Questions about statistics

gistfile1.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "from collections import Counter\n",
    "from sklearn.feature_extraction.text import CountVectorizer\n",
    "from sklearn.feature_extraction.text import TfidfTransformer\n",
    "from datetime import datetime\n",
    "from wordcloud import WordCloud"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "invalid literal for int() with base 10: 'Boost Post'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32mpandas/parser.pyx\u001b[0m in \u001b[0;36mpandas.parser.TextReader._convert_tokens (pandas/parser.c:14411)\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;31mTypeError\u001b[0m: Cannot cast array from dtype('O') to dtype('int64') according to the rule 'safe'",
      "\nDuring handling of the above exception, another exception occurred:\n",
      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-4-899490a0f71d>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mdf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread_csv\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'freeCodeCamp-facebook-page-activity.csv'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mdtype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m{\u001b[0m\u001b[0;34m'title'\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'reach'\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mint\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'clicks'\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mint\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'reactions'\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mint\u001b[0m\u001b[0;34m}\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparse_dates\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'date'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/pandas/io/parsers.py\u001b[0m in \u001b[0;36mparser_f\u001b[0;34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, squeeze, prefix, mangle_dupe_cols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, dayfirst, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, escapechar, comment, encoding, dialect, tupleize_cols, error_bad_lines, warn_bad_lines, skipfooter, skip_footer, doublequote, delim_whitespace, as_recarray, compact_ints, use_unsigned, low_memory, buffer_lines, memory_map, float_precision)\u001b[0m\n\u001b[1;32m    644\u001b[0m                     skip_blank_lines=skip_blank_lines)\n\u001b[1;32m    645\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 646\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0m_read\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    647\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    648\u001b[0m     \u001b[0mparser_f\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__name__\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/pandas/io/parsers.py\u001b[0m in \u001b[0;36m_read\u001b[0;34m(filepath_or_buffer, kwds)\u001b[0m\n\u001b[1;32m    399\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mparser\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    400\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 401\u001b[0;31m     \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mparser\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    402\u001b[0m     \u001b[0mparser\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mclose\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    403\u001b[0m     \u001b[0;32mreturn\u001b[0m \u001b[0mdata\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/pandas/io/parsers.py\u001b[0m in \u001b[0;36mread\u001b[0;34m(self, nrows)\u001b[0m\n\u001b[1;32m    937\u001b[0m                 \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'skipfooter not supported for iteration'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    938\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 939\u001b[0;31m         \u001b[0mret\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnrows\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    940\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    941\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moptions\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'as_recarray'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/pandas/io/parsers.py\u001b[0m in \u001b[0;36mread\u001b[0;34m(self, nrows)\u001b[0m\n\u001b[1;32m   1506\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnrows\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1507\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1508\u001b[0;31m             \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_reader\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnrows\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1509\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mStopIteration\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1510\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_first_chunk\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mpandas/parser.pyx\u001b[0m in \u001b[0;36mpandas.parser.TextReader.read (pandas/parser.c:10415)\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;32mpandas/parser.pyx\u001b[0m in \u001b[0;36mpandas.parser.TextReader._read_low_memory (pandas/parser.c:10691)\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;32mpandas/parser.pyx\u001b[0m in \u001b[0;36mpandas.parser.TextReader._read_rows (pandas/parser.c:11728)\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;32mpandas/parser.pyx\u001b[0m in \u001b[0;36mpandas.parser.TextReader._convert_column_data (pandas/parser.c:13162)\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;32mpandas/parser.pyx\u001b[0m in \u001b[0;36mpandas.parser.TextReader._convert_tokens (pandas/parser.c:14487)\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;31mValueError\u001b[0m: invalid literal for int() with base 10: 'Boost Post'"
     ]
    }
   ],
   "source": [
    "df = pd.read_csv('freeCodeCamp-facebook-page-activity.csv',dtype={'title': str, 'reach': int, 'clicks': int, 'reactions': int}, parse_dates=['date'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "Quincy Larson @QuincyLarson Ago 18 20:03\n",
    "freeCodeCamp-facebook-page-activity.csv\n",
    "\n",
    "Hey data science enthusiasts, I have a new dataset for you to take a look at. Here is the past 10 months of data from the freeCodeCamp Facebook page. I am making it open data with the hope that you all can glean some insights as to how we can recommend content that campers find more interesting and helpful.\n",
    "Facebook makes these data intentionally difficult to obtain, and I had to manually copy/paste then clean all these data myself.\n",
    "One quick note: The only thing Facebook classifies as a non-link (a photo or video) is content that is directly uploaded to Facebook. YouTube videos, for example, are not qualified as links.\n",
    "I am happy to answer any questions you all may have about these data.\n",
    "Who wants to dig in and see what insights you can find?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv('freeCodeCamp-facebook-page-activity.csv',dtype={'title': str, 'reach': int, 'clicks': int})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>date</th>\n",
       "      <th>time</th>\n",
       "      <th>title</th>\n",
       "      <th>type</th>\n",
       "      <th>reach</th>\n",
       "      <th>clicks</th>\n",
       "      <th>reactions</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>08/18/2017</td>\n",
       "      <td>3:45 pm</td>\n",
       "      <td>The origins of t-distributions and how they ca...</td>\n",
       "      <td>Link</td>\n",
       "      <td>1768</td>\n",
       "      <td>44</td>\n",
       "      <td>21</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>08/18/2017</td>\n",
       "      <td>11:27 am</td>\n",
       "      <td>How one camper got his developer dream job</td>\n",
       "      <td>Link</td>\n",
       "      <td>6941</td>\n",
       "      <td>536</td>\n",
       "      <td>99</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>08/17/2017</td>\n",
       "      <td>7:18 pm</td>\n",
       "      <td>Trying to code when chat's open</td>\n",
       "      <td>Video</td>\n",
       "      <td>17399</td>\n",
       "      <td>2236</td>\n",
       "      <td>750</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>08/17/2017</td>\n",
       "      <td>4:55 pm</td>\n",
       "      <td>An interaction designer explains how a \"homele...</td>\n",
       "      <td>Link</td>\n",
       "      <td>3751</td>\n",
       "      <td>167</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>08/17/2017</td>\n",
       "      <td>7:56 am</td>\n",
       "      <td>How to build a neural network in 30 lines of J...</td>\n",
       "      <td>Link</td>\n",
       "      <td>18248</td>\n",
       "      <td>1946</td>\n",
       "      <td>474</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         date      time                                              title  \\\n",
       "0  08/18/2017   3:45 pm  The origins of t-distributions and how they ca...   \n",
       "1  08/18/2017  11:27 am         How one camper got his developer dream job   \n",
       "2  08/17/2017   7:18 pm                    Trying to code when chat's open   \n",
       "3  08/17/2017   4:55 pm  An interaction designer explains how a \"homele...   \n",
       "4  08/17/2017   7:56 am  How to build a neural network in 30 lines of J...   \n",
       "\n",
       "    type  reach  clicks reactions  \n",
       "0   Link   1768      44        21  \n",
       "1   Link   6941     536        99  \n",
       "2  Video  17399    2236       750  \n",
       "3   Link   3751     167        10  \n",
       "4   Link  18248    1946       474  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['21', '99', '750', '10', '474', '56', '466', '403', '217', '109',\n",
       "       '165', '54', '171', '511', '176', '335', '475', '42', '287', '1841',\n",
       "       '729', '313', '311', '867', '309', '662', '29', '193', '123', '154',\n",
       "       '680', '61', '264', '619', '35', '555', '24', '67', '231', '80',\n",
       "       '84', '40', '415', '43', '136', '50', '34', '138', '106', '539',\n",
       "       '70', '65', '19', '77', '785', '83', '249', '146', '91', '187',\n",
       "       '227', '132', '115', '272', '223', '46', 'Boost Post', '267',\n",
       "       '1140', '104', '575', '78', '96', '111', '647', '41', '159', '51',\n",
       "       '695', '483', '530', '265', '312', '131', '225', '219', '262',\n",
       "       '711', '39', '422', '355', '63', '120', '173', '129', '433', '48',\n",
       "       '297', '293', '463', '127', '244', '562', '541', '242', '437', '64',\n",
       "       '37', '552', '315', '991', '279', '1558', '72', '772', '240', '32',\n",
       "       '88', '33', '707', '651', '417', '319', '57', '68', '241', '116',\n",
       "       '436', '210', '197', '112', '420', '359', '273', '207', '358',\n",
       "       '879', '122', '605', '424', '150', '3593', '66', '348', '102',\n",
       "       '259', '161', '97', '347', '137', '779', '391', '296', '368', '119',\n",
       "       '2648', '188', '172', '166', '179', '516', '49', '214', '845',\n",
       "       '945', '220', '822', '245', '202', '701', '103', '203', '360',\n",
       "       '521', '198', '215', '2002', '286', '538', '133', '79', '274', '82',\n",
       "       '268', '350', '1872', '145', '1539', '117', '1210', '229', '85',\n",
       "       '280', '395', '301', '258', '45', '140', '868', '158', '181', '730',\n",
       "       '447', '234', '87', '205', '38', '292', '121', '75', '26', '239',\n",
       "       '260', '59', '252', '364', '1407', '55', '269', '255', '100', '190',\n",
       "       '725', '547', '94', '118', '278', '199', '95', '167', '216', '142',\n",
       "       '448', '1477', '147', '387', '71', '361', '323', '139', '162',\n",
       "       '204', '74', '351', '101', '52', '169', '617', '25', '353', '18',\n",
       "       '134', '366', '329', '228', '47', '911', '31', '114', '525', '1437',\n",
       "       '677', '62', '2500', '839', '582', '27', '20', '105', '53', '11',\n",
       "       '44', '836', '520', '15226', '184', '503', '126', '404', '592',\n",
       "       '397', '195', '1329', '73', '76', '108', '212', '58', '155', '69',\n",
       "       '453'], dtype=object)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.reactions.unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "df.ix[df['reactions']=='Boost Post', 'reactions'] = -1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "df['reactions'] = df['reactions'].astype(dtype=int)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "# Comparing between types\n",
    "## Question 1: standardise the data\n",
    "*As I advised to someone else in the chatroom, given the sample sizes are so different better to find ways to standardise the data. A simple way to do that is percentage. You can also apply other normalization techniques, but percentage, although a transformation that bring some problems to the data, is usually more intuitive, specially for the public we are communicating here in FCC.*\n",
    "\n",
    "**When you say to standardise the data with percentage, what do you mean? Get how % of all clicks that each type has? If we wanted to go further, should I do a t-test or ANOVA? What would be these other normalization techniques? (right now I'll not use the typer anymore, but I want to learn more about this).** \n",
    "\n",
    "**When sample sizes are different should I make a t-test to see if the difference in clicks were by chance or not?**\n",
    "\n",
    "## Question 2: click distributions\n",
    "*I would suggest to find a stat to compare eg. click distributions - it is possible that it won't be reliable but we could try.*\n",
    "\n",
    "**How should I plot these click distributions to compare? Like this? (next 3 cells)**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x111a1d4e0>"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAZkAAAEKCAYAAADAVygjAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nMpKkbgwZSVI3howkqZtff30LkixDJ7gAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x111459048>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from scipy.stats import norm\n",
    "sns.distplot(df.clicks[df['type']=='Video'], hist=False, color=\"g\", fit=norm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x111b5ca20>"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAZAAAAEKCAYAAAA8QgPpAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nlPLI/wcan43SeAPniAAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x1113bf400>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.distplot(df.clicks[df['type']=='Photo'], hist=False, color=\"b\", fit=norm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x111ba1fd0>"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYoAAAEKCAYAAAAMzhLIAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x111e2e4e0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.distplot(df.clicks[df['type']=='Link'], hist=False, color=\"r\", fit=norm)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Number of words in titles\n",
    "\n",
    "## Question 3: standardization\n",
    "*Good one! Delighted with this part. Can you please exploit this part in particular and prepare a report for the rest in the FCC Data Science Channel? Again, some standardization would be advisable. Photos has a really small samples.*\n",
    "\n",
    "**How should I do this standardization? (again, we are droping the type comparasion, but just to make sure I got it). Should I go with % also?**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "df['word_count'] = df['title'].apply(lambda x: len(x.split(\" \")))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1122f2978>"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX0AAAELCAYAAAA1AlaNAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nxkUs9I0xxkUs9I0xxkX+P+gASkMSOM+pAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x111e359b0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.distplot(df.word_count, bins=20, rug=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABDAAAADQCAYAAADxn5GHAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAAYPQ0MAAAAIDR+/8CWbNO+aMrqQAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x1134fe470>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "g = sns.FacetGrid(df, col=\"type\")\n",
    "g.map(plt.hist, \"word_count\");"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.JointGrid at 0x10f096b00>"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAbIAAAGoCAYAAAAjPmDhAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x10f096ac8>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# The bivariate analogue of a histogram is known as a “hexbin” plot, because it shows the counts of observations that fall within hexagonal bins. \n",
    "# This plot works best with relatively large datasets. \n",
    "sns.jointplot(x=\"word_count\", y=\"clicks\", data=df[df['clicks'] < 3840], kind='hex')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "### Bins for number of words\n",
    "* A medium-length title is between 8 and 15 words, if it's more than that I'm considering it to be a long title"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "bins = [0, 8, 15, df.word_count.max()]\n",
    "group_names = ['short', 'medium', 'long']\n",
    "df['title_length'] = pd.cut(df['word_count'], bins, labels=group_names)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "* https://stats.stackexchange.com/questions/10289/whats-the-difference-between-normalization-and-standardization\n",
    "* http://www.theanalysisfactor.com/two-types-effect-size-statistic/\n",
    "* https://stats.stackexchange.com/questions/45666/small-and-unbalanced-sample-sizes-for-two-groups-what-to-do\n",
    "* https://www.researchgate.net/post/comparing_frequency_counts_between_two_groups_of_different_sample_size_Chi-square\n",
    "* http://onlinestatbook.com/2/tests_of_means/difference_means.html"
   ]
  }
 ],
 "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": "3.5.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}