{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Methods and Attributes\n",
    "__Remember__\n",
    "* Methods ends with **parentheses**, while **attributes** don't\n",
    "* df.shape: Attribute\n",
    "* df.info(): Method"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# import pandas \n",
    "import pandas as pd "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# read a dataset of top-rated IMDb movies into a DataFrame\n",
    "movies = pd.read_csv('http://bit.ly/imdbratings')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>star_rating</th>\n",
       "      <th>title</th>\n",
       "      <th>content_rating</th>\n",
       "      <th>genre</th>\n",
       "      <th>duration</th>\n",
       "      <th>actors_list</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>9.3</td>\n",
       "      <td>The Shawshank Redemption</td>\n",
       "      <td>R</td>\n",
       "      <td>Crime</td>\n",
       "      <td>142</td>\n",
       "      <td>[u'Tim Robbins', u'Morgan Freeman', u'Bob Gunt...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>9.2</td>\n",
       "      <td>The Godfather</td>\n",
       "      <td>R</td>\n",
       "      <td>Crime</td>\n",
       "      <td>175</td>\n",
       "      <td>[u'Marlon Brando', u'Al Pacino', u'James Caan']</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>9.1</td>\n",
       "      <td>The Godfather: Part II</td>\n",
       "      <td>R</td>\n",
       "      <td>Crime</td>\n",
       "      <td>200</td>\n",
       "      <td>[u'Al Pacino', u'Robert De Niro', u'Robert Duv...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>9.0</td>\n",
       "      <td>The Dark Knight</td>\n",
       "      <td>PG-13</td>\n",
       "      <td>Action</td>\n",
       "      <td>152</td>\n",
       "      <td>[u'Christian Bale', u'Heath Ledger', u'Aaron E...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>8.9</td>\n",
       "      <td>Pulp Fiction</td>\n",
       "      <td>R</td>\n",
       "      <td>Crime</td>\n",
       "      <td>154</td>\n",
       "      <td>[u'John Travolta', u'Uma Thurman', u'Samuel L....</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   star_rating                     title content_rating   genre  duration  \\\n",
       "0          9.3  The Shawshank Redemption              R   Crime       142   \n",
       "1          9.2             The Godfather              R   Crime       175   \n",
       "2          9.1    The Godfather: Part II              R   Crime       200   \n",
       "3          9.0           The Dark Knight          PG-13  Action       152   \n",
       "4          8.9              Pulp Fiction              R   Crime       154   \n",
       "\n",
       "                                         actors_list  \n",
       "0  [u'Tim Robbins', u'Morgan Freeman', u'Bob Gunt...  \n",
       "1    [u'Marlon Brando', u'Al Pacino', u'James Caan']  \n",
       "2  [u'Al Pacino', u'Robert De Niro', u'Robert Duv...  \n",
       "3  [u'Christian Bale', u'Heath Ledger', u'Aaron E...  \n",
       "4  [u'John Travolta', u'Uma Thurman', u'Samuel L....  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# example method: show the first 5 rows \n",
    "movies.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>star_rating</th>\n",
       "      <th>duration</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>count</td>\n",
       "      <td>979.000000</td>\n",
       "      <td>979.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>mean</td>\n",
       "      <td>7.889785</td>\n",
       "      <td>120.979571</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>std</td>\n",
       "      <td>0.336069</td>\n",
       "      <td>26.218010</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>min</td>\n",
       "      <td>7.400000</td>\n",
       "      <td>64.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>25%</td>\n",
       "      <td>7.600000</td>\n",
       "      <td>102.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>50%</td>\n",
       "      <td>7.800000</td>\n",
       "      <td>117.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>75%</td>\n",
       "      <td>8.100000</td>\n",
       "      <td>134.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>max</td>\n",
       "      <td>9.300000</td>\n",
       "      <td>242.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       star_rating    duration\n",
       "count   979.000000  979.000000\n",
       "mean      7.889785  120.979571\n",
       "std       0.336069   26.218010\n",
       "min       7.400000   64.000000\n",
       "25%       7.600000  102.000000\n",
       "50%       7.800000  117.000000\n",
       "75%       8.100000  134.000000\n",
       "max       9.300000  242.000000"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# example method: calculate summary statistics\n",
    "movies.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(979, 6)"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# example attribute: number of rows and columns \n",
    "movies.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "star_rating       float64\n",
       "title              object\n",
       "content_rating     object\n",
       "genre              object\n",
       "duration            int64\n",
       "actors_list        object\n",
       "dtype: object"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# example attribute: data type of each column\n",
    "movies.dtypes"
   ]
  },
  {
   "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>title</th>\n",
       "      <th>content_rating</th>\n",
       "      <th>genre</th>\n",
       "      <th>actors_list</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>count</td>\n",
       "      <td>979</td>\n",
       "      <td>976</td>\n",
       "      <td>979</td>\n",
       "      <td>979</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>unique</td>\n",
       "      <td>975</td>\n",
       "      <td>12</td>\n",
       "      <td>16</td>\n",
       "      <td>969</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>top</td>\n",
       "      <td>True Grit</td>\n",
       "      <td>R</td>\n",
       "      <td>Drama</td>\n",
       "      <td>[u'Daniel Radcliffe', u'Emma Watson', u'Rupert...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>freq</td>\n",
       "      <td>2</td>\n",
       "      <td>460</td>\n",
       "      <td>278</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            title content_rating  genre  \\\n",
       "count         979            976    979   \n",
       "unique        975             12     16   \n",
       "top     True Grit              R  Drama   \n",
       "freq            2            460    278   \n",
       "\n",
       "                                              actors_list  \n",
       "count                                                 979  \n",
       "unique                                                969  \n",
       "top     [u'Daniel Radcliffe', u'Emma Watson', u'Rupert...  \n",
       "freq                                                    6  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# use an optional parameter to the describe method to summarize only 'object' column\n",
    "movies.describe(include='object')"
   ]
  }
 ],
 "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": "3.7.4"
  },
  "latex_envs": {
   "LaTeX_envs_menu_present": true,
   "autoclose": false,
   "autocomplete": true,
   "bibliofile": "biblio.bib",
   "cite_by": "apalike",
   "current_citInitial": 1,
   "eqLabelWithNumbers": true,
   "eqNumInitial": 1,
   "hotkeys": {
    "equation": "Ctrl-E",
    "itemize": "Ctrl-I"
   },
   "labels_anchors": false,
   "latex_user_defs": false,
   "report_style_numbering": false,
   "user_envs_cfg": false
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": true,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}