{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pwd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_dir = \"/home/ec2-user/SageMaker/aws-recomendador-anime/recomendador-de-anime/anime-data\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "anime_with_synopsis = pd.read_csv(data_dir + '/anime_with_synopsis.csv',index_col='MAL_ID')\n",
    "anime_with_synopsis.sample(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Crear columna Name_Lower"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "anime_with_synopsis['Name_Lower'] = anime_with_synopsis['Name'].str.lower()\n",
    "anime_with_synopsis.sample(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "new_anime_with_synopsis = \"new_anime_with_synopsis.csv\"\n",
    "anime_with_synopsis.to_csv((data_dir+\"/\"+new_anime_with_synopsis), index=True, float_format='%.0f')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Copiar archivo en S3"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Copiar archivo en S3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import boto3\n",
    "import json"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('/opt/ml/metadata/resource-metadata.json') as notebook_info:\n",
    "    data = json.load(notebook_info)\n",
    "    resource_arn = data['ResourceArn']\n",
    "    region = resource_arn.split(':')[3]\n",
    "print(region)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "s3 = boto3.client('s3')\n",
    "account_id = boto3.client('sts').get_caller_identity().get('Account')\n",
    "bucket_name = account_id + \"-\" + region + \"-\" + \"personalize-anime-dataset1\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_file_path = f\"{data_dir}/{new_anime_with_synopsis}\"\n",
    "boto3.Session().resource('s3').Bucket(bucket_name).Object(new_anime_with_synopsis).upload_file(data_file_path)\n",
    "s3DataPath = \"s3://\"+bucket_name+\"/\"+data_file_path"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.9.6 64-bit",
   "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": "3.9.6"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}