{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Data is from https://grouplens.org/datasets/movielens/\n",
    "# Use \"MovieLens 1M Dataset\"\n",
    "dir = \"/Users/giri/Documents/Teach/DataScience/PythonNotebooks/Lec2/\"\n",
    "unames = ['user_id', 'gender', 'age', 'occupation', 'zip'] \n",
    "users = pd.read_table(dir + 'data/ml-1m/users.dat', sep='::', header=None, \n",
    "                      names=unames, engine='python')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "rnames = ['user_id', 'movie_id', 'rating', 'timestamp']\n",
    "ratings = pd.read_table(dir + 'data/ml-1m/ratings.dat', sep='::', header=None, \n",
    "                        names=rnames, engine='python')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "mnames = ['movie_id', 'title', 'genres']\n",
    "movies = pd.read_table(dir + 'data/ml-1m/movies.dat', sep='::', header=None,\n",
    "                        names=mnames, engine='python')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "users[:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "ratings[:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies[:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "ratings.iloc[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = pd.merge(pd.merge(ratings, users), movies)\n",
    "data.iloc[5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "data.iloc[438]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "data.iloc[443889]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Get average ratings of all movies and separate by gender\n",
    "mean_ratings = data.pivot_table('rating', 'title', \n",
    "                                'gender', aggfunc='mean')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "mean_ratings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "num_ratings = data.groupby('title').size()\n",
    "num_ratings[:10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# meaningful ratings are when we have at least 250 people rate a movie\n",
    "meaningful_ratings = num_ratings.index[num_ratings >= 250]\n",
    "meaningful_ratings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "meaningful_mean_ratings = mean_ratings.loc[meaningful_ratings]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "meaningful_mean_ratings[:10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_female_ratings = meaningful_mean_ratings.sort_values(by='F', ascending=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_female_ratings[:10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_male_ratings = meaningful_mean_ratings.sort_values(by='M', ascending=False)\n",
    "top_male_ratings[:10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "meaningful_mean_ratings['diff'] = meaningful_mean_ratings['M'] - meaningful_mean_ratings['F']\n",
    "sorted_by_diff = meaningful_mean_ratings.sort_values(by='diff')\n",
    "sorted_by_diff[:10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "sorted_by_diff[-10:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "rating_std = data.groupby('title')['rating'].std()\n",
    "rating_std = rating_std.loc[meaningful_ratings] # filter only meaningful ones\n",
    "rating_std.sort_values(ascending=False)[:10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "rating_std.sort_values()[:10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}