{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Natural Language Toolkit"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's load _The Gold Bug_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "THE GOLD-BUG\n",
      "\n",
      "          What ho! what ho! this fellow is dancing mad!\n",
      "\n",
      "               He hath been b\n"
     ]
    }
   ],
   "source": [
    "with open(\"data/goldBug.txt\", \"r\") as f:\n",
    "    goldBugString = f.read()\n",
    "print(goldBugString[:100])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's tokenize!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['the', 'gold-bug', 'what', 'ho', '!', 'what', 'ho', '!', 'this', 'fellow']"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import nltk\n",
    "goldBugTokens = nltk.word_tokenize(goldBugString.lower())\n",
    "goldBugTokens[:10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['the', 'what', 'ho', 'what', 'ho', 'this', 'fellow']\n",
      "['the', 'what', 'ho', 'what', 'ho', 'this', 'fellow']\n"
     ]
    }
   ],
   "source": [
    "filterTokens = []\n",
    "for word in goldBugTokens[:10]:\n",
    "    if word.isalpha():\n",
    "        filterTokens.append(word)\n",
    "print(filterTokens)\n",
    "\n",
    "print([word for word in goldBugTokens[:10] if word.isalpha()])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "goldBugWords = [word for word in goldBugTokens if any([char for char in word if char.isalpha()])]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('the', 877),\n",
       " ('of', 465),\n",
       " ('and', 359),\n",
       " ('i', 336),\n",
       " ('to', 329),\n",
       " ('a', 327),\n",
       " ('in', 238),\n",
       " ('it', 213),\n",
       " ('you', 162),\n",
       " ('was', 137)]"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wordFrequencies = nltk.FreqDist(goldBugWords)\n",
    "wordFrequencies.most_common(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['i', 'me', 'my', 'myself', 'we', 'our', 'ours', 'ourselves', 'you', 'your', 'yours', 'yourself', 'yourselves', 'he', 'him', 'his', 'himself', 'she', 'her', 'hers', 'herself', 'it', 'its', 'itself', 'they', 'them', 'their', 'theirs', 'themselves', 'what', 'which', 'who', 'whom', 'this', 'that', 'these', 'those', 'am', 'is', 'are', 'was', 'were', 'be', 'been', 'being', 'have', 'has', 'had', 'having', 'do', 'does', 'did', 'doing', 'a', 'an', 'the', 'and', 'but', 'if', 'or', 'because', 'as', 'until', 'while', 'of', 'at', 'by', 'for', 'with', 'about', 'against', 'between', 'into', 'through', 'during', 'before', 'after', 'above', 'below', 'to', 'from', 'up', 'down', 'in', 'out', 'on', 'off', 'over', 'under', 'again', 'further', 'then', 'once', 'here', 'there', 'when', 'where', 'why', 'how', 'all', 'any', 'both', 'each', 'few', 'more', 'most', 'other', 'some', 'such', 'no', 'nor', 'not', 'only', 'own', 'same', 'so', 'than', 'too', 'very', 's', 't', 'can', 'will', 'just', 'don', 'should', 'now']\n"
     ]
    }
   ],
   "source": [
    "stopwords = nltk.corpus.stopwords.words(\"English\")\n",
    "print(stopwords)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('upon', 81),\n",
       " ('de', 73),\n",
       " (\"'s\", 56),\n",
       " ('jupiter', 53),\n",
       " ('legrand', 47),\n",
       " ('one', 38),\n",
       " ('said', 35),\n",
       " ('well', 35),\n",
       " ('massa', 34),\n",
       " ('could', 33),\n",
       " ('bug', 32),\n",
       " ('skull', 29),\n",
       " ('parchment', 27),\n",
       " ('made', 25),\n",
       " ('tree', 25),\n",
       " ('first', 24),\n",
       " ('time', 24),\n",
       " ('two', 23),\n",
       " ('much', 23),\n",
       " ('us', 23)]"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "goldBugFilteredWords = [word for word in goldBugWords if not word in stopwords]\n",
    "nltk.FreqDist(goldBugFilteredWords).most_common(20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}