00-0-convert_raw_cnndailymail_to_json.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_train = pd.read_csv(\"./data/cnn_dailymail/raw/train.csv\")\n",
    "df_val = pd.read_csv(\"./data/cnn_dailymail/raw/validation.csv\")\n",
    "df_test = pd.read_csv(\"./data/cnn_dailymail/raw/test.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "if not os.path.exists(\"./data/cnn_dailymail/pre/\"):\n",
    "    os.makedirs(\"./data/cnn_dailymail/pre/\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_train.to_json(\"./data/cnn_dailymail/pre/train.json\")\n",
    "df_val.to_json(\"./data/cnn_dailymail/pre/val.json\")\n",
    "df_test.to_json(\"./data/cnn_dailymail/pre/test.json\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "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": "3.9.13"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}