{
    "cells": [
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "# Movies ratings and rankings example"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "Packages to load"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 1,
            "metadata": {},
            "outputs": [],
            "source": [
                "import ratingslib.ratings as rl\n",
                "import pandas as pd\n",
                "from ratingslib.datasets.filenames import FILENAME_MOVIES_EXAMPLE, dataset_path\n",
                "from ratingslib.datasets.parse import create_pairs_data, parse_pairs_data\n",
                "from ratingslib.utils.methods import parse_columns"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "Prepare data"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 2,
            "metadata": {},
            "outputs": [],
            "source": [
                "filename = dataset_path(FILENAME_MOVIES_EXAMPLE)\n",
                "user_movie_df = pd.read_csv(filename, index_col='User')"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "Create movie-movie dataframe. Movies are placed in pairs which means that every pair is a\n",
                "hypothetical matchup. The columns of movie_movie dataframe are\n",
                "set in COLUMNS dictionary."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 3,
            "metadata": {},
            "outputs": [],
            "source": [
                "COLUMNS = {'item_i': 'MovieI',\n",
                "           'item_j': 'MovieJ',\n",
                "           'points_i': 'RatingI',\n",
                "           'points_j': 'RatingJ'\n",
                "           }\n",
                "\n",
                "col_names = parse_columns(COLUMNS)\n",
                "movie_movie_df = create_pairs_data(user_movie_df, columns_dict=COLUMNS)"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "Parse movie-movie dataframe as pairs data."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 4,
            "metadata": {},
            "outputs": [],
            "source": [
                "data_df, items_df = parse_pairs_data(movie_movie_df, columns_dict=COLUMNS)"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "Colley method"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 5,
            "metadata": {},
            "outputs": [
                {
                    "data": {
                        "text/html": [
                            "<div>\n",
                            "<style scoped>\n",
                            "    .dataframe tbody tr th:only-of-type {\n",
                            "        vertical-align: middle;\n",
                            "    }\n",
                            "\n",
                            "    .dataframe tbody tr th {\n",
                            "        vertical-align: top;\n",
                            "    }\n",
                            "\n",
                            "    .dataframe thead th {\n",
                            "        text-align: right;\n",
                            "    }\n",
                            "</style>\n",
                            "<table border=\"1\" class=\"dataframe\">\n",
                            "  <thead>\n",
                            "    <tr style=\"text-align: right;\">\n",
                            "      <th></th>\n",
                            "      <th>Item</th>\n",
                            "      <th>rating</th>\n",
                            "      <th>ranking</th>\n",
                            "    </tr>\n",
                            "  </thead>\n",
                            "  <tbody>\n",
                            "    <tr>\n",
                            "      <th>2</th>\n",
                            "      <td>Movie3</td>\n",
                            "      <td>0.750</td>\n",
                            "      <td>1</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>1</th>\n",
                            "      <td>Movie2</td>\n",
                            "      <td>0.425</td>\n",
                            "      <td>2</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>0</th>\n",
                            "      <td>Movie1</td>\n",
                            "      <td>0.325</td>\n",
                            "      <td>3</td>\n",
                            "    </tr>\n",
                            "  </tbody>\n",
                            "</table>\n",
                            "</div>"
                        ],
                        "text/plain": [
                            "     Item  rating  ranking\n",
                            "2  Movie3   0.750        1\n",
                            "1  Movie2   0.425        2\n",
                            "0  Movie1   0.325        3"
                        ]
                    },
                    "execution_count": 5,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "rl.Colley().rate(data_df, items_df,\n",
                "                          columns_dict=COLUMNS, sort=True)"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "Massey method"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 6,
            "metadata": {},
            "outputs": [
                {
                    "data": {
                        "text/html": [
                            "<div>\n",
                            "<style scoped>\n",
                            "    .dataframe tbody tr th:only-of-type {\n",
                            "        vertical-align: middle;\n",
                            "    }\n",
                            "\n",
                            "    .dataframe tbody tr th {\n",
                            "        vertical-align: top;\n",
                            "    }\n",
                            "\n",
                            "    .dataframe thead th {\n",
                            "        text-align: right;\n",
                            "    }\n",
                            "</style>\n",
                            "<table border=\"1\" class=\"dataframe\">\n",
                            "  <thead>\n",
                            "    <tr style=\"text-align: right;\">\n",
                            "      <th></th>\n",
                            "      <th>Item</th>\n",
                            "      <th>rating</th>\n",
                            "      <th>ranking</th>\n",
                            "    </tr>\n",
                            "  </thead>\n",
                            "  <tbody>\n",
                            "    <tr>\n",
                            "      <th>2</th>\n",
                            "      <td>Movie3</td>\n",
                            "      <td>1.166667</td>\n",
                            "      <td>1</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>1</th>\n",
                            "      <td>Movie2</td>\n",
                            "      <td>0.104167</td>\n",
                            "      <td>2</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>0</th>\n",
                            "      <td>Movie1</td>\n",
                            "      <td>-1.270833</td>\n",
                            "      <td>3</td>\n",
                            "    </tr>\n",
                            "  </tbody>\n",
                            "</table>\n",
                            "</div>"
                        ],
                        "text/plain": [
                            "     Item    rating  ranking\n",
                            "2  Movie3  1.166667        1\n",
                            "1  Movie2  0.104167        2\n",
                            "0  Movie1 -1.270833        3"
                        ]
                    },
                    "execution_count": 6,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "rl.Massey().rate(data_df, items_df,\n",
                "                          columns_dict=COLUMNS, sort=True)"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "Keener method"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 7,
            "metadata": {},
            "outputs": [
                {
                    "data": {
                        "text/html": [
                            "<div>\n",
                            "<style scoped>\n",
                            "    .dataframe tbody tr th:only-of-type {\n",
                            "        vertical-align: middle;\n",
                            "    }\n",
                            "\n",
                            "    .dataframe tbody tr th {\n",
                            "        vertical-align: top;\n",
                            "    }\n",
                            "\n",
                            "    .dataframe thead th {\n",
                            "        text-align: right;\n",
                            "    }\n",
                            "</style>\n",
                            "<table border=\"1\" class=\"dataframe\">\n",
                            "  <thead>\n",
                            "    <tr style=\"text-align: right;\">\n",
                            "      <th></th>\n",
                            "      <th>Item</th>\n",
                            "      <th>rating</th>\n",
                            "      <th>ranking</th>\n",
                            "    </tr>\n",
                            "  </thead>\n",
                            "  <tbody>\n",
                            "    <tr>\n",
                            "      <th>2</th>\n",
                            "      <td>Movie3</td>\n",
                            "      <td>0.510552</td>\n",
                            "      <td>1</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>1</th>\n",
                            "      <td>Movie2</td>\n",
                            "      <td>0.288870</td>\n",
                            "      <td>2</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>0</th>\n",
                            "      <td>Movie1</td>\n",
                            "      <td>0.200577</td>\n",
                            "      <td>3</td>\n",
                            "    </tr>\n",
                            "  </tbody>\n",
                            "</table>\n",
                            "</div>"
                        ],
                        "text/plain": [
                            "     Item    rating  ranking\n",
                            "2  Movie3  0.510552        1\n",
                            "1  Movie2  0.288870        2\n",
                            "0  Movie1  0.200577        3"
                        ]
                    },
                    "execution_count": 7,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "rl.Keener(normalization=True).rate(data_df, items_df,\n",
                "                                            columns_dict=COLUMNS,\n",
                "                                            sort=True)"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "Offense-Defense method"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 8,
            "metadata": {},
            "outputs": [
                {
                    "data": {
                        "text/html": [
                            "<div>\n",
                            "<style scoped>\n",
                            "    .dataframe tbody tr th:only-of-type {\n",
                            "        vertical-align: middle;\n",
                            "    }\n",
                            "\n",
                            "    .dataframe tbody tr th {\n",
                            "        vertical-align: top;\n",
                            "    }\n",
                            "\n",
                            "    .dataframe thead th {\n",
                            "        text-align: right;\n",
                            "    }\n",
                            "</style>\n",
                            "<table border=\"1\" class=\"dataframe\">\n",
                            "  <thead>\n",
                            "    <tr style=\"text-align: right;\">\n",
                            "      <th></th>\n",
                            "      <th>Item</th>\n",
                            "      <th>rating</th>\n",
                            "      <th>ranking</th>\n",
                            "    </tr>\n",
                            "  </thead>\n",
                            "  <tbody>\n",
                            "    <tr>\n",
                            "      <th>2</th>\n",
                            "      <td>Movie3</td>\n",
                            "      <td>21.998853</td>\n",
                            "      <td>1</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>1</th>\n",
                            "      <td>Movie2</td>\n",
                            "      <td>15.821345</td>\n",
                            "      <td>2</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>0</th>\n",
                            "      <td>Movie1</td>\n",
                            "      <td>10.618677</td>\n",
                            "      <td>3</td>\n",
                            "    </tr>\n",
                            "  </tbody>\n",
                            "</table>\n",
                            "</div>"
                        ],
                        "text/plain": [
                            "     Item     rating  ranking\n",
                            "2  Movie3  21.998853        1\n",
                            "1  Movie2  15.821345        2\n",
                            "0  Movie1  10.618677        3"
                        ]
                    },
                    "execution_count": 8,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "rl.OffenseDefense(tol=0.001).rate(data_df, items_df,\n",
                "                                       columns_dict=COLUMNS, sort=True)"
            ]
        }
    ],
    "metadata": {
        "kernelspec": {
            "display_name": "Python 3.8.13 ('py38')",
            "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": "3.8.13"
        },
        "orig_nbformat": 4,
        "vscode": {
            "interpreter": {
                "hash": "23ceb7112fbf9d0e38ecbf60d6e6d5e2dcebcc82200eeb1e5a5d5f9ffb9e27ca"
            }
        }
    },
    "nbformat": 4,
    "nbformat_minor": 2
}