{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import os.path\n",
    "import gzip\n",
    "import shutil\n",
    "import torch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "if not os.path.isfile('train/train.tsv'):\n",
    "    import lzma\n",
    "    with lzma.open('train/train.tsv.xz', 'rb') as f_in:\n",
    "        with open('train/train.tsv', 'wb') as f_out:\n",
    "            shutil.copyfileobj(f_in, f_out)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "raw_data = pd.read_csv('train/train.tsv', sep='\\t', names=['labels', 'text'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Label</th>\n",
       "      <th>Word</th>\n",
       "      <th>WordLen</th>\n",
       "      <th>WordHasDigit</th>\n",
       "      <th>CapitalFirst</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: [Label, Word, WordLen, WordHasDigit, CapitalFirst]\n",
       "Index: []"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data = []\n",
    "for sentence in raw_data.to_numpy():\n",
    "    for label, word in zip(sentence[0].split(), sentence[1].split()):\n",
    "        data.append([label,word,len(word), any(c.isdigit() for c in word), word.isupper()])\n",
    "df = pd.DataFrame(data, columns=['Label', 'Word', 'WordLen', 'WordHasDigit', 'CapitalFirst'], index=None)\n",
    "df[df[\"Label\"]==None]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "def labels_process(dt):\n",
    "    return [ torch.tensor([0] + document + [0], dtype = torch.long) for document in dt]\n",
    "\n",
    "def data_process(dt):\n",
    "    return [ torch.tensor([vocab['<bos>']] +[vocab[token]  for token in  document ] + [vocab['<eos>']], dtype = torch.long) for document in dt]"
   ]
  }
 ],
 "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}