{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "# col_names = [\"region\",\"video_id\", \"timeFetched\", \"title\", \"channel_title\", \"category_id\", \"publish_time\", \"tags\", \"views\", \"likes\",\"dislikes\", \"comment_count\", \"thumbnail_link\", \"comments_disabled\", \"ratings_disabled\", \"video_error_or_removed\", \"description\"]\n",
    "# data = pd.read_csv(\"combinedNewOld.csv\", names=col_names)\n",
    "data = pd.read_csv(\"oldAndNewData.csv\", engine='python')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "def del_Rows(data):\n",
    "    \n",
    "    rows = len(data)\n",
    "    #titleInd = \n",
    "    for i in range(rows): #iterates through every row in data \n",
    "        s = str(data.loc[i]['videoTitle']) #converts the title to a string\n",
    "        if (not(s.isascii())):\n",
    "            data.drop(i, axis = 0, inplace = True) #if not english, that row is deleted\n",
    "            \n",
    "    #return data.to_csv(\"MODIFIED.csv\", sep=str(','))\n",
    "    return data.to_csv(\"oldAndNewOnlyEnglish.csv\", index = False)\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "del_Rows(data)"
   ]
  }
 ],
 "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": "3.7.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}