{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pathlib import Path\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "paths = list(Path('../data/text').iterdir())\n",
    "labels = []\n",
    "texts = []\n",
    "\n",
    "for path in paths:    \n",
    "    for filepath in path.glob('*.txt'):\n",
    "        if not filepath.name == 'LICENSE.txt':\n",
    "            with open(filepath) as f:\n",
    "                next(f)\n",
    "                next(f)\n",
    "                text = f.read().replace('\\u3000','').replace('\\n','')\n",
    "            \n",
    "            texts.append(text)\n",
    "            labels.append(path.name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [],
   "source": [
    "news_df = pd.DataFrame({\n",
    "    'label': labels,\n",
    "    'text': texts\n",
    "})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "news_df.to_csv('../data/news.csv.gz', compression='gzip', index=False)"
   ]
  }
 ],
 "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}