{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Getting the dataset prepared in Lab `1-DataPrep`"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's load the dataset with the features we engineered in 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_train_path = 'train.csv'\n",
    "train_df = pd.read_csv(local_train_path, header=None)\n",
    "train_df.head()\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",
    "train_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Let's check the validation dataset\n",
    "local_validation_path = 'validation.csv'\n",
    "validation_df = pd.read_csv(local_validation_path, header=None)\n",
    "validation_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "If you remember from previous lab, we saved the CSV without headers. CSV with headers are stored in `config/training-dataset-with-header.csv`.\n",
    "\n",
    "To see our train set with headers:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "pd.read_csv(\"training-dataset-with-header.csv\").head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now we'll upload the files to S3 for training."
   ]
  },
  {
   "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": [
    "train_dir = f\"{prefix}/data/train\"\n",
    "val_dir = f\"{prefix}/data/validation\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Return the URLs of the uploaded file, so they can be reviewed or used elsewhere\n",
    "s3uri_train = sagemaker.s3.S3Uploader.upload(local_train_path, 's3://{}/{}'.format(bucket, train_dir))\n",
    "s3uri_validation = sagemaker.s3.S3Uploader.upload(local_validation_path, 's3://{}/{}'.format(bucket, val_dir))"
   ]
  },
  {
   "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,train_dir)}>S3 Train object</a>\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "display(HTML(f\"<a href={s3_url_placeholder.format(bucket,val_dir)}>S3 Validation 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 train_dir\n",
    "%store val_dir\n",
    "%store s3uri_train\n",
    "%store s3uri_validation"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "[You can now go back to modeling.ipynb](../modeling.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-2:429704687514: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
}