NMF.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "NMF.ipynb",
      "provenance": [],
      "collapsed_sections": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "metadata": {
        "id": "bfVvo9JhS_5N",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "!pip install -U -q PyDrive"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "oOuF3IOSUYO1",
        "colab_type": "code",
        "outputId": "ab4ababd-56d9-44a3-b589-6f93c4c97f28",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        }
      },
      "source": [
        "from pydrive.auth import GoogleAuth\n",
        "from pydrive.drive import GoogleDrive\n",
        "from google.colab import auth\n",
        "from oauth2client.client import GoogleCredentials\n",
        "\n",
        "auth.authenticate_user()\n",
        "gauth = GoogleAuth()\n",
        "gauth.credentials = GoogleCredentials.get_application_default()\n",
        "drive = GoogleDrive(gauth)\n",
        "\n",
        "link = 'https://drive.google.com/open?id=1Xm1AGjdpZKgp11oajGgLgkRZIE3sQPTY'\n",
        "fluff, id = link.split('=')\n",
        "\n",
        "print (id)\n",
        "\n",
        "downloaded = drive.CreateFile({'id':id}) \n",
        "downloaded.GetContentFile('movieLens_ratings.csv') "
      ],
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "1Xm1AGjdpZKgp11oajGgLgkRZIE3sQPTY\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "UZsxG0ZezcXG",
        "colab_type": "code",
        "outputId": "cb14a1d8-2996-4562-a851-0c620e213e72",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        }
      },
      "source": [
        "from pydrive.auth import GoogleAuth\n",
        "from pydrive.drive import GoogleDrive\n",
        "from google.colab import auth\n",
        "from oauth2client.client import GoogleCredentials\n",
        "\n",
        "auth.authenticate_user()\n",
        "gauth = GoogleAuth()\n",
        "gauth.credentials = GoogleCredentials.get_application_default()\n",
        "drive = GoogleDrive(gauth)\n",
        "\n",
        "link = 'https://drive.google.com/open?id=10XJSBZzHmzajA3_h923XEhaaMn5qXuJ8'\n",
        "fluff, id = link.split('=')\n",
        "\n",
        "print (id)\n",
        "\n",
        "downloaded = drive.CreateFile({'id':id}) \n",
        "downloaded.GetContentFile('movies.csv') "
      ],
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "10XJSBZzHmzajA3_h923XEhaaMn5qXuJ8\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "gAmSg8J2vHeE",
        "colab_type": "code",
        "outputId": "6fee7206-8e16-4150-f42e-d860c214f03e",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        }
      },
      "source": [
        "import pandas as pd \n",
        "import numpy as np\n",
        "import warnings\n",
        "%matplotlib inline \n",
        "# warnings.filterwarnings('ignore')\n",
        "\n",
        "#ratings\n",
        "ratings_df = pd.read_csv('movieLens_ratings.csv')\n",
        "ratings_df.head()\n"
      ],
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>userId</th>\n",
              "      <th>movieId</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>1</td>\n",
              "      <td>4.0</td>\n",
              "      <td>964982703</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>3</td>\n",
              "      <td>4.0</td>\n",
              "      <td>964981247</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>1</td>\n",
              "      <td>6</td>\n",
              "      <td>4.0</td>\n",
              "      <td>964982224</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>1</td>\n",
              "      <td>47</td>\n",
              "      <td>5.0</td>\n",
              "      <td>964983815</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>1</td>\n",
              "      <td>50</td>\n",
              "      <td>5.0</td>\n",
              "      <td>964982931</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   userId  movieId  rating  timestamp\n",
              "0       1        1     4.0  964982703\n",
              "1       1        3     4.0  964981247\n",
              "2       1        6     4.0  964982224\n",
              "3       1       47     5.0  964983815\n",
              "4       1       50     5.0  964982931"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 3
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "gguM3GlmD1VL",
        "colab_type": "code",
        "outputId": "abc21449-fa12-45ca-f965-0f76065e7ba5",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 51
        }
      },
      "source": [
        "n_users = len(ratings_df['userId'].unique())\n",
        "n_items = len(ratings_df['movieId'].unique())\n",
        "R_shape = (n_users, n_items)\n",
        "print(str(n_users) + ' users')\n",
        "print(str(n_items) + ' items')"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "610 users\n",
            "9724 items\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Ld4b1IGiEVNc",
        "colab_type": "code",
        "outputId": "bbd1fe9c-8867-4ae8-c64f-afe049dae109",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 170
        }
      },
      "source": [
        "ratings_df['rating'].describe()"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "count    100836.000000\n",
              "mean          3.501557\n",
              "std           1.042529\n",
              "min           0.500000\n",
              "25%           3.000000\n",
              "50%           3.500000\n",
              "75%           4.000000\n",
              "max           5.000000\n",
              "Name: rating, dtype: float64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "D9daFYP5Eqsr",
        "colab_type": "code",
        "outputId": "8ef7f812-3a0e-4d21-e653-8a7e17e90863",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 499
        }
      },
      "source": [
        "import matplotlib.pyplot as plt\n",
        "from sklearn.preprocessing import scale\n",
        "\n",
        "plt.xlabel('Rating')\n",
        "plt.ylabel('Frequency')\n",
        "plt.title('Distribution of ratings')\n",
        "\n",
        "# Plot histogram \n",
        "binwidth = 0.1\n",
        "data = ratings_df['rating']\n",
        "plt.hist(data, bins=np.arange(min(data), max(data) + 0.5, binwidth))\n",
        "# plt.hist(ratings_df['rating'], color='purple', rwidth=0.85)\n",
        "# plt.show()"
      ],
      "execution_count": 21,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(array([ 1370.,     0.,     0.,     0.,     0.,  2811.,     0.,     0.,\n",
              "            0.,     0.,  1791.,     0.,     0.,     0.,     0.,  7551.,\n",
              "            0.,     0.,     0.,     0.,  5550.,     0.,     0.,     0.,\n",
              "            0., 20047.,     0.,     0.,     0.,     0., 13136.,     0.,\n",
              "            0.,     0.,     0., 26818.,     0.,     0.,     0.,     0.,\n",
              "         8551.,     0.,     0.,     0.,     0., 13211.,     0.,     0.,\n",
              "            0.]),\n",
              " array([0.5, 0.6, 0.7, 0.8, 0.9, 1. , 1.1, 1.2, 1.3, 1.4, 1.5, 1.6, 1.7,\n",
              "        1.8, 1.9, 2. , 2.1, 2.2, 2.3, 2.4, 2.5, 2.6, 2.7, 2.8, 2.9, 3. ,\n",
              "        3.1, 3.2, 3.3, 3.4, 3.5, 3.6, 3.7, 3.8, 3.9, 4. , 4.1, 4.2, 4.3,\n",
              "        4.4, 4.5, 4.6, 4.7, 4.8, 4.9, 5. , 5.1, 5.2, 5.3, 5.4]),\n",
              " <a list of 49 Patch objects>)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 21
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "x4uwSrtYIhXT",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        },
        "outputId": "0bd0fcd6-f3a3-4fbf-9f35-92b5c84c16c6"
      },
      "source": [
        "ratings_df.rating.value_counts()"
      ],
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "4.0    26818\n",
              "3.0    20047\n",
              "5.0    13211\n",
              "3.5    13136\n",
              "4.5     8551\n",
              "2.0     7551\n",
              "2.5     5550\n",
              "1.0     2811\n",
              "1.5     1791\n",
              "0.5     1370\n",
              "Name: rating, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "aQScrh00KvN8",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 170
        },
        "outputId": "d3fe14d8-c59a-47ae-f4a7-c4580a03dd9f"
      },
      "source": [
        "ratings_df.rating.describe()"
      ],
      "execution_count": 22,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "count    100836.000000\n",
              "mean          3.501557\n",
              "std           1.042529\n",
              "min           0.500000\n",
              "25%           3.000000\n",
              "50%           3.500000\n",
              "75%           4.000000\n",
              "max           5.000000\n",
              "Name: rating, dtype: float64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 22
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "OW6UOT1SRqV7",
        "colab_type": "code",
        "outputId": "46cdad66-bce2-447d-b988-9067b73e5ab7",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 298
        }
      },
      "source": [
        "x = ratings_df['rating']\n",
        "\n",
        "# Create the boxplot\n",
        "fig1, ax1 = plt.subplots()\n",
        "ax1.boxplot(x)\n",
        "plt.ylabel('Rating')\n",
        "plt.title('Box plot')"
      ],
      "execution_count": 25,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Text(0.5, 1.0, 'Box plot')"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 25
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "6RtPX82OLs0d",
        "colab_type": "code",
        "outputId": "6a7a5ba7-3288-4c11-cc4e-d754b4419b70",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 312
        }
      },
      "source": [
        "#average number of ppl rated the movies\n",
        "\n",
        "# count number of ratings per user\n",
        "users = ratings_df.groupby('userId')['movieId'].nunique()\n",
        "\n",
        "binwidth = 50\n",
        "users.hist(bins=np.arange(min(users), max(users) + binwidth, binwidth))    \n",
        "plt.xlabel('Number of ratings per user')\n",
        "plt.ylabel('Number of users')\n",
        "plt.title('Distribution of ratings count per user')"
      ],
      "execution_count": 33,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Text(0.5, 1.0, 'Distribution of ratings count per user')"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 33
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ravsLF7OzWRD",
        "colab_type": "code",
        "outputId": "721855fb-354a-480d-bb21-c07a90b37ce2",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        }
      },
      "source": [
        "#movie titles\n",
        "movie_titles = pd.read_csv('movies.csv')\n",
        "movie_titles.head()"
      ],
      "execution_count": 68,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>movieId</th>\n",
              "      <th>title</th>\n",
              "      <th>genres</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>9737</th>\n",
              "      <td>193581</td>\n",
              "      <td>Black Butler: Book of the Atlantic (2017)</td>\n",
              "      <td>Action|Animation|Comedy|Fantasy</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>9738</th>\n",
              "      <td>193583</td>\n",
              "      <td>No Game No Life: Zero (2017)</td>\n",
              "      <td>Animation|Comedy|Fantasy</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>9739</th>\n",
              "      <td>193585</td>\n",
              "      <td>Flint (2017)</td>\n",
              "      <td>Drama</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>9740</th>\n",
              "      <td>193587</td>\n",
              "      <td>Bungo Stray Dogs: Dead Apple (2018)</td>\n",
              "      <td>Action|Animation</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>9741</th>\n",
              "      <td>193609</td>\n",
              "      <td>Andrew Dice Clay: Dice Rules (1991)</td>\n",
              "      <td>Comedy</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "      movieId  ...                           genres\n",
              "9737   193581  ...  Action|Animation|Comedy|Fantasy\n",
              "9738   193583  ...         Animation|Comedy|Fantasy\n",
              "9739   193585  ...                            Drama\n",
              "9740   193587  ...                 Action|Animation\n",
              "9741   193609  ...                           Comedy\n",
              "\n",
              "[5 rows x 3 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 68
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "QEFLsbTMbi9n",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 297
        },
        "outputId": "f72fc49b-920a-4c63-c96a-5dde49654768"
      },
      "source": [
        "movie_titles.describe()"
      ],
      "execution_count": 70,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>movieId</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>9742.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>42200.353623</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>52160.494854</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>3248.250000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>7300.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>76232.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>193609.000000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "             movieId\n",
              "count    9742.000000\n",
              "mean    42200.353623\n",
              "std     52160.494854\n",
              "min         1.000000\n",
              "25%      3248.250000\n",
              "50%      7300.000000\n",
              "75%     76232.000000\n",
              "max    193609.000000"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 70
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "iOmmILnf0AVn",
        "colab_type": "code",
        "outputId": "5d856d02-2268-40a8-d66c-bcc00c2d45df",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        }
      },
      "source": [
        "df = pd.merge(ratings_df, movie_titles, on='movieId')\n",
        "df.head()\n"
      ],
      "execution_count": 71,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>userId</th>\n",
              "      <th>movieId</th>\n",
              "      <th>rating</th>\n",
              "      <th>timestamp</th>\n",
              "      <th>title</th>\n",
              "      <th>genres</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>4.0</td>\n",
              "      <td>964982703</td>\n",
              "      <td>Toy Story (1995)</td>\n",
              "      <td>Adventure|Animation|Children|Comedy|Fantasy</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>5</td>\n",
              "      <td>1</td>\n",
              "      <td>4.0</td>\n",
              "      <td>847434962</td>\n",
              "      <td>Toy Story (1995)</td>\n",
              "      <td>Adventure|Animation|Children|Comedy|Fantasy</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>7</td>\n",
              "      <td>1</td>\n",
              "      <td>4.5</td>\n",
              "      <td>1106635946</td>\n",
              "      <td>Toy Story (1995)</td>\n",
              "      <td>Adventure|Animation|Children|Comedy|Fantasy</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>15</td>\n",
              "      <td>1</td>\n",
              "      <td>2.5</td>\n",
              "      <td>1510577970</td>\n",
              "      <td>Toy Story (1995)</td>\n",
              "      <td>Adventure|Animation|Children|Comedy|Fantasy</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>17</td>\n",
              "      <td>1</td>\n",
              "      <td>4.5</td>\n",
              "      <td>1305696483</td>\n",
              "      <td>Toy Story (1995)</td>\n",
              "      <td>Adventure|Animation|Children|Comedy|Fantasy</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   userId  ...                                       genres\n",
              "0       1  ...  Adventure|Animation|Children|Comedy|Fantasy\n",
              "1       5  ...  Adventure|Animation|Children|Comedy|Fantasy\n",
              "2       7  ...  Adventure|Animation|Children|Comedy|Fantasy\n",
              "3      15  ...  Adventure|Animation|Children|Comedy|Fantasy\n",
              "4      17  ...  Adventure|Animation|Children|Comedy|Fantasy\n",
              "\n",
              "[5 rows x 6 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 71
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "8xksVSNRUKbo",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "#split df to test and train\n",
        "msk = np.random.rand(len(df)) < 0.8\n",
        "# train = df[msk]\n",
        "test = df[~msk]\n",
        "\n"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "8NvZC0qCZ7oW",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 68
        },
        "outputId": "c82e6a31-afda-4ac7-807b-c5bae815fdcc"
      },
      "source": [
        "# train set \n",
        "#-when we split whole data to train/test there mght be some items (users or movies) that appear just in test set,\n",
        "# therefor would be no row or column for them on user-movie matrix\n",
        "# to solve this we initialize train set with the whole data and rows which belong to test set, their movie rating will be replaced with nan (zero)\n",
        "train = df.copy()\n",
        "for index, row in test.iterrows():\n",
        "  uid = row[\"userId\"]\n",
        "  mid = row[\"movieId\"]\n",
        "\n",
        "  indx = train.index[(train['userId'] == uid) & (train['movieId'] == mid)][0]\n",
        "  train.iloc[indx, train.columns.get_loc('rating')] = 0 #np.nan\n",
        "\n",
        "print(df.shape)\n",
        "print(\"train: \", train.shape)\n",
        "print(\"test: \", test.shape)"
      ],
      "execution_count": 133,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "(100836, 6)\n",
            "train:  (100836, 6)\n",
            "test:  (20096, 6)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "umGRxSS-02yB",
        "colab_type": "code",
        "outputId": "546fb8ef-7fa6-43a5-d1d3-6eb741056fc0",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 284
        }
      },
      "source": [
        "#make user-movie matrix out of train dataset\n",
        "movie_matrix = train.pivot_table(index='userId', columns='movieId', values='rating') #use Train\n",
        "movie_matrix.head()\n"
      ],
      "execution_count": 139,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>movieId</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>11</th>\n",
              "      <th>12</th>\n",
              "      <th>13</th>\n",
              "      <th>14</th>\n",
              "      <th>15</th>\n",
              "      <th>16</th>\n",
              "      <th>17</th>\n",
              "      <th>18</th>\n",
              "      <th>19</th>\n",
              "      <th>20</th>\n",
              "      <th>21</th>\n",
              "      <th>22</th>\n",
              "      <th>23</th>\n",
              "      <th>24</th>\n",
              "      <th>25</th>\n",
              "      <th>26</th>\n",
              "      <th>27</th>\n",
              "      <th>28</th>\n",
              "      <th>29</th>\n",
              "      <th>30</th>\n",
              "      <th>31</th>\n",
              "      <th>32</th>\n",
              "      <th>34</th>\n",
              "      <th>36</th>\n",
              "      <th>38</th>\n",
              "      <th>39</th>\n",
              "      <th>40</th>\n",
              "      <th>41</th>\n",
              "      <th>42</th>\n",
              "      <th>43</th>\n",
              "      <th>...</th>\n",
              "      <th>185135</th>\n",
              "      <th>185435</th>\n",
              "      <th>185473</th>\n",
              "      <th>185585</th>\n",
              "      <th>186587</th>\n",
              "      <th>187031</th>\n",
              "      <th>187541</th>\n",
              "      <th>187593</th>\n",
              "      <th>187595</th>\n",
              "      <th>187717</th>\n",
              "      <th>188189</th>\n",
              "      <th>188301</th>\n",
              "      <th>188675</th>\n",
              "      <th>188751</th>\n",
              "      <th>188797</th>\n",
              "      <th>188833</th>\n",
              "      <th>189043</th>\n",
              "      <th>189111</th>\n",
              "      <th>189333</th>\n",
              "      <th>189381</th>\n",
              "      <th>189547</th>\n",
              "      <th>189713</th>\n",
              "      <th>190183</th>\n",
              "      <th>190207</th>\n",
              "      <th>190209</th>\n",
              "      <th>190213</th>\n",
              "      <th>190215</th>\n",
              "      <th>190219</th>\n",
              "      <th>190221</th>\n",
              "      <th>191005</th>\n",
              "      <th>193565</th>\n",
              "      <th>193567</th>\n",
              "      <th>193571</th>\n",
              "      <th>193573</th>\n",
              "      <th>193579</th>\n",
              "      <th>193581</th>\n",
              "      <th>193583</th>\n",
              "      <th>193585</th>\n",
              "      <th>193587</th>\n",
              "      <th>193609</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>userId</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>4.0</td>\n",
              "      <td>NaN</td>\n",
              "      <td>0.0</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>4.0</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",
              "      <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>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>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",
              "      <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>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>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>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>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>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",
              "      <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>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>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>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>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>0.5</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",
              "      <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>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>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>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>3.0</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",
              "      <td>2.0</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",
              "      <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>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>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>4.0</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",
              "      <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>4.0</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",
              "      <td>NaN</td>\n",
              "      <td>4.0</td>\n",
              "      <td>4.0</td>\n",
              "      <td>NaN</td>\n",
              "      <td>3.0</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",
              "      <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>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>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 × 9724 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "movieId  1       2       3       4       ...  193583  193585  193587  193609\n",
              "userId                                   ...                                \n",
              "1           4.0     NaN     0.0     NaN  ...     NaN     NaN     NaN     NaN\n",
              "2           NaN     NaN     NaN     NaN  ...     NaN     NaN     NaN     NaN\n",
              "3           NaN     NaN     NaN     NaN  ...     NaN     NaN     NaN     NaN\n",
              "4           NaN     NaN     NaN     NaN  ...     NaN     NaN     NaN     NaN\n",
              "5           4.0     NaN     NaN     NaN  ...     NaN     NaN     NaN     NaN\n",
              "\n",
              "[5 rows x 9724 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 139
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Ylr4ta_bkyL4",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "colid2movieId = dict(zip(range(len(movie_matrix.columns)), list(movie_matrix.columns)))\n",
        "rowid2userId = dict(zip(range(len(movie_matrix.index)), list(movie_matrix.index)))\n",
        "\n",
        "movieId2colid = {v: k for k, v in colid2movieId.items()}\n",
        "userId2rowid = {v: k for k, v in rowid2userId.items()}"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "HuCOtItMVLW2",
        "colab_type": "code",
        "outputId": "96958201-5c87-40dd-b664-c537247c477e",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        }
      },
      "source": [
        "#convert dataframe to list\n",
        "movie_matrix = movie_matrix.values.tolist()\n",
        "R = np.asarray(movie_matrix)\n",
        "R[0]\n",
        "R.shape"
      ],
      "execution_count": 141,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(610, 9724)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 141
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "f7fwsVMSRDZE",
        "colab_type": "code",
        "outputId": "a1ebeae9-d53a-4f4c-f98f-a8601cd71f21",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        }
      },
      "source": [
        "# replace nans to zero\n",
        "R = np.nan_to_num(R)\n",
        "R[0]"
      ],
      "execution_count": 142,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([4., 0., 0., ..., 0., 0., 0.])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 142
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "RKvKjSE-P1kI",
        "colab_type": "code",
        "outputId": "0d93402f-1f54-482f-f4c8-e1621aa58253",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        }
      },
      "source": [
        "# Computing the sparsity of R\n",
        "print(len(R.nonzero()[0]) / float(R.shape[0] * R.shape[1]))\n",
        "# Sparsity is 1.3%. This means that 1.3% of the user-item ratings have a value. "
      ],
      "execution_count": 143,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "0.013611749870187671\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ZIcLsSH4fN6B",
        "colab_type": "code",
        "outputId": "51eef454-d770-407a-9f12-a60b7f9b3dbf",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 238
        }
      },
      "source": [
        "from sklearn.decomposition import NMF\n",
        "\n",
        "\n",
        "nmf_model = NMF(n_components=100)     # starts with 20 latents factors\n",
        "\n",
        "# Matrix factorization               # V ~ W.H  (Find two non-negative matrices (W, H) whose product approximates the non- negative matrix X. )\n",
        "nmf_model.fit(R)                     # R can be array-like or sparse, here it is array-like (dense)\n",
        "P = nmf_model.transform(R)       # user latent factors (= W, called the features matrix)\n",
        "Q = nmf_model.components_.T          # item latent factors (= H.T) (H is called the coefficient matrix)\n",
        "\n",
        "         \n",
        "R_pred = P.dot(Q.T)              \n",
        "\n",
        "\n",
        "print(\"R: \", R.shape)\n",
        "print('User features - P:', P.shape)\n",
        "print('Item features - Q:', Q.shape)\n",
        "print('Predicted R:', R_pred.shape)\n",
        "print()\n",
        "print('R ~ P * Q.T:')\n",
        "print(R_pred.round(2))\n"
      ],
      "execution_count": 144,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "R:  (610, 9724)\n",
            "User features - P: (610, 100)\n",
            "Item features - Q: (9724, 100)\n",
            "Predicted R: (610, 9724)\n",
            "\n",
            "R ~ P * Q.T:\n",
            "[[4.7  0.   0.   ... 0.   0.   0.  ]\n",
            " [0.29 0.01 0.   ... 0.   0.   0.04]\n",
            " [0.09 0.06 0.05 ... 0.   0.   0.  ]\n",
            " ...\n",
            " [0.   1.99 1.87 ... 0.   0.   0.02]\n",
            " [0.75 0.74 0.24 ... 0.   0.   0.  ]\n",
            " [0.   0.01 0.   ... 0.   0.   0.  ]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "OILtr6DsU7hi",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 306
        },
        "outputId": "9cdea78b-5d8c-4160-f3dd-154647e0ac92"
      },
      "source": [
        "#predict ratings for test set\n",
        "\n",
        "\n",
        "def pred_rating(row):\n",
        "  uid = row[\"userId\"]\n",
        "  rowid = userId2rowid[uid]\n",
        "  mid = row[\"movieId\"]\n",
        "  colid = movieId2colid[mid]\n",
        "\n",
        "  return R_pred[rowid][colid]\n",
        "\n",
        "test['pred_rating'] = test.apply (lambda row: pred_rating(row), axis=1)\n",
        "\n",
        "test.head()\n",
        "\n"
      ],
      "execution_count": 145,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py:10: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
            "Try using .loc[row_indexer,col_indexer] = value instead\n",
            "\n",
            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
            "  # Remove the CWD from sys.path while we load stuff.\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "execute_result",
          "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>userId</th>\n",
              "      <th>movieId</th>\n",
              "      <th>rating</th>\n",
              "      <th>timestamp</th>\n",
              "      <th>title</th>\n",
              "      <th>genres</th>\n",
              "      <th>pred_rating</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>7</td>\n",
              "      <td>1</td>\n",
              "      <td>4.5</td>\n",
              "      <td>1106635946</td>\n",
              "      <td>Toy Story (1995)</td>\n",
              "      <td>Adventure|Animation|Children|Comedy|Fantasy</td>\n",
              "      <td>1.041422</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>18</td>\n",
              "      <td>1</td>\n",
              "      <td>3.5</td>\n",
              "      <td>1455209816</td>\n",
              "      <td>Toy Story (1995)</td>\n",
              "      <td>Adventure|Animation|Children|Comedy|Fantasy</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>10</th>\n",
              "      <td>32</td>\n",
              "      <td>1</td>\n",
              "      <td>3.0</td>\n",
              "      <td>856736119</td>\n",
              "      <td>Toy Story (1995)</td>\n",
              "      <td>Adventure|Animation|Children|Comedy|Fantasy</td>\n",
              "      <td>2.459576</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>12</th>\n",
              "      <td>40</td>\n",
              "      <td>1</td>\n",
              "      <td>5.0</td>\n",
              "      <td>832058959</td>\n",
              "      <td>Toy Story (1995)</td>\n",
              "      <td>Adventure|Animation|Children|Comedy|Fantasy</td>\n",
              "      <td>0.868060</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>17</th>\n",
              "      <td>50</td>\n",
              "      <td>1</td>\n",
              "      <td>3.0</td>\n",
              "      <td>1514238116</td>\n",
              "      <td>Toy Story (1995)</td>\n",
              "      <td>Adventure|Animation|Children|Comedy|Fantasy</td>\n",
              "      <td>0.931626</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "    userId  movieId  ...                                       genres  pred_rating\n",
              "2        7        1  ...  Adventure|Animation|Children|Comedy|Fantasy     1.041422\n",
              "5       18        1  ...  Adventure|Animation|Children|Comedy|Fantasy     0.000000\n",
              "10      32        1  ...  Adventure|Animation|Children|Comedy|Fantasy     2.459576\n",
              "12      40        1  ...  Adventure|Animation|Children|Comedy|Fantasy     0.868060\n",
              "17      50        1  ...  Adventure|Animation|Children|Comedy|Fantasy     0.931626\n",
              "\n",
              "[5 rows x 7 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 145
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "qBxP-s4V0g5v",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "032f4fbf-e214-4e20-cf67-5f789d5116c0"
      },
      "source": [
        "#compute RMSE \n",
        "\n",
        "y_predicted = test['pred_rating']\n",
        "y_actual = test['rating']\n",
        "\n",
        "from sklearn.metrics import mean_squared_error\n",
        "from math import sqrt\n",
        "\n",
        "rms = sqrt(mean_squared_error(y_actual, y_predicted))\n",
        "print(rms)"
      ],
      "execution_count": 149,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "3.3432432169842823\n"
          ],
          "name": "stdout"
        }
      ]
    }
  ]
}