KNN_without_Scikit.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 140,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Problem 1\n",
    "#### Preprocessing and data analysis\n",
    "Read the training data from csv file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 141,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5500, 800)"
      ]
     },
     "execution_count": 141,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vstable = pd.read_csv(\"C:/Users/USER/Desktop/DSC/DSC_478 Programming to Machine Learning A/Assignment/Assignment_2/Problem_1/trainMatrixModified.txt\", sep=\"\\t\" , header=None)\n",
    "vstable.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Showing the sample of first 10 rows"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 142,
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>...</th>\n",
       "      <th>790</th>\n",
       "      <th>791</th>\n",
       "      <th>792</th>\n",
       "      <th>793</th>\n",
       "      <th>794</th>\n",
       "      <th>795</th>\n",
       "      <th>796</th>\n",
       "      <th>797</th>\n",
       "      <th>798</th>\n",
       "      <th>799</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>8.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>8.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>10 rows × 800 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   0    1    2    3    4    5    6    7    8    9    ...  790  791  792  793  \\\n",
       "0  2.0  0.0  0.0  2.0  2.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  0.0  0.0   \n",
       "1  2.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  3.0  0.0   \n",
       "2  2.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  0.0  0.0   \n",
       "3  1.0  1.0  1.0  1.0  1.0  1.0  2.0  1.0  1.0  1.0  ...  1.0  1.0  1.0  1.0   \n",
       "4  8.0  1.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  2.0  0.0   \n",
       "5  6.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  0.0  0.0   \n",
       "6  2.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  2.0  0.0  0.0  0.0   \n",
       "7  8.0  0.0  2.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  2.0  0.0  0.0  0.0   \n",
       "8  2.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  0.0  0.0   \n",
       "9  4.0  0.0  1.0  0.0  0.0  0.0  0.0  2.0  0.0  0.0  ...  0.0  0.0  1.0  0.0   \n",
       "\n",
       "   794  795  796  797  798  799  \n",
       "0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "1  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "2  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "3  1.0  1.0  1.0  1.0  1.0  1.0  \n",
       "4  0.0  0.0  0.0  0.0  0.0  1.0  \n",
       "5  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "6  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "7  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "8  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "9  1.0  0.0  0.0  0.0  0.0  0.0  \n",
       "\n",
       "[10 rows x 800 columns]"
      ]
     },
     "execution_count": 142,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vstable.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 143,
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>...</th>\n",
       "      <th>790</th>\n",
       "      <th>791</th>\n",
       "      <th>792</th>\n",
       "      <th>793</th>\n",
       "      <th>794</th>\n",
       "      <th>795</th>\n",
       "      <th>796</th>\n",
       "      <th>797</th>\n",
       "      <th>798</th>\n",
       "      <th>799</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>8.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>8.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>10 rows × 800 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   0    1    2    3    4    5    6    7    8    9    ...  790  791  792  793  \\\n",
       "0  2.0  0.0  0.0  2.0  2.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  0.0  0.0   \n",
       "1  2.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  3.0  0.0   \n",
       "2  2.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  0.0  0.0   \n",
       "3  1.0  1.0  1.0  1.0  1.0  1.0  2.0  1.0  1.0  1.0  ...  1.0  1.0  1.0  1.0   \n",
       "4  8.0  1.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  2.0  0.0   \n",
       "5  6.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  0.0  0.0   \n",
       "6  2.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  2.0  0.0  0.0  0.0   \n",
       "7  8.0  0.0  2.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  2.0  0.0  0.0  0.0   \n",
       "8  2.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  0.0  0.0   \n",
       "9  4.0  0.0  1.0  0.0  0.0  0.0  0.0  2.0  0.0  0.0  ...  0.0  0.0  1.0  0.0   \n",
       "\n",
       "   794  795  796  797  798  799  \n",
       "0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "1  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "2  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "3  1.0  1.0  1.0  1.0  1.0  1.0  \n",
       "4  0.0  0.0  0.0  0.0  0.0  1.0  \n",
       "5  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "6  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "7  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "8  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "9  1.0  0.0  0.0  0.0  0.0  0.0  \n",
       "\n",
       "[10 rows x 800 columns]"
      ]
     },
     "execution_count": 143,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vs_train = vstable.copy()\n",
    "vs_train.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 144,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 5500 entries, 0 to 5499\n",
      "Columns: 800 entries, 0 to 799\n",
      "dtypes: float64(800)\n",
      "memory usage: 33.6 MB\n"
     ]
    }
   ],
   "source": [
    "vs_train.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Read the terms from csv file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 145,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5500, 1)"
      ]
     },
     "execution_count": 145,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# The list of our index terms\n",
    "terms = pd.read_csv(\"C:/Users/USER/Desktop/DSC/DSC_478 Programming to Machine Learning A/Assignment/Assignment_2/Problem_1/modifiedterms.txt\", sep=\"\\t\" , header=None)\n",
    "terms.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 146,
   "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>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>david</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>rex</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>wood</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>subject</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>call</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>librari</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>creat</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>widget</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>multipl</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>time</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         0\n",
       "0    david\n",
       "1      rex\n",
       "2     wood\n",
       "3  subject\n",
       "4     call\n",
       "5  librari\n",
       "6    creat\n",
       "7   widget\n",
       "8  multipl\n",
       "9     time"
      ]
     },
     "execution_count": 146,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "terms.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 147,
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>...</th>\n",
       "      <th>5490</th>\n",
       "      <th>5491</th>\n",
       "      <th>5492</th>\n",
       "      <th>5493</th>\n",
       "      <th>5494</th>\n",
       "      <th>5495</th>\n",
       "      <th>5496</th>\n",
       "      <th>5497</th>\n",
       "      <th>5498</th>\n",
       "      <th>5499</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>795</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>796</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>797</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>798</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>799</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>800 rows × 5500 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     0     1     2     3     4     5     6     7     8     9     ...  5490  \\\n",
       "0     2.0   2.0   2.0   1.0   8.0   6.0   2.0   8.0   2.0   4.0  ...   0.0   \n",
       "1     0.0   0.0   0.0   1.0   1.0   0.0   0.0   0.0   0.0   0.0  ...   0.0   \n",
       "2     0.0   0.0   0.0   1.0   0.0   0.0   0.0   2.0   0.0   1.0  ...   0.0   \n",
       "3     2.0   0.0   0.0   1.0   0.0   0.0   0.0   0.0   0.0   0.0  ...   0.0   \n",
       "4     2.0   0.0   0.0   1.0   0.0   0.0   0.0   0.0   0.0   0.0  ...   0.0   \n",
       "..    ...   ...   ...   ...   ...   ...   ...   ...   ...   ...  ...   ...   \n",
       "795   0.0   0.0   0.0   1.0   0.0   0.0   0.0   0.0   0.0   0.0  ...   0.0   \n",
       "796   0.0   0.0   0.0   1.0   0.0   0.0   0.0   0.0   0.0   0.0  ...   0.0   \n",
       "797   0.0   0.0   0.0   1.0   0.0   0.0   0.0   0.0   0.0   0.0  ...   0.0   \n",
       "798   0.0   0.0   0.0   1.0   0.0   0.0   0.0   0.0   0.0   0.0  ...   0.0   \n",
       "799   0.0   0.0   0.0   1.0   1.0   0.0   0.0   0.0   0.0   0.0  ...   0.0   \n",
       "\n",
       "     5491  5492  5493  5494  5495  5496  5497  5498  5499  \n",
       "0     0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "1     0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "2     0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "3     0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "4     0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "..    ...   ...   ...   ...   ...   ...   ...   ...   ...  \n",
       "795   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "796   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "797   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "798   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "799   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "\n",
       "[800 rows x 5500 columns]"
      ]
     },
     "execution_count": 147,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#transpose the training dataset from term vs. doc into doc. vs term\n",
    "DT = vs_train.T\n",
    "DT"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 148,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(800, 5500)"
      ]
     },
     "execution_count": 148,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "DT.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 149,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of terms: 5500\n",
      "Number of documents: 800\n"
     ]
    }
   ],
   "source": [
    "numTerms=DT.shape[1]\n",
    "NDocs = DT.shape[0]\n",
    "lst = []\n",
    "print('Number of terms:',numTerms)\n",
    "print('Number of documents:',NDocs)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Computing term frequencies to find the distributions across the corpus."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 150,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Term frequencies:\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "0       102.0\n",
       "1        11.0\n",
       "2        22.0\n",
       "3       959.0\n",
       "4       222.0\n",
       "        ...  \n",
       "5495      3.0\n",
       "5496      3.0\n",
       "5497      2.0\n",
       "5498      2.0\n",
       "5499      2.0\n",
       "Length: 5500, dtype: float64"
      ]
     },
     "execution_count": 150,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "termFreqs = vs_train.sum(axis=1)\n",
    "print('Term frequencies:')\n",
    "termFreqs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 151,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYsAAAEWCAYAAACXGLsWAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/d3fzzAAAACXBIWXMAAAsTAAALEwEAmpwYAAAh9klEQVR4nO3deZxddX3/8dd79swkZJ2EkIQsElmEKhi2YiuKCMUl/FoXfj8XVFr6a9Vqtb+C+mu1tvahrWWzthZFf2CRRVCJiEtYtNZHCSSCrIUMYclGMlnIvufz++N8bzhz5yb3ZjJ3zszk/Xw87mPO+Z5zz/18J5P5zHc536OIwMzM7EAaig7AzMwGPycLMzOrysnCzMyqcrIwM7OqnCzMzKwqJwszM6vKycLMzKpysrDCSNqce+2VtC23/56i46sHSWenuubr/sOi4zKrpqnoAOzwFREjS9uSngP+MCLuPphrSGqKiN39HVudrYiIqQc6YYjWy4Yxtyxs0JHUIOlySc9IWivpVknj0rEZkkLSJZJeAO6V9AFJv5J0paSXJC2R9NupfKmk1ZIuzl3/AklPSNokabmkv6gQQ2u61om5ss7U+pkoaYKkO9M56yT9UlKf/z+V1WEt8LkUw5clvSBplaSvSRqRe8//kbRS0gpJH0rfl2PSsZ9L+sOy6/9nbv84SfNT7E9Jelfu2P+T9FVJP0rfowWSXpE7/qrce1dJ+rSkIyVtlTQ+d94pkrolNff1+2KDh5OFDUYfBS4EXg8cBawHvlp2zuuB44Hz0v7pwCPAeOA7wM3AqcAxwHuBf5ZUaslcB/xxRIwCTgTuLQ8gInYA3wP+Z674XcAvImI18ElgGdAJTAI+DRzq2jmnA0vS9b4AfBF4JfCaVI8pwF8DSDof+AvgXGA28KZaP0RSBzCf7Ps0EbgI+BdJJ+ROuwj4G2As0JXiQdIo4G7gJ2T/NscA90TEi8DPyb5HJe8Dbo6IXbXGZoOXk4UNRv8b+ExELEu/tD8HvENSvtv0cxGxJSK2pf1nI+JbEbEHuAWYBnw+InZExM+AnWS/2AB2ASdIOiIi1kfEr/cTx3fIfmmW/K9UVrrGZGB6ROyKiF9G7QutHZVaJKVX6Rfsioj4Sup+2g5cCvx5RKyLiE3A3+fieRfwrYh4LCK2pO9Rrd4KPJe+X7sj4iHgduCduXO+HxEPpFhuJEtYpfe+GBH/FBHbI2JTRCxIx64nS8xIaiRLtN8+iLhsEHOysMFoOvD90i9T4ElgD9lf3CVLy96zKre9DSAiystKLYs/AC4Anpf0C0ln7ieO+4B2SadLmkH2C/P76dg/kv3F/bPU7XV57dVjRUSMyb1urVCnTqAdWJT7PvwklUP2V33+/OcP4vOnA6fnExbwHuDI3Dkv5ra38vL3bhrwzH6uewdZEp5J1uLZEBEPHERcNoh5gNsGo6XAhyLiV+UH0i9tOIQun4h4EJib+tI/AtxK9kuw/Lw9km4l+wt5FXBn+guf9PWTwCfTuMa9kh6MiHv6Ghc967SGLMG9KiKWVzh3ZVnMR5cd30KWbEryiWApWXfauX2IcSk9W1v7RMT29P16L3AcblUMK25Z2GD0NeALkqbDvoHluf1xYUktkt4jaXTqS98I7D3AW74DvJvsL+9SFxSS3irpGEkCNpC1fA50nYMSEXuBrwNXSpqYPnOKpNIYza3ABySdIKkd+GzZJR4Gfl9Sexr0viR37E7glZLeJ6k5vU6VdHwNod0JTJb08TQAP0rS6bnjNwAfAN6Ok8Ww4mRhg9HVwDyyLp5NwP1kg7/95X3Ac5I2ko2P7PeejtQfv4Ws2+fHuUOzyQZ6NwP/BfxLRNwHIOnHkj7dD3FeRtbVdX+K9W7g2BTXj4GryAbnu+g9SH8l2TjNKrKxhBtzddoEvJmshbCCrMvpS0BrtYDSe88F3pbetxh4Q+74r8iS5q8j4mC6xmyQkx9+ZDY8SApgdkR0FRzHvcB3IuIbRcZh/ctjFmbWbySdCpwC9Eu3oQ0e7oYys34h6XqyrrKPlyYC2PDhbigzM6uqbi0LSd9UtszCY7mycWmZgMXp69hULknXSOqS9IikU3LvuTidv1i5JRvMzGzg1K1lIel3yWaK3BARJ6ayfwDWRcQX001MYyPiMkkXkC3xcAHZrJerI+J0ZesBLQTmkM1BXwS8NiLWH+izJ0yYEDNmzKhLvczMhqtFixatiYjOSsfqNsAdEf+Ru4GqZC5wdtq+nmwtmctS+Q1puYT7JY2RNDmdOz8i1gFImg+cD9x0oM+eMWMGCxcu7J+KmJkdJiTtd7rzQA9wT4qIlWn7RV5evmEKPZcuWJbK9lfei6RLJS2UtLC7u7t/ozYzO8wVNhsqtSL6rQ8sIq6NiDkRMaezs2IryszM+migk8Wq1L1E+ro6lS+n5zo3U1PZ/srNzGwADXSymAeUZjRdTLZKZan8/WlW1Blkq1WuBH4KvFnS2DRz6s2pzMzMBlDdBrgl3UQ2QD1B0jKyhc6+CNwq6RKyJZVL6/jfRTYTqotsOeQPAkTEOkl/CzyYzvt8abDbzMwGzrC8KW/OnDnh2VBmZgdH0qKImFPpmJf7MDOzqpwscl7csJ0rfvYUz3RvLjoUM7NBxckiZ9XG7VxzbxfPr91SdChmZoOKk0UFw3AYx8zskDhZ5EhFR2BmNjg5WVTgloWZWU9OFjnCTQszs0qcLCpww8LMrCcni5zSmMVwvFHRzOxQOFmYmVlVThYVuF1hZtaTk0WOp86amVXmZFGBhyzMzHpyssjx1Fkzs8qcLCpy08LMLM/JIsdjFmZmlTlZVOAxCzOznpwsctyyMDOrzMmiAjcszMx6crLIKc2GcjeUmVlPThY57oYyM6vMyaKCcEeUmVkPThY5bliYmVXmZFGBxyzMzHpyssjxmIWZWWVOFhW4YWFm1pOTRQ9uWpiZVeJkUYEfq2pm1pOTRY7HLMzMKnOyMDOzqpwsctywMDOrzMmiAg9ZmJn1VEiykPTnkh6X9JikmyS1SZopaYGkLkm3SGpJ57am/a50fEYd4wK83IeZWbkBTxaSpgB/BsyJiBOBRuAi4EvAlRFxDLAeuCS95RJgfSq/Mp1Xn9jqdWEzsyGuqG6oJmCEpCagHVgJvBG4LR2/Hrgwbc9N+6Tj50j1nbfkbigzs54GPFlExHLgy8ALZEliA7AIeCkidqfTlgFT0vYUYGl67+50/vjy60q6VNJCSQu7u7v7FJunzpqZVVZEN9RYstbCTOAooAM4/1CvGxHXRsSciJjT2dl5iNc61GjMzIaXIrqh3gQ8GxHdEbEL+B5wFjAmdUsBTAWWp+3lwDSAdHw0sLYegcmjFmZmFRWRLF4AzpDUnsYezgGeAO4D3pHOuRi4I23PS/uk4/dGndfjcMPCzKynIsYsFpANVP8aeDTFcC1wGfAJSV1kYxLXpbdcB4xP5Z8ALq9XbB6zMDOrrKn6Kf0vIj4LfLaseAlwWoVztwPvHIi4cp85kB9nZjbo+Q5uMzOrysmiArcrzMx6crLI2Tdm4WxhZtaDk0VOnW8MNzMbspwsKvBCgmZmPTlZ5LhdYWZWmZNFBZ45a2bWk5NFjocszMwqc7KowA0LM7OenCxyvJCgmVllThYVeMzCzKwnJ4scj1mYmVXmZFGB77MwM+vJySLHDQszs8qcLCrwmIWZWU9OFnmpaeFcYWbWk5NFjqfOmplV5mRRifuhzMx6cLLI8dRZM7PKnCwqcLvCzKwnJ4scNyzMzCpzsqjAQxZmZj05WeT4sapmZpU5WVQQblqYmfXgZJHjdoWZWWVOFhW4XWFm1pOTRU5pyMK9UGZmPTlZ5Hi5DzOzypwsKnDDwsysJyeLPDcszMwqcrKowFNnzcx6crLI8T15ZmaVFZIsJI2RdJuk/5b0pKQzJY2TNF/S4vR1bDpXkq6R1CXpEUmnFBGzmdnhrKiWxdXATyLiOODVwJPA5cA9ETEbuCftA/weMDu9LgX+tV5BuWFhZlbZgCcLSaOB3wWuA4iInRHxEjAXuD6ddj1wYdqeC9wQmfuBMZIm1zNGD1mYmfVURMtiJtANfEvSQ5K+IakDmBQRK9M5LwKT0vYUYGnu/ctSWQ+SLpW0UNLC7u7uPgXmhQTNzCorIlk0AacA/xoRJwNbeLnLCYDIpiMd1N/3EXFtRMyJiDmdnZ2HFGD4Tgszsx5qShaSTurHz1wGLIuIBWn/NrLksarUvZS+rk7HlwPTcu+fmsr6ndsVZmaV1dqy+BdJD0j60zTm0GcR8SKwVNKxqegc4AlgHnBxKrsYuCNtzwPen2ZFnQFsyHVX1YXHLMzMemqq5aSI+B1Js4EPAYskPQB8KyLm9/FzPwrcKKkFWAJ8kCxx3SrpEuB54F3p3LuAC4AuYGs6ty72LSRYrw8wMxuiakoWABGxWNL/BRYC1wAnKxsR/nREfO9gPjQiHgbmVDh0ToVzA/jwwVy/rxpStnDLwsysp1rHLH5L0pVk90O8EXhbRByftq+sY3wDqtSy2OtsYWbWQ60ti68A3yBrRWwrFUbEitTaGBYaU7bYu9fJwswsr9Zk8RZgW0TsAZDUALRFxNaI+HbdohtgpW6oPW5ZmJn1UOtsqLuBEbn99lQ2rDQ0pJaFc4WZWQ+1Jou2iNhc2knb7fUJqVgNcjeUmVm5WpPFlvxqr5JeC2w7wPlDVoPkAW4zszK1jll8HPiupBVkNzofCby7XkEVqaFB7oYyMytT6015D0o6Dijddf1UROyqX1jFaZCnzpqZlav5pjzgVGBGes8pkoiIG+oSVYEaJY9ZmJmVqSlZSPo28ArgYWBPKg5g2CWLBslTZ83MytTaspgDnJCW3hjWGhrk5T7MzMrUOhvqMbJB7WGvQbDH3VBmZj3U2rKYADyRVpvdUSqMiLfXJaoCNTZ46qyZWblak8Xn6hnEYCLfZ2Fm1kutU2d/IWk6MDsi7pbUDjTWN7RiZHdwFx2FmdngUusS5X9E9vjTf0tFU4Af1CmmQjW6ZWFm1kutA9wfBs4CNkL2ICRgYr2CKpI8ddbMrJdak8WOiNhZ2pHUxDB9+mijp86amfVSa7L4haRPAyMknQt8F/hh/cIqjqfOmpn1VmuyuBzoBh4F/hi4Cxg2T8jLa/DUWTOzXmqdDbUX+Hp6DWteotzMrLda14Z6lgpjFBExq98jKli2kGDRUZiZDS4HszZUSRvwTmBc/4dTPMnP4DYzK1fTmEVErM29lkfEVcBb6htaMRqypdeLDsPMbFCptRvqlNxuA1lL42CehTFkNPpJeWZmvdT6C/+fctu7geeAd/V7NIOAp86amfVW62yoN9Q7kMHCU2fNzHqrtRvqEwc6HhFX9E84xfPUWTOz3g5mNtSpwLy0/zbgAWBxPYIqkqfOmpn1VmuymAqcEhGbACR9DvhRRLy3XoEVxVNnzcx6q3W5j0nAztz+zlQ27GQLCTpZmJnl1dqyuAF4QNL30/6FwPV1iahgDZJnQ5mZlan1prwvAB8E1qfXByPi7w/lgyU1SnpI0p1pf6akBZK6JN0iqSWVt6b9rnR8xqF8bvW48H0WZmZlau2GAmgHNkbE1cAySTMP8bM/BjyZ2/8ScGVEHEOWkC5J5ZcA61P5lem8unE3lJlZb7U+VvWzwGXAp1JRM/Dvff1QSVPJlgv5RtoX8EayR7dC1sV1Ydqey8tdXrcB56Tz66LBT8ozM+ul1pbF/wDeDmwBiIgVwKhD+NyrgL8ESpNUxwMvRcTutL+M7DnfpK9L0+fuBjak8+uiwVNnzcx6qTVZ7IysbyYAJHX09QMlvRVYHRGL+nqN/Vz3UkkLJS3s7u7u83UahG/KMzMrU2uyuFXSvwFjJP0RcDd9fxDSWcDbJT0H3EzW/XR1unZpdtZUYHnaXg5Mg33P/h4NrC2/aERcGxFzImJOZ2dnH0MrLSToZGFmllc1WaTxgVvIxgtuB44F/joivtKXD4yIT0XE1IiYAVwE3BsR7wHuA96RTrsYuCNtz0v7pOP3Rh1HoD111syst6r3WURESLorIk4C5tcxlsuAmyX9HfAQcF0qvw74tqQuYB1ZgqmbhgbhhoWZWU+13pT3a0mnRsSD/fnhEfFz4OdpewlwWoVztpM9mW9ANHi5DzOzXmpNFqcD703jDFsAkTU6fqtegRXFq86amfV2wGQh6eiIeAE4b4DiKZynzpqZ9VatZfEDstVmn5d0e0T8wQDEVChPnTUz663abKj8ndKz6hnIYOGps2ZmvVVLFrGf7WFLEnvcDWVm1kO1bqhXS9pI1sIYkbbh5QHuI+oaXQEaG/BCgmZmZQ6YLCKicaACGSy8kKCZWW8Hs0T5YSGbDeVkYWaW52RRJrvPougozMwGFyeLMg2C3b7RwsysByeLMhOPaGX7rr1s2Lar6FDMzAYNJ4syY9pbANjoZGFmto+TRZkj2poB2LjdycLMrMTJoswRbdls4o3bdlc508zs8OFkUWZUallscsvCzGwfJ4syR4zIWhabtrtlYWZW4mRRZpTHLMzMenGyKDOqzS0LM7NyThZlmhsbaGtu8JiFmVmOk0UFR7Q1u2VhZpbjZFFBR2sTW3fuKToMM7NBw8migrbmRrbtcrIwMytxsqhgRHMD29yyMDPbx8mighEtblmYmeU5WVQwornRLQszsxwniwpGtjaxaYenzpqZlThZVNA5qpXVG3cQfha3mRngZFHR2I4Wduzey47dfmKemRk4WVQ0sjVb8mPzDt+YZ2YGThYVdbRkyWKLk4WZGeBkUdHINrcszMzynCwqKD1adcNWz4gyMwMni4qOHN0GwMoN2wuOxMxscBjwZCFpmqT7JD0h6XFJH0vl4yTNl7Q4fR2byiXpGkldkh6RdEq9Y5y8L1lsq/dHmZkNCUW0LHYDn4yIE4AzgA9LOgG4HLgnImYD96R9gN8DZqfXpcC/1jvAtuZGxrQ38+JGtyzMzKCAZBERKyPi12l7E/AkMAWYC1yfTrseuDBtzwVuiMz9wBhJk+sd55FHtPGiu6HMzICCxywkzQBOBhYAkyJiZTr0IjApbU8BlubetiyVlV/rUkkLJS3s7u4+5NiOHN3mloWZWVJYspA0Ergd+HhEbMwfi2ydjYNaayMiro2IORExp7Oz85Djmzy6jceWb/SSH2ZmFJQsJDWTJYobI+J7qXhVqXspfV2dypcD03Jvn5rK6mp8RyuAWxdmZhQzG0rAdcCTEXFF7tA84OK0fTFwR678/WlW1BnAhlx3Vd2cMWs8AM+t2VrvjzIzG/SKaFmcBbwPeKOkh9PrAuCLwLmSFgNvSvsAdwFLgC7g68CfDkSQ08e3A/DCui0D8XFmZoNa00B/YET8J6D9HD6nwvkBfLiuQVUweXQbbc0NPLly00B/tJnZoOM7uPejqbGBYyeN4qePv1h0KGZmhXOyOIAZEzpYu2Une/d6RpSZHd6cLA7gjFnj2bl7L8tf8rIfZnZ4c7I4gFkTOgB4pntzwZGYmRXLyeIAZnWOBOBXXWsKjsTMrFhOFgcwYWQLTQ1yN5SZHfacLA5AEuedeCS/Wbqh6FDMzArlZFHFydPGsPylbaxw68LMDmNOFlW86fhs8dvLbn+k4EjMzIrjZFHFjAkdnH1sJ79cvMazoszssOVkUYO/eusJAPz7/c8XHImZWTGcLGrwis6RvHraGH74mxV+voWZHZacLGp03qsmsWbzTn74SN1XRzczG3ScLGr0gd+eAcCf3fQQO3bvKTYYM7MB5mRRo/aWJj5x7isB+PwPnyg4GjOzgeVkcRA+8oZjePXU0dy44AWuuvvposMxMxswThYHoaFB3HTpGUwf385Vdy/muv98tuiQzMwGhJPFQWpvaeL2P/ltjpk4kr+98wku/uYDbN25u+iwzMzqysmiDyaMbGXeR87i90+ewi+e7ubcK/6Dl7buLDosM7O6cbLoo/aWJq5492v45LmvZPlL23jDl3/Og8+tKzosM7O6cLI4RB89ZzZff/8c1m/dxTu/9l9cc89idu3ZW3RYZmb9ysmiH5x7wiTu/OjrmDJmBFfMf5rj/+onfPr7j/L82i1Fh2Zm1i80HJevmDNnTixcuHDAPzciuG3RMm5c8AIPL30JgAtOOpLLzj+O6eM7BjweM7ODIWlRRMypeMzJoj4eW76Ba+5ZzM+eWAXAcUeO4tQZ4zjn+ImcfezEQmMzM6vEyaJAjy7bwE0PvsD9z6xlyZqsW2pEcyPnvWoSb3v1UfzO7E5amtwbaGbFO1CyaBroYA43J00dzUlTTwJgzeYd3L5oGXc/uYofPLyCHzy8glGtTbzr1Gmcc/xEXjt9LK1NjQVHbGbWm1sWBVmzeQc//M0Kvn3/8yzpzlocDYLp4zs4+egxvP6VnZw2cxyTR48oOFIzO1y4G2qQW71pOz96ZCVPr9rEw0s38OTKjfuOdY5qZdrYERwzcSSzOkdyTOdITp81jtamRndfmVm/cjfUIDdxVBsfPGvmvv3NO3azYMla7l+ylmfXbOHZNVv47qJllOf1yaPbmNXZwcwJHcwY38HY9hZOmjqaV04aNcA1MLPhzsliEBrZ2sQ5x0/inOMn7SvbsXsPazfv5MHn1rFs/TbWbt7J06s28eyaLfyqa22vaxw9rp0JI1uYMb6D0e3NzBjfQXtLI2PbWzh6fDstjQ1MH9+OpIGsmpkNUU4WQ0RrUyNHjRnB3NdM6XVs+649bNy2i2e6t/D4ig08t3YLS9dtY+WGbdz31GrWb9213+u2NTcwdWw74zpaGNHcyCs6R9LYAE2NDcyc0MGI5kZGj2hm+vh2AJobGzhqjMdRzA43ThbDQFtzI23NjUw8oo0zXzG+1/FtO/ewZvMOdu3ZS9fqzezaEyxdv5X1W3ayfutOXli3lb17s3tDSutbbd25/6cBtjQ2MKLl5Vlb7S1Zkik1UiaOamPy6LYe72lvTeeUXWtWZwej2pp7fcbI1iY6Wv3jaTZYDJn/jZLOB64GGoFvRMQXCw5pyBjR0si0cVnLYFbnyJres2HbLro3bWfXnuCZ7s3s3J2td7V03TbW51bY3bVnL0u6t7AlLdO+aftuFixZx57cAMuevX2bRNE5qrVXcikZ097M0eP2f1d8YwPMmNDByJbafsTHdrTs+x5VM3l0GxNHtdZ0bjkhjhjR5O4/G3KGRLKQ1Ah8FTgXWAY8KGleRPj5pnUyekQzo0dkf/EfP/mIQ77e82u3sGl7z+d+bNi2i+fXbu117q49e3l2zZb9Put82849PLtmCyte2rbfz1u5YRs/fXzVoQVdJ6PamhjT3rs11RctjQ3MnDCS1ub6zYzLd08OtClj2hk/smXgP7hOZk2o3JI+FE2NonkA/nGGRLIATgO6ImIJgKSbgbmAk8UQsb+1sc46pj6fFxE1t2gCeOrFTezYXX214CxRbWZ3H1tLazfvPGCSOxgBabbc5n65XiV7I0v0fayuDYCmBjF9fDsNqbV69rGdfOYtJ/T/5/T7FetjCrA0t78MOD1/gqRLgUsBjj766IGLzAYlSTQ11t7Vc+KU0TWf+7rZE/oS0pC1c/feQpbd375rD0+v2kwwPDLVxtSS7s/a7E7dwNtzrfBJR7Qd4B19N1SSRVURcS1wLWQ35RUcjtmw0dLUUMgNoB2tTZw5sm9jQ9b/hsotwMuBabn9qanMzMwGwFBJFg8CsyXNlNQCXATMKzgmM7PDxpDohoqI3ZI+AvyUbOrsNyPi8YLDMjM7bAyJZAEQEXcBdxUdh5nZ4WiodEOZmVmBnCzMzKwqJwszM6vKycLMzKoalk/Kk9QNPH8Il5gArOmncAYb123oGs71c90Gh+kR0VnpwLBMFodK0sL9PVpwqHPdhq7hXD/XbfBzN5SZmVXlZGFmZlU5WVR2bdEB1JHrNnQN5/q5boOcxyzMzKwqtyzMzKwqJwszM6vKySJH0vmSnpLUJenyouOphaRvSlot6bFc2ThJ8yUtTl/HpnJJuibV7xFJp+Tec3E6f7Gki4uoSzlJ0yTdJ+kJSY9L+lgqHy71a5P0gKTfpPr9TSqfKWlBqsctaVl+JLWm/a50fEbuWp9K5U9JOq+gKvUiqVHSQ5LuTPvDqW7PSXpU0sOSFqayYfGzWVFE+JWN2zQCzwCzgBbgN8AJRcdVQ9y/C5wCPJYr+wfg8rR9OfCltH0B8GNAwBnAglQ+DliSvo5N22MHQd0mA6ek7VHA08AJw6h+Akam7WZgQYr7VuCiVP414E/S9p8CX0vbFwG3pO0T0s9rKzAz/Rw3Fl2/FNsngO8Ad6b94VS354AJZWXD4mez0ssti5edBnRFxJKI2AncDMwtOKaqIuI/gHVlxXOB69P29cCFufIbInM/MEbSZOA8YH5ErIuI9cB84Py6B19FRKyMiF+n7U3Ak2TPYx8u9YuI2Jx2m9MrgDcCt6Xy8vqV6n0bcI4kpfKbI2JHRDwLdJH9PBdK0lTgLcA30r4YJnU7gGHxs1mJk8XLpgBLc/vLUtlQNCkiVqbtF4FJaXt/dRz0dU/dEieT/fU9bOqXumkeBlaT/aJ4BngpInanU/Kx7qtHOr4BGM/grd9VwF8Ce9P+eIZP3SBL7D+TtEjSpals2PxslhsyDz+yvomIkDSk50dLGgncDnw8IjZmf3Bmhnr9ImIP8BpJY4DvA8cVG1H/kPRWYHVELJJ0dsHh1MvrImK5pInAfEn/nT841H82y7ll8bLlwLTc/tRUNhStSk1c0tfVqXx/dRy0dZfUTJYoboyI76XiYVO/koh4CbgPOJOsi6L0h1w+1n31SMdHA2sZnPU7C3i7pOfIunTfCFzN8KgbABGxPH1dTZboT2MY/myWOFm87EFgdpqt0UI2yDav4Jj6ah5QmlVxMXBHrvz9aWbGGcCG1GT+KfBmSWPT7I03p7JCpT7r64AnI+KK3KHhUr/O1KJA0gjgXLJxmfuAd6TTyutXqvc7gHsjGyWdB1yUZhTNBGYDDwxIJfYjIj4VEVMjYgbZ/6V7I+I9DIO6AUjqkDSqtE32M/UYw+Rns6KiR9gH04tsxsLTZP3Gnyk6nhpjvglYCewi6++8hKyv9x5gMXA3MC6dK+CrqX6PAnNy1/kQ2eBhF/DBouuVYnodWb/wI8DD6XXBMKrfbwEPpfo9Bvx1Kp9F9guxC/gu0JrK29J+Vzo+K3etz6R6PwX8XtF1K6vn2bw8G2pY1C3V4zfp9Xjp98Vw+dms9PJyH2ZmVpW7oczMrConCzMzq8rJwszMqnKyMDOzqpwszMysKt/BbdYHkkpTJAGOBPYA3Wn/tMjWFzMbNjx11uwQSfocsDkivlzDuU3x8tpIZkOGu6HM+omk10r6RVpY7qe5ZR9+Lumq9MyDj6X9KyUtlPSkpFMlfS89z+Dv0ns6JP1I2bMuHpP07kIrZ4c9d0OZ9Q8BXwHmRkR3+uX+BbK7cwFaImIOgKS3ATsjYo6yBzrdAbyWbKn5ZyRdSXbX84qIeEt6z+gBrY1ZGScLs/7RCpxItvooZA/TWpk7fkvZ+aV1xx4FHo+0rLWkJWQLyz0K/JOkL5EtlfHLOsZuVpWThVn/ENkv/TP3c3xL2f6O9HVvbru03xQRT6dHb14A/J2keyLi8/0asdlB8JiFWf/YAXRKOhOypdUlvaqvF5N0FLA1Iv4d+EeyR+eaFcYtC7P+sZdsae1r0vhCE9mT4h7v4/VOAv5R0l6yFYX/pD+CNOsrT501M7Oq3A1lZmZVOVmYmVlVThZmZlaVk4WZmVXlZGFmZlU5WZiZWVVOFmZmVtX/B94TQdbmd4c4AAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(sorted(termFreqs, reverse=True))\n",
    "plt.title(\"Terms vs. Frequency\")\n",
    "plt.xlabel(\"Terms\")\n",
    "plt.ylabel(\"Frequency\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The above graph shows  Zipf pattern. The values at the curve have the least impact has they appear more frequently as compared to other terms.\n",
    "\n",
    "We convert the dataframe into a Numpy array which will be used as input for our search function."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 152,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[2., 2., 2., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       ...,\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.]])"
      ]
     },
     "execution_count": 152,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "DTM = np.array(DT)\n",
    "DTM"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Read the test data from csv file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 153,
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>...</th>\n",
       "      <th>190</th>\n",
       "      <th>191</th>\n",
       "      <th>192</th>\n",
       "      <th>193</th>\n",
       "      <th>194</th>\n",
       "      <th>195</th>\n",
       "      <th>196</th>\n",
       "      <th>197</th>\n",
       "      <th>198</th>\n",
       "      <th>199</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5495</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5496</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5497</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5498</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5499</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5500 rows × 200 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      0    1    2    3    4    5    6    7    8    9    ...  190  191  192  \\\n",
       "0     0.0  0.0  1.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  0.0   \n",
       "1     0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  0.0   \n",
       "2     0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  0.0   \n",
       "3     1.0  1.0  1.0  1.0  1.0  1.0  2.0  1.0  1.0  1.0  ...  1.0  2.0  1.0   \n",
       "4     0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  2.0  0.0  ...  0.0  0.0  0.0   \n",
       "...   ...  ...  ...  ...  ...  ...  ...  ...  ...  ...  ...  ...  ...  ...   \n",
       "5495  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  0.0   \n",
       "5496  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  0.0   \n",
       "5497  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  0.0   \n",
       "5498  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  0.0   \n",
       "5499  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  0.0   \n",
       "\n",
       "      193  194  195  196  197  198  199  \n",
       "0     0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "1     0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "2     0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "3     1.0  1.0  1.0  1.0  1.0  1.0  1.0  \n",
       "4     0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "...   ...  ...  ...  ...  ...  ...  ...  \n",
       "5495  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "5496  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "5497  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "5498  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "5499  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "\n",
       "[5500 rows x 200 columns]"
      ]
     },
     "execution_count": 153,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vstable_test = pd.read_csv(\"C:/Users/USER/Desktop/DSC/DSC_478 Programming to Machine Learning A/Assignment/Assignment_2/Problem_1/testMatrixModified.txt\", sep=\"\\t\" , header=None)\n",
    "vs_test = vstable_test.copy()\n",
    "vs_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 154,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       [1., 0., 0., ..., 0., 0., 0.],\n",
       "       ...,\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.]])"
      ]
     },
     "execution_count": 154,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#transpose the training dataset from term vs. doc into doc. vs term\n",
    "DT_test = np.array(vs_test.T)\n",
    "DT_test"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The search function takes a query object (in this case a vector of words), and searches for the K most similar (least distant) items in the data (our index of documents). The \"measure\" parameter allows us to use either the Euclidean distance or the inverse of Cosine similarity as our ditance metric. The function returns the indices of the K most similar neighbors and a list of their distances to the query object.\n",
    "#### Function to calculate distance"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 155,
   "metadata": {},
   "outputs": [],
   "source": [
    "def knn_search(x, D, K, measure):\n",
    "    \"\"\" find K nearest neighbors of an instance x among the instances in D \"\"\"\n",
    "    if measure == 0:\n",
    "        # euclidean distances from the other points\n",
    "        dists = np.sqrt(((D - x)**2).sum(axis=1))\n",
    "    elif measure == 1:\n",
    "        # first find the vector norm for each instance in D as wel as the norm for vector x\n",
    "        D_norm = np.array([np.linalg.norm(D[i]) for i in range(len(D))])\n",
    "        x_norm = np.linalg.norm(x)\n",
    "        # Compute Cosine: divide the dot product o x and each instance in D by the product of the two norms\n",
    "        sims = np.dot(D,x)/(D_norm * x_norm)\n",
    "        # The distance measure will be the inverse of Cosine similarity\n",
    "        dists = 1 - sims\n",
    "    idx = np.argsort(dists) # sorting\n",
    "    # return the indexes of K nearest neighbors\n",
    "    return idx[:K], dists"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The function below will use our previous knn_search function to identify the label/category for for an instance x to be classifed, using the majority label of the K nearest neighbors of x.\n",
    "#### Function to fetch first N neighbors"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 156,
   "metadata": {},
   "outputs": [],
   "source": [
    "def knn_classify(x, D, K, labels, measure):\n",
    "    from collections import Counter\n",
    "    neigh_idx, distances = knn_search(x, D, K, measure)\n",
    "    neigh_labels = labels[neigh_idx]\n",
    "    count = Counter(neigh_labels)\n",
    "    #print(\"Labels for top \", K, \"neighbors: \", count)\n",
    "    return count.most_common(1)[0][0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### Loading target variables"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 157,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Windows', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Hockey',\n",
       "       'Windows', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Windows', 'Windows',\n",
       "       'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Windows',\n",
       "       'Hockey', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Windows', 'Windows', 'Windows', 'Windows',\n",
       "       'Hockey', 'Windows', 'Windows', 'Windows', 'Windows', 'Hockey', 'Windows', 'Windows', 'Windows', 'Windows',\n",
       "       'Hockey', 'Windows', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Hockey',\n",
       "       'Windows', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Windows',\n",
       "       'Windows', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Windows',\n",
       "       'Windows', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Hockey',\n",
       "       'Hockey', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Hockey',\n",
       "       'Windows', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Windows',\n",
       "       'Hockey', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Windows', 'Windows',\n",
       "       'Windows', 'Windows', 'Windows', 'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Hockey',\n",
       "       'Windows', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Windows',\n",
       "       'Hockey', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Windows',\n",
       "       'Hockey', 'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Hockey',\n",
       "       'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Hockey',\n",
       "       'Windows', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Hockey',\n",
       "       'Windows', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Windows', 'Windows', 'Windows', 'Hockey',\n",
       "       'Hockey', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Hockey',\n",
       "       'Hockey', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Windows', 'Windows', 'Windows',\n",
       "       'Windows', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Windows',\n",
       "       'Hockey', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Hockey',\n",
       "       'Windows', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Windows', 'Windows', 'Windows', 'Hockey',\n",
       "       'Windows', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Hockey',\n",
       "       'Hockey', 'Windows', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Windows',\n",
       "       'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Windows', 'Windows', 'Windows',\n",
       "       'Windows', 'Windows', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Windows',\n",
       "       'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Windows',\n",
       "       'Windows', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Hockey',\n",
       "       'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Hockey',\n",
       "       'Windows', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Hockey',\n",
       "       'Windows', 'Windows', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Windows', 'Windows', 'Windows',\n",
       "       'Windows', 'Hockey', 'Windows', 'Windows', 'Windows', 'Windows', 'Windows', 'Windows', 'Hockey', 'Hockey',\n",
       "       'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows',\n",
       "       'Hockey', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Windows',\n",
       "       'Hockey', 'Windows', 'Windows', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Hockey',\n",
       "       'Windows', 'Hockey', 'Windows', 'Windows', 'Windows', 'Windows', 'Windows', 'Windows', 'Windows', 'Windows',\n",
       "       'Hockey', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Windows', 'Windows',\n",
       "       'Windows', 'Hockey', 'Windows', 'Windows', 'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Hockey',\n",
       "       'Windows', 'Windows', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows',\n",
       "       'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Windows', 'Windows', 'Windows', 'Windows',\n",
       "       'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Windows',\n",
       "       'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Windows',\n",
       "       'Hockey', 'Windows', 'Hockey', 'Windows', 'Windows', 'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey',\n",
       "       'Windows', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Hockey',\n",
       "       'Windows', 'Windows', 'Windows', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Hockey',\n",
       "       'Windows', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Windows',\n",
       "       'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Hockey',\n",
       "       'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Hockey',\n",
       "       'Windows', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Hockey',\n",
       "       'Windows', 'Windows', 'Windows', 'Windows', 'Windows', 'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey',\n",
       "       'Hockey', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Hockey',\n",
       "       'Hockey', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Hockey',\n",
       "       'Hockey', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Windows', 'Windows', 'Windows', 'Hockey', 'Hockey',\n",
       "       'Hockey', 'Windows', 'Windows', 'Windows', 'Windows', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Windows',\n",
       "       'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Hockey',\n",
       "       'Windows', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Windows', 'Windows', 'Hockey', 'Windows', 'Windows',\n",
       "       'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Windows', 'Hockey', 'Windows', 'Windows',\n",
       "       'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Windows',\n",
       "       'Windows', 'Windows', 'Windows', 'Windows', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Hockey',\n",
       "       'Windows', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Windows', 'Windows', 'Windows', 'Windows', 'Hockey',\n",
       "       'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Windows',\n",
       "       'Hockey', 'Windows', 'Windows', 'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Windows',\n",
       "       'Hockey', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Windows', 'Hockey', 'Windows',\n",
       "       'Hockey', 'Windows', 'Windows', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Windows',\n",
       "       'Windows', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Hockey',\n",
       "       'Hockey', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Windows',\n",
       "       'Hockey', 'Windows', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Windows',\n",
       "       'Hockey', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Windows',\n",
       "       'Windows', 'Hockey', 'Windows', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Hockey',\n",
       "       'Hockey', 'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Windows', 'Windows', 'Windows', 'Windows',\n",
       "       'Windows', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Hockey',\n",
       "       'Windows', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Windows',\n",
       "       'Hockey', 'Windows', 'Hockey', 'Windows', 'Windows', 'Windows', 'Windows', 'Hockey', 'Windows', 'Hockey',\n",
       "       'Windows', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey',\n",
       "       'Hockey', 'Hockey', 'Windows', 'Windows', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows',\n",
       "       'Windows', 'Windows', 'Windows', 'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Hockey',\n",
       "       'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Hockey'],\n",
       "      dtype=object)"
      ]
     },
     "execution_count": 157,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Let's load labels to our original data\n",
    "train_class = pd.read_csv(\"C:/Users/USER/Desktop/DSC/DSC_478 Programming to Machine Learning A/Assignment/Assignment_2/Problem_1/trainClasses.txt\", sep=\"\\t\" , header=None, index_col =0)\n",
    "train_class.rename(columns={1:'Category'}, inplace=True)\n",
    "train_class['Category'] = train_class['Category'].replace({0:'Windows', 1:'Hockey'})\n",
    "train_class = train_class.astype(object)\n",
    "train_class.index.name  = None\n",
    "train_class = np.array(train_class).ravel()\n",
    "train_class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 158,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Hockey', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Hockey',\n",
       "       'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Windows',\n",
       "       'Windows', 'Windows', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Hockey',\n",
       "       'Hockey', 'Windows', 'Windows', 'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Hockey',\n",
       "       'Hockey', 'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Windows',\n",
       "       'Hockey', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Hockey', 'Hockey',\n",
       "       'Windows', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Windows',\n",
       "       'Hockey', 'Hockey', 'Windows', 'Windows', 'Windows', 'Windows', 'Windows', 'Hockey', 'Windows', 'Hockey',\n",
       "       'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Windows', 'Windows',\n",
       "       'Windows', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Windows', 'Windows', 'Windows', 'Hockey', 'Hockey',\n",
       "       'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Hockey',\n",
       "       'Hockey', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Hockey',\n",
       "       'Windows', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Hockey',\n",
       "       'Windows', 'Hockey', 'Hockey', 'Hockey', 'Hockey', 'Windows', 'Windows', 'Windows', 'Hockey', 'Windows',\n",
       "       'Windows', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey',\n",
       "       'Hockey', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Windows', 'Windows', 'Windows', 'Windows', 'Hockey',\n",
       "       'Hockey', 'Hockey', 'Windows', 'Windows', 'Windows', 'Hockey', 'Windows', 'Windows', 'Hockey', 'Windows',\n",
       "       'Hockey', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Hockey',\n",
       "       'Hockey', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Windows', 'Hockey', 'Hockey', 'Windows',\n",
       "       'Windows', 'Windows', 'Windows', 'Windows', 'Hockey', 'Hockey', 'Windows', 'Hockey', 'Hockey'], dtype=object)"
      ]
     },
     "execution_count": 158,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Let's load labels to our original data\n",
    "test_class = pd.read_csv(\"C:/Users/USER/Desktop/DSC/DSC_478 Programming to Machine Learning A/Assignment/Assignment_2/Problem_1/testClasses.txt\", sep=\"\\t\" , header=None, index_col =0)\n",
    "test_class.rename(columns={1:'Category'}, inplace=True)\n",
    "test_class['Category'] = test_class['Category'].replace({0:'Windows', 1:'Hockey'})\n",
    "test_class = test_class.astype(object)\n",
    "test_class.index.name  = None\n",
    "test_class = np.array(test_class).ravel()\n",
    "test_class"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Using KNN classifer to evaluate it's classification accuracy. Running the classifier on each test instance in our test data and compare the predicted class to the actual class for each. We will maintain the number of agreements which allows us to compute the final accuracy rate across all test instances.\n",
    "#### Evaluation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 159,
   "metadata": {},
   "outputs": [],
   "source": [
    "def knn_evaluate(test_set, train_set, train_class, test_class, measure):\n",
    "    numTestVecs = len(test_class)\n",
    "    for k in range (5,101,5):\n",
    "        accCount = 0.0\n",
    "        for i in range(numTestVecs):\n",
    "            classifierResult = knn_classify(test_set[i,:], train_set, k, train_class, measure)\n",
    "            if (classifierResult == test_class[i]):\n",
    "                accCount += 1.0\n",
    "        lst.append([measure,k,accCount/float(numTestVecs)])\n",
    "        print(\"Value of k:\",k)\n",
    "        print(\"Total accuracy rate:\", accCount/float(numTestVecs) ,'\\n')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### Euclidean Distance"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 160,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Value of k: 5\n",
      "Total accuracy rate: 0.815 \n",
      "\n",
      "Value of k: 10\n",
      "Total accuracy rate: 0.85 \n",
      "\n",
      "Value of k: 15\n",
      "Total accuracy rate: 0.785 \n",
      "\n",
      "Value of k: 20\n",
      "Total accuracy rate: 0.765 \n",
      "\n",
      "Value of k: 25\n",
      "Total accuracy rate: 0.73 \n",
      "\n",
      "Value of k: 30\n",
      "Total accuracy rate: 0.725 \n",
      "\n",
      "Value of k: 35\n",
      "Total accuracy rate: 0.69 \n",
      "\n",
      "Value of k: 40\n",
      "Total accuracy rate: 0.7 \n",
      "\n",
      "Value of k: 45\n",
      "Total accuracy rate: 0.655 \n",
      "\n",
      "Value of k: 50\n",
      "Total accuracy rate: 0.67 \n",
      "\n",
      "Value of k: 55\n",
      "Total accuracy rate: 0.655 \n",
      "\n",
      "Value of k: 60\n",
      "Total accuracy rate: 0.66 \n",
      "\n",
      "Value of k: 65\n",
      "Total accuracy rate: 0.625 \n",
      "\n",
      "Value of k: 70\n",
      "Total accuracy rate: 0.625 \n",
      "\n",
      "Value of k: 75\n",
      "Total accuracy rate: 0.63 \n",
      "\n",
      "Value of k: 80\n",
      "Total accuracy rate: 0.615 \n",
      "\n",
      "Value of k: 85\n",
      "Total accuracy rate: 0.615 \n",
      "\n",
      "Value of k: 90\n",
      "Total accuracy rate: 0.61 \n",
      "\n",
      "Value of k: 95\n",
      "Total accuracy rate: 0.605 \n",
      "\n",
      "Value of k: 100\n",
      "Total accuracy rate: 0.605 \n",
      "\n"
     ]
    }
   ],
   "source": [
    "knn_evaluate(DT_test, DTM, train_class, test_class, 0)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### Cosine similarity measure"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 161,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Value of k: 5\n",
      "Total accuracy rate: 0.97 \n",
      "\n",
      "Value of k: 10\n",
      "Total accuracy rate: 0.985 \n",
      "\n",
      "Value of k: 15\n",
      "Total accuracy rate: 0.985 \n",
      "\n",
      "Value of k: 20\n",
      "Total accuracy rate: 0.975 \n",
      "\n",
      "Value of k: 25\n",
      "Total accuracy rate: 0.97 \n",
      "\n",
      "Value of k: 30\n",
      "Total accuracy rate: 0.98 \n",
      "\n",
      "Value of k: 35\n",
      "Total accuracy rate: 0.98 \n",
      "\n",
      "Value of k: 40\n",
      "Total accuracy rate: 0.98 \n",
      "\n",
      "Value of k: 45\n",
      "Total accuracy rate: 0.975 \n",
      "\n",
      "Value of k: 50\n",
      "Total accuracy rate: 0.98 \n",
      "\n",
      "Value of k: 55\n",
      "Total accuracy rate: 0.975 \n",
      "\n",
      "Value of k: 60\n",
      "Total accuracy rate: 0.98 \n",
      "\n",
      "Value of k: 65\n",
      "Total accuracy rate: 0.975 \n",
      "\n",
      "Value of k: 70\n",
      "Total accuracy rate: 0.975 \n",
      "\n",
      "Value of k: 75\n",
      "Total accuracy rate: 0.975 \n",
      "\n",
      "Value of k: 80\n",
      "Total accuracy rate: 0.975 \n",
      "\n",
      "Value of k: 85\n",
      "Total accuracy rate: 0.975 \n",
      "\n",
      "Value of k: 90\n",
      "Total accuracy rate: 0.975 \n",
      "\n",
      "Value of k: 95\n",
      "Total accuracy rate: 0.975 \n",
      "\n",
      "Value of k: 100\n",
      "Total accuracy rate: 0.975 \n",
      "\n"
     ]
    }
   ],
   "source": [
    "knn_evaluate(DT_test, DTM, train_class, test_class, 1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Accuracy rate from Euclidean distance and Cosine measure"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 162,
   "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>Measure</th>\n",
       "      <th>k</th>\n",
       "      <th>Accuracy</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>0.81</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>10</td>\n",
       "      <td>0.85</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>15</td>\n",
       "      <td>0.79</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>20</td>\n",
       "      <td>0.77</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>25</td>\n",
       "      <td>0.73</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0</td>\n",
       "      <td>30</td>\n",
       "      <td>0.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0</td>\n",
       "      <td>35</td>\n",
       "      <td>0.69</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>0.70</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0</td>\n",
       "      <td>45</td>\n",
       "      <td>0.66</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>0</td>\n",
       "      <td>50</td>\n",
       "      <td>0.67</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>0</td>\n",
       "      <td>55</td>\n",
       "      <td>0.66</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>0</td>\n",
       "      <td>60</td>\n",
       "      <td>0.66</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>0</td>\n",
       "      <td>65</td>\n",
       "      <td>0.62</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>0</td>\n",
       "      <td>70</td>\n",
       "      <td>0.62</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>0</td>\n",
       "      <td>75</td>\n",
       "      <td>0.63</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>0</td>\n",
       "      <td>80</td>\n",
       "      <td>0.61</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>0</td>\n",
       "      <td>85</td>\n",
       "      <td>0.61</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>0</td>\n",
       "      <td>90</td>\n",
       "      <td>0.61</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>0</td>\n",
       "      <td>95</td>\n",
       "      <td>0.60</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>0</td>\n",
       "      <td>100</td>\n",
       "      <td>0.60</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>0.97</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>0.98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>1</td>\n",
       "      <td>15</td>\n",
       "      <td>0.98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>1</td>\n",
       "      <td>20</td>\n",
       "      <td>0.97</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>1</td>\n",
       "      <td>25</td>\n",
       "      <td>0.97</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>1</td>\n",
       "      <td>30</td>\n",
       "      <td>0.98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>1</td>\n",
       "      <td>35</td>\n",
       "      <td>0.98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>1</td>\n",
       "      <td>40</td>\n",
       "      <td>0.98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>1</td>\n",
       "      <td>45</td>\n",
       "      <td>0.97</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>1</td>\n",
       "      <td>50</td>\n",
       "      <td>0.98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30</th>\n",
       "      <td>1</td>\n",
       "      <td>55</td>\n",
       "      <td>0.97</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31</th>\n",
       "      <td>1</td>\n",
       "      <td>60</td>\n",
       "      <td>0.98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32</th>\n",
       "      <td>1</td>\n",
       "      <td>65</td>\n",
       "      <td>0.97</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>33</th>\n",
       "      <td>1</td>\n",
       "      <td>70</td>\n",
       "      <td>0.97</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34</th>\n",
       "      <td>1</td>\n",
       "      <td>75</td>\n",
       "      <td>0.97</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>35</th>\n",
       "      <td>1</td>\n",
       "      <td>80</td>\n",
       "      <td>0.97</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>36</th>\n",
       "      <td>1</td>\n",
       "      <td>85</td>\n",
       "      <td>0.97</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37</th>\n",
       "      <td>1</td>\n",
       "      <td>90</td>\n",
       "      <td>0.97</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>38</th>\n",
       "      <td>1</td>\n",
       "      <td>95</td>\n",
       "      <td>0.97</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39</th>\n",
       "      <td>1</td>\n",
       "      <td>100</td>\n",
       "      <td>0.97</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    Measure    k  Accuracy\n",
       "0         0    5      0.81\n",
       "1         0   10      0.85\n",
       "2         0   15      0.79\n",
       "3         0   20      0.77\n",
       "4         0   25      0.73\n",
       "5         0   30      0.72\n",
       "6         0   35      0.69\n",
       "7         0   40      0.70\n",
       "8         0   45      0.66\n",
       "9         0   50      0.67\n",
       "10        0   55      0.66\n",
       "11        0   60      0.66\n",
       "12        0   65      0.62\n",
       "13        0   70      0.62\n",
       "14        0   75      0.63\n",
       "15        0   80      0.61\n",
       "16        0   85      0.61\n",
       "17        0   90      0.61\n",
       "18        0   95      0.60\n",
       "19        0  100      0.60\n",
       "20        1    5      0.97\n",
       "21        1   10      0.98\n",
       "22        1   15      0.98\n",
       "23        1   20      0.97\n",
       "24        1   25      0.97\n",
       "25        1   30      0.98\n",
       "26        1   35      0.98\n",
       "27        1   40      0.98\n",
       "28        1   45      0.97\n",
       "29        1   50      0.98\n",
       "30        1   55      0.97\n",
       "31        1   60      0.98\n",
       "32        1   65      0.97\n",
       "33        1   70      0.97\n",
       "34        1   75      0.97\n",
       "35        1   80      0.97\n",
       "36        1   85      0.97\n",
       "37        1   90      0.97\n",
       "38        1   95      0.97\n",
       "39        1  100      0.97"
      ]
     },
     "execution_count": 162,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.DataFrame(lst, columns=['Measure','k','Accuracy'])\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### Plotting graph"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 163,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = plt.gca()\n",
    "\n",
    "df[(df.Measure == 0)].plot(kind='line',x='k',y='Accuracy',label='Euclidean distance',color='blue', marker='o',ax=ax)\n",
    "df[(df.Measure == 1)].plot(kind='line',x='k',y='Accuracy',label='Cosine similarity measure',color='red',marker='d', ax=ax)\n",
    "\n",
    "plt.legend(bbox_to_anchor=(1.04,1), loc=\"upper left\")\n",
    "plt.xlabel('k Value')\n",
    "plt.ylabel('Accuracy rate')\n",
    "plt.suptitle('Accuracy rate vs. k value', fontsize=15)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### TFxIDF weights "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 164,
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>...</th>\n",
       "      <th>790</th>\n",
       "      <th>791</th>\n",
       "      <th>792</th>\n",
       "      <th>793</th>\n",
       "      <th>794</th>\n",
       "      <th>795</th>\n",
       "      <th>796</th>\n",
       "      <th>797</th>\n",
       "      <th>798</th>\n",
       "      <th>799</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>8.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>8.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>10 rows × 800 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   0    1    2    3    4    5    6    7    8    9    ...  790  791  792  793  \\\n",
       "0  2.0  0.0  0.0  2.0  2.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  0.0  0.0   \n",
       "1  2.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  3.0  0.0   \n",
       "2  2.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  0.0  0.0   \n",
       "3  1.0  1.0  1.0  1.0  1.0  1.0  2.0  1.0  1.0  1.0  ...  1.0  1.0  1.0  1.0   \n",
       "4  8.0  1.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  2.0  0.0   \n",
       "5  6.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  0.0  0.0   \n",
       "6  2.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  2.0  0.0  0.0  0.0   \n",
       "7  8.0  0.0  2.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  2.0  0.0  0.0  0.0   \n",
       "8  2.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0  0.0  0.0   \n",
       "9  4.0  0.0  1.0  0.0  0.0  0.0  0.0  2.0  0.0  0.0  ...  0.0  0.0  1.0  0.0   \n",
       "\n",
       "   794  795  796  797  798  799  \n",
       "0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "1  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "2  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "3  1.0  1.0  1.0  1.0  1.0  1.0  \n",
       "4  0.0  0.0  0.0  0.0  0.0  1.0  \n",
       "5  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "6  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "7  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "8  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "9  1.0  0.0  0.0  0.0  0.0  0.0  \n",
       "\n",
       "[10 rows x 800 columns]"
      ]
     },
     "execution_count": 164,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "TD = vstable.copy()\n",
    "TD.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 165,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5500, 800)"
      ]
     },
     "execution_count": 165,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "TD.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 166,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of terms: 5500\n",
      "Number of documents: 800\n"
     ]
    }
   ],
   "source": [
    "numTerms=TD.shape[0]\n",
    "NDocs = TD.shape[1]\n",
    "print('Number of terms:',numTerms)\n",
    "print('Number of documents:',NDocs)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Computing term frequencies to find the distributions across the corpus."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 167,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0       102.0\n",
       "1        11.0\n",
       "2        22.0\n",
       "3       959.0\n",
       "4       222.0\n",
       "        ...  \n",
       "5495      3.0\n",
       "5496      3.0\n",
       "5497      2.0\n",
       "5498      2.0\n",
       "5499      2.0\n",
       "Length: 5500, dtype: float64"
      ]
     },
     "execution_count": 167,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "termFreqs = TD.sum(axis=1)\n",
    "termFreqs"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Transforming the data to TFxIDF weights:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 168,
   "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>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>108</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5495</th>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5496</th>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5497</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5498</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5499</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5500 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        0\n",
       "0      50\n",
       "1       7\n",
       "2      10\n",
       "3     800\n",
       "4     108\n",
       "...   ...\n",
       "5495    3\n",
       "5496    3\n",
       "5497    2\n",
       "5498    2\n",
       "5499    2\n",
       "\n",
       "[5500 rows x 1 columns]"
      ]
     },
     "execution_count": 168,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Note: doc frequency (df) for a term t is the number of docs in which t appears divided by total number of docs\n",
    "\n",
    "# finding the doc counts for each term\n",
    "\n",
    "DF = pd.DataFrame([(TD!=0).sum(1)]).T\n",
    "DF"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 169,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[800. 800. 800. ... 800. 800. 800.]\n",
      " [800. 800. 800. ... 800. 800. 800.]\n",
      " [800. 800. 800. ... 800. 800. 800.]\n",
      " ...\n",
      " [800. 800. 800. ... 800. 800. 800.]\n",
      " [800. 800. 800. ... 800. 800. 800.]\n",
      " [800. 800. 800. ... 800. 800. 800.]]\n"
     ]
    }
   ],
   "source": [
    "# Create a matrix with all entries = NDocs\n",
    "NMatrix=np.ones(np.shape(TD), dtype=float)*NDocs\n",
    "np.set_printoptions(precision=2,suppress=True,linewidth=120)\n",
    "print(NMatrix)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 170,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Convert each entry into IDF values\n",
    "# IDF is the log of the inverse of document frequency\n",
    "# IDF is only a function of the term, so all columns will be identical.\n",
    "\n",
    "IDF = np.log2(np.divide(NMatrix, np.array(DF)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 171,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[4.   4.   4.   ... 4.   4.   4.  ]\n",
      " [6.84 6.84 6.84 ... 6.84 6.84 6.84]\n",
      " [6.32 6.32 6.32 ... 6.32 6.32 6.32]\n",
      " ...\n",
      " [8.64 8.64 8.64 ... 8.64 8.64 8.64]\n",
      " [8.64 8.64 8.64 ... 8.64 8.64 8.64]\n",
      " [8.64 8.64 8.64 ... 8.64 8.64 8.64]]\n"
     ]
    }
   ],
   "source": [
    "print(IDF)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 172,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Computing the TFxIDF values for each document-term entry\n",
    "TD_tfidf = TD * IDF"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 173,
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>...</th>\n",
       "      <th>790</th>\n",
       "      <th>791</th>\n",
       "      <th>792</th>\n",
       "      <th>793</th>\n",
       "      <th>794</th>\n",
       "      <th>795</th>\n",
       "      <th>796</th>\n",
       "      <th>797</th>\n",
       "      <th>798</th>\n",
       "      <th>799</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>8.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>13.67</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>20.51</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>12.64</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>23.11</td>\n",
       "      <td>2.89</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.78</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.89</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5495</th>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5496</th>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5497</th>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5498</th>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5499</th>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5500 rows × 800 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        0     1    2    3    4    5    6    7    8    9    ...  790  791  \\\n",
       "0      8.00  0.00  0.0  8.0  8.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0   \n",
       "1     13.67  0.00  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0   \n",
       "2     12.64  0.00  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0   \n",
       "3      0.00  0.00  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0   \n",
       "4     23.11  2.89  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0   \n",
       "...     ...   ...  ...  ...  ...  ...  ...  ...  ...  ...  ...  ...  ...   \n",
       "5495   0.00  0.00  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0   \n",
       "5496   0.00  0.00  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0   \n",
       "5497   0.00  0.00  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0   \n",
       "5498   0.00  0.00  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0   \n",
       "5499   0.00  0.00  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0   \n",
       "\n",
       "        792  793  794  795  796  797  798   799  \n",
       "0      0.00  0.0  0.0  0.0  0.0  0.0  0.0  0.00  \n",
       "1     20.51  0.0  0.0  0.0  0.0  0.0  0.0  0.00  \n",
       "2      0.00  0.0  0.0  0.0  0.0  0.0  0.0  0.00  \n",
       "3      0.00  0.0  0.0  0.0  0.0  0.0  0.0  0.00  \n",
       "4      5.78  0.0  0.0  0.0  0.0  0.0  0.0  2.89  \n",
       "...     ...  ...  ...  ...  ...  ...  ...   ...  \n",
       "5495   0.00  0.0  0.0  0.0  0.0  0.0  0.0  0.00  \n",
       "5496   0.00  0.0  0.0  0.0  0.0  0.0  0.0  0.00  \n",
       "5497   0.00  0.0  0.0  0.0  0.0  0.0  0.0  0.00  \n",
       "5498   0.00  0.0  0.0  0.0  0.0  0.0  0.0  0.00  \n",
       "5499   0.00  0.0  0.0  0.0  0.0  0.0  0.0  0.00  \n",
       "\n",
       "[5500 rows x 800 columns]"
      ]
     },
     "execution_count": 173,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.set_option(\"display.precision\", 2)\n",
    "\n",
    "TD_tfidf"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Repeat the k-nearest-neighbor using the TFxIDF weighted document vectors."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 174,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0., 0., 1., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       ...,\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.]])"
      ]
     },
     "execution_count": 174,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_test = vstable_test.copy()\n",
    "x_test = np.array(x_test)\n",
    "x_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 175,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([4.  , 6.84, 6.32, ..., 8.64, 8.64, 8.64])"
      ]
     },
     "execution_count": 175,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "IDF.T[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### TFxIDF transformation on the query"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 176,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[0. 0. 0. ... 0. 0. 0.]\n",
      " [0. 0. 0. ... 0. 0. 0.]\n",
      " [4. 0. 0. ... 0. 0. 0.]\n",
      " ...\n",
      " [0. 0. 0. ... 0. 0. 0.]\n",
      " [0. 0. 0. ... 0. 0. 0.]\n",
      " [0. 0. 0. ... 0. 0. 0.]]\n"
     ]
    }
   ],
   "source": [
    "# Each term in query x must be multiplied by the idf value of the term we computed earlier (the IDF matrix)\n",
    "x = IDF.T[0]\n",
    "x_tfidf = x_test * x[:, None]  # note that this coordinatewise multiplication of two vectors\n",
    "x_tfidf=np.array(x_tfidf.T)\n",
    "print(x_tfidf)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 177,
   "metadata": {},
   "outputs": [],
   "source": [
    "# The KNN Search function expects a document x term materix as an np array, so transposing the TF_tfidf matrix\n",
    "DT_tfidf = TD_tfidf.T\n",
    "DT_array = np.array(DT_tfidf)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 178,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Value of k: 5\n",
      "Total accuracy rate: 0.98 \n",
      "\n",
      "Value of k: 10\n",
      "Total accuracy rate: 0.99 \n",
      "\n",
      "Value of k: 15\n",
      "Total accuracy rate: 0.99 \n",
      "\n",
      "Value of k: 20\n",
      "Total accuracy rate: 1.0 \n",
      "\n",
      "Value of k: 25\n",
      "Total accuracy rate: 0.995 \n",
      "\n",
      "Value of k: 30\n",
      "Total accuracy rate: 0.995 \n",
      "\n",
      "Value of k: 35\n",
      "Total accuracy rate: 0.99 \n",
      "\n",
      "Value of k: 40\n",
      "Total accuracy rate: 0.995 \n",
      "\n",
      "Value of k: 45\n",
      "Total accuracy rate: 0.995 \n",
      "\n",
      "Value of k: 50\n",
      "Total accuracy rate: 0.99 \n",
      "\n",
      "Value of k: 55\n",
      "Total accuracy rate: 0.995 \n",
      "\n",
      "Value of k: 60\n",
      "Total accuracy rate: 0.995 \n",
      "\n",
      "Value of k: 65\n",
      "Total accuracy rate: 0.99 \n",
      "\n",
      "Value of k: 70\n",
      "Total accuracy rate: 0.995 \n",
      "\n",
      "Value of k: 75\n",
      "Total accuracy rate: 0.995 \n",
      "\n",
      "Value of k: 80\n",
      "Total accuracy rate: 0.995 \n",
      "\n",
      "Value of k: 85\n",
      "Total accuracy rate: 0.99 \n",
      "\n",
      "Value of k: 90\n",
      "Total accuracy rate: 0.99 \n",
      "\n",
      "Value of k: 95\n",
      "Total accuracy rate: 0.985 \n",
      "\n",
      "Value of k: 100\n",
      "Total accuracy rate: 0.985 \n",
      "\n"
     ]
    }
   ],
   "source": [
    "knn_evaluate(x_tfidf, DT_array, train_class, test_class, 1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As compared to the previous KNN classifier using original data, TD * IDF distance measure performs better with Cosine similarity measure. The accuracy rate of TD * IDF shows a accuracy rate of 98 - 100 % and is consistent for different values of k ranging from 5 to 100.\n",
    "\n",
    "Euclidean distance on original data drops drastically with decreasing value of k while cosine similarity measure shows a consistent accuracy rate of 97 - 98 % for different values of k.\n",
    "\n",
    "To conclude, knn classifier using cosine similarity measure is a better performing model for both the original data as well as TD * IDF weights.\n",
    "#### Rocchio Method\n",
    "##### Original Data\n",
    "\n",
    "Loading the training data and the training class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 179,
   "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>Category</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Windows</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Hockey</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Windows</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Hockey</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Windows</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Category\n",
       "0  Windows\n",
       "1   Hockey\n",
       "2  Windows\n",
       "3   Hockey\n",
       "4  Windows"
      ]
     },
     "execution_count": 179,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_class_rocchio = pd.read_csv(\"C:/Users/USER/Desktop/DSC/DSC_478 Programming to Machine Learning A/Assignment/Assignment_2/Problem_1/trainClasses.txt\", sep=\"\\t\" , header=None, index_col =0)\n",
    "train_class_rocchio.rename(columns={1:'Category'}, inplace=True)\n",
    "train_class_rocchio['Category'] = train_class_rocchio['Category'].replace({0:'Windows', 1:'Hockey'})\n",
    "train_class_rocchio = train_class_rocchio.astype(object)\n",
    "train_class_rocchio.index.name  = None\n",
    "train_class_rocchio.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 180,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(200, 1)"
      ]
     },
     "execution_count": 180,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Let's load labels to our original data\n",
    "test_class_rocchio = pd.read_csv(\"C:/Users/USER/Desktop/DSC/DSC_478 Programming to Machine Learning A/Assignment/Assignment_2/Problem_1/testClasses.txt\", sep=\"\\t\" , header=None, index_col =0)\n",
    "test_class_rocchio.rename(columns={1:'Category'}, inplace=True)\n",
    "test_class_rocchio['Category'] = test_class_rocchio['Category'].replace({0:'Windows', 1:'Hockey'})\n",
    "test_class_rocchio = test_class_rocchio.astype(object)\n",
    "test_class_rocchio.index.name  = None\n",
    "test_class_rocchio.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 181,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(800, 5500)\n"
     ]
    },
    {
     "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>...</th>\n",
       "      <th>5490</th>\n",
       "      <th>5491</th>\n",
       "      <th>5492</th>\n",
       "      <th>5493</th>\n",
       "      <th>5494</th>\n",
       "      <th>5495</th>\n",
       "      <th>5496</th>\n",
       "      <th>5497</th>\n",
       "      <th>5498</th>\n",
       "      <th>5499</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 5500 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   0     1     2     3     4     5     6     7     8     9     ...  5490  \\\n",
       "0   2.0   2.0   2.0   1.0   8.0   6.0   2.0   8.0   2.0   4.0  ...   0.0   \n",
       "1   0.0   0.0   0.0   1.0   1.0   0.0   0.0   0.0   0.0   0.0  ...   0.0   \n",
       "2   0.0   0.0   0.0   1.0   0.0   0.0   0.0   2.0   0.0   1.0  ...   0.0   \n",
       "3   2.0   0.0   0.0   1.0   0.0   0.0   0.0   0.0   0.0   0.0  ...   0.0   \n",
       "4   2.0   0.0   0.0   1.0   0.0   0.0   0.0   0.0   0.0   0.0  ...   0.0   \n",
       "\n",
       "   5491  5492  5493  5494  5495  5496  5497  5498  5499  \n",
       "0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "1   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "2   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "3   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "4   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "\n",
       "[5 rows x 5500 columns]"
      ]
     },
     "execution_count": 181,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vs_train_rocchio = vs_train.copy()\n",
    "vs_train_rocchio = vs_train_rocchio.T\n",
    "print(vs_train_rocchio.shape)\n",
    "vs_train_rocchio.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Merging the training data set and the class labels"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 182,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(800, 5501)\n"
     ]
    },
    {
     "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>...</th>\n",
       "      <th>5491</th>\n",
       "      <th>5492</th>\n",
       "      <th>5493</th>\n",
       "      <th>5494</th>\n",
       "      <th>5495</th>\n",
       "      <th>5496</th>\n",
       "      <th>5497</th>\n",
       "      <th>5498</th>\n",
       "      <th>5499</th>\n",
       "      <th>Category</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Windows</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Hockey</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Windows</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Hockey</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Windows</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 5501 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     0    1    2    3    4    5    6    7    8    9  ...  5491  5492  5493  \\\n",
       "0  2.0  2.0  2.0  1.0  8.0  6.0  2.0  8.0  2.0  4.0  ...   0.0   0.0   0.0   \n",
       "1  0.0  0.0  0.0  1.0  1.0  0.0  0.0  0.0  0.0  0.0  ...   0.0   0.0   0.0   \n",
       "2  0.0  0.0  0.0  1.0  0.0  0.0  0.0  2.0  0.0  1.0  ...   0.0   0.0   0.0   \n",
       "3  2.0  0.0  0.0  1.0  0.0  0.0  0.0  0.0  0.0  0.0  ...   0.0   0.0   0.0   \n",
       "4  2.0  0.0  0.0  1.0  0.0  0.0  0.0  0.0  0.0  0.0  ...   0.0   0.0   0.0   \n",
       "\n",
       "   5494  5495  5496  5497  5498  5499  Category  \n",
       "0   0.0   0.0   0.0   0.0   0.0   0.0   Windows  \n",
       "1   0.0   0.0   0.0   0.0   0.0   0.0    Hockey  \n",
       "2   0.0   0.0   0.0   0.0   0.0   0.0   Windows  \n",
       "3   0.0   0.0   0.0   0.0   0.0   0.0    Hockey  \n",
       "4   0.0   0.0   0.0   0.0   0.0   0.0   Windows  \n",
       "\n",
       "[5 rows x 5501 columns]"
      ]
     },
     "execution_count": 182,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vs_train_rocchio = vs_train_rocchio.join(train_class_rocchio, how='outer').fillna(0)\n",
    "print(vs_train_rocchio.shape)\n",
    "vs_train_rocchio.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Sum all the columns based on the classes. Create a training prototype."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 183,
   "metadata": {},
   "outputs": [],
   "source": [
    "def train_prototype (train_set, grouping_column):\n",
    "    vs_train_ptype = train_set.groupby(grouping_column).sum().reset_index()\n",
    "    vs_target_train = vs_train_ptype[grouping_column]\n",
    "    print('Output of training prototype with class variable')\n",
    "    print(vs_train_ptype.head())\n",
    "    del vs_train_ptype[grouping_column]\n",
    "    DTM_R = np.array(vs_train_ptype)\n",
    "    print('Separating the class variable')\n",
    "    print(vs_target_train.head())\n",
    "    vs_target_train = np.array(vs_target_train).ravel()\n",
    "    return DTM_R, vs_target_train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 184,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Output of training prototype with class variable\n",
      "  Category     0    1     2      3      4     5     6      7     8  ...  5490  \\\n",
      "0   Hockey  45.0  7.0  17.0  418.0   65.0   0.0   9.0    0.0   1.0  ...   3.0   \n",
      "1  Windows  57.0  4.0   5.0  541.0  157.0  84.0  99.0  262.0  54.0  ...   0.0   \n",
      "\n",
      "   5491  5492  5493  5494  5495  5496  5497  5498  5499  \n",
      "0   2.0   0.0   0.0   0.0   1.0   0.0   1.0   0.0   0.0  \n",
      "1   0.0   1.0   2.0   3.0   2.0   3.0   1.0   2.0   2.0  \n",
      "\n",
      "[2 rows x 5501 columns]\n",
      "Separating the class variable\n",
      "0     Hockey\n",
      "1    Windows\n",
      "Name: Category, dtype: object\n"
     ]
    }
   ],
   "source": [
    "column_name ='Category' # Column name with classes\n",
    "DTM_R,vs_target_train = train_prototype(vs_train_rocchio,column_name)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Loading the test dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 185,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(200, 5500)\n"
     ]
    },
    {
     "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>...</th>\n",
       "      <th>5490</th>\n",
       "      <th>5491</th>\n",
       "      <th>5492</th>\n",
       "      <th>5493</th>\n",
       "      <th>5494</th>\n",
       "      <th>5495</th>\n",
       "      <th>5496</th>\n",
       "      <th>5497</th>\n",
       "      <th>5498</th>\n",
       "      <th>5499</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 5500 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   0     1     2     3     4     5     6     7     8     9     ...  5490  \\\n",
       "0   0.0   0.0   0.0   1.0   0.0   0.0   0.0   0.0   0.0   1.0  ...   0.0   \n",
       "1   0.0   0.0   0.0   1.0   0.0   0.0   0.0   0.0   0.0   0.0  ...   0.0   \n",
       "2   1.0   0.0   0.0   1.0   0.0   0.0   0.0   0.0   0.0   0.0  ...   0.0   \n",
       "3   0.0   0.0   0.0   1.0   0.0   0.0   0.0   0.0   0.0   0.0  ...   0.0   \n",
       "4   0.0   0.0   0.0   1.0   0.0   0.0   0.0   0.0   0.0   1.0  ...   0.0   \n",
       "\n",
       "   5491  5492  5493  5494  5495  5496  5497  5498  5499  \n",
       "0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "1   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "2   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "3   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "4   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "\n",
       "[5 rows x 5500 columns]"
      ]
     },
     "execution_count": 185,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vs_test_rocchio = vstable_test.copy()\n",
    "vs_test_rocchio = vs_test_rocchio.T\n",
    "print(vs_test_rocchio.shape)\n",
    "vs_test_rocchio.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Converting dataset into array type"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 186,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_class_rocchio = np.array(test_class_rocchio).ravel()\n",
    "DT_R = np.array(vs_test_rocchio)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Creating function to evaluate Rocchio method. We are using the classifer using the Cosine similarity and pick the most similar record.\n",
    "\n",
    "The value of index is set to 1 because we want the most similar measure from prototype."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 187,
   "metadata": {},
   "outputs": [],
   "source": [
    "def rocchio_measure(x, D):\n",
    "    D_norm = np.array([np.linalg.norm(D[i]) for i in range(len(D))])\n",
    "    x_norm = np.linalg.norm(x)\n",
    "    # Compute Cosine: divide the dot product o x and each instance in D by the product of the two norms\n",
    "    sims = np.dot(D,x)/(D_norm * x_norm)\n",
    "    # The distance measure will be the inverse of Cosine similarity\n",
    "    #dists = 1 - sims\n",
    "    idx = np.argsort(-sims) # sorting\n",
    "    return idx[:1]\n",
    "       "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 188,
   "metadata": {},
   "outputs": [],
   "source": [
    "def rocchio_evaluate(test_set, train_set, train_class, test_class):\n",
    "    numTestVecs = len(test_class)\n",
    "    accCount = 0.0\n",
    "    for i in range(numTestVecs):\n",
    "        index = rocchio_measure(test_set[i,:], train_set) # Setting the value of k to 1 and reusing the previous classifier model\n",
    "        classifierResult = train_class[index]\n",
    "        if (classifierResult == test_class[i]):\n",
    "            accCount += 1.0\n",
    "    print(\"Total accuracy rate:\", accCount/float(numTestVecs) ,'\\n')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 189,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total accuracy rate: 0.975 \n",
      "\n"
     ]
    }
   ],
   "source": [
    "rocchio_evaluate(DT_R, DTM_R, vs_target_train, test_class_rocchio)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Rocchio Method\n",
    "##### TD IDF Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 190,
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>...</th>\n",
       "      <th>5490</th>\n",
       "      <th>5491</th>\n",
       "      <th>5492</th>\n",
       "      <th>5493</th>\n",
       "      <th>5494</th>\n",
       "      <th>5495</th>\n",
       "      <th>5496</th>\n",
       "      <th>5497</th>\n",
       "      <th>5498</th>\n",
       "      <th>5499</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>8.0</td>\n",
       "      <td>13.67</td>\n",
       "      <td>12.64</td>\n",
       "      <td>0.0</td>\n",
       "      <td>23.11</td>\n",
       "      <td>27.86</td>\n",
       "      <td>7.89</td>\n",
       "      <td>32.71</td>\n",
       "      <td>9.78</td>\n",
       "      <td>8.03</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.89</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>8.18</td>\n",
       "      <td>0.00</td>\n",
       "      <td>2.01</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>8.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>8.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>795</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>796</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>797</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>798</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>799</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.89</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>800 rows × 5500 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     0      1      2     3      4      5     6      7     8     9     ...  \\\n",
       "0     8.0  13.67  12.64   0.0  23.11  27.86  7.89  32.71  9.78  8.03  ...   \n",
       "1     0.0   0.00   0.00   0.0   2.89   0.00  0.00   0.00  0.00  0.00  ...   \n",
       "2     0.0   0.00   0.00   0.0   0.00   0.00  0.00   8.18  0.00  2.01  ...   \n",
       "3     8.0   0.00   0.00   0.0   0.00   0.00  0.00   0.00  0.00  0.00  ...   \n",
       "4     8.0   0.00   0.00   0.0   0.00   0.00  0.00   0.00  0.00  0.00  ...   \n",
       "..    ...    ...    ...   ...    ...    ...   ...    ...   ...   ...  ...   \n",
       "795   0.0   0.00   0.00   0.0   0.00   0.00  0.00   0.00  0.00  0.00  ...   \n",
       "796   0.0   0.00   0.00   0.0   0.00   0.00  0.00   0.00  0.00  0.00  ...   \n",
       "797   0.0   0.00   0.00   0.0   0.00   0.00  0.00   0.00  0.00  0.00  ...   \n",
       "798   0.0   0.00   0.00   0.0   0.00   0.00  0.00   0.00  0.00  0.00  ...   \n",
       "799   0.0   0.00   0.00   0.0   2.89   0.00  0.00   0.00  0.00  0.00  ...   \n",
       "\n",
       "     5490  5491  5492  5493  5494  5495  5496  5497  5498  5499  \n",
       "0     0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "1     0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "2     0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "3     0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "4     0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "..    ...   ...   ...   ...   ...   ...   ...   ...   ...   ...  \n",
       "795   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "796   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "797   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "798   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "799   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "\n",
       "[800 rows x 5500 columns]"
      ]
     },
     "execution_count": 190,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "TD_tfidf_R = TD_tfidf.copy()\n",
    "TD_tfidf_R = TD_tfidf_R.T\n",
    "TD_tfidf_R"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Loading the training class, testing class and dataset into a different variables. The previous one is already converted into numpy array."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 191,
   "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>Category</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Windows</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Hockey</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Windows</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Hockey</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Windows</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Category\n",
       "0  Windows\n",
       "1   Hockey\n",
       "2  Windows\n",
       "3   Hockey\n",
       "4  Windows"
      ]
     },
     "execution_count": 191,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "TD_train_class_rocchio = pd.read_csv(\"C:/Users/USER/Desktop/DSC/DSC_478 Programming to Machine Learning A/Assignment/Assignment_2/Problem_1/trainClasses.txt\", sep=\"\\t\" , header=None, index_col =0)\n",
    "TD_train_class_rocchio.rename(columns={1:'Category'}, inplace=True)\n",
    "TD_train_class_rocchio['Category'] = TD_train_class_rocchio['Category'].replace({0:'Windows', 1:'Hockey'})\n",
    "TD_train_class_rocchio = TD_train_class_rocchio.astype(object)\n",
    "TD_train_class_rocchio.index.name  = None\n",
    "TD_train_class_rocchio.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 192,
   "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>Category</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Hockey</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Windows</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Windows</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Hockey</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Hockey</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Category\n",
       "0   Hockey\n",
       "1  Windows\n",
       "2  Windows\n",
       "3   Hockey\n",
       "4   Hockey"
      ]
     },
     "execution_count": 192,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Let's load labels to our original data\n",
    "TD_test_class_rocchio = pd.read_csv(\"C:/Users/USER/Desktop/DSC/DSC_478 Programming to Machine Learning A/Assignment/Assignment_2/Problem_1/testClasses.txt\", sep=\"\\t\" , header=None, index_col =0)\n",
    "TD_test_class_rocchio.rename(columns={1:'Category'}, inplace=True)\n",
    "TD_test_class_rocchio['Category'] = TD_test_class_rocchio['Category'].replace({0:'Windows', 1:'Hockey'})\n",
    "TD_test_class_rocchio = TD_test_class_rocchio.astype(object)\n",
    "TD_test_class_rocchio.index.name  = None\n",
    "TD_test_class_rocchio.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Merging the TD * IDF dataset into the training class variable to create a prototype"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 193,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(800, 5501)\n"
     ]
    },
    {
     "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>...</th>\n",
       "      <th>5491</th>\n",
       "      <th>5492</th>\n",
       "      <th>5493</th>\n",
       "      <th>5494</th>\n",
       "      <th>5495</th>\n",
       "      <th>5496</th>\n",
       "      <th>5497</th>\n",
       "      <th>5498</th>\n",
       "      <th>5499</th>\n",
       "      <th>Category</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>8.0</td>\n",
       "      <td>13.67</td>\n",
       "      <td>12.64</td>\n",
       "      <td>0.0</td>\n",
       "      <td>23.11</td>\n",
       "      <td>27.86</td>\n",
       "      <td>7.89</td>\n",
       "      <td>32.71</td>\n",
       "      <td>9.78</td>\n",
       "      <td>8.03</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Windows</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.89</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Hockey</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>8.18</td>\n",
       "      <td>0.00</td>\n",
       "      <td>2.01</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Windows</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>8.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Hockey</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>8.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Windows</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 5501 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     0      1      2    3      4      5     6      7     8     9  ...  5491  \\\n",
       "0  8.0  13.67  12.64  0.0  23.11  27.86  7.89  32.71  9.78  8.03  ...   0.0   \n",
       "1  0.0   0.00   0.00  0.0   2.89   0.00  0.00   0.00  0.00  0.00  ...   0.0   \n",
       "2  0.0   0.00   0.00  0.0   0.00   0.00  0.00   8.18  0.00  2.01  ...   0.0   \n",
       "3  8.0   0.00   0.00  0.0   0.00   0.00  0.00   0.00  0.00  0.00  ...   0.0   \n",
       "4  8.0   0.00   0.00  0.0   0.00   0.00  0.00   0.00  0.00  0.00  ...   0.0   \n",
       "\n",
       "   5492  5493  5494  5495  5496  5497  5498  5499  Category  \n",
       "0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   Windows  \n",
       "1   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0    Hockey  \n",
       "2   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   Windows  \n",
       "3   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0    Hockey  \n",
       "4   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   Windows  \n",
       "\n",
       "[5 rows x 5501 columns]"
      ]
     },
     "execution_count": 193,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "TD_tfidf_train_rocchio = TD_tfidf_R.join(TD_train_class_rocchio, how='outer').fillna(0)\n",
    "print(TD_tfidf_train_rocchio.shape)\n",
    "TD_tfidf_train_rocchio.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Calling the prototype function to return the TD IDF prototype."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 194,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Output of training prototype with class variable\n",
      "  Category      0      1       2    3       4       5       6        7  \\\n",
      "0   Hockey  180.0  47.86  107.47  0.0  187.78    0.00   35.49     0.00   \n",
      "1  Windows  228.0  27.35   31.61  0.0  453.57  390.08  390.40  1071.39   \n",
      "\n",
      "        8  ...   5490   5491  5492   5493   5494   5495   5496  5497   5498  \\\n",
      "0    4.89  ...  25.93  17.29  0.00   0.00   0.00   8.06   0.00  8.64   0.00   \n",
      "1  264.00  ...   0.00   0.00  9.64  17.29  24.18  16.12  24.18  8.64  17.29   \n",
      "\n",
      "    5499  \n",
      "0   0.00  \n",
      "1  17.29  \n",
      "\n",
      "[2 rows x 5501 columns]\n",
      "Separating the class variable\n",
      "0     Hockey\n",
      "1    Windows\n",
      "Name: Category, dtype: object\n"
     ]
    }
   ],
   "source": [
    "column_name ='Category' # Column name with classes\n",
    "DTM_R,vs_target_train = train_prototype(TD_tfidf_train_rocchio, column_name)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Using the test dataset and applying the same TD IDF function on the test dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 195,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0., 0., 1., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       ...,\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.]])"
      ]
     },
     "execution_count": 195,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "TD_tfidf_test = vstable_test.copy()\n",
    "TD_tfidf_test = np.array(TD_tfidf_test)\n",
    "TD_tfidf_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 196,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[0. 0. 0. ... 0. 0. 0.]\n",
      " [0. 0. 0. ... 0. 0. 0.]\n",
      " [4. 0. 0. ... 0. 0. 0.]\n",
      " ...\n",
      " [0. 0. 0. ... 0. 0. 0.]\n",
      " [0. 0. 0. ... 0. 0. 0.]\n",
      " [0. 0. 0. ... 0. 0. 0.]]\n"
     ]
    }
   ],
   "source": [
    "# Each term in query x must be multiplied by the idf value of the term we computed earlier (the IDF matrix)\n",
    "x = IDF.T[0]\n",
    "x_tfidf_R = TD_tfidf_test * x[:, None]  # note that this coordinatewise multiplication of two vectors\n",
    "x_tfidf_R=np.array(x_tfidf_R.T)\n",
    "print(x_tfidf_R)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Converting into numpy array"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 197,
   "metadata": {},
   "outputs": [],
   "source": [
    "TD_test_class_rocchio = np.array(TD_test_class_rocchio).ravel()\n",
    "DT_R = np.array(x_tfidf_R)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Running the Rocchio method for TD IDF dataset "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 198,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total accuracy rate: 0.98 \n",
      "\n"
     ]
    }
   ],
   "source": [
    "rocchio_evaluate(DT_R, DTM_R, vs_target_train, TD_test_class_rocchio)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As compared to Rocchio method, KNN TD * IDF classifier method is a slightly better performing model with a accuracy of 0.98 - 1.00.\n",
    "The best performing KNN TD * IDF has an accuracy rate of 1.00.\n",
    "\n",
    "Rocchio method TD * IDF returns an accuracy rate of 0.98.\n",
    "\n",
    "KNN classifier using original with Euclidean distance performs poorly on this dataset. "
   ]
  }
 ],
 "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": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}