{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Data Analysis Examples"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "rc = {\"figure.figsize\" : (14, 6)}\n",
    "sns.set(rc = rc)\n",
    "my_palette = sns.color_palette(\"husl\", 4)\n",
    "sns.set_palette(my_palette)\n",
    "sns.set_style(\"whitegrid\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## USA.gov data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Load the dataset\n",
    "Use the `json` module to load the data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "path = \"datasets/bitly_usagov/example.txt\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'a': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.78 Safari/535.11',\n",
       " 'al': 'en-US,en;q=0.8',\n",
       " 'c': 'US',\n",
       " 'cy': 'Danvers',\n",
       " 'g': 'A6qOVH',\n",
       " 'gr': 'MA',\n",
       " 'h': 'wfLQtf',\n",
       " 'hc': 1331822918,\n",
       " 'hh': '1.usa.gov',\n",
       " 'l': 'orofrog',\n",
       " 'll': [42.576698, -70.954903],\n",
       " 'nk': 1,\n",
       " 'r': 'http://www.facebook.com/l/7AQEFzjSi/1.usa.gov/wfLQtf',\n",
       " 't': 1331923247,\n",
       " 'tz': 'America/New_York',\n",
       " 'u': 'http://www.ncbi.nlm.nih.gov/pubmed/22415991'}"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "records = [json.loads(line) for line in open(path)]\n",
    "records[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Count the number of timezones with pandas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>_heartbeat_</th>\n",
       "      <th>a</th>\n",
       "      <th>al</th>\n",
       "      <th>c</th>\n",
       "      <th>cy</th>\n",
       "      <th>g</th>\n",
       "      <th>gr</th>\n",
       "      <th>h</th>\n",
       "      <th>hc</th>\n",
       "      <th>hh</th>\n",
       "      <th>kw</th>\n",
       "      <th>l</th>\n",
       "      <th>ll</th>\n",
       "      <th>nk</th>\n",
       "      <th>r</th>\n",
       "      <th>t</th>\n",
       "      <th>tz</th>\n",
       "      <th>u</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>NaN</td>\n",
       "      <td>Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKi...</td>\n",
       "      <td>en-US,en;q=0.8</td>\n",
       "      <td>US</td>\n",
       "      <td>Danvers</td>\n",
       "      <td>A6qOVH</td>\n",
       "      <td>MA</td>\n",
       "      <td>wfLQtf</td>\n",
       "      <td>1.331823e+09</td>\n",
       "      <td>1.usa.gov</td>\n",
       "      <td>NaN</td>\n",
       "      <td>orofrog</td>\n",
       "      <td>[42.576698, -70.954903]</td>\n",
       "      <td>1.0</td>\n",
       "      <td>http://www.facebook.com/l/7AQEFzjSi/1.usa.gov/...</td>\n",
       "      <td>1.331923e+09</td>\n",
       "      <td>America/New_York</td>\n",
       "      <td>http://www.ncbi.nlm.nih.gov/pubmed/22415991</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>NaN</td>\n",
       "      <td>GoogleMaps/RochesterNY</td>\n",
       "      <td>NaN</td>\n",
       "      <td>US</td>\n",
       "      <td>Provo</td>\n",
       "      <td>mwszkS</td>\n",
       "      <td>UT</td>\n",
       "      <td>mwszkS</td>\n",
       "      <td>1.308262e+09</td>\n",
       "      <td>j.mp</td>\n",
       "      <td>NaN</td>\n",
       "      <td>bitly</td>\n",
       "      <td>[40.218102, -111.613297]</td>\n",
       "      <td>0.0</td>\n",
       "      <td>http://www.AwareMap.com/</td>\n",
       "      <td>1.331923e+09</td>\n",
       "      <td>America/Denver</td>\n",
       "      <td>http://www.monroecounty.gov/etc/911/rss.php</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>NaN</td>\n",
       "      <td>Mozilla/4.0 (compatible; MSIE 8.0; Windows NT ...</td>\n",
       "      <td>en-US</td>\n",
       "      <td>US</td>\n",
       "      <td>Washington</td>\n",
       "      <td>xxr3Qb</td>\n",
       "      <td>DC</td>\n",
       "      <td>xxr3Qb</td>\n",
       "      <td>1.331920e+09</td>\n",
       "      <td>1.usa.gov</td>\n",
       "      <td>NaN</td>\n",
       "      <td>bitly</td>\n",
       "      <td>[38.9007, -77.043098]</td>\n",
       "      <td>1.0</td>\n",
       "      <td>http://t.co/03elZC4Q</td>\n",
       "      <td>1.331923e+09</td>\n",
       "      <td>America/New_York</td>\n",
       "      <td>http://boxer.senate.gov/en/press/releases/0316...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>NaN</td>\n",
       "      <td>Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_8)...</td>\n",
       "      <td>pt-br</td>\n",
       "      <td>BR</td>\n",
       "      <td>Braz</td>\n",
       "      <td>zCaLwp</td>\n",
       "      <td>27</td>\n",
       "      <td>zUtuOu</td>\n",
       "      <td>1.331923e+09</td>\n",
       "      <td>1.usa.gov</td>\n",
       "      <td>NaN</td>\n",
       "      <td>alelex88</td>\n",
       "      <td>[-23.549999, -46.616699]</td>\n",
       "      <td>0.0</td>\n",
       "      <td>direct</td>\n",
       "      <td>1.331923e+09</td>\n",
       "      <td>America/Sao_Paulo</td>\n",
       "      <td>http://apod.nasa.gov/apod/ap120312.html</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>NaN</td>\n",
       "      <td>Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKi...</td>\n",
       "      <td>en-US,en;q=0.8</td>\n",
       "      <td>US</td>\n",
       "      <td>Shrewsbury</td>\n",
       "      <td>9b6kNl</td>\n",
       "      <td>MA</td>\n",
       "      <td>9b6kNl</td>\n",
       "      <td>1.273672e+09</td>\n",
       "      <td>bit.ly</td>\n",
       "      <td>NaN</td>\n",
       "      <td>bitly</td>\n",
       "      <td>[42.286499, -71.714699]</td>\n",
       "      <td>0.0</td>\n",
       "      <td>http://www.shrewsbury-ma.gov/selco/</td>\n",
       "      <td>1.331923e+09</td>\n",
       "      <td>America/New_York</td>\n",
       "      <td>http://www.shrewsbury-ma.gov/egov/gallery/1341...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   _heartbeat_                                                  a  \\\n",
       "0          NaN  Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKi...   \n",
       "1          NaN                             GoogleMaps/RochesterNY   \n",
       "2          NaN  Mozilla/4.0 (compatible; MSIE 8.0; Windows NT ...   \n",
       "3          NaN  Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_8)...   \n",
       "4          NaN  Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKi...   \n",
       "\n",
       "               al   c          cy       g  gr       h            hc  \\\n",
       "0  en-US,en;q=0.8  US     Danvers  A6qOVH  MA  wfLQtf  1.331823e+09   \n",
       "1             NaN  US       Provo  mwszkS  UT  mwszkS  1.308262e+09   \n",
       "2           en-US  US  Washington  xxr3Qb  DC  xxr3Qb  1.331920e+09   \n",
       "3           pt-br  BR        Braz  zCaLwp  27  zUtuOu  1.331923e+09   \n",
       "4  en-US,en;q=0.8  US  Shrewsbury  9b6kNl  MA  9b6kNl  1.273672e+09   \n",
       "\n",
       "          hh   kw         l                        ll   nk  \\\n",
       "0  1.usa.gov  NaN   orofrog   [42.576698, -70.954903]  1.0   \n",
       "1       j.mp  NaN     bitly  [40.218102, -111.613297]  0.0   \n",
       "2  1.usa.gov  NaN     bitly     [38.9007, -77.043098]  1.0   \n",
       "3  1.usa.gov  NaN  alelex88  [-23.549999, -46.616699]  0.0   \n",
       "4     bit.ly  NaN     bitly   [42.286499, -71.714699]  0.0   \n",
       "\n",
       "                                                   r             t  \\\n",
       "0  http://www.facebook.com/l/7AQEFzjSi/1.usa.gov/...  1.331923e+09   \n",
       "1                           http://www.AwareMap.com/  1.331923e+09   \n",
       "2                               http://t.co/03elZC4Q  1.331923e+09   \n",
       "3                                             direct  1.331923e+09   \n",
       "4                http://www.shrewsbury-ma.gov/selco/  1.331923e+09   \n",
       "\n",
       "                  tz                                                  u  \n",
       "0   America/New_York        http://www.ncbi.nlm.nih.gov/pubmed/22415991  \n",
       "1     America/Denver        http://www.monroecounty.gov/etc/911/rss.php  \n",
       "2   America/New_York  http://boxer.senate.gov/en/press/releases/0316...  \n",
       "3  America/Sao_Paulo            http://apod.nasa.gov/apod/ap120312.html  \n",
       "4   America/New_York  http://www.shrewsbury-ma.gov/egov/gallery/1341...  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.DataFrame(records)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 3560 entries, 0 to 3559\n",
      "Data columns (total 18 columns):\n",
      "_heartbeat_    120 non-null float64\n",
      "a              3440 non-null object\n",
      "al             3094 non-null object\n",
      "c              2919 non-null object\n",
      "cy             2919 non-null object\n",
      "g              3440 non-null object\n",
      "gr             2919 non-null object\n",
      "h              3440 non-null object\n",
      "hc             3440 non-null float64\n",
      "hh             3440 non-null object\n",
      "kw             93 non-null object\n",
      "l              3440 non-null object\n",
      "ll             2919 non-null object\n",
      "nk             3440 non-null float64\n",
      "r              3440 non-null object\n",
      "t              3440 non-null float64\n",
      "tz             3440 non-null object\n",
      "u              3440 non-null object\n",
      "dtypes: float64(4), object(14)\n",
      "memory usage: 500.7+ KB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "America/New_York     4\n",
       "                     3\n",
       "Europe/Warsaw        1\n",
       "America/Denver       1\n",
       "America/Sao_Paulo    1\n",
       "Name: tz, dtype: int64"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"tz\"][:10].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "clean_tz = df[\"tz\"].fillna(\"Missing\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "clean_tz[clean_tz == \"\"] = \"Unknown\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0        America/New_York\n",
       "1          America/Denver\n",
       "2        America/New_York\n",
       "3       America/Sao_Paulo\n",
       "4        America/New_York\n",
       "5        America/New_York\n",
       "6           Europe/Warsaw\n",
       "7                 Unknown\n",
       "8                 Unknown\n",
       "9                 Unknown\n",
       "10    America/Los_Angeles\n",
       "11       America/New_York\n",
       "12       America/New_York\n",
       "13                Missing\n",
       "14       America/New_York\n",
       "15         Asia/Hong_Kong\n",
       "16         Asia/Hong_Kong\n",
       "17       America/New_York\n",
       "18         America/Denver\n",
       "19            Europe/Rome\n",
       "Name: tz, dtype: object"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clean_tz.head(n = 20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "America/New_York       8\n",
       "Unknown                3\n",
       "America/Denver         2\n",
       "Asia/Hong_Kong         2\n",
       "Missing                1\n",
       "America/Los_Angeles    1\n",
       "Europe/Rome            1\n",
       "America/Sao_Paulo      1\n",
       "Europe/Warsaw          1\n",
       "Name: tz, dtype: int64"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clean_tz[:20].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7f29c423b780>"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA4EAAAFlCAYAAABV4O1xAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f29c4293940>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.barplot(y = clean_tz[:10].values, x = clean_tz[:10].index)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## MovieLens data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ubuntu/anaconda3/lib/python3.6/site-packages/ipykernel_launcher.py:4: ParserWarning: Falling back to the 'python' engine because the 'c' engine does not support regex separators (separators > 1 char and different from '\\s+' are interpreted as regex); you can avoid this warning by specifying engine='python'.\n",
      "  after removing the cwd from sys.path.\n",
      "/home/ubuntu/anaconda3/lib/python3.6/site-packages/ipykernel_launcher.py:6: ParserWarning: Falling back to the 'python' engine because the 'c' engine does not support regex separators (separators > 1 char and different from '\\s+' are interpreted as regex); you can avoid this warning by specifying engine='python'.\n",
      "  \n",
      "/home/ubuntu/anaconda3/lib/python3.6/site-packages/ipykernel_launcher.py:8: ParserWarning: Falling back to the 'python' engine because the 'c' engine does not support regex separators (separators > 1 char and different from '\\s+' are interpreted as regex); you can avoid this warning by specifying engine='python'.\n",
      "  \n"
     ]
    }
   ],
   "source": [
    "# Make display smaller\n",
    "pd.options.display.max_rows = 15\n",
    "unames = ['user_id', 'gender', 'age', 'occupation', 'zip']\n",
    "users = pd.read_table('datasets/movielens/users.dat', sep='::',header=None, names=unames)\n",
    "rnames = ['user_id', 'movie_id', 'rating', 'timestamp']\n",
    "ratings = pd.read_table('datasets/movielens/ratings.dat', sep='::',header=None, names=rnames)\n",
    "mnames = ['movie_id', 'title', 'genres']\n",
    "movies = pd.read_table('datasets/movielens/movies.dat', sep='::',header=None, names=mnames)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>user_id</th>\n",
       "      <th>gender</th>\n",
       "      <th>age</th>\n",
       "      <th>occupation</th>\n",
       "      <th>zip</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>F</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>48067</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>M</td>\n",
       "      <td>56</td>\n",
       "      <td>16</td>\n",
       "      <td>70072</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>M</td>\n",
       "      <td>25</td>\n",
       "      <td>15</td>\n",
       "      <td>55117</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>M</td>\n",
       "      <td>45</td>\n",
       "      <td>7</td>\n",
       "      <td>02460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>M</td>\n",
       "      <td>25</td>\n",
       "      <td>20</td>\n",
       "      <td>55455</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   user_id gender  age  occupation    zip\n",
       "0        1      F    1          10  48067\n",
       "1        2      M   56          16  70072\n",
       "2        3      M   25          15  55117\n",
       "3        4      M   45           7  02460\n",
       "4        5      M   25          20  55455"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "users.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>user_id</th>\n",
       "      <th>movie_id</th>\n",
       "      <th>rating</th>\n",
       "      <th>timestamp</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1193</td>\n",
       "      <td>5</td>\n",
       "      <td>978300760</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>661</td>\n",
       "      <td>3</td>\n",
       "      <td>978302109</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>914</td>\n",
       "      <td>3</td>\n",
       "      <td>978301968</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>3408</td>\n",
       "      <td>4</td>\n",
       "      <td>978300275</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>2355</td>\n",
       "      <td>5</td>\n",
       "      <td>978824291</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   user_id  movie_id  rating  timestamp\n",
       "0        1      1193       5  978300760\n",
       "1        1       661       3  978302109\n",
       "2        1       914       3  978301968\n",
       "3        1      3408       4  978300275\n",
       "4        1      2355       5  978824291"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ratings.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>movie_id</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>Toy Story (1995)</td>\n",
       "      <td>Animation|Children's|Comedy</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>Jumanji (1995)</td>\n",
       "      <td>Adventure|Children's|Fantasy</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>Grumpier Old Men (1995)</td>\n",
       "      <td>Comedy|Romance</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>Waiting to Exhale (1995)</td>\n",
       "      <td>Comedy|Drama</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>Father of the Bride Part II (1995)</td>\n",
       "      <td>Comedy</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   movie_id                               title                        genres\n",
       "0         1                    Toy Story (1995)   Animation|Children's|Comedy\n",
       "1         2                      Jumanji (1995)  Adventure|Children's|Fantasy\n",
       "2         3             Grumpier Old Men (1995)                Comedy|Romance\n",
       "3         4            Waiting to Exhale (1995)                  Comedy|Drama\n",
       "4         5  Father of the Bride Part II (1995)                        Comedy"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>user_id</th>\n",
       "      <th>movie_id</th>\n",
       "      <th>rating</th>\n",
       "      <th>timestamp</th>\n",
       "      <th>gender</th>\n",
       "      <th>age</th>\n",
       "      <th>occupation</th>\n",
       "      <th>zip</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1193</td>\n",
       "      <td>5</td>\n",
       "      <td>978300760</td>\n",
       "      <td>F</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>48067</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>661</td>\n",
       "      <td>3</td>\n",
       "      <td>978302109</td>\n",
       "      <td>F</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>48067</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>914</td>\n",
       "      <td>3</td>\n",
       "      <td>978301968</td>\n",
       "      <td>F</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>48067</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>3408</td>\n",
       "      <td>4</td>\n",
       "      <td>978300275</td>\n",
       "      <td>F</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>48067</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>2355</td>\n",
       "      <td>5</td>\n",
       "      <td>978824291</td>\n",
       "      <td>F</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>48067</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   user_id  movie_id  rating  timestamp gender  age  occupation    zip\n",
       "0        1      1193       5  978300760      F    1          10  48067\n",
       "1        1       661       3  978302109      F    1          10  48067\n",
       "2        1       914       3  978301968      F    1          10  48067\n",
       "3        1      3408       4  978300275      F    1          10  48067\n",
       "4        1      2355       5  978824291      F    1          10  48067"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "first_merge = pd.merge(ratings, users, on = \"user_id\")\n",
    "first_merge.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>user_id</th>\n",
       "      <th>movie_id</th>\n",
       "      <th>rating</th>\n",
       "      <th>timestamp</th>\n",
       "      <th>gender</th>\n",
       "      <th>age</th>\n",
       "      <th>occupation</th>\n",
       "      <th>zip</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>1193</td>\n",
       "      <td>5</td>\n",
       "      <td>978300760</td>\n",
       "      <td>F</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>48067</td>\n",
       "      <td>One Flew Over the Cuckoo's Nest (1975)</td>\n",
       "      <td>Drama</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1193</td>\n",
       "      <td>5</td>\n",
       "      <td>978298413</td>\n",
       "      <td>M</td>\n",
       "      <td>56</td>\n",
       "      <td>16</td>\n",
       "      <td>70072</td>\n",
       "      <td>One Flew Over the Cuckoo's Nest (1975)</td>\n",
       "      <td>Drama</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>12</td>\n",
       "      <td>1193</td>\n",
       "      <td>4</td>\n",
       "      <td>978220179</td>\n",
       "      <td>M</td>\n",
       "      <td>25</td>\n",
       "      <td>12</td>\n",
       "      <td>32793</td>\n",
       "      <td>One Flew Over the Cuckoo's Nest (1975)</td>\n",
       "      <td>Drama</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>15</td>\n",
       "      <td>1193</td>\n",
       "      <td>4</td>\n",
       "      <td>978199279</td>\n",
       "      <td>M</td>\n",
       "      <td>25</td>\n",
       "      <td>7</td>\n",
       "      <td>22903</td>\n",
       "      <td>One Flew Over the Cuckoo's Nest (1975)</td>\n",
       "      <td>Drama</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>17</td>\n",
       "      <td>1193</td>\n",
       "      <td>5</td>\n",
       "      <td>978158471</td>\n",
       "      <td>M</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "      <td>95350</td>\n",
       "      <td>One Flew Over the Cuckoo's Nest (1975)</td>\n",
       "      <td>Drama</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   user_id  movie_id  rating  timestamp gender  age  occupation    zip  \\\n",
       "0        1      1193       5  978300760      F    1          10  48067   \n",
       "1        2      1193       5  978298413      M   56          16  70072   \n",
       "2       12      1193       4  978220179      M   25          12  32793   \n",
       "3       15      1193       4  978199279      M   25           7  22903   \n",
       "4       17      1193       5  978158471      M   50           1  95350   \n",
       "\n",
       "                                    title genres  \n",
       "0  One Flew Over the Cuckoo's Nest (1975)  Drama  \n",
       "1  One Flew Over the Cuckoo's Nest (1975)  Drama  \n",
       "2  One Flew Over the Cuckoo's Nest (1975)  Drama  \n",
       "3  One Flew Over the Cuckoo's Nest (1975)  Drama  \n",
       "4  One Flew Over the Cuckoo's Nest (1975)  Drama  "
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "second_merge = pd.merge(first_merge, movies, on = \"movie_id\")\n",
    "second_merge.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1000209, 10)"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "second_merge.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = second_merge"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>rating</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>gender</th>\n",
       "      <th>title</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"7\" valign=\"top\">F</th>\n",
       "      <th>$1,000,000 Duck (1971)</th>\n",
       "      <td>3.375000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>'Night Mother (1986)</th>\n",
       "      <td>3.388889</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>'Til There Was You (1997)</th>\n",
       "      <td>2.675676</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>'burbs, The (1989)</th>\n",
       "      <td>2.793478</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...And Justice for All (1979)</th>\n",
       "      <td>3.828571</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1-900 (1994)</th>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10 Things I Hate About You (1999)</th>\n",
       "      <td>3.646552</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"7\" valign=\"top\">M</th>\n",
       "      <th>Your Friends and Neighbors (1998)</th>\n",
       "      <td>3.536585</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zachariah (1971)</th>\n",
       "      <td>3.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zed &amp; Two Noughts, A (1985)</th>\n",
       "      <td>3.380952</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zero Effect (1998)</th>\n",
       "      <td>3.723140</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zero Kelvin (Kj�rlighetens kj�tere) (1995)</th>\n",
       "      <td>3.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zeus and Roxanne (1997)</th>\n",
       "      <td>2.357143</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>eXistenZ (1999)</th>\n",
       "      <td>3.289086</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>7152 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                     rating\n",
       "gender title                                               \n",
       "F      $1,000,000 Duck (1971)                      3.375000\n",
       "       'Night Mother (1986)                        3.388889\n",
       "       'Til There Was You (1997)                   2.675676\n",
       "       'burbs, The (1989)                          2.793478\n",
       "       ...And Justice for All (1979)               3.828571\n",
       "       1-900 (1994)                                2.000000\n",
       "       10 Things I Hate About You (1999)           3.646552\n",
       "...                                                     ...\n",
       "M      Your Friends and Neighbors (1998)           3.536585\n",
       "       Zachariah (1971)                            3.500000\n",
       "       Zed & Two Noughts, A (1985)                 3.380952\n",
       "       Zero Effect (1998)                          3.723140\n",
       "       Zero Kelvin (Kj�rlighetens kj�tere) (1995)  3.500000\n",
       "       Zeus and Roxanne (1997)                     2.357143\n",
       "       eXistenZ (1999)                             3.289086\n",
       "\n",
       "[7152 rows x 1 columns]"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby([\"gender\", \"title\"])[[\"rating\"]].agg(\"mean\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>gender</th>\n",
       "      <th>F</th>\n",
       "      <th>M</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>title</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>$1,000,000 Duck (1971)</th>\n",
       "      <td>3.375000</td>\n",
       "      <td>2.761905</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>'Night Mother (1986)</th>\n",
       "      <td>3.388889</td>\n",
       "      <td>3.352941</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>'Til There Was You (1997)</th>\n",
       "      <td>2.675676</td>\n",
       "      <td>2.733333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>'burbs, The (1989)</th>\n",
       "      <td>2.793478</td>\n",
       "      <td>2.962085</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...And Justice for All (1979)</th>\n",
       "      <td>3.828571</td>\n",
       "      <td>3.689024</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1-900 (1994)</th>\n",
       "      <td>2.000000</td>\n",
       "      <td>3.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10 Things I Hate About You (1999)</th>\n",
       "      <td>3.646552</td>\n",
       "      <td>3.311966</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Your Friends and Neighbors (1998)</th>\n",
       "      <td>2.888889</td>\n",
       "      <td>3.536585</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zachariah (1971)</th>\n",
       "      <td>NaN</td>\n",
       "      <td>3.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zed &amp; Two Noughts, A (1985)</th>\n",
       "      <td>3.500000</td>\n",
       "      <td>3.380952</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zero Effect (1998)</th>\n",
       "      <td>3.864407</td>\n",
       "      <td>3.723140</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zero Kelvin (Kj�rlighetens kj�tere) (1995)</th>\n",
       "      <td>NaN</td>\n",
       "      <td>3.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zeus and Roxanne (1997)</th>\n",
       "      <td>2.777778</td>\n",
       "      <td>2.357143</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>eXistenZ (1999)</th>\n",
       "      <td>3.098592</td>\n",
       "      <td>3.289086</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3706 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "gender                                             F         M\n",
       "title                                                         \n",
       "$1,000,000 Duck (1971)                      3.375000  2.761905\n",
       "'Night Mother (1986)                        3.388889  3.352941\n",
       "'Til There Was You (1997)                   2.675676  2.733333\n",
       "'burbs, The (1989)                          2.793478  2.962085\n",
       "...And Justice for All (1979)               3.828571  3.689024\n",
       "1-900 (1994)                                2.000000  3.000000\n",
       "10 Things I Hate About You (1999)           3.646552  3.311966\n",
       "...                                              ...       ...\n",
       "Your Friends and Neighbors (1998)           2.888889  3.536585\n",
       "Zachariah (1971)                                 NaN  3.500000\n",
       "Zed & Two Noughts, A (1985)                 3.500000  3.380952\n",
       "Zero Effect (1998)                          3.864407  3.723140\n",
       "Zero Kelvin (Kj�rlighetens kj�tere) (1995)       NaN  3.500000\n",
       "Zeus and Roxanne (1997)                     2.777778  2.357143\n",
       "eXistenZ (1999)                             3.098592  3.289086\n",
       "\n",
       "[3706 rows x 2 columns]"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.pivot_table(\"rating\", index = \"title\", columns = \"gender\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>gender</th>\n",
       "      <th>F</th>\n",
       "      <th>M</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>title</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>$1,000,000 Duck (1971)</th>\n",
       "      <td>3.375000</td>\n",
       "      <td>2.761905</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>'Night Mother (1986)</th>\n",
       "      <td>3.388889</td>\n",
       "      <td>3.352941</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>'Til There Was You (1997)</th>\n",
       "      <td>2.675676</td>\n",
       "      <td>2.733333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>'burbs, The (1989)</th>\n",
       "      <td>2.793478</td>\n",
       "      <td>2.962085</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...And Justice for All (1979)</th>\n",
       "      <td>3.828571</td>\n",
       "      <td>3.689024</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1-900 (1994)</th>\n",
       "      <td>2.000000</td>\n",
       "      <td>3.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10 Things I Hate About You (1999)</th>\n",
       "      <td>3.646552</td>\n",
       "      <td>3.311966</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Your Friends and Neighbors (1998)</th>\n",
       "      <td>2.888889</td>\n",
       "      <td>3.536585</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zachariah (1971)</th>\n",
       "      <td>NaN</td>\n",
       "      <td>3.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zed &amp; Two Noughts, A (1985)</th>\n",
       "      <td>3.500000</td>\n",
       "      <td>3.380952</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zero Effect (1998)</th>\n",
       "      <td>3.864407</td>\n",
       "      <td>3.723140</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zero Kelvin (Kj�rlighetens kj�tere) (1995)</th>\n",
       "      <td>NaN</td>\n",
       "      <td>3.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zeus and Roxanne (1997)</th>\n",
       "      <td>2.777778</td>\n",
       "      <td>2.357143</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>eXistenZ (1999)</th>\n",
       "      <td>3.098592</td>\n",
       "      <td>3.289086</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3706 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "gender                                             F         M\n",
       "title                                                         \n",
       "$1,000,000 Duck (1971)                      3.375000  2.761905\n",
       "'Night Mother (1986)                        3.388889  3.352941\n",
       "'Til There Was You (1997)                   2.675676  2.733333\n",
       "'burbs, The (1989)                          2.793478  2.962085\n",
       "...And Justice for All (1979)               3.828571  3.689024\n",
       "1-900 (1994)                                2.000000  3.000000\n",
       "10 Things I Hate About You (1999)           3.646552  3.311966\n",
       "...                                              ...       ...\n",
       "Your Friends and Neighbors (1998)           2.888889  3.536585\n",
       "Zachariah (1971)                                 NaN  3.500000\n",
       "Zed & Two Noughts, A (1985)                 3.500000  3.380952\n",
       "Zero Effect (1998)                          3.864407  3.723140\n",
       "Zero Kelvin (Kj�rlighetens kj�tere) (1995)       NaN  3.500000\n",
       "Zeus and Roxanne (1997)                     2.777778  2.357143\n",
       "eXistenZ (1999)                             3.098592  3.289086\n",
       "\n",
       "[3706 rows x 2 columns]"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "avg = df.pivot_table(\"rating\", index = \"title\", columns = \"gender\", aggfunc = \"mean\")\n",
    "avg"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>title</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>title</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>$1,000,000 Duck (1971)</th>\n",
       "      <td>37</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>'Night Mother (1986)</th>\n",
       "      <td>70</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>'Til There Was You (1997)</th>\n",
       "      <td>52</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>'burbs, The (1989)</th>\n",
       "      <td>303</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...And Justice for All (1979)</th>\n",
       "      <td>199</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1-900 (1994)</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10 Things I Hate About You (1999)</th>\n",
       "      <td>700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Your Friends and Neighbors (1998)</th>\n",
       "      <td>109</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zachariah (1971)</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zed &amp; Two Noughts, A (1985)</th>\n",
       "      <td>29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zero Effect (1998)</th>\n",
       "      <td>301</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zero Kelvin (Kj�rlighetens kj�tere) (1995)</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zeus and Roxanne (1997)</th>\n",
       "      <td>23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>eXistenZ (1999)</th>\n",
       "      <td>410</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3706 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                            title\n",
       "title                                            \n",
       "$1,000,000 Duck (1971)                         37\n",
       "'Night Mother (1986)                           70\n",
       "'Til There Was You (1997)                      52\n",
       "'burbs, The (1989)                            303\n",
       "...And Justice for All (1979)                 199\n",
       "1-900 (1994)                                    2\n",
       "10 Things I Hate About You (1999)             700\n",
       "...                                           ...\n",
       "Your Friends and Neighbors (1998)             109\n",
       "Zachariah (1971)                                2\n",
       "Zed & Two Noughts, A (1985)                    29\n",
       "Zero Effect (1998)                            301\n",
       "Zero Kelvin (Kj�rlighetens kj�tere) (1995)      2\n",
       "Zeus and Roxanne (1997)                        23\n",
       "eXistenZ (1999)                               410\n",
       "\n",
       "[3706 rows x 1 columns]"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ratings_by_title = df.groupby(\"title\")[[\"title\"]].count()\n",
    "ratings_by_title"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['American Beauty (1999)', 'Back to the Future (1985)', 'Fargo (1996)',\n",
       "       'Jurassic Park (1993)', 'Matrix, The (1999)', 'Men in Black (1997)',\n",
       "       'Raiders of the Lost Ark (1981)', 'Saving Private Ryan (1998)',\n",
       "       'Silence of the Lambs, The (1991)',\n",
       "       'Star Wars: Episode IV - A New Hope (1977)',\n",
       "       'Star Wars: Episode V - The Empire Strikes Back (1980)',\n",
       "       'Star Wars: Episode VI - Return of the Jedi (1983)',\n",
       "       'Terminator 2: Judgment Day (1991)'],\n",
       "      dtype='object', name='title')"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ratings_2500 = ratings_by_title.index[ratings_by_title.title >= 2500]\n",
    "ratings_2500"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>gender</th>\n",
       "      <th>F</th>\n",
       "      <th>M</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>title</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>American Beauty (1999)</th>\n",
       "      <td>4.238901</td>\n",
       "      <td>4.347301</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Back to the Future (1985)</th>\n",
       "      <td>3.932707</td>\n",
       "      <td>4.009259</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Fargo (1996)</th>\n",
       "      <td>4.217656</td>\n",
       "      <td>4.267780</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Jurassic Park (1993)</th>\n",
       "      <td>3.579407</td>\n",
       "      <td>3.814197</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Matrix, The (1999)</th>\n",
       "      <td>4.128405</td>\n",
       "      <td>4.362235</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Men in Black (1997)</th>\n",
       "      <td>3.817844</td>\n",
       "      <td>3.719000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Raiders of the Lost Ark (1981)</th>\n",
       "      <td>4.332168</td>\n",
       "      <td>4.520597</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Saving Private Ryan (1998)</th>\n",
       "      <td>4.114783</td>\n",
       "      <td>4.398941</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Silence of the Lambs, The (1991)</th>\n",
       "      <td>4.271955</td>\n",
       "      <td>4.381944</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Star Wars: Episode IV - A New Hope (1977)</th>\n",
       "      <td>4.302937</td>\n",
       "      <td>4.495307</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Star Wars: Episode V - The Empire Strikes Back (1980)</th>\n",
       "      <td>4.106481</td>\n",
       "      <td>4.344577</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Star Wars: Episode VI - Return of the Jedi (1983)</th>\n",
       "      <td>3.865237</td>\n",
       "      <td>4.069058</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Terminator 2: Judgment Day (1991)</th>\n",
       "      <td>3.785088</td>\n",
       "      <td>4.115367</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "gender                                                     F         M\n",
       "title                                                                 \n",
       "American Beauty (1999)                              4.238901  4.347301\n",
       "Back to the Future (1985)                           3.932707  4.009259\n",
       "Fargo (1996)                                        4.217656  4.267780\n",
       "Jurassic Park (1993)                                3.579407  3.814197\n",
       "Matrix, The (1999)                                  4.128405  4.362235\n",
       "Men in Black (1997)                                 3.817844  3.719000\n",
       "Raiders of the Lost Ark (1981)                      4.332168  4.520597\n",
       "Saving Private Ryan (1998)                          4.114783  4.398941\n",
       "Silence of the Lambs, The (1991)                    4.271955  4.381944\n",
       "Star Wars: Episode IV - A New Hope (1977)           4.302937  4.495307\n",
       "Star Wars: Episode V - The Empire Strikes Back ...  4.106481  4.344577\n",
       "Star Wars: Episode VI - Return of the Jedi (1983)   3.865237  4.069058\n",
       "Terminator 2: Judgment Day (1991)                   3.785088  4.115367"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "avg.loc[ratings_2500]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>gender</th>\n",
       "      <th>F</th>\n",
       "      <th>M</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>title</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Clean Slate (Coup de Torchon) (1981)</th>\n",
       "      <td>5.0</td>\n",
       "      <td>3.857143</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ballad of Narayama, The (Narayama Bushiko) (1958)</th>\n",
       "      <td>5.0</td>\n",
       "      <td>3.428571</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Raw Deal (1948)</th>\n",
       "      <td>5.0</td>\n",
       "      <td>3.307692</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Bittersweet Motel (2000)</th>\n",
       "      <td>5.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Skipped Parts (2000)</th>\n",
       "      <td>5.0</td>\n",
       "      <td>4.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Lamerica (1994)</th>\n",
       "      <td>5.0</td>\n",
       "      <td>4.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Gambler, The (A J�t�kos) (1997)</th>\n",
       "      <td>5.0</td>\n",
       "      <td>3.166667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Wings of Courage (1995)</th>\n",
       "      <td>NaN</td>\n",
       "      <td>3.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>With Byrd at the South Pole (1930)</th>\n",
       "      <td>NaN</td>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>With Friends Like These... (1998)</th>\n",
       "      <td>NaN</td>\n",
       "      <td>4.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Wooden Man's Bride, The (Wu Kui) (1994)</th>\n",
       "      <td>NaN</td>\n",
       "      <td>3.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Year of the Horse (1997)</th>\n",
       "      <td>NaN</td>\n",
       "      <td>3.250000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zachariah (1971)</th>\n",
       "      <td>NaN</td>\n",
       "      <td>3.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zero Kelvin (Kj�rlighetens kj�tere) (1995)</th>\n",
       "      <td>NaN</td>\n",
       "      <td>3.500000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3706 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "gender                                               F         M\n",
       "title                                                           \n",
       "Clean Slate (Coup de Torchon) (1981)               5.0  3.857143\n",
       "Ballad of Narayama, The (Narayama Bushiko) (1958)  5.0  3.428571\n",
       "Raw Deal (1948)                                    5.0  3.307692\n",
       "Bittersweet Motel (2000)                           5.0       NaN\n",
       "Skipped Parts (2000)                               5.0  4.000000\n",
       "Lamerica (1994)                                    5.0  4.666667\n",
       "Gambler, The (A J�t�kos) (1997)                    5.0  3.166667\n",
       "...                                                ...       ...\n",
       "Wings of Courage (1995)                            NaN  3.000000\n",
       "With Byrd at the South Pole (1930)                 NaN  2.000000\n",
       "With Friends Like These... (1998)                  NaN  4.000000\n",
       "Wooden Man's Bride, The (Wu Kui) (1994)            NaN  3.000000\n",
       "Year of the Horse (1997)                           NaN  3.250000\n",
       "Zachariah (1971)                                   NaN  3.500000\n",
       "Zero Kelvin (Kj�rlighetens kj�tere) (1995)         NaN  3.500000\n",
       "\n",
       "[3706 rows x 2 columns]"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sorted_titles = avg.sort_values(ascending = False, by = \"F\")\n",
    "sorted_titles"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "avg[\"mean_diff\"] = np.abs(avg.F - avg.M)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>gender</th>\n",
       "      <th>F</th>\n",
       "      <th>M</th>\n",
       "      <th>mean_diff</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>title</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>$1,000,000 Duck (1971)</th>\n",
       "      <td>3.375000</td>\n",
       "      <td>2.761905</td>\n",
       "      <td>0.613095</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>'Night Mother (1986)</th>\n",
       "      <td>3.388889</td>\n",
       "      <td>3.352941</td>\n",
       "      <td>0.035948</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>'Til There Was You (1997)</th>\n",
       "      <td>2.675676</td>\n",
       "      <td>2.733333</td>\n",
       "      <td>0.057658</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>'burbs, The (1989)</th>\n",
       "      <td>2.793478</td>\n",
       "      <td>2.962085</td>\n",
       "      <td>0.168607</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...And Justice for All (1979)</th>\n",
       "      <td>3.828571</td>\n",
       "      <td>3.689024</td>\n",
       "      <td>0.139547</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1-900 (1994)</th>\n",
       "      <td>2.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10 Things I Hate About You (1999)</th>\n",
       "      <td>3.646552</td>\n",
       "      <td>3.311966</td>\n",
       "      <td>0.334586</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Your Friends and Neighbors (1998)</th>\n",
       "      <td>2.888889</td>\n",
       "      <td>3.536585</td>\n",
       "      <td>0.647696</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zachariah (1971)</th>\n",
       "      <td>NaN</td>\n",
       "      <td>3.500000</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zed &amp; Two Noughts, A (1985)</th>\n",
       "      <td>3.500000</td>\n",
       "      <td>3.380952</td>\n",
       "      <td>0.119048</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zero Effect (1998)</th>\n",
       "      <td>3.864407</td>\n",
       "      <td>3.723140</td>\n",
       "      <td>0.141266</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zero Kelvin (Kj�rlighetens kj�tere) (1995)</th>\n",
       "      <td>NaN</td>\n",
       "      <td>3.500000</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zeus and Roxanne (1997)</th>\n",
       "      <td>2.777778</td>\n",
       "      <td>2.357143</td>\n",
       "      <td>0.420635</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>eXistenZ (1999)</th>\n",
       "      <td>3.098592</td>\n",
       "      <td>3.289086</td>\n",
       "      <td>0.190494</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3706 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "gender                                             F         M  mean_diff\n",
       "title                                                                    \n",
       "$1,000,000 Duck (1971)                      3.375000  2.761905   0.613095\n",
       "'Night Mother (1986)                        3.388889  3.352941   0.035948\n",
       "'Til There Was You (1997)                   2.675676  2.733333   0.057658\n",
       "'burbs, The (1989)                          2.793478  2.962085   0.168607\n",
       "...And Justice for All (1979)               3.828571  3.689024   0.139547\n",
       "1-900 (1994)                                2.000000  3.000000   1.000000\n",
       "10 Things I Hate About You (1999)           3.646552  3.311966   0.334586\n",
       "...                                              ...       ...        ...\n",
       "Your Friends and Neighbors (1998)           2.888889  3.536585   0.647696\n",
       "Zachariah (1971)                                 NaN  3.500000        NaN\n",
       "Zed & Two Noughts, A (1985)                 3.500000  3.380952   0.119048\n",
       "Zero Effect (1998)                          3.864407  3.723140   0.141266\n",
       "Zero Kelvin (Kj�rlighetens kj�tere) (1995)       NaN  3.500000        NaN\n",
       "Zeus and Roxanne (1997)                     2.777778  2.357143   0.420635\n",
       "eXistenZ (1999)                             3.098592  3.289086   0.190494\n",
       "\n",
       "[3706 rows x 3 columns]"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "avg"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>gender</th>\n",
       "      <th>F</th>\n",
       "      <th>M</th>\n",
       "      <th>mean_diff</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>title</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Tigrero: A Film That Was Never Made (1994)</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>4.333333</td>\n",
       "      <td>3.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Spiders, The (Die Spinnen, 1. Teil: Der Goldene See) (1919)</th>\n",
       "      <td>4.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Neon Bible, The (1995)</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>3.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>James Dean Story, The (1957)</th>\n",
       "      <td>4.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Country Life (1994)</th>\n",
       "      <td>5.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>3.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Enfer, L' (1994)</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.750000</td>\n",
       "      <td>2.750000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Babyfever (1994)</th>\n",
       "      <td>3.666667</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Santa with Muscles (1996)</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Wirey Spindell (1999)</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Nelly &amp; Monsieur Arnaud (1995)</th>\n",
       "      <td>3.600000</td>\n",
       "      <td>3.600000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Walk in the Sun, A (1945)</th>\n",
       "      <td>4.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Inferno (1980)</th>\n",
       "      <td>3.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Shopping (1994)</th>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Loaded (1994)</th>\n",
       "      <td>2.666667</td>\n",
       "      <td>2.666667</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3446 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "gender                                                     F         M  \\\n",
       "title                                                                    \n",
       "Tigrero: A Film That Was Never Made (1994)          1.000000  4.333333   \n",
       "Spiders, The (Die Spinnen, 1. Teil: Der Goldene...  4.000000  1.000000   \n",
       "Neon Bible, The (1995)                              1.000000  4.000000   \n",
       "James Dean Story, The (1957)                        4.000000  1.000000   \n",
       "Country Life (1994)                                 5.000000  2.000000   \n",
       "Enfer, L' (1994)                                    1.000000  3.750000   \n",
       "Babyfever (1994)                                    3.666667  1.000000   \n",
       "...                                                      ...       ...   \n",
       "Santa with Muscles (1996)                           1.000000  1.000000   \n",
       "Wirey Spindell (1999)                               1.000000  1.000000   \n",
       "Nelly & Monsieur Arnaud (1995)                      3.600000  3.600000   \n",
       "Walk in the Sun, A (1945)                           4.000000  4.000000   \n",
       "Inferno (1980)                                      3.000000  3.000000   \n",
       "Shopping (1994)                                     2.000000  2.000000   \n",
       "Loaded (1994)                                       2.666667  2.666667   \n",
       "\n",
       "gender                                              mean_diff  \n",
       "title                                                          \n",
       "Tigrero: A Film That Was Never Made (1994)           3.333333  \n",
       "Spiders, The (Die Spinnen, 1. Teil: Der Goldene...   3.000000  \n",
       "Neon Bible, The (1995)                               3.000000  \n",
       "James Dean Story, The (1957)                         3.000000  \n",
       "Country Life (1994)                                  3.000000  \n",
       "Enfer, L' (1994)                                     2.750000  \n",
       "Babyfever (1994)                                     2.666667  \n",
       "...                                                       ...  \n",
       "Santa with Muscles (1996)                            0.000000  \n",
       "Wirey Spindell (1999)                                0.000000  \n",
       "Nelly & Monsieur Arnaud (1995)                       0.000000  \n",
       "Walk in the Sun, A (1945)                            0.000000  \n",
       "Inferno (1980)                                       0.000000  \n",
       "Shopping (1994)                                      0.000000  \n",
       "Loaded (1994)                                        0.000000  \n",
       "\n",
       "[3446 rows x 3 columns]"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "avg.sort_values(by = \"mean_diff\", ascending = False).dropna()"
   ]
  },
  {
   "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": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}