{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Getting the test dataset prepared in Lab `1-DataPrep`"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's load the test dataset from the previous lab 1-DataPrep.\n",
    "\n",
    "(If you want, just run all cells. Go to the top toolbar click on `Run -> Run All Cells`)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import boto3\n",
    "import sagemaker\n",
    "\n",
    "sess = boto3.Session()\n",
    "sm = sess.client('sagemaker')\n",
    "role = sagemaker.get_execution_role()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Set the paths for the datasets saved locally\n",
    "local_test_path = 'test.csv'\n",
    "test_df = pd.read_csv(local_test_path, header=None)\n",
    "\n",
    "pd.set_option('display.max_columns', 500)     # Make sure we can see all of the columns\n",
    "pd.set_option('display.max_rows', 10)         # Keep the output on one page\n",
    "test_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "If you remember from the previous data preparation lab, we saved the CSV without headers and the features engineered."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now we'll upload the file to S3 for testing."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%store -r bucket\n",
    "%store -r prefix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_dir = f\"{prefix}/data/test\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Upload test dataset to S3\n",
    "s3uri_test = sagemaker.s3.S3Uploader.upload(local_test_path, f\"s3://{bucket}/{test_dir}\")\n",
    "s3uri_test"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Moving the data to the main directory of this lab:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!cp test-dataset.csv ../"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Uploading the model trained in the previous 2-Modeling lab to S3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "s3uri_model = sagemaker.s3.S3Uploader.upload(\"model.tar.gz\", f\"s3://{bucket}/{prefix}/model\")\n",
    "s3uri_model"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Saving variables to use in the main notebook for this lab"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "If you want to see in the console, go to S3 and verify the 2 CSV files are there:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from IPython.core.display import display, HTML\n",
    "s3_url_placeholder = \"https://s3.console.aws.amazon.com/s3/buckets/{}?&prefix={}/\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "display(HTML(f\"<a href={s3_url_placeholder.format(bucket,test_dir)}>S3 Test object</a>\"))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Saving variables to use in the main notebook for this lab"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%store test_dir"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%store s3uri_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%store s3uri_model"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "[You can now go back to evaluation.ipynb](../evaluation.ipynb)"
   ]
  }
 ],
 "metadata": {
  "instance_type": "ml.t3.medium",
  "kernelspec": {
   "display_name": "Python 3 (Data Science)",
   "language": "python",
   "name": "python3__SAGEMAKER_INTERNAL__arn:aws:sagemaker:us-east-1:081325390199:image/datascience-1.0"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}