{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Visualize forecast\n",
    "In this notebook, you will visualize the results predicted by Amazon Forecast."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Get your exported forecast filename in S3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import boto3\n",
    "sts = boto3.client('sts')\n",
    "id_info = sts.get_caller_identity()\n",
    "print(id_info['Account'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "bucket_name = 'workshop-timeseries-retail-' + id_info['Account'] + '-source'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "bucket_name"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import re\n",
    "s3 = boto3.resource('s3')\n",
    "bucket = s3.Bucket(bucket_name)\n",
    "for obj in bucket.objects.filter(Prefix='output/'):\n",
    "    if re.search('part0.csv$', obj.key):\n",
    "        file = re.sub('^output/', '', obj.key)\n",
    "print(file)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Download forecast result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import boto3\n",
    "\n",
    "s3 = boto3.resource('s3') \n",
    "bucket = s3.Bucket(bucket_name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!mkdir -p ./exported_forecast\n",
    "bucket.download_file(f'output/{file}', './exported_forecast/result.csv')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Visualization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "forecast = pd.read_csv('./exported_forecast/result.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "forecast.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "forecast.plot(x=forecast.columns[1],figsize=(20, 10),title='EC Sales Forecast of United Kingdom',grid=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This is the end of the workshop. I hope you've seen how easy it is to build a pipeline through simple code. This notebook allowed us to visualize the results of our predictions in a simple way, and with the integration of Amazon QuickSight, we can also visualize them in a dashboard."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Next\n",
    "Finally, For cleaning up the environment by running 4_clean.ipynb."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "conda_python3",
   "language": "python",
   "name": "conda_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": "3.6.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}