PBPatil/twitter_analysis.ipynb

## twitter_analysis.ipynb
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Preliminaries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "import re\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Data Reading "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "tweets_data_path = 'twitter_data.txt'\n",
    "\n",
    "tweets_data = []\n",
    "tweets_file = open(tweets_data_path, \"r\")\n",
    "for line in tweets_file:\n",
    "    try:\n",
    "        tweet = json.loads(line)\n",
    "        tweets_data.append(tweet)\n",
    "    except:\n",
    "        continue"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total Tweets Count:79359\n"
     ]
    }
   ],
   "source": [
    "print ('Total Tweets Count:{}'.format(len(tweets_data))) "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Structuring the raw data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "tweets = pd.DataFrame()\n",
    "tweets['text'] = map(lambda tweet:tweet['text'] if 'text' in tweet else ' ', tweets_data)\n",
    "tweets['lang'] = map(lambda tweet: tweet.get('lang', None), tweets_data)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- Drawing insights"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "tweets_by_lang = tweets['lang'].value_counts()\n",
    "\n",
    "fig, ax = plt.subplots()\n",
    "ax.tick_params(axis='x', labelsize=15)\n",
    "ax.tick_params(axis='y', labelsize=10)\n",
    "ax.set_xlabel('Languages', fontsize=15)\n",
    "ax.set_ylabel('Number of tweets' , fontsize=15)\n",
    "ax.set_title('Top 5 languages', fontsize=15, fontweight='bold')\n",
    "tweets_by_lang[:5].plot(ax=ax, kind='bar', color='orange');\n",
    "plt.savefig('top_5_langs.jpg',bbox_inches='tight', pad_inches=0.3)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Mining Tweets based on Keywords"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "def word_in_text(word, text):\n",
    "    word = word.lower()\n",
    "    text = text.lower()\n",
    "    match = re.search(word, text)\n",
    "    if match:\n",
    "        return True\n",
    "    return False"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "tweets['FIFA'] = tweets['text'].apply(lambda tweet: word_in_text('#FIFA', tweet))\n",
    "tweets['WorldCup'] = tweets['text'].apply(lambda tweet: word_in_text('#WorldCup', tweet))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "keywords = ['FIFA','WorldCup']\n",
    "tweets_by_keywords = [tweets['FIFA'].value_counts()[True],tweets['WorldCup'].value_counts()[True]]\n",
    "x = list(range(len(keywords)))\n",
    "width = 0.8\n",
    "fig, ax = plt.subplots()\n",
    "plt.bar(x, tweets_by_keywords, width, alpha=1, color='g')\n",
    "\n",
    "# Setting axis labels and ticks\n",
    "ax.set_ylabel('Number of tweets', fontsize=15)\n",
    "ax.set_title('Feed', fontsize=10, fontweight='bold')\n",
    "ax.set_xticks([p + 0.4 * width for p in x])\n",
    "ax.set_xticklabels(keywords, rotation=90)\n",
    "plt.grid()\n",
    "plt.tight_layout()\n",
    "plt.savefig('selected_keywords.jpg',bbox_inches='tight', pad_inches=0.3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Tweets with keyword FIFA: 835\n",
      "Tweets with keyword WorldCup: 9818\n"
     ]
    }
   ],
   "source": [
    "#Counting Tweets\n",
    "print ('Tweets with keyword FIFA: {}'.format(tweets['FIFA'].value_counts()[True]))\n",
    "print ('Tweets with keyword WorldCup: {}'.format(tweets['WorldCup'].value_counts()[True]))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "__Note__: \n",
    "Keywords used are:\n",
    "- FIFA,World,Cup,football,FIFA World Cup,#FIFA2018,WorldCup,#WorldCup2018,#FifaWorldCup,#FIFAWorldCup,RUSKSA,#RUSKSA,prediction,win,#FIFA.\n",
    "- Hence the total count is 79K+ .For simlplicity sake I have taken two keywords here."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "***"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Targeted Selection"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Selecting HashTags of corrosponding teams from the fixture\n",
    "tweets['#RUS'] = tweets['text'].apply(lambda tweet: word_in_text('#RUS', tweet))\n",
    "tweets['#KSA'] = tweets['text'].apply(lambda tweet: word_in_text('#KSA', tweet))\n",
    "tweets['Neutral'] = tweets['text'].apply(lambda tweet: word_in_text('#RUS', tweet) or word_in_text('#KSA', tweet) or word_in_text('#RUSKSA', tweet))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "keywords= ['#RUS','#KSA','#RUSKSA']\n",
    "tweets_by_keywords = [tweets[tweets['Neutral'] == True]['#RUS'].value_counts()[True], \n",
    "                      tweets[tweets['Neutral'] == True]['#KSA'].value_counts()[True], \n",
    "                      tweets[tweets['Neutral'] == True]['Neutral'].value_counts()[True]]\n",
    "x = list(range(len(keywords)))\n",
    "width = 0.8\n",
    "fig, ax = plt.subplots()\n",
    "plt.bar(x, tweets_by_keywords, width,alpha=1,color='r')\n",
    "ax.set_ylabel('Number of tweets', fontsize=15)\n",
    "ax.set_title('Support: Russia vs.Saudi Arabia vs. #RUSKSA ', fontsize=10, fontweight='bold')\n",
    "ax.set_xticks([p + 0.4 * width for p in x])\n",
    "ax.set_xticklabels(keywords)\n",
    "plt.grid()\n",
    "plt.savefig('Twitter_feed.jpg',bbox_inches='tight', pad_inches=0.3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Russian Supporters:7796\n",
      "Saudi Supporters:4527\n",
      "Neutral:8488\n"
     ]
    }
   ],
   "source": [
    "#Counting Tweets\n",
    "print ('Russian Supporters:{}'.format(tweets['#RUS'].value_counts()[True]))\n",
    "print ('Saudi Supporters:{}'.format(tweets['#KSA'].value_counts()[True]))\n",
    "print ('Neutral:{}'.format(tweets['Neutral'].value_counts()[True]))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "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": "2.7.15"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}