sentiment.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "code2sentiment = {0:\"negative\",\n",
    "1: \"somewhat negative\",\n",
    "2: \"neutral\",\n",
    "3: \"somewhat positive\",\n",
    "4:\"positive\"}\n",
    "\n",
    "data = pd.read_csv(\"data/sentiment.tsv\",sep=\"\\t\")[[\"SentenceId\",\"Phrase\",\"Sentiment\"]]\n",
    "data.drop_duplicates(subset=[\"SentenceId\"],inplace=True,keep=\"first\")\n",
    "data[\"Sentiment\"] = data[\"Sentiment\"].apply(lambda code : code2sentiment[code])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "answers = []\n",
    "for _, row in data[[\"Phrase\",\"Sentiment\"]].iterrows():\n",
    "    review = row[\"Phrase\"]\n",
    "    for symbol in [\"?\",\"!\",\",\",\".\",\"'\",\"n't\"]:\n",
    "        review = review.replace(\" \"+symbol,symbol)\n",
    "    sentiment = row[\"Sentiment\"]\n",
    "    answers.append(f\"{sentiment} | {review}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"reviews_sentiment.txt\",'w') as f:\n",
    "    f.write(\"\\n\".join(answers))"
   ]
  }
 ],
 "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
}