работа_с_данными.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Данные"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "from datetime import datetime\n",
    "\n",
    "def print_time_range(times):\n",
    "    print 'Time from: {0}, to: {1}'.format(datetime.fromtimestamp(times.min()), datetime.fromtimestamp(times.max()))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Лайки"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(111251, 4)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>user_id</th>\n",
       "      <th>item_id</th>\n",
       "      <th>channel</th>\n",
       "      <th>time</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>612d8e8eef05acff3278c061ec10f704</td>\n",
       "      <td>7aa5d00445cb9d61d1739dd0df9a0a88</td>\n",
       "      <td>1f0e3dad99908345f7439f8ffabdffc4</td>\n",
       "      <td>1389733974</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>71a7f1d1be96603971ba66e4a17e845c</td>\n",
       "      <td>5edaf734b432e5cc954a10b59cb97e70</td>\n",
       "      <td>ec5decca5ed3d6b8079e2e7e7bacc9f2</td>\n",
       "      <td>1390459377</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>6eaa117728d50265e6b2ac24a80e04ae</td>\n",
       "      <td>8ad97d075fce19c2d182eb2a4539aa1c</td>\n",
       "      <td>98f13708210194c475687be6106a3b84</td>\n",
       "      <td>1391063963</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                            user_id                           item_id  \\\n",
       "0  612d8e8eef05acff3278c061ec10f704  7aa5d00445cb9d61d1739dd0df9a0a88   \n",
       "1  71a7f1d1be96603971ba66e4a17e845c  5edaf734b432e5cc954a10b59cb97e70   \n",
       "2  6eaa117728d50265e6b2ac24a80e04ae  8ad97d075fce19c2d182eb2a4539aa1c   \n",
       "\n",
       "                            channel        time  \n",
       "0  1f0e3dad99908345f7439f8ffabdffc4  1389733974  \n",
       "1  ec5decca5ed3d6b8079e2e7e7bacc9f2  1390459377  \n",
       "2  98f13708210194c475687be6106a3b84  1391063963  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_likes_df = pd.read_csv('train_likes.csv')\n",
    "print train_likes_df.shape\n",
    "train_likes_df.head(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Time from: 2014-01-10 17:15:37, to: 2016-02-24 15:15:37\n"
     ]
    }
   ],
   "source": [
    "print_time_range(train_likes_df.time)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Контент"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[u'duration', u'f_110698', u'f_110704', u'f_110705', u'f_119091', u'f_122282', u'f_122494', u'f_130892', u'f_144583', u'f_148957', u'f_148972', u'f_151440', u'f_153601', u'f_158463', u'f_163719', u'f_168477', u'f_187511', u'f_191091', u'f_205162', u'f_207186', u'f_210900', u'f_30859', u'f_39933', u'f_44251', u'f_46518', u'f_49968', u'f_74564', u'genre', u'id', u'year']\n"
     ]
    }
   ],
   "source": [
    "import json\n",
    "\n",
    "with open('items.json') as f:\n",
    "    items_dicts = json.load(f)\n",
    "    \n",
    "print sorted(items_dicts[0].keys())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "У каждой единицы контента есть четыре обязательные характеристики:\n",
    "- id --- идентификатор\n",
    "- duration --- коэффициент продолжительности\n",
    "- year --- коэффициент года производства\n",
    "- genre --- жанр (категориальная переменная)\n",
    "\n",
    "и множество опциональныйх переменных вида \"f_N\"."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Замечание\n",
    "Описание есть не для всего контента (покрыто порядка 2/3 лайков)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Расписание"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "time_end,time_start,item_id,channel\r\n",
      "1457356808.0,1457354408.0,84868d868783ee3a41b963a2fb2629ec,02522a2b2726fb0a03bb19f2d8d9524d\r\n",
      "1457360408.0,1457356808.0,84868d868783ee3a41b963a2fb2629ec,02522a2b2726fb0a03bb19f2d8d9524d\r\n",
      "1457371208.0,1457369408.0,574629dcccbf0f871e9eec4ef14ff270,02522a2b2726fb0a03bb19f2d8d9524d\r\n",
      "1458467708.0,1458467108.0,1613b303565352254d5551886ec677c2,04025959b191f8f9de3f924f0940515f\r\n",
      "1458464708.0,1458462008.0,6d38003a9c000dd30e05edad1559b711,43baa6762fa81bb43b39c62553b2970d\r\n",
      "1457302808.0,1457301008.0,574629dcccbf0f871e9eec4ef14ff270,7f1de29e6da19d22b51c68001e7e0e54\r\n",
      "1457311808.0,1457310008.0,f5905aaeeece9fe55335b16009dfca7b,7f1de29e6da19d22b51c68001e7e0e54\r\n",
      "1457313608.0,1457311808.0,574629dcccbf0f871e9eec4ef14ff270,7f1de29e6da19d22b51c68001e7e0e54\r\n",
      "1457325908.0,1457324408.0,574629dcccbf0f871e9eec4ef14ff270,7f1de29e6da19d22b51c68001e7e0e54\r\n"
     ]
    }
   ],
   "source": [
    "#число строк в расписании\n",
    "!head schedule.csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1000, 4)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>time_end</th>\n",
       "      <th>time_start</th>\n",
       "      <th>item_id</th>\n",
       "      <th>channel</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1457356808</td>\n",
       "      <td>1457354408</td>\n",
       "      <td>84868d868783ee3a41b963a2fb2629ec</td>\n",
       "      <td>02522a2b2726fb0a03bb19f2d8d9524d</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1457360408</td>\n",
       "      <td>1457356808</td>\n",
       "      <td>84868d868783ee3a41b963a2fb2629ec</td>\n",
       "      <td>02522a2b2726fb0a03bb19f2d8d9524d</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1457371208</td>\n",
       "      <td>1457369408</td>\n",
       "      <td>574629dcccbf0f871e9eec4ef14ff270</td>\n",
       "      <td>02522a2b2726fb0a03bb19f2d8d9524d</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     time_end  time_start                           item_id  \\\n",
       "0  1457356808  1457354408  84868d868783ee3a41b963a2fb2629ec   \n",
       "1  1457360408  1457356808  84868d868783ee3a41b963a2fb2629ec   \n",
       "2  1457371208  1457369408  574629dcccbf0f871e9eec4ef14ff270   \n",
       "\n",
       "                            channel  \n",
       "0  02522a2b2726fb0a03bb19f2d8d9524d  \n",
       "1  02522a2b2726fb0a03bb19f2d8d9524d  \n",
       "2  02522a2b2726fb0a03bb19f2d8d9524d  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "schedule_df = pd.read_csv('schedule.csv', \n",
    "                          nrows=1000,# Первые 1000 строк\n",
    "                         )\n",
    "print schedule_df.shape\n",
    "schedule_df.head(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}