Tweet Analysis Part (1).ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pyLDAvis\n",
    "import pyLDAvis.sklearn\n",
    "pyLDAvis.enable_notebook()\n",
    "from __future__ import print_function\n",
    "import nltk\n",
    "\n",
    "#Collection of all Tweet text for topic modelling \n",
    "data_dump=data['Tweets_Cln'].str.cat(sep=', ')\n",
    "\n",
    "#Making sure we have just alphbest and numerals \n",
    "words = set(nltk.corpus.words.words())\n",
    "data_dump= \" \".join(w for w in nltk.wordpunct_tokenize(data_dump) \\\n",
    "                          if w.lower() in words and w.isalpha())"
   ]
  }
 ],
 "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": "3.7.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}