Gist with notebook complementing my post on Medium

medium-whatstk.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This notebook complements my blog post **Exploring WhatsApp data, Analyze your WhatsApp chat data using Python** on Medium."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Install dependencies\n",
    "!pip install whatstk==0.4.1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Load a chat"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load chat\n",
    "from whatstk import WhatsAppChat\n",
    "filepath = 'http://raw.githubusercontent.com/lucasrodes/whatstk/develop/chats/whatsapp/lorem-2000.txt'  # change to your chat file\n",
    "chat = WhatsAppChat.from_source(filepath=filepath)\n",
    "# Chat as Dataframe available in chat.df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Loading chat setting hformat manually (skip if previous cell worked)\n",
    "# hformat = '[%y-%m-%d %H:%M] %name:'  # change to hformat of your chat\n",
    "# chat = WhatsAppChat.from_source(filepath=filepath, hformat=hformat)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## First data overview"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "First date is: 2019-04-16 02:09:00\n",
      "Last date is: 2020-06-13 00:00:00\n"
     ]
    }
   ],
   "source": [
    "init_date = chat.df.date.min()\n",
    "end_date = chat.df.date.max()\n",
    "print(f\"First date is: {init_date}\\nLast date is: {end_date}\")"
   ]
  },
  {
   "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>message</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>username</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>+1 123 456 789</th>\n",
       "      <td>507</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Giuseppe</th>\n",
       "      <td>516</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>John</th>\n",
       "      <td>481</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mary</th>\n",
       "      <td>496</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                message\n",
       "username               \n",
       "+1 123 456 789      507\n",
       "Giuseppe            516\n",
       "John                481\n",
       "Mary                496"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chat.df.groupby('username').agg('count')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>num_messages</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2019-07-01</th>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2019-07-26</th>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2019-07-11</th>\n",
       "      <td>19</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2019-08-22</th>\n",
       "      <td>18</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-03-23</th>\n",
       "      <td>18</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2019-08-23</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2019-05-28</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2019-05-02</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2019-04-18</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-06-13</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>235 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "            num_messages\n",
       "2019-07-01            20\n",
       "2019-07-26            20\n",
       "2019-07-11            19\n",
       "2019-08-22            18\n",
       "2020-03-23            18\n",
       "...                  ...\n",
       "2019-08-23             1\n",
       "2019-05-28             1\n",
       "2019-05-02             1\n",
       "2019-04-18             1\n",
       "2020-06-13             1\n",
       "\n",
       "[235 rows x 1 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Day with the most number of messages sent\n",
    "chat.df.groupby(chat.df.date).agg(num_messages=('message', 'count')).sort_values(by='num_messages', ascending=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Who talks the most?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'temp-plot.html'"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Number of messages sent\n",
    "from whatstk import FigureBuilder\n",
    "from plotly.offline import plot\n",
    "fb = FigureBuilder(chat=chat)\n",
    "fig = fb.user_interventions_count_linechart(cumulative=True, title='User inteventions count (cumulative)')\n",
    "plot(fig)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'temp-plot.html'"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Number of characters sent\n",
    "fig = fb.user_interventions_count_linechart(cumulative=True, msg_length=True, title='Count of sent characters (cumulative)')\n",
    "plot(fig)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## User message length"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'temp-plot.html'"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fig = fb.user_msg_length_boxplot()\n",
    "plot(fig)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## User interaction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'temp-plot.html'"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fig = fb.user_message_responses_heatmap()\n",
    "plot(fig)"
   ]
  }
 ],
 "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": "3.8.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}