{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## RusAge\n",
    "Data from RusAge (https://www.kaggle.com/oldaandozerskaya/fiction-corpus-for-agebased-text-classification)\n",
    "\n",
    "RusAge: Corpus for Age-Based Text Classification\n",
    "Russian fiction books' previews with age rating labels."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import nltk\n",
    "nltk.download('punkt')\n",
    "nltk.download('stopwords')\n",
    "from nltk.corpus import stopwords\n",
    "import string\n",
    "from nltk.corpus import PlaintextCorpusReader\n",
    "from nltk.text import Text"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<img src=\"imgs/capture-rusage.png\">"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "corpus = PlaintextCorpusReader(\"./rusage/abstracts/\", '.*\\.txt', encoding='utf-8')\n",
    "corpus_tokens = corpus.words()\n",
    "print(corpus_tokens[:10])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "files=corpus.fileids()\n",
    "\n",
    "for f in files:\n",
    "    print (f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "freq = nltk.FreqDist(corpus.words())\n",
    "#common words \n",
    "print(\"Common Words:\", freq.most_common(10))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "russian_stopwords = stopwords.words(\"russian\") + list(string.punctuation)\n",
    "\n",
    "#Preprocess function\n",
    "def preprocess_text(words):\n",
    "    \n",
    "    wordsFiltered = []\n",
    "\n",
    "    for w in words:\n",
    "        if w not in russian_stopwords:\n",
    "            wordsFiltered.append(w)\n",
    "\n",
    "    return wordsFiltered\n",
    "\n",
    "\n",
    "preprocess_corpus = preprocess_text(corpus.words())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "freq = nltk.FreqDist(preprocess_corpus)\n",
    "#common words \n",
    "print(\"Common Words:\", freq.most_common(20))\n",
    "#specific words \n",
    "print(\"Specific Word: \", freq.get(\"истории\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "t = Text(corpus_tokens)\n",
    "t.concordance('Толстого', lines=20)"
   ]
  }
 ],
 "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": "3.6.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}