item_based-_rough_draft.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "column_names=['user_id','item_id', 'rating', 'timestamp']\n",
    "movie_columns=['item_id', 'movietitle']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['user_id', 'item_id', 'rating', 'timestamp']"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "column_names"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'D:\\\\Recommender System'"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pwd\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "df=pd.read_csv('ratings.csv', sep=',', names=column_names)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>user_id</th>\n",
       "      <th>item_id</th>\n",
       "      <th>rating</th>\n",
       "      <th>timestamp</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1193</td>\n",
       "      <td>5</td>\n",
       "      <td>978300760</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>661</td>\n",
       "      <td>3</td>\n",
       "      <td>978302109</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>914</td>\n",
       "      <td>3</td>\n",
       "      <td>978301968</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>3408</td>\n",
       "      <td>4</td>\n",
       "      <td>978300275</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>2355</td>\n",
       "      <td>5</td>\n",
       "      <td>978824291</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>1</td>\n",
       "      <td>1197</td>\n",
       "      <td>3</td>\n",
       "      <td>978302268</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>1</td>\n",
       "      <td>1287</td>\n",
       "      <td>5</td>\n",
       "      <td>978302039</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>1</td>\n",
       "      <td>2804</td>\n",
       "      <td>5</td>\n",
       "      <td>978300719</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>1</td>\n",
       "      <td>594</td>\n",
       "      <td>4</td>\n",
       "      <td>978302268</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>1</td>\n",
       "      <td>919</td>\n",
       "      <td>4</td>\n",
       "      <td>978301368</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   user_id  item_id  rating  timestamp\n",
       "0        1     1193       5  978300760\n",
       "1        1      661       3  978302109\n",
       "2        1      914       3  978301968\n",
       "3        1     3408       4  978300275\n",
       "4        1     2355       5  978824291\n",
       "5        1     1197       3  978302268\n",
       "6        1     1287       5  978302039\n",
       "7        1     2804       5  978300719\n",
       "8        1      594       4  978302268\n",
       "9        1      919       4  978301368"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "movie_titles=pd.read_csv('movies.csv', sep=',', names=movie_columns, encoding='latin-1')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>item_id</th>\n",
       "      <th>movietitle</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>Toy Story (1995)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>Jumanji (1995)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>Grumpier Old Men (1995)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>Waiting to Exhale (1995)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>Father of the Bride Part II (1995)</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   item_id                          movietitle\n",
       "0        1                    Toy Story (1995)\n",
       "1        2                      Jumanji (1995)\n",
       "2        3             Grumpier Old Men (1995)\n",
       "3        4            Waiting to Exhale (1995)\n",
       "4        5  Father of the Bride Part II (1995)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movie_titles.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "df=pd.merge(df,movie_titles, on='item_id', how='left', sort='False')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>user_id</th>\n",
       "      <th>item_id</th>\n",
       "      <th>rating</th>\n",
       "      <th>timestamp</th>\n",
       "      <th>movietitle</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>978824268</td>\n",
       "      <td>Toy Story (1995)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>978237008</td>\n",
       "      <td>Toy Story (1995)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>978233496</td>\n",
       "      <td>Toy Story (1995)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>9</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>978225952</td>\n",
       "      <td>Toy Story (1995)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>10</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>978226474</td>\n",
       "      <td>Toy Story (1995)</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   user_id  item_id  rating  timestamp        movietitle\n",
       "0        1        1       5  978824268  Toy Story (1995)\n",
       "1        6        1       4  978237008  Toy Story (1995)\n",
       "2        8        1       4  978233496  Toy Story (1995)\n",
       "3        9        1       5  978225952  Toy Story (1995)\n",
       "4       10        1       5  978226474  Toy Story (1995)"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "moviemat=df.pivot_table(index='user_id', columns='item_id', values='rating')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "diff=set(range(1,3953))-set(moviemat.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "columns=set(moviemat.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3706"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1000209, 5)"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "6040"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "moviemat.shape[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#Chinmay's code for inplace splitting of train set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "y=range(moviemat.shape[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "indices=moviemat.iloc[1][moviemat.iloc[1].notnull()==True]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "129"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "num=indices.count()\n",
    "num"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "25"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "num_of_instances=int(0.2*num)\n",
    "num_of_instances"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "item_id\n",
       "2427    2.0\n",
       "3071    4.0\n",
       "2571    4.0\n",
       "648     4.0\n",
       "1917    3.0\n",
       "3699    2.0\n",
       "1247    5.0\n",
       "459     3.0\n",
       "3107    2.0\n",
       "1357    5.0\n",
       "1210    4.0\n",
       "1259    5.0\n",
       "3654    3.0\n",
       "2268    5.0\n",
       "2916    3.0\n",
       "1968    2.0\n",
       "1527    4.0\n",
       "2006    3.0\n",
       "3578    5.0\n",
       "982     4.0\n",
       "3471    5.0\n",
       "1246    5.0\n",
       "1253    3.0\n",
       "1370    5.0\n",
       "349     4.0\n",
       "Name: 2, dtype: float64"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test=indices.sample(n=num_of_instances, replace=False)\n",
    "test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([   1,    2,    3, ..., 6038, 6039, 6040])"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.arange(1,6041)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ True,  True,  True, ...,  True,  True,  True], dtype=bool)"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "moviemat.columns.notnull()==True"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "t_items=columns\n",
    "t_users=np.arange(1,6041)\n",
    "test_set=pd.DataFrame(index=t_items, columns=t_users)\n",
    "train_set=pd.DataFrame(index=t_items, columns=t_users)\n",
    "for user in t_users:\n",
    "    rated_movies=moviemat.loc[user][moviemat.loc[user].notnull()==True]\n",
    "    movie_count=rated_movies.count()\n",
    "    test_set_count=int(0.2*movie_count)\n",
    "    movie_for_tset=rated_movies.sample(n=test_set_count, replace=False)\n",
    "    test_set[user][movie_for_tset.index]=movie_for_tset\n",
    "    movie_for_train_set=rated_movies[~rated_movies.index.isin(movie_for_tset.index)]\n",
    "    train_set[user][movie_for_train_set.index]=movie_for_train_set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#splitting of train set and test set done"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></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>10</th>\n",
       "      <th>...</th>\n",
       "      <th>6031</th>\n",
       "      <th>6032</th>\n",
       "      <th>6033</th>\n",
       "      <th>6034</th>\n",
       "      <th>6035</th>\n",
       "      <th>6036</th>\n",
       "      <th>6037</th>\n",
       "      <th>6038</th>\n",
       "      <th>6039</th>\n",
       "      <th>6040</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 6040 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "  1    2    3    4    5    6    7    8    9    10   ...  6031 6032 6033 6034  \\\n",
       "1  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN ...   NaN    4  NaN  NaN   \n",
       "2  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN ...   NaN  NaN  NaN  NaN   \n",
       "3  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN ...   NaN  NaN  NaN  NaN   \n",
       "4  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN ...   NaN  NaN  NaN  NaN   \n",
       "5  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN ...   NaN  NaN  NaN  NaN   \n",
       "\n",
       "  6035 6036 6037 6038 6039 6040  \n",
       "1    4  NaN  NaN  NaN  NaN  NaN  \n",
       "2  NaN  NaN  NaN  NaN  NaN  NaN  \n",
       "3  NaN  NaN  NaN  NaN  NaN  NaN  \n",
       "4  NaN  NaN  NaN  NaN  NaN  NaN  \n",
       "5  NaN  NaN  NaN  NaN  NaN  NaN  \n",
       "\n",
       "[5 rows x 6040 columns]"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_set.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(3706, 6040)"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_set.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "train_set=train_set.transpose()\n",
    "test_set=test_set.transpose()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></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>10</th>\n",
       "      <th>...</th>\n",
       "      <th>3943</th>\n",
       "      <th>3944</th>\n",
       "      <th>3945</th>\n",
       "      <th>3946</th>\n",
       "      <th>3947</th>\n",
       "      <th>3948</th>\n",
       "      <th>3949</th>\n",
       "      <th>3950</th>\n",
       "      <th>3951</th>\n",
       "      <th>3952</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 3706 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "  1    2    3    4    5    6    7    8    9    10   ...  3943 3944 3945 3946  \\\n",
       "1    5  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN ...   NaN  NaN  NaN  NaN   \n",
       "2  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN ...   NaN  NaN  NaN  NaN   \n",
       "3  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN ...   NaN  NaN  NaN  NaN   \n",
       "4  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN ...   NaN  NaN  NaN  NaN   \n",
       "5  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN  NaN ...   NaN  NaN  NaN  NaN   \n",
       "\n",
       "  3947 3948 3949 3950 3951 3952  \n",
       "1  NaN  NaN  NaN  NaN  NaN  NaN  \n",
       "2  NaN  NaN  NaN  NaN  NaN  NaN  \n",
       "3  NaN  NaN  NaN  NaN  NaN  NaN  \n",
       "4  NaN  NaN  NaN  NaN  NaN  NaN  \n",
       "5  NaN  NaN  NaN  NaN  NaN  NaN  \n",
       "\n",
       "[5 rows x 3706 columns]"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_set.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.metrics import pairwise_distances"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn import metrics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "mean_X=train_set.copy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "mean_per_user=train_set.mean(axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "mean_X=mean_X.sub(mean_per_user,axis='index')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(6040, 3706)"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mean_X.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "X1=(mean_X.fillna(value=0,inplace=False))#mean_x_filled with 0s"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import sklearn.metrics as metrics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.metrics import pairwise_distances"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#adjusted_cosine_similarity"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></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>10</th>\n",
       "      <th>...</th>\n",
       "      <th>3943</th>\n",
       "      <th>3944</th>\n",
       "      <th>3945</th>\n",
       "      <th>3946</th>\n",
       "      <th>3947</th>\n",
       "      <th>3948</th>\n",
       "      <th>3949</th>\n",
       "      <th>3950</th>\n",
       "      <th>3951</th>\n",
       "      <th>3952</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.860465</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</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>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</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>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</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>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</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>5</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</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 × 3706 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       1     2     3     4     5     6     7     8     9     10    ...   3943  \\\n",
       "1  0.860465   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  ...    0.0   \n",
       "2  0.000000   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  ...    0.0   \n",
       "3  0.000000   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  ...    0.0   \n",
       "4  0.000000   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  ...    0.0   \n",
       "5  0.000000   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  ...    0.0   \n",
       "\n",
       "   3944  3945  3946  3947  3948  3949  3950  3951  3952  \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",
       "5   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "\n",
       "[5 rows x 3706 columns]"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X1.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#transpose"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "X2=X1.transpose()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></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>10</th>\n",
       "      <th>...</th>\n",
       "      <th>6031</th>\n",
       "      <th>6032</th>\n",
       "      <th>6033</th>\n",
       "      <th>6034</th>\n",
       "      <th>6035</th>\n",
       "      <th>6036</th>\n",
       "      <th>6037</th>\n",
       "      <th>6038</th>\n",
       "      <th>6039</th>\n",
       "      <th>6040</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.860465</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.070175</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.133929</td>\n",
       "      <td>1.317647</td>\n",
       "      <td>0.878505</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>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.549451</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.878505</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>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</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>-1.580357</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.866071</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</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>-0.580357</td>\n",
       "      <td>-1.341772</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</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>-1.580357</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 6040 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       1     2     3     4     5         6     7         8         9     \\\n",
       "1  0.860465   0.0   0.0   0.0   0.0  0.070175   0.0  0.133929  1.317647   \n",
       "2  0.000000   0.0   0.0   0.0   0.0  0.000000   0.0  0.000000  0.000000   \n",
       "3  0.000000   0.0   0.0   0.0   0.0  0.000000   0.0  0.000000  0.000000   \n",
       "4  0.000000   0.0   0.0   0.0   0.0  0.000000   0.0 -0.866071  0.000000   \n",
       "5  0.000000   0.0   0.0   0.0   0.0  0.000000   0.0  0.000000  0.000000   \n",
       "\n",
       "       10      ...     6031  6032  6033  6034      6035      6036  6037  6038  \\\n",
       "1  0.878505    ...      0.0   0.0   0.0   0.0  0.000000  0.000000   0.0   0.0   \n",
       "2  0.878505    ...      0.0   0.0   0.0   0.0  0.000000  0.000000   0.0   0.0   \n",
       "3  0.000000    ...      0.0   0.0   0.0   0.0 -1.580357  0.000000   0.0   0.0   \n",
       "4  0.000000    ...      0.0   0.0   0.0   0.0 -0.580357 -1.341772   0.0   0.0   \n",
       "5  0.000000    ...      0.0   0.0   0.0   0.0 -1.580357  0.000000   0.0   0.0   \n",
       "\n",
       "   6039      6040  \n",
       "1   0.0 -0.549451  \n",
       "2   0.0  0.000000  \n",
       "3   0.0  0.000000  \n",
       "4   0.0  0.000000  \n",
       "5   0.0  0.000000  \n",
       "\n",
       "[5 rows x 6040 columns]"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X2.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "adjusted_cosine_sim=1-pairwise_distances(X2,metric='cosine')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "X4=(pd.DataFrame(data=adjusted_cosine_sim,index=columns,columns=columns)).copy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "mean_X_trans=mean_X.transpose()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "X_train_trans=train_set.transpose()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "X_train_trans=X_train_trans.fillna(value=0, inplace=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#adjusted _cosine_similarity calculation done"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#cosine_similarity"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [],
   "source": [
    "cosine_sim=1-pairwise_distances(X_train_trans,metric='cosine')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [],
   "source": [
    "X3=(pd.DataFrame(data=cosine_sim,index=columns,columns=columns)).copy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#cosine_similarity_ends"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#pearson_correlation"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "pearson_sim=1-pairwise_distances(X2,metric='correlation')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "X5=pd.DataFrame(pearson_sim)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#pearson_correlation_ends"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "############################begin nearest_neighbours_calculation using pandas"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "sorted_item_similarity=pd.DataFrame(index=columns,columns=columns);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "for i in columns:\n",
    "    sorted_item_similarity[i]=X4[i].sort_values(ascending=False).index"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "sorted_item_similarity.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "###########################end calculation using pandas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "###########################begin complete prediction calculation using numpy arrays"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [],
   "source": [
    "sorted_item_similarity=(X4.values).copy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#creating dictionary to map array indices of items to actual item indices in dataframe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "dict_indices={}\n",
    "X4_indices=X4.index\n",
    "np_array_indices=range(0,len(X4_indices))\n",
    "dict_indices=dict(zip(np_array_indices,X4_indices))    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 1.        , -0.0263386 , -0.04987279, ...,  0.00863616,\n",
       "        0.00837243,  0.04506548])"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sorted_item_similarity[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "sorted_item_similarity=(-sorted_item_similarity).argsort(axis=1)\n",
    "#AXIS='columns'\n",
    "#(-sign)to do sorting in descending order\n",
    "#sorting each row in descending order and storing the index of sorted elements"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([   0, 2898, 1108, ...,  532, 2440,  154], dtype=int64)"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sorted_item_similarity[0]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#replacing the np indices by actual indices from dictionary (dict_indices)\n",
    "for i in np_array_indices:\n",
    "    sorted_item_similarity[i]=[dict_indices[x] for x in sorted_item_similarity[i]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([   1, 3114, 1198, ...,  546, 2642,  160], dtype=int64)"
      ]
     },
     "execution_count": 69,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sorted_item_similarity[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#..........................prediction calculation starts using k nearest neighbours"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></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>10</th>\n",
       "      <th>...</th>\n",
       "      <th>3943</th>\n",
       "      <th>3944</th>\n",
       "      <th>3945</th>\n",
       "      <th>3946</th>\n",
       "      <th>3947</th>\n",
       "      <th>3948</th>\n",
       "      <th>3949</th>\n",
       "      <th>3950</th>\n",
       "      <th>3951</th>\n",
       "      <th>3952</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</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>5</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>5 rows × 3706 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   1     2     3     4     5     6     7     8     9     10    ...   3943  \\\n",
       "1   5.0   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   \n",
       "3   0.0   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  ...    0.0   \n",
       "5   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  ...    0.0   \n",
       "\n",
       "   3944  3945  3946  3947  3948  3949  3950  3951  3952  \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",
       "5   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "\n",
       "[5 rows x 3706 columns]"
      ]
     },
     "execution_count": 71,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_set=train_set.fillna(value=0)\n",
    "train_set.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#creating np array of test_set\n",
    "test_set_np=(test_set.values).copy()\n",
    "test_set_np=test_set_np.astype('float64')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#create numpy arrays for train_set and predictions for faster calculations"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "train_set_np=(train_set.values).copy()\n",
    "train_set_np=train_set_np.astype('float64')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [],
   "source": [
    "predictions=test_set_np.copy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#create a dictionary to map actual items to numpy indices by reversing dict_indices"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "rev_indices={v:k for k,v in dict_indices.items()}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#create a dictionary to map actual users to numpy indices"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "metadata": {},
   "outputs": [],
   "source": [
    "rev_user_indices=dict(zip(list(test_set.index),range(0,len(test_set.index))))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "metadata": {},
   "outputs": [],
   "source": [
    "#creating a dictionary which maps each items to its active users in test set(users who rated that item)\n",
    "items=list(test_set.columns)\n",
    "indices={}\n",
    "for target_item in items:\n",
    "    active_users=test_set[target_item][test_set[target_item].isnull()==False].index\n",
    "    indices.update({target_item:active_users})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# indices[7]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#Code to generate predictions on a test_set for a given k"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "metadata": {},
   "outputs": [],
   "source": [
    "#for a given k\n",
    "k=500\n",
    "for target_item in items:\n",
    "    rev_tar_item=rev_indices[target_item]#np index of target item \n",
    "    for users in indices[target_item]:\n",
    "        k_sim=sorted_item_similarity[rev_tar_item][1:k]\n",
    "        #note k_sim contains actual indices of k similar items\n",
    "        weighted_sum=0\n",
    "        similarity_sum=0\n",
    "        rev_user_idx=rev_user_indices[users]#np index of user\n",
    "        for j in k_sim:\n",
    "            rev_j=rev_indices[j]#np index of each similar item j\n",
    "            weighted_sum+=adjusted_cosine_sim[rev_tar_item][rev_j]*train_set_np[rev_user_idx][rev_j] \n",
    "            similarity_sum+=abs(adjusted_cosine_sim[rev_tar_item][rev_j])\n",
    "        if similarity_sum!=0:\n",
    "            predictions[rev_user_idx,rev_tar_item]=(weighted_sum/similarity_sum)\n",
    "        else:\n",
    "            predictions[rev_user_idx,rev_tar_item]=0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [],
   "source": [
    "pred_dataframe=pd.DataFrame(data=predictions,index=test_set.index,columns=test_set.columns)\n",
    "pred_dataframe=pred_dataframe.astype('float64')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "metadata": {},
   "outputs": [],
   "source": [
    "pred_dataframe=pred_dataframe.add(mean_per_user,axis='index')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "metadata": {},
   "outputs": [],
   "source": [
    "absolute_predictions=(pred_dataframe.values).copy()\n",
    "absolute_predictions=absolute_predictions.astype('float64')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Roshan\\Anaconda3\\lib\\site-packages\\ipykernel_launcher.py:1: RuntimeWarning: invalid value encountered in greater\n",
      "  \"\"\"Entry point for launching an IPython kernel.\n",
      "C:\\Users\\Roshan\\Anaconda3\\lib\\site-packages\\ipykernel_launcher.py:2: RuntimeWarning: invalid value encountered in less\n",
      "  \n"
     ]
    }
   ],
   "source": [
    "absolute_predictions[absolute_predictions>5]=5\n",
    "absolute_predictions[absolute_predictions<1]=1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#######################################end predictions using numpy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#########################################begin predictions using pandas dataframe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "##...checking for active users who rated in test_set for item 1..\n",
    "#indices=test_set[1][test_set[1].isnull()==False].index"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "items=list(test_set.columns)\n",
    "len(items)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# creating a list of active users of each item"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "indices={}\n",
    "for target_item in items:\n",
    "    active_users=test_set[target_item][test_set[target_item].isnull()==False].index\n",
    "    indices.update({target_item:active_users})\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#.....................Checking first k columns of sorted_similarity_matrix and predicitng on basis of that...\n",
    "#...................."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "k=6\n",
    "predictions=test_set.copy()\n",
    "for target_item in items:\n",
    "    for users in indices[target_item]:\n",
    "        k_sim=sorted_item_similarity[target_item][2:k+1]\n",
    "        weighted_sum=0\n",
    "        similarity_sum=0\n",
    "        for j in k_sim:\n",
    "            weighted_sum+=X4.loc[target_item][j]*train_set.loc[users][j] \n",
    "            similarity_sum+=X4.loc[target_item][j]\n",
    "        predictions.loc[users][target_item]=(weighted_sum/similarity_sum)     `\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "predictions.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#........END of calculating predictions using given k"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#.....................Checking Entire Row  of sorted_item_similarity_matrix for k similar items Code...........\n",
    "#............"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "\n",
    " indices=test_set[1][test_set[1].isnull()==False].index\n",
    "k=5\n",
    "predictions=[]\n",
    "for users in indices:\n",
    "    countItemsChecked=0\n",
    "    k_sim=sorted_item_similarity[1][2:k+1]\n",
    "    weighted_sum=0\n",
    "    similarity_sum=0\n",
    "    for j in k_sim:\n",
    "        if pd.isnull(train_set.loc[users][j]):\n",
    "            weighted_sum+=X4.loc[1][j]*train_set.loc[users][j] \n",
    "            similarity_sum+=X4.loc[1][j]\n",
    "            countItemsChecked+=1\n",
    "        if countItemsChecked==k:\n",
    "            break\n",
    "    if similarity_sum==0 or weighted_sum==0:\n",
    "            predictions.append(0)\n",
    "    else:\n",
    "        predictions.append(weighted_sum/similarity_sum)\n",
    "    \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#.....................END OF Checking Entire Row  of sorted_item_similarity_matrix for k similar items Code...........\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#######################################Calculation of Error metrics##############"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#begin code for pandas"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "y_test=test_set.copy()\n",
    "predictions_without_nan=predictions.copy()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "y_test.fillna(value=0,inplace=True)\n",
    "predictions_without_nan.fillna(value=0,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#end code for pandas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#begin code for numpy"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#Useless code\n",
    "predictions_without_nan=predictions.copy()\n",
    "y_test=test_set_np.copy()\n",
    "where_are_nans=np.isnan(np.array(predictions,dtype=np.float64))\n",
    "predictions_without_nan[where_are_nans]=0\n",
    "where_are_nans=np.isnan(np.array(test_set_np,dtype=np.float64))\n",
    "y_test[where_are_nans]=0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# extract all non-nan values from test set and predictions\n",
    "y_pred=absolute_predictions[~np.isnan(absolute_predictions)]\n",
    "y_true=test_set_np[~np.isnan(test_set_np)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#end code for numpy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAE: 0.892588666018\n",
      "MSE: 1.33083041416\n",
      "RMSE: 1.15361623348\n"
     ]
    }
   ],
   "source": [
    "from sklearn import metrics\n",
    "print('MAE:', metrics.mean_absolute_error(y_true,y_pred))\n",
    "print('MSE:', metrics.mean_squared_error(y_true,y_pred))\n",
    "print('RMSE:', np.sqrt(metrics.mean_squared_error(y_true,y_pred)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#..............END of calculation of error metrics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "################################plotting error vs k#################################"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "from sklearn import metrics"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "error=[]\n",
    "k_values=[521,729,786]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "train_set=train_set.fillna(value=0)\n",
    "train_set.head()\n",
    "#creating np array of test_set\n",
    "test_set_np=(test_set.values).copy()\n",
    "test_set_np=test_set_np.astype('float64')\n",
    "predictions=test_set_np.copy()\n",
    "rev_indices={v:k for k,v in dict_indices.items()}\n",
    "rev_user_indices=dict(zip(list(test_set.index),range(0,len(test_set.index))))\n",
    "#creating a dictionary which maps each items to its active users in test set(users who rated that item)\n",
    "items=list(test_set.columns)\n",
    "indices={}\n",
    "for target_item in items:\n",
    "    active_users=test_set[target_item][test_set[target_item].isnull()==False].index\n",
    "    indices.update({target_item:active_users})\n",
    "for k in k_values:\n",
    "    print(k)\n",
    "    for target_item in items:\n",
    "        rev_tar_item=rev_indices[target_item]#np index of target item \n",
    "        for users in indices[target_item]:\n",
    "            k_sim=sorted_item_similarity[rev_tar_item][1:k]\n",
    "            #note k_sim contains actual indices of k similar items\n",
    "            weighted_sum=0\n",
    "            similarity_sum=0\n",
    "            rev_user_idx=rev_user_indices[users]#np index of user\n",
    "            for j in k_sim:\n",
    "                rev_j=rev_indices[j]#np index of each similar item j\n",
    "                weighted_sum+=adjusted_cosine_sim[rev_tar_item][rev_j]*train_set_np[rev_user_idx][rev_j] \n",
    "                similarity_sum+=abs(adjusted_cosine_sim[rev_tar_item][rev_j])\n",
    "            if similarity_sum!=0:\n",
    "                predictions[rev_user_idx,rev_tar_item]=(weighted_sum/similarity_sum)\n",
    "            else:\n",
    "                predictions[rev_user_idx,rev_tar_item]=0\n",
    "    #error calculation\n",
    "    pred_dataframe=pd.DataFrame(data=predictions,index=test_set.index,columns=test_set.columns)\n",
    "    pred_dataframe=pred_dataframe.astype('float64')\n",
    "    pred_dataframe=pred_dataframe.add(mean_per_user,axis='index')\n",
    "    absolute_predictions=(pred_dataframe.values).copy()\n",
    "    absolute_predictions=absolute_predictions.astype('float64')\n",
    "    absolute_predictions[absolute_predictions>5]=5\n",
    "    absolute_predictions[absolute_predictions<0]=0\n",
    "    # extract all non-nan values from test set and predictions\n",
    "    y_pred=absolute_predictions[~np.isnan(absolute_predictions)]\n",
    "    y_true=test_set_np[~np.isnan(test_set_np)]\n",
    "    error.append(metrics.mean_absolute_error(y_true,y_pred))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "error"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "error=error[3:]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "error"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "plt.figure(figsize=(10,6))\n",
    "plt.plot(k_values,error,color='blue', linestyle='dashed', marker='o',\n",
    "         markerfacecolor='red', markersize=10)\n",
    "plt.title('Error Rate vs. K Value')\n",
    "plt.xlabel('K')\n",
    "plt.ylabel('Error Rate')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "################################Precision and Recall"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "precision=  0.706263481002157\n",
      "recall=  0.7480602785466368\n",
      "f1 score=  0.72656126650878\n"
     ]
    }
   ],
   "source": [
    "tp=y_pred[(y_pred>=4) &(y_true>=4)].shape[0]\n",
    "fp=y_pred[(y_pred>=4) & (y_true<4)].shape[0]\n",
    "tn=y_pred[(y_pred<4) & (y_true>=4)].shape[0]\n",
    "precision=tp/(tp+fp)\n",
    "recall=tp/(tp+tn)\n",
    "f1_score=2*precision*recall/(precision+recall)\n",
    "print('precision= ',precision)\n",
    "print('recall= ',recall)\n",
    "print('f1 score= ',f1_score)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}