Cosine_Similarity_Recommender_.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "id": "zjJT42FLZbU1"
   },
   "outputs": [],
   "source": [
    "# importing libraries\n",
    "%matplotlib inline\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import LabelEncoder\n",
    "import time"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "7Uayu4WLZU8s",
    "outputId": "dd7e946d-9fe2-4ce4-a027-54f17812d596"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "User Data :\n",
      "shape :  (943, 5)\n",
      "\n",
      "Ratings Data :\n",
      "shape :  (100000, 4)\n",
      "\n",
      "Item Data :\n",
      "shape :  (1682, 24)\n"
     ]
    }
   ],
   "source": [
    "\n",
    "# reading users file:\n",
    "u_cols = ['user_id', 'age', 'sex', 'occupation', 'zip_code']\n",
    "users = pd.read_csv('u.user', sep='|', names=u_cols,encoding='latin-1')\n",
    "\n",
    "# reading ratings file:\n",
    "r_cols = ['user_id', 'movie_id', 'rating', 'unix_timestamp']\n",
    "ratings = pd.read_csv('u.data', sep='\\t', names=r_cols,encoding='latin-1')\n",
    "\n",
    "# reading items file:\n",
    "i_cols = ['movie id', 'movie title' ,'release date','video release date', 'IMDb URL', 'unknown', 'Action', 'Adventure',\n",
    "'Animation', 'Children\\'s', 'Comedy', 'Crime', 'Documentary', 'Drama', 'Fantasy',\n",
    "'Film-Noir', 'Horror', 'Musical', 'Mystery', 'Romance', 'Sci-Fi', 'Thriller', 'War', 'Western']\n",
    "items = pd.read_csv('u.item', sep='|', names=i_cols,\n",
    "encoding='latin-1')\n",
    "\n",
    "# After loading the dataset, we should look at the content of each file (users, ratings, items).\n",
    "\n",
    "# Looking at the user file\n",
    "print(\"\\nUser Data :\")\n",
    "print(\"shape : \", users.shape)\n",
    "#print(users.head())\n",
    "\n",
    "# We have 943 users in the dataset and each user has 5 features, i.e. user_ID, age, sex, occupation and zip_code. Now let’s look at the ratings file.\n",
    "\n",
    "# Ratings Data\n",
    "print(\"\\nRatings Data :\")\n",
    "print(\"shape : \", ratings.shape)\n",
    "#print(ratings.head())\n",
    "\n",
    "# We have 100k ratings for different user and movie combinations. Now finally examine the items file.\n",
    "\n",
    "# Item Data\n",
    "print(\"\\nItem Data :\")\n",
    "print(\"shape : \", items.shape)\n",
    "#print(items.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "id": "BfIj3JatZVAQ",
    "outputId": "c4586144-f1d2-4361-858c-a4ed0db81a05"
   },
   "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>user_id</th>\n",
       "      <th>age</th>\n",
       "      <th>sex</th>\n",
       "      <th>occupation</th>\n",
       "      <th>zip_code</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>24</td>\n",
       "      <td>M</td>\n",
       "      <td>technician</td>\n",
       "      <td>85711</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>53</td>\n",
       "      <td>F</td>\n",
       "      <td>other</td>\n",
       "      <td>94043</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>23</td>\n",
       "      <td>M</td>\n",
       "      <td>writer</td>\n",
       "      <td>32067</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>24</td>\n",
       "      <td>M</td>\n",
       "      <td>technician</td>\n",
       "      <td>43537</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>33</td>\n",
       "      <td>F</td>\n",
       "      <td>other</td>\n",
       "      <td>15213</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   user_id  age sex  occupation zip_code\n",
       "0        1   24   M  technician    85711\n",
       "1        2   53   F       other    94043\n",
       "2        3   23   M      writer    32067\n",
       "3        4   24   M  technician    43537\n",
       "4        5   33   F       other    15213"
      ]
     },
     "execution_count": 5,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "users.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "id": "qNvHN71vXvph",
    "outputId": "a87bdaf7-e35b-4293-b778-02f7974a7620"
   },
   "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>user_id</th>\n",
       "      <th>movie_id</th>\n",
       "      <th>rating</th>\n",
       "      <th>unix_timestamp</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>196</td>\n",
       "      <td>242</td>\n",
       "      <td>3</td>\n",
       "      <td>881250949</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>186</td>\n",
       "      <td>302</td>\n",
       "      <td>3</td>\n",
       "      <td>891717742</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>22</td>\n",
       "      <td>377</td>\n",
       "      <td>1</td>\n",
       "      <td>878887116</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>244</td>\n",
       "      <td>51</td>\n",
       "      <td>2</td>\n",
       "      <td>880606923</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>166</td>\n",
       "      <td>346</td>\n",
       "      <td>1</td>\n",
       "      <td>886397596</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   user_id  movie_id  rating  unix_timestamp\n",
       "0      196       242       3       881250949\n",
       "1      186       302       3       891717742\n",
       "2       22       377       1       878887116\n",
       "3      244        51       2       880606923\n",
       "4      166       346       1       886397596"
      ]
     },
     "execution_count": 8,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ratings.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "id": "U9sWyhFGAUQt",
    "outputId": "210d43be-09be-4ade-b0c6-43ebfc1b86e6"
   },
   "outputs": [],
   "source": [
    "#converting the unix timestamp of ratings to a  date\n",
    "from datetime import datetime\n",
    "def time_stamp(k):\n",
    "  return datetime.fromtimestamp(k).strftime('%d-%m-%Y')\n",
    "ratings['rating_date'] = ratings['unix_timestamp'].apply(time_stamp)\n",
    "ratings.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "6ZtwHCXpBD7P",
    "outputId": "b051bc58-2b58-4bd2-d03b-625ed1a09cae"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1997\n",
      "1998\n"
     ]
    }
   ],
   "source": [
    "print(pd.DatetimeIndex(ratings['rating_date']).year.min())\n",
    "print(pd.DatetimeIndex(ratings['rating_date']).year.max())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "id": "gLTMfGYCAUUx",
    "outputId": "62c906cb-78d1-4632-c34f-017845064575"
   },
   "outputs": [],
   "source": [
    "#finding the no of days since the rating is given on movies from a specified date('01-11-1998')\n",
    "date_format = \"%d-%m-%Y\"\n",
    "def sub_dates(a):\n",
    "  return (datetime.strptime('01-11-1998', date_format)-a).days   \n",
    "def dat_strp(a):\n",
    "    return datetime.strptime(a, date_format)\n",
    "ratings['new_date']=ratings['rating_date'].apply(dat_strp)    \n",
    "ratings['days_diff']=ratings['new_date'].apply(sub_dates) \n",
    "#conversion of no of days to years\n",
    "ratings['years_diff']=round(ratings['days_diff']/365,2)\n",
    "ratings.head() "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "id": "7vzT2TvZFG9y",
    "outputId": "b93c86a1-d431-4259-83d5-f04ee2573b91"
   },
   "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>user_id</th>\n",
       "      <th>movie_id</th>\n",
       "      <th>rating</th>\n",
       "      <th>rating_date</th>\n",
       "      <th>days_diff</th>\n",
       "      <th>years_diff</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>196</td>\n",
       "      <td>242</td>\n",
       "      <td>3</td>\n",
       "      <td>04-12-1997</td>\n",
       "      <td>332</td>\n",
       "      <td>0.91</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>186</td>\n",
       "      <td>302</td>\n",
       "      <td>3</td>\n",
       "      <td>04-04-1998</td>\n",
       "      <td>211</td>\n",
       "      <td>0.58</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>22</td>\n",
       "      <td>377</td>\n",
       "      <td>1</td>\n",
       "      <td>07-11-1997</td>\n",
       "      <td>359</td>\n",
       "      <td>0.98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>244</td>\n",
       "      <td>51</td>\n",
       "      <td>2</td>\n",
       "      <td>27-11-1997</td>\n",
       "      <td>339</td>\n",
       "      <td>0.93</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>166</td>\n",
       "      <td>346</td>\n",
       "      <td>1</td>\n",
       "      <td>02-02-1998</td>\n",
       "      <td>272</td>\n",
       "      <td>0.75</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   user_id  movie_id  rating rating_date  days_diff  years_diff\n",
       "0      196       242       3  04-12-1997        332        0.91\n",
       "1      186       302       3  04-04-1998        211        0.58\n",
       "2       22       377       1  07-11-1997        359        0.98\n",
       "3      244        51       2  27-11-1997        339        0.93\n",
       "4      166       346       1  02-02-1998        272        0.75"
      ]
     },
     "execution_count": 13,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#dropping the below columns \n",
    "ratings.drop(['unix_timestamp','new_date'],axis=1,inplace=True)\n",
    "ratings.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "a7fszSUFFHDe",
    "outputId": "bd54957c-e24a-4e07-a60a-a90d732fb555"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    100000.000000\n",
       "mean          0.837096\n",
       "std           0.169676\n",
       "min           0.530000\n",
       "25%           0.690000\n",
       "50%           0.860000\n",
       "75%           0.970000\n",
       "max           1.120000\n",
       "Name: years_diff, dtype: float64"
      ]
     },
     "execution_count": 13,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ratings['years_diff'].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "id": "rA5RTsvQFHFz",
    "outputId": "eced2c49-767a-40bf-fa7c-9c806669dff9"
   },
   "outputs": [],
   "source": [
    "#for these values select m=0.425 and n=0.25\n",
    "m,n=0.425,0.25\n",
    "ratings['weighted_diff']=m*ratings['years_diff']+n\n",
    "ratings.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "id": "sBa1sxvkJ6SJ",
    "outputId": "20739da1-4d96-4903-aeb9-58d15a94878f"
   },
   "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>user_id</th>\n",
       "      <th>movie_id</th>\n",
       "      <th>rating</th>\n",
       "      <th>rating_date</th>\n",
       "      <th>days_diff</th>\n",
       "      <th>years_diff</th>\n",
       "      <th>weighted_diff</th>\n",
       "      <th>final_ratings</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>196</td>\n",
       "      <td>242</td>\n",
       "      <td>3</td>\n",
       "      <td>04-12-1997</td>\n",
       "      <td>332</td>\n",
       "      <td>0.91</td>\n",
       "      <td>0.63675</td>\n",
       "      <td>4.71</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>186</td>\n",
       "      <td>302</td>\n",
       "      <td>3</td>\n",
       "      <td>04-04-1998</td>\n",
       "      <td>211</td>\n",
       "      <td>0.58</td>\n",
       "      <td>0.49650</td>\n",
       "      <td>6.04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>22</td>\n",
       "      <td>377</td>\n",
       "      <td>1</td>\n",
       "      <td>07-11-1997</td>\n",
       "      <td>359</td>\n",
       "      <td>0.98</td>\n",
       "      <td>0.66650</td>\n",
       "      <td>1.50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>244</td>\n",
       "      <td>51</td>\n",
       "      <td>2</td>\n",
       "      <td>27-11-1997</td>\n",
       "      <td>339</td>\n",
       "      <td>0.93</td>\n",
       "      <td>0.64525</td>\n",
       "      <td>3.10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>166</td>\n",
       "      <td>346</td>\n",
       "      <td>1</td>\n",
       "      <td>02-02-1998</td>\n",
       "      <td>272</td>\n",
       "      <td>0.75</td>\n",
       "      <td>0.56875</td>\n",
       "      <td>1.76</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   user_id  movie_id  rating  ... years_diff  weighted_diff  final_ratings\n",
       "0      196       242       3  ...       0.91        0.63675           4.71\n",
       "1      186       302       3  ...       0.58        0.49650           6.04\n",
       "2       22       377       1  ...       0.98        0.66650           1.50\n",
       "3      244        51       2  ...       0.93        0.64525           3.10\n",
       "4      166       346       1  ...       0.75        0.56875           1.76\n",
       "\n",
       "[5 rows x 8 columns]"
      ]
     },
     "execution_count": 15,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Now I am gonna create new ratings which are time based/temporal\n",
    "ratings['final_ratings']=round(ratings['rating']/ratings['weighted_diff'],2)\n",
    "ratings.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "UIz-sSSBJ6XO",
    "outputId": "ea2d930b-8e19-48b1-adfe-4ea417f81644"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    100000.000000\n",
       "mean          5.911761\n",
       "std           2.037374\n",
       "min           1.380000\n",
       "25%           4.560000\n",
       "50%           6.000000\n",
       "75%           7.450000\n",
       "max          10.520000\n",
       "Name: final_ratings, dtype: float64"
      ]
     },
     "execution_count": 16,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ratings['final_ratings'].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "id": "5lfQ1dkFd9WY"
   },
   "outputs": [],
   "source": [
    "n_users = ratings.user_id.unique().shape[0]\n",
    "n_items = ratings.movie_id.unique().shape[0]\n",
    "data_matrix = np.zeros((n_users, n_items))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "Ijit9kaMfM_D",
    "outputId": "a5a01c11-05a3-4d82-daa5-d56fe4686f3a"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[6.93, 4.31, 5.96, ..., 0.  , 0.  , 0.  ],\n",
       "       [7.42, 0.  , 0.  , ..., 0.  , 0.  , 0.  ],\n",
       "       [0.  , 0.  , 0.  , ..., 0.  , 0.  , 0.  ],\n",
       "       ...,\n",
       "       [6.93, 0.  , 0.  , ..., 0.  , 0.  , 0.  ],\n",
       "       [0.  , 0.  , 0.  , ..., 0.  , 0.  , 0.  ],\n",
       "       [0.  , 9.35, 0.  , ..., 0.  , 0.  , 0.  ]])"
      ]
     },
     "execution_count": 18,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#basically here I am filling the respective user ids(line[1]) and movies(line[2]) with the value final ratings(line[8])\n",
    "for line in ratings.itertuples():\n",
    "    #print(line[1],line[2])\n",
    "    data_matrix[line[1]-1, line[2]-1] = line[8]\n",
    "data_matrix    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "id": "PwK7xmLdd9ZT"
   },
   "outputs": [],
   "source": [
    "#gonna use cosine similarity to determine similarities between movies and between users\n",
    "from sklearn.metrics.pairwise import pairwise_distances \n",
    "user_similarity = pairwise_distances(data_matrix, metric='cosine') #similarities between users \n",
    "item_similarity = pairwise_distances(data_matrix.T, metric='cosine') #similarities between movies\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "id": "B0lCDXLkd9fy"
   },
   "outputs": [],
   "source": [
    "def predict(ratings, similarity, type='user'):\n",
    "    if type == 'user':\n",
    "        mean_user_rating = ratings.mean(axis=1)\n",
    "        #np.newaxis is used to make dimensions similar for ratings and mean_user_rating\n",
    "        ratings_diff = (ratings - mean_user_rating[:, np.newaxis])\n",
    "        #prediction for ratings on the basis of similarity\n",
    "        pred = mean_user_rating[:, np.newaxis] + similarity.dot(ratings_diff) / np.array([np.abs(similarity).sum(axis=1)]).T\n",
    "    elif type == 'item':\n",
    "        pred = ratings.dot(similarity) / np.array([np.abs(similarity).sum(axis=1)])\n",
    "    return pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "id": "hUnCP5BOd9i7"
   },
   "outputs": [],
   "source": [
    "user_prediction = predict(data_matrix, user_similarity, type='user') #prediction of ratings using user-user similarity\n",
    "item_prediction = predict(data_matrix, item_similarity, type='item') #prediction of ratings using item-item similarity"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "QZeSL0m1d9lv",
    "outputId": "dcd84c86-0950-49e9-b599-33d8ca37c32f"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([3.29829425, 1.10668241, 0.92190528, ..., 0.53257039, 0.53145376,\n",
       "       0.53049004])"
      ]
     },
     "execution_count": 47,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "user_prediction[0]"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "name": "Cosine Similarity Recommender .ipynb",
   "provenance": []
  },
  "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": 1
}