment: done\n",
      "\n",
      "## Package Plan ##\n",
      "\n",
      "  environment location: /opt/conda/envs/Python36\n",
      "\n",
      "  added / updated specs: \n",
      "    - seaborn\n",
      "\n",
      "\n",
      "The following packages will be downloaded:\n",
      "\n",
      "    package                    |            build\n",
      "    ---------------------------|-----------------\n",
      "    certifi-2019.9.11          |           py36_0         154 KB  anaconda\n",
      "    openssl-1.1.1              |       h7b6447c_0         5.0 MB  anaconda\n",
      "    seaborn-0.9.0              |     pyh91ea838_1         164 KB  anaconda\n",
      "    ca-certificates-2019.10.16 |                0         131 KB  anaconda\n",
      "    ------------------------------------------------------------\n",
      "                                           Total:         5.5 MB\n",
      "\n",
      "The following packages will be UPDATED:\n",
      "\n",
      "    ca-certificates: 2019.10.16-0      --> 2019.10.16-0       anaconda\n",
      "    certifi:         2019.9.11-py36_0  --> 2019.9.11-py36_0   anaconda\n",
      "    openssl:         1.1.1d-h7b6447c_3 --> 1.1.1-h7b6447c_0   anaconda\n",
      "    seaborn:         0.9.0-py36_0      --> 0.9.0-pyh91ea838_1 anaconda\n",
      "\n",
      "\n",
      "Downloading and Extracting Packages\n",
      "certifi-2019.9.11    | 154 KB    | ##################################### | 100% \n",
      "openssl-1.1.1        | 5.0 MB    | ##################################### | 100% \n",
      "seaborn-0.9.0        | 164 KB    | ##################################### | 100% \n",
      "ca-certificates-2019 | 131 KB    | ##################################### | 100% \n",
      "Preparing transaction: done\n",
      "Verifying transaction: done\n",
      "Executing transaction: done\n"
     ]
    }
   ],
   "source": [
    "# notice: installing seaborn might takes a few minutes\n",
    "!conda install -c anaconda seaborn -y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x216 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import seaborn as sns\n",
    "\n",
    "bins = np.linspace(df.Principal.min(), df.Principal.max(), 10)\n",
    "g = sns.FacetGrid(df, col=\"Gender\", hue=\"loan_status\", palette=\"Set1\", col_wrap=2)\n",
    "g.map(plt.hist, 'Principal', bins=bins, ec=\"k\")\n",
    "\n",
    "g.axes[-1].legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x216 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "bins = np.linspace(df.age.min(), df.age.max(), 10)\n",
    "g = sns.FacetGrid(df, col=\"Gender\", hue=\"loan_status\", palette=\"Set1\", col_wrap=2)\n",
    "g.map(plt.hist, 'age', bins=bins, ec=\"k\")\n",
    "\n",
    "g.axes[-1].legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "# Pre-processing:  Feature selection/extraction"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "### Lets look at the day of the week people get the loan "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x216 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df['dayofweek'] = df['effective_date'].dt.dayofweek\n",
    "bins = np.linspace(df.dayofweek.min(), df.dayofweek.max(), 10)\n",
    "g = sns.FacetGrid(df, col=\"Gender\", hue=\"loan_status\", palette=\"Set1\", col_wrap=2)\n",
    "g.map(plt.hist, 'dayofweek', bins=bins, ec=\"k\")\n",
    "g.axes[-1].legend()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "We see that people who get the loan at the end of the week dont pay it off, so lets use Feature binarization to set a threshold values less then day 4 "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Unnamed: 0</th>\n",
       "      <th>Unnamed: 0.1</th>\n",
       "      <th>loan_status</th>\n",
       "      <th>Principal</th>\n",
       "      <th>terms</th>\n",
       "      <th>effective_date</th>\n",
       "      <th>due_date</th>\n",
       "      <th>age</th>\n",
       "      <th>education</th>\n",
       "      <th>Gender</th>\n",
       "      <th>dayofweek</th>\n",
       "      <th>weekend</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>2016-09-08</td>\n",
       "      <td>2016-10-07</td>\n",
       "      <td>45</td>\n",
       "      <td>High School or Below</td>\n",
       "      <td>male</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>2016-09-08</td>\n",
       "      <td>2016-10-07</td>\n",
       "      <td>33</td>\n",
       "      <td>Bechalor</td>\n",
       "      <td>female</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>1000</td>\n",
       "      <td>15</td>\n",
       "      <td>2016-09-08</td>\n",
       "      <td>2016-09-22</td>\n",
       "      <td>27</td>\n",
       "      <td>college</td>\n",
       "      <td>male</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>2016-09-09</td>\n",
       "      <td>2016-10-08</td>\n",
       "      <td>28</td>\n",
       "      <td>college</td>\n",
       "      <td>female</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6</td>\n",
       "      <td>6</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>2016-09-09</td>\n",
       "      <td>2016-10-08</td>\n",
       "      <td>29</td>\n",
       "      <td>college</td>\n",
       "      <td>male</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Unnamed: 0  Unnamed: 0.1 loan_status  Principal  terms effective_date  \\\n",
       "0           0             0     PAIDOFF       1000     30     2016-09-08   \n",
       "1           2             2     PAIDOFF       1000     30     2016-09-08   \n",
       "2           3             3     PAIDOFF       1000     15     2016-09-08   \n",
       "3           4             4     PAIDOFF       1000     30     2016-09-09   \n",
       "4           6             6     PAIDOFF       1000     30     2016-09-09   \n",
       "\n",
       "    due_date  age             education  Gender  dayofweek  weekend  \n",
       "0 2016-10-07   45  High School or Below    male          3        0  \n",
       "1 2016-10-07   33              Bechalor  female          3        0  \n",
       "2 2016-09-22   27               college    male          3        0  \n",
       "3 2016-10-08   28               college  female          4        1  \n",
       "4 2016-10-08   29               college    male          4        1  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['weekend'] = df['dayofweek'].apply(lambda x: 1 if (x>3)  else 0)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "## Convert Categorical features to numerical values"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "Lets look at gender:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Gender  loan_status\n",
       "female  PAIDOFF        0.865385\n",
       "        COLLECTION     0.134615\n",
       "male    PAIDOFF        0.731293\n",
       "        COLLECTION     0.268707\n",
       "Name: loan_status, dtype: float64"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby(['Gender'])['loan_status'].value_counts(normalize=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "86 % of female pay there loans while only 73 % of males pay there loan\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "Lets convert male to 0 and female to 1:\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Unnamed: 0</th>\n",
       "      <th>Unnamed: 0.1</th>\n",
       "      <th>loan_status</th>\n",
       "      <th>Principal</th>\n",
       "      <th>terms</th>\n",
       "      <th>effective_date</th>\n",
       "      <th>due_date</th>\n",
       "      <th>age</th>\n",
       "      <th>education</th>\n",
       "      <th>Gender</th>\n",
       "      <th>dayofweek</th>\n",
       "      <th>weekend</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>2016-09-08</td>\n",
       "      <td>2016-10-07</td>\n",
       "      <td>45</td>\n",
       "      <td>High School or Below</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>2016-09-08</td>\n",
       "      <td>2016-10-07</td>\n",
       "      <td>33</td>\n",
       "      <td>Bechalor</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>1000</td>\n",
       "      <td>15</td>\n",
       "      <td>2016-09-08</td>\n",
       "      <td>2016-09-22</td>\n",
       "      <td>27</td>\n",
       "      <td>college</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>2016-09-09</td>\n",
       "      <td>2016-10-08</td>\n",
       "      <td>28</td>\n",
       "      <td>college</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6</td>\n",
       "      <td>6</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>2016-09-09</td>\n",
       "      <td>2016-10-08</td>\n",
       "      <td>29</td>\n",
       "      <td>college</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Unnamed: 0  Unnamed: 0.1 loan_status  Principal  terms effective_date  \\\n",
       "0           0             0     PAIDOFF       1000     30     2016-09-08   \n",
       "1           2             2     PAIDOFF       1000     30     2016-09-08   \n",
       "2           3             3     PAIDOFF       1000     15     2016-09-08   \n",
       "3           4             4     PAIDOFF       1000     30     2016-09-09   \n",
       "4           6             6     PAIDOFF       1000     30     2016-09-09   \n",
       "\n",
       "    due_date  age             education  Gender  dayofweek  weekend  \n",
       "0 2016-10-07   45  High School or Below       0          3        0  \n",
       "1 2016-10-07   33              Bechalor       1          3        0  \n",
       "2 2016-09-22   27               college       0          3        0  \n",
       "3 2016-10-08   28               college       1          4        1  \n",
       "4 2016-10-08   29               college       0          4        1  "
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Gender'].replace(to_replace=['male','female'], value=[0,1],inplace=True)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "## One Hot Encoding  \n",
    "#### How about education?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "education             loan_status\n",
       "Bechalor              PAIDOFF        0.750000\n",
       "                      COLLECTION     0.250000\n",
       "High School or Below  PAIDOFF        0.741722\n",
       "                      COLLECTION     0.258278\n",
       "Master or Above       COLLECTION     0.500000\n",
       "                      PAIDOFF        0.500000\n",
       "college               PAIDOFF        0.765101\n",
       "                      COLLECTION     0.234899\n",
       "Name: loan_status, dtype: float64"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby(['education'])['loan_status'].value_counts(normalize=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "#### Feature befor One Hot Encoding"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Principal</th>\n",
       "      <th>terms</th>\n",
       "      <th>age</th>\n",
       "      <th>Gender</th>\n",
       "      <th>education</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>45</td>\n",
       "      <td>0</td>\n",
       "      <td>High School or Below</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>33</td>\n",
       "      <td>1</td>\n",
       "      <td>Bechalor</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1000</td>\n",
       "      <td>15</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>college</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>28</td>\n",
       "      <td>1</td>\n",
       "      <td>college</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>29</td>\n",
       "      <td>0</td>\n",
       "      <td>college</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Principal  terms  age  Gender             education\n",
       "0       1000     30   45       0  High School or Below\n",
       "1       1000     30   33       1              Bechalor\n",
       "2       1000     15   27       0               college\n",
       "3       1000     30   28       1               college\n",
       "4       1000     30   29       0               college"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[['Principal','terms','age','Gender','education']].head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "#### Use one hot encoding technique to conver categorical varables to binary variables and append them to the feature Data Frame "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Principal</th>\n",
       "      <th>terms</th>\n",
       "      <th>age</th>\n",
       "      <th>Gender</th>\n",
       "      <th>weekend</th>\n",
       "      <th>Bechalor</th>\n",
       "      <th>High School or Below</th>\n",
       "      <th>college</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>45</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>33</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1000</td>\n",
       "      <td>15</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>28</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>29</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Principal  terms  age  Gender  weekend  Bechalor  High School or Below  \\\n",
       "0       1000     30   45       0        0         0                     1   \n",
       "1       1000     30   33       1        0         1                     0   \n",
       "2       1000     15   27       0        0         0                     0   \n",
       "3       1000     30   28       1        1         0                     0   \n",
       "4       1000     30   29       0        1         0                     0   \n",
       "\n",
       "   college  \n",
       "0        0  \n",
       "1        0  \n",
       "2        1  \n",
       "3        1  \n",
       "4        1  "
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Feature = df[['Principal','terms','age','Gender','weekend']]\n",
    "Feature = pd.concat([Feature,pd.get_dummies(df['education'])], axis=1)\n",
    "Feature.drop(['Master or Above'], axis = 1,inplace=True)\n",
    "Feature.head()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "### Feature selection"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "Lets defind feature sets, X:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Principal</th>\n",
       "      <th>terms</th>\n",
       "      <th>age</th>\n",
       "      <th>Gender</th>\n",
       "      <th>weekend</th>\n",
       "      <th>Bechalor</th>\n",
       "      <th>High School or Below</th>\n",
       "      <th>college</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>45</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>33</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1000</td>\n",
       "      <td>15</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>28</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>29</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Principal  terms  age  Gender  weekend  Bechalor  High School or Below  \\\n",
       "0       1000     30   45       0        0         0                     1   \n",
       "1       1000     30   33       1        0         1                     0   \n",
       "2       1000     15   27       0        0         0                     0   \n",
       "3       1000     30   28       1        1         0                     0   \n",
       "4       1000     30   29       0        1         0                     0   \n",
       "\n",
       "   college  \n",
       "0        0  \n",
       "1        0  \n",
       "2        1  \n",
       "3        1  \n",
       "4        1  "
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X = Feature\n",
    "X[0:5]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "What are our lables?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    0\n",
       "1    0\n",
       "2    0\n",
       "3    0\n",
       "4    0\n",
       "Name: loan_status, dtype: int64"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y = df['loan_status'].values\n",
    "y[0:5]\n",
    "y = df['loan_status'].apply(lambda loan_status: 0 if loan_status == 'PAIDOFF' else 1)\n",
    "y[0:5]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "## Normalize Data "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "Data Standardization give data zero mean and unit variance (technically should be done after train test split )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 0.51578458,  0.92071769,  2.33152555, -0.42056004, -1.20577805,\n",
       "        -0.38170062,  1.13639374, -0.86968108],\n",
       "       [ 0.51578458,  0.92071769,  0.34170148,  2.37778177, -1.20577805,\n",
       "         2.61985426, -0.87997669, -0.86968108],\n",
       "       [ 0.51578458, -0.95911111, -0.65321055, -0.42056004, -1.20577805,\n",
       "        -0.38170062, -0.87997669,  1.14984679],\n",
       "       [ 0.51578458,  0.92071769, -0.48739188,  2.37778177,  0.82934003,\n",
       "        -0.38170062, -0.87997669,  1.14984679],\n",
       "       [ 0.51578458,  0.92071769, -0.3215732 , -0.42056004,  0.82934003,\n",
       "        -0.38170062, -0.87997669,  1.14984679]])"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X= preprocessing.StandardScaler().fit(X).transform(X)\n",
    "X[0:5]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "# Classification "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "# import scoring methods\n",
    "from sklearn.metrics import jaccard_similarity_score\n",
    "from sklearn.metrics import f1_score\n",
    "from sklearn.metrics import log_loss\n",
    "from sklearn.model_selection import cross_val_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "# our data for training (used '_train' just for improving readability)\n",
    "X_train, y_train=X,y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((346, 8), (346,))"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "X_train.shape, y_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "trainScores={}"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "Now, it is your turn, use the training set to build an accurate model. Then use the test set to report the accuracy of the model\n",
    "You should use the following algorithm:\n",
    "- K Nearest Neighbor(KNN)\n",
    "- Decision Tree\n",
    "- Support Vector Machine\n",
    "- Logistic Regression\n",
    "\n",
    "\n",
    "\n",
    "__ Notice:__ \n",
    "- You can go above and change the pre-processing, feature selection, feature-extraction, and so on, to make a better model.\n",
    "- You should use either scikit-learn, Scipy or Numpy libraries for developing the classification algorithms.\n",
    "- You should include the code of the algorithm in the following cells."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# K Nearest Neighbor(KNN)\n",
    "Notice: You should find the best k to build the model with the best accuracy.  \n",
    "**warning:** You should not use the __loan_test.csv__ for finding the best k, however, you can split your train_loan.csv into train and test to find the best __k__."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train set: (276, 8) (276,)\n",
      "Test set: (70, 8) (70,)\n"
     ]
    }
   ],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.2, random_state=4)\n",
    "print ('Train set:', X_train.shape,  y_train.shape)\n",
    "print ('Test set:', X_test.shape,  y_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn import metrics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.67142857, 0.77142857, 0.71428571, 0.77142857, 0.75714286,\n",
       "       0.78571429, 0.78571429, 0.77142857, 0.77142857])"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Ks = 10\n",
    "mean_acc = np.zeros((Ks-1))\n",
    "std_acc = np.zeros((Ks-1))\n",
    "ConfustionMx = [];\n",
    "for n in range(1,Ks):\n",
    "    \n",
    "    #Train Model and Predict  \n",
    "    neigh = KNeighborsClassifier(n_neighbors = n).fit(X_train,y_train)\n",
    "    yhat=neigh.predict(X_test)\n",
    "    mean_acc[n-1] = metrics.accuracy_score(y_test, yhat)\n",
    "\n",
    "    \n",
    "    std_acc[n-1]=np.std(yhat==y_test)/np.sqrt(yhat.shape[0])\n",
    "\n",
    "mean_acc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',\n",
       "           metric_params=None, n_jobs=None, n_neighbors=7, p=2,\n",
       "           weights='uniform')"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "k = 7\n",
    "#Train Model and Predict  \n",
    "neigh = KNeighborsClassifier(n_neighbors = k).fit(X_train,y_train)\n",
    "neigh"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 0, 0, 0])"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "yhat = neigh.predict(X_test)\n",
    "yhat[0:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train set Accuracy:  0.8115942028985508\n",
      "Test set Accuracy:  0.7857142857142857\n"
     ]
    }
   ],
   "source": [
    "print(\"Train set Accuracy: \", metrics.accuracy_score(y_train, neigh.predict(X_train)))\n",
    "print(\"Test set Accuracy: \", metrics.accuracy_score(y_test, yhat))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import jaccard_similarity_score\n",
    "from sklearn.metrics import f1_score\n",
    "from sklearn.metrics import log_loss"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Jaccard score:  0.7857142857142857\n",
      "Logloss score:  0.46719489000030034\n",
      "F1 score:  0.4444444444444445\n"
     ]
    }
   ],
   "source": [
    "print(\"Jaccard score: \", jaccard_similarity_score(y_test,yhat))\n",
    "print(\"Logloss score: \", log_loss(y_test,neigh.predict_proba(X_test)))\n",
    "print(\"F1 score: \", f1_score(y_test,yhat))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Decision Tree"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DecisionTreeClassifier(class_weight=None, criterion='entropy', max_depth=4,\n",
       "            max_features=None, max_leaf_nodes=None,\n",
       "            min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "            min_samples_leaf=1, min_samples_split=2,\n",
       "            min_weight_fraction_leaf=0.0, presort=False, random_state=None,\n",
       "            splitter='best')"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.tree import DecisionTreeClassifier\n",
    "Tree = DecisionTreeClassifier(criterion=\"entropy\", max_depth = 4)\n",
    "Tree"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [],
   "source": [
    "Tree.fit(X_train,y_train)\n",
    "yhat_tree = Tree.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "DecisionTrees's Accuracy:  0.7857142857142857\n",
      "Jaccard score:  0.7857142857142857\n",
      "Logloss score:  1.3752811756372592\n",
      "F1 score:  0.0\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/envs/Python36/lib/python3.6/site-packages/sklearn/metrics/classification.py:1143: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no predicted samples.\n",
      "  'precision', 'predicted', average, warn_for)\n"
     ]
    }
   ],
   "source": [
    "print(\"DecisionTrees's Accuracy: \", metrics.accuracy_score(y_test, yhat_tree))\n",
    "print(\"Jaccard score: \", jaccard_similarity_score(y_test,yhat_tree))\n",
    "print(\"Logloss score: \", log_loss(y_test,Tree.predict_proba(X_test)))\n",
    "print(\"F1 score: \", f1_score(y_test,yhat_tree))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Support Vector Machine"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/envs/Python36/lib/python3.6/site-packages/sklearn/svm/base.py:196: FutureWarning: The default value of gamma will change from 'auto' to 'scale' in version 0.22 to account better for unscaled features. Set gamma explicitly to 'auto' or 'scale' to avoid this warning.\n",
      "  \"avoid this warning.\", FutureWarning)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,\n",
       "  decision_function_shape='ovr', degree=3, gamma='auto_deprecated',\n",
       "  kernel='rbf', max_iter=-1, probability=False, random_state=None,\n",
       "  shrinking=True, tol=0.001, verbose=False)"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn import svm\n",
    "clf = svm.SVC(kernel='rbf')\n",
    "clf.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 0, 0, 0, 0])"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "yhat_svm = clf.predict(X_test)\n",
    "yhat_svm [0:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "SVM's Accuracy:  0.7428571428571429\n"
     ]
    }
   ],
   "source": [
    "print(\"SVM's Accuracy: \", metrics.accuracy_score(y_test, yhat_svm))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import classification_report, confusion_matrix\n",
    "import itertools"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [],
   "source": [
    "def plot_confusion_matrix(cm, classes,\n",
    "                          normalize=False,\n",
    "                          title='Confusion matrix',\n",
    "                          cmap=plt.cm.Blues):\n",
    "    \"\"\"\n",
    "    This function prints and plots the confusion matrix.\n",
    "    Normalization can be applied by setting `normalize=True`.\n",
    "    \"\"\"\n",
    "    if normalize:\n",
    "        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]\n",
    "        print(\"Normalized confusion matrix\")\n",
    "    else:\n",
    "        print('Confusion matrix, without normalization')\n",
    "\n",
    "    print(cm)\n",
    "\n",
    "    plt.imshow(cm, interpolation='nearest', cmap=cmap)\n",
    "    plt.title(title)\n",
    "    plt.colorbar()\n",
    "    tick_marks = np.arange(len(classes))\n",
    "    plt.xticks(tick_marks, classes, rotation=45)\n",
    "    plt.yticks(tick_marks, classes)\n",
    "\n",
    "    fmt = '.2f' if normalize else 'd'\n",
    "    thresh = cm.max() / 2.\n",
    "    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):\n",
    "        plt.text(j, i, format(cm[i, j], fmt),\n",
    "                 horizontalalignment=\"center\",\n",
    "                 color=\"white\" if cm[i, j] > thresh else \"black\")\n",
    "\n",
    "    plt.tight_layout()\n",
    "    plt.ylabel('True label')\n",
    "    plt.xlabel('Predicted label')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.81      0.87      0.84        55\n",
      "           1       0.36      0.27      0.31        15\n",
      "\n",
      "   micro avg       0.74      0.74      0.74        70\n",
      "   macro avg       0.59      0.57      0.57        70\n",
      "weighted avg       0.72      0.74      0.73        70\n",
      "\n",
      "Confusion matrix, without normalization\n",
      "[[48  7]\n",
      " [11  4]]\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "cnf_matrix = confusion_matrix(y_test, yhat_svm, labels=[0,1])\n",
    "np.set_printoptions(precision=2)\n",
    "\n",
    "print (classification_report(y_test, yhat_svm))\n",
    "\n",
    "# Plot non-normalized confusion matrix\n",
    "plt.figure()\n",
    "plot_confusion_matrix(cnf_matrix, classes=['PAIDOFF(0)','COLLECTION(1)'],normalize= False,  title='Confusion matrix')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Logistic Regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LogisticRegression(C=0.01, class_weight=None, dual=False, fit_intercept=True,\n",
       "          intercept_scaling=1, max_iter=100, multi_class='warn',\n",
       "          n_jobs=None, penalty='l2', random_state=None, solver='liblinear',\n",
       "          tol=0.0001, verbose=0, warm_start=False)"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "LR = LogisticRegression(C=0.01, solver='liblinear').fit(X_train,y_train)\n",
    "LR"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0,\n",
       "       1, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 1,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0,\n",
       "       0, 0, 0, 0])"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "yhat_lr = LR.predict(X_test)\n",
    "yhat_lr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.78      0.84      0.81        55\n",
      "           1       0.18      0.13      0.15        15\n",
      "\n",
      "   micro avg       0.69      0.69      0.69        70\n",
      "   macro avg       0.48      0.48      0.48        70\n",
      "weighted avg       0.65      0.69      0.67        70\n",
      "\n",
      "Confusion matrix, without normalization\n",
      "[[46  9]\n",
      " [13  2]]\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Compute confusion matrix\n",
    "cnf_matrix = confusion_matrix(y_test, yhat_lr, labels=[0,1])\n",
    "np.set_printoptions(precision=2)\n",
    "\n",
    "print (classification_report(y_test, yhat_lr))\n",
    "\n",
    "# Plot non-normalized confusion matrix\n",
    "plt.figure()\n",
    "plot_confusion_matrix(cnf_matrix, classes=['PAIDOFF(0)','COLLECTION(1)'],normalize= False,  title='Confusion matrix')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Model Evaluation using Test set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import jaccard_similarity_score\n",
    "from sklearn.metrics import f1_score\n",
    "from sklearn.metrics import log_loss"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "--2019-11-22 11:19:07--  https://s3-api.us-geo.objectstorage.softlayer.net/cf-courses-data/CognitiveClass/ML0101ENv3/labs/loan_test.csv\n",
      "Resolving s3-api.us-geo.objectstorage.softlayer.net (s3-api.us-geo.objectstorage.softlayer.net)... 67.228.254.196\n",
      "Connecting to s3-api.us-geo.objectstorage.softlayer.net (s3-api.us-geo.objectstorage.softlayer.net)|67.228.254.196|:443... connected.\n",
      "HTTP request sent, awaiting response... 200 OK\n",
      "Length: 3642 (3.6K) [text/csv]\n",
      "Saving to: ‘loan_test.csv’\n",
      "\n",
      "100%[======================================>] 3,642       --.-K/s   in 0s      \n",
      "\n",
      "2019-11-22 11:19:07 (210 MB/s) - ‘loan_test.csv’ saved [3642/3642]\n",
      "\n"
     ]
    }
   ],
   "source": [
    "!wget -O loan_test.csv https://s3-api.us-geo.objectstorage.softlayer.net/cf-courses-data/CognitiveClass/ML0101ENv3/labs/loan_test.csv"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "First, download and load the test set:"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "### Load Test set for evaluation "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Unnamed: 0</th>\n",
       "      <th>Unnamed: 0.1</th>\n",
       "      <th>loan_status</th>\n",
       "      <th>Principal</th>\n",
       "      <th>terms</th>\n",
       "      <th>effective_date</th>\n",
       "      <th>due_date</th>\n",
       "      <th>age</th>\n",
       "      <th>education</th>\n",
       "      <th>Gender</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>9/8/2016</td>\n",
       "      <td>10/7/2016</td>\n",
       "      <td>50</td>\n",
       "      <td>Bechalor</td>\n",
       "      <td>female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>300</td>\n",
       "      <td>7</td>\n",
       "      <td>9/9/2016</td>\n",
       "      <td>9/15/2016</td>\n",
       "      <td>35</td>\n",
       "      <td>Master or Above</td>\n",
       "      <td>male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>21</td>\n",
       "      <td>21</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>9/10/2016</td>\n",
       "      <td>10/9/2016</td>\n",
       "      <td>43</td>\n",
       "      <td>High School or Below</td>\n",
       "      <td>female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>24</td>\n",
       "      <td>24</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>9/10/2016</td>\n",
       "      <td>10/9/2016</td>\n",
       "      <td>26</td>\n",
       "      <td>college</td>\n",
       "      <td>male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>35</td>\n",
       "      <td>35</td>\n",
       "      <td>PAIDOFF</td>\n",
       "      <td>800</td>\n",
       "      <td>15</td>\n",
       "      <td>9/11/2016</td>\n",
       "      <td>9/25/2016</td>\n",
       "      <td>29</td>\n",
       "      <td>Bechalor</td>\n",
       "      <td>male</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Unnamed: 0  Unnamed: 0.1 loan_status  Principal  terms effective_date  \\\n",
       "0           1             1     PAIDOFF       1000     30       9/8/2016   \n",
       "1           5             5     PAIDOFF        300      7       9/9/2016   \n",
       "2          21            21     PAIDOFF       1000     30      9/10/2016   \n",
       "3          24            24     PAIDOFF       1000     30      9/10/2016   \n",
       "4          35            35     PAIDOFF        800     15      9/11/2016   \n",
       "\n",
       "    due_date  age             education  Gender  \n",
       "0  10/7/2016   50              Bechalor  female  \n",
       "1  9/15/2016   35       Master or Above    male  \n",
       "2  10/9/2016   43  High School or Below  female  \n",
       "3  10/9/2016   26               college    male  \n",
       "4  9/25/2016   29              Bechalor    male  "
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_df = pd.read_csv('loan_test.csv')\n",
    "test_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_df['due_date'] = pd.to_datetime(test_df['due_date'])\n",
    "test_df['effective_date'] = pd.to_datetime(test_df['effective_date'])\n",
    "test_df['dayofweek'] = test_df['effective_date'].dt.dayofweek\n",
    "test_df['weekend'] = test_df['dayofweek'].apply(lambda x: 1 if (x>3)  else 0)\n",
    "test_df['Gender'].replace(to_replace=['male','female'], value=[0,1],inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Principal</th>\n",
       "      <th>terms</th>\n",
       "      <th>age</th>\n",
       "      <th>Gender</th>\n",
       "      <th>weekend</th>\n",
       "      <th>Bechalor</th>\n",
       "      <th>High School or Below</th>\n",
       "      <th>college</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>300</td>\n",
       "      <td>7</td>\n",
       "      <td>35</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>43</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1000</td>\n",
       "      <td>30</td>\n",
       "      <td>26</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>800</td>\n",
       "      <td>15</td>\n",
       "      <td>29</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Principal  terms  age  Gender  weekend  Bechalor  High School or Below  \\\n",
       "0       1000     30   50       1        0         1                     0   \n",
       "1        300      7   35       0        1         0                     0   \n",
       "2       1000     30   43       1        1         0                     1   \n",
       "3       1000     30   26       0        1         0                     0   \n",
       "4        800     15   29       0        1         1                     0   \n",
       "\n",
       "   college  \n",
       "0        0  \n",
       "1        0  \n",
       "2        0  \n",
       "3        1  \n",
       "4        0  "
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Feature_test = test_df[['Principal','terms','age','Gender','weekend']]\n",
    "Feature_test = pd.concat([Feature_test,pd.get_dummies(test_df['education'])], axis=1)\n",
    "Feature_test.drop(['Master or Above'], axis = 1,inplace=True)\n",
    "Feature_test.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_X = Feature_test\n",
    "test_y = test_df['loan_status'].apply(lambda loan_status: 0 if loan_status == 'PAIDOFF' else 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/envs/Python36/lib/python3.6/site-packages/sklearn/preprocessing/data.py:645: DataConversionWarning: Data with input dtype uint8, int64 were all converted to float64 by StandardScaler.\n",
      "  return self.partial_fit(X, y)\n",
      "/opt/conda/envs/Python36/lib/python3.6/site-packages/ipykernel/__main__.py:1: DataConversionWarning: Data with input dtype uint8, int64 were all converted to float64 by StandardScaler.\n",
      "  if __name__ == '__main__':\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([[ 0.49,  0.93,  3.06,  1.98, -1.3 ,  2.4 , -0.8 , -0.86],\n",
       "       [-3.56, -1.7 ,  0.53, -0.51,  0.77, -0.42, -0.8 , -0.86],\n",
       "       [ 0.49,  0.93,  1.88,  1.98,  0.77, -0.42,  1.25, -0.86],\n",
       "       [ 0.49,  0.93, -0.98, -0.51,  0.77, -0.42, -0.8 ,  1.16],\n",
       "       [-0.67, -0.79, -0.48, -0.51,  0.77,  2.4 , -0.8 , -0.86]])"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_X= preprocessing.StandardScaler().fit(test_X).transform(test_X)\n",
    "test_X[0:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train set Accuracy:  0.8092485549132948\n",
      "Test set Accuracy:  0.7222222222222222\n"
     ]
    }
   ],
   "source": [
    "from sklearn import metrics\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "final_neigh = KNeighborsClassifier(n_neighbors = 7).fit(X,y)\n",
    "yhat_knn = final_neigh.predict(test_X)\n",
    "print(\"Train set Accuracy: \", metrics.accuracy_score(y, final_neigh.predict(X)))\n",
    "print(\"Test set Accuracy: \", metrics.accuracy_score(test_y, yhat_knn))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "KNN Jaccard score:  0.7222222222222222\n",
      "KNN Logloss score:  1.110076176019243\n",
      "KNN F1 score:  0.7001989201477693\n"
     ]
    }
   ],
   "source": [
    "knn_jaccard = jaccard_similarity_score(test_y,yhat_knn)\n",
    "knn_log_loss = log_loss(test_y,final_neigh.predict_proba(test_X))\n",
    "knn_f1 = f1_score(test_y,yhat_knn,average='weighted')\n",
    "print(\"KNN Jaccard score: \", knn_jaccard)\n",
    "print(\"KNN Logloss score: \", knn_log_loss)\n",
    "print(\"KNN F1 score: \", knn_f1)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train set Accuracy:  0.7514450867052023\n",
      "Test set Accuracy:  0.7407407407407407\n"
     ]
    }
   ],
   "source": [
    "from sklearn.tree import DecisionTreeClassifier\n",
    "final_Tree = DecisionTreeClassifier(criterion=\"entropy\", max_depth = 4)\n",
    "final_Tree.fit(X,y)\n",
    "final_yhat_tree = final_Tree.predict(test_X)\n",
    "print(\"Train set Accuracy: \", metrics.accuracy_score(y, final_Tree.predict(X)))\n",
    "print(\"Test set Accuracy: \", metrics.accuracy_score(test_y, final_yhat_tree))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Tree Jaccard score:  0.7407407407407407\n",
      "Tree Logloss score:  0.9910204875489526\n",
      "Tree F1 score:  0.6304176516942475\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/envs/Python36/lib/python3.6/site-packages/sklearn/metrics/classification.py:1143: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 in labels with no predicted samples.\n",
      "  'precision', 'predicted', average, warn_for)\n"
     ]
    }
   ],
   "source": [
    "tree_jaccard = jaccard_similarity_score(test_y,final_yhat_tree)\n",
    "tree_log_loss = log_loss(test_y,final_Tree.predict_proba(test_X))\n",
    "tree_f1 = f1_score(test_y,final_yhat_tree,average='weighted')\n",
    "print(\"Tree Jaccard score: \", tree_jaccard)\n",
    "print(\"Tree Logloss score: \", tree_log_loss)\n",
    "print(\"Tree F1 score: \", tree_f1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train set Accuracy:  0.7601156069364162\n",
      "Test set Accuracy:  0.7222222222222222\n"
     ]
    }
   ],
   "source": [
    "from sklearn import svm\n",
    "clf = svm.SVC(kernel='rbf')\n",
    "clf.fit(X, y)\n",
    "final_yhat_svm = clf.predict(test_X)\n",
    "print(\"Train set Accuracy: \", metrics.accuracy_score(y, clf.predict(X)))\n",
    "print(\"Test set Accuracy: \", metrics.accuracy_score(test_y, final_yhat_svm))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "SVM Jaccard score:  0.7222222222222222\n",
      "SVM F1 score:  0.6212664277180406\n"
     ]
    }
   ],
   "source": [
    "svm_jaccard = jaccard_similarity_score(test_y,final_yhat_svm)\n",
    "#svm_log_loss = log_loss(test_y,clf.predict_proba(test_X))\n",
    "svm_f1 = f1_score(test_y,final_yhat_svm,average='weighted')\n",
    "print(\"SVM Jaccard score: \", svm_jaccard)\n",
    "#print(\"SVM Logloss score: \", svm_log_loss)\n",
    "print(\"SVM F1 score: \", svm_f1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train set Accuracy:  0.7485549132947977\n",
      "Test set Accuracy:  0.7407407407407407\n"
     ]
    }
   ],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "LR = LogisticRegression(C=0.01, solver='liblinear').fit(X,y)\n",
    "final_yhat_lr = LR.predict(test_X)\n",
    "print(\"Train set Accuracy: \", metrics.accuracy_score(y, LR.predict(X)))\n",
    "print(\"Test set Accuracy: \", metrics.accuracy_score(test_y, final_yhat_lr))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "LR Jaccard score:  0.7407407407407407\n",
      "LR Logloss score:  0.5566084946309207\n",
      "LR F1 score:  0.6304176516942475\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/envs/Python36/lib/python3.6/site-packages/sklearn/metrics/classification.py:1143: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 in labels with no predicted samples.\n",
      "  'precision', 'predicted', average, warn_for)\n"
     ]
    }
   ],
   "source": [
    "lr_jaccard = jaccard_similarity_score(test_y,final_yhat_lr)\n",
    "lr_log_loss = log_loss(test_y,LR.predict_proba(test_X))\n",
    "lr_f1 = f1_score(test_y,final_yhat_lr,average='weighted')\n",
    "print(\"LR Jaccard score: \", lr_jaccard)\n",
    "print(\"LR Logloss score: \", lr_log_loss)\n",
    "print(\"LR F1 score: \", lr_f1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table>\n",
       "<thead>\n",
       "<tr><th>Algorithm         </th><th style=\"text-align: right;\">  Jaccard</th><th style=\"text-align: right;\">  F1-score</th><th>LogLoss           </th></tr>\n",
       "</thead>\n",
       "<tbody>\n",
       "<tr><td>KNN               </td><td style=\"text-align: right;\"> 0.722222</td><td style=\"text-align: right;\">  0.700199</td><td>NA                </td></tr>\n",
       "<tr><td>Decision Tree     </td><td style=\"text-align: right;\"> 0.740741</td><td style=\"text-align: right;\">  0.630418</td><td>NA                </td></tr>\n",
       "<tr><td>SVM               </td><td style=\"text-align: right;\"> 0.722222</td><td style=\"text-align: right;\">  0.621266</td><td>NA                </td></tr>\n",
       "<tr><td>LogisticRegression</td><td style=\"text-align: right;\"> 0.740741</td><td style=\"text-align: right;\">  0.630418</td><td>0.5566084946309207</td></tr>\n",
       "</tbody>\n",
       "</table>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "execution_count": 71,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "table = [[\"KNN\",knn_jaccard,knn_f1,'NA'],[\"Decision Tree\",tree_jaccard,tree_f1,'NA'],\n",
    "...          [\"SVM\",svm_jaccard,svm_f1,'NA'],[\"LogisticRegression\",lr_jaccard,lr_f1,lr_log_loss]]\n",
    "\n",
    "from tabulate import tabulate\n",
    "from IPython.display import HTML\n",
    "HTML(tabulate(table, headers= ['Algorithm', 'Jaccard', 'F1-score','LogLoss'], tablefmt='html'))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Report\n",
    "You should be able to report the accuracy of the built model using different evaluation metrics:"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "| Algorithm          |   Jaccard   |   F1-score   | LogLoss |\n",
    "|--------------------|-------------|--------------|---------|\n",
    "| KNN                | 0.722       | 0.700        | NA      |\n",
    "| Decision Tree      | 0.740       | 0.630        | NA      |\n",
    "| SVM                | 0.722       | 0.621        | NA      |\n",
    "| LogisticRegression | 0.740       | 0.630        | 0.556   |"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "button": false,
    "new_sheet": false,
    "run_control": {
     "read_only": false
    }
   },
   "source": [
    "<h2>Want to learn more?</h2>\n",
    "\n",
    "IBM SPSS Modeler is a comprehensive analytics platform that has many machine learning algorithms. It has been designed to bring predictive intelligence to decisions made by individuals, by groups, by systems – by your enterprise as a whole. A free trial is available through this course, available here: <a href=\"http://cocl.us/ML0101EN-SPSSModeler\">SPSS Modeler</a>\n",
    "\n",
    "Also, you can use Watson Studio to run these notebooks faster with bigger datasets. Watson Studio is IBM's leading cloud solution for data scientists, built by data scientists. With Jupyter notebooks, RStudio, Apache Spark and popular libraries pre-packaged in the cloud, Watson Studio enables data scientists to collaborate on their projects without having to install anything. Join the fast-growing community of Watson Studio users today with a free account at <a href=\"https://cocl.us/ML0101EN_DSX\">Watson Studio</a>\n",
    "\n",
    "<h3>Thanks for completing this lesson!</h3>\n",
    "\n",
    "<h4>Author:  <a href=\"https://ca.linkedin.com/in/saeedaghabozorgi\">Saeed Aghabozorgi</a></h4>\n",
    "<p><a href=\"https://ca.linkedin.com/in/saeedaghabozorgi\">Saeed Aghabozorgi</a>, PhD is a Data Scientist in IBM with a track record of developing enterprise level applications that substantially increases clients’ ability to turn data into actionable knowledge. He is a researcher in data mining field and expert in developing advanced analytic methods like machine learning and statistical modelling on large datasets.</p>\n",
    "\n",
    "<hr>\n",
    "\n",
    "<p>Copyright &copy; 2018 <a href=\"https://cocl.us/DX0108EN_CC\">Cognitive Class</a>. This notebook and its source code are released under the terms of the <a href=\"https://bigdatauniversity.com/mit-license/\">MIT License</a>.</p>"
   ]
  }
 ],
 "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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}