{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "import csv\n",
    "from sklearn.utils import shuffle\n",
    "food_raw_data, non_food_raw_data, food_rectify = [], [], []\n",
    "food_data, non_food_data = [], []\n",
    "\n",
    "with open(\"food_rectify.csv\") as f:\n",
    "    reader = csv.reader(f)\n",
    "    for row in reader:\n",
    "        food_rectify.append(row)\n",
    "\n",
    "with open(\"food.csv\") as f:\n",
    "    reader = csv.reader(f)\n",
    "    for row in reader:\n",
    "        food_raw_data.append(row)\n",
    "        \n",
    "with open(\"no_food.csv\") as f:\n",
    "    reader = csv.reader(f)\n",
    "    for row in reader:\n",
    "        non_food_raw_data.append(row)\n",
    "     \n",
    "food_data = food_raw_data\n",
    "\n",
    "for i in non_food_raw_data:\n",
    "    if i[0] not in food_rectify:\n",
    "        non_food_data.append(i)\n",
    "    else:\n",
    "        food_data.append(i)\n",
    "\n",
    "food_data = shuffle(food_data)\n",
    "non_food_data = shuffle(non_food_data)\n",
    "\n",
    "ratio = 0.75   \n",
    "train_food_len = int(len(food_data) * ratio)\n",
    "train_non_food_len = train_food_len\n",
    "\n",
    "test_food_len = len(food_data) - train_food_len\n",
    "test_non_food_len = int(len(non_food_data) * (1 - ratio))\n",
    "\n",
    "\n",
    "train_food = food_data[0:train_food_len]\n",
    "test_food = food_data[train_food_len:train_food_len + test_food_len]\n",
    "\n",
    "train_non_food = non_food_data[0:train_non_food_len]\n",
    "test_non_food = non_food_data[train_non_food_len:train_non_food_len + test_non_food_len]\n",
    "\n",
    "with open('train_food.csv', 'w') as f:\n",
    "    write = csv.writer(f)\n",
    "    write.writerows(train_food)\n",
    "    \n",
    "with open('train_non_food.csv', 'w') as f:\n",
    "    write = csv.writer(f)\n",
    "    write.writerows(train_non_food )\n",
    "\n",
    "with open('test_food.csv', 'w') as f:\n",
    "    write = csv.writer(f)\n",
    "    write.writerows(test_food )\n",
    "with open('test_non_food.csv', 'w') as f:\n",
    "    write = csv.writer(f)\n",
    "    write.writerows(test_non_food)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a = [i for i in range(10)]\n",
    "print(a)\n",
    "print(a[0:4])\n",
    "print(a[4:7])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "non_food_raw_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": "3.9.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}