{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "___\n",
    "\n",
    "<a href='http://www.pieriandata.com'><img src='../Pierian_Data_Logo.png'/></a>\n",
    "___\n",
    "<center><em>Copyright by Pierian Data Inc.</em></center>\n",
    "<center><em>For more information, visit us at <a href='http://www.pieriandata.com'>www.pieriandata.com</a></em></center>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Serving a Model as an API\n",
    "\n",
    "**NOTE: While we show this inside a Jupyter Notebook, you would probably never deploy something as a notebook in a real-world setting. Everything here is in one cell to reflect that this should be a .py file. We also included a duplicate .py file in this folder.**\n",
    "\n",
    "\n",
    "---\n",
    "\n",
    "**NOTE: You will need to install Flask to serve the API: https://flask.palletsprojects.com/en/2.0.x/installation/**\n",
    "\n",
    "    pip install flask\n",
    "    \n",
    "    or\n",
    "    \n",
    "    conda install flask\n",
    "\n",
    "---\n",
    "\n",
    "\n",
    "## api.py  (Run this as a script as shown in the video, NOT from within a Jupyter Cell)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "############################\n",
    "######## IMPORTS ##########\n",
    "##########################\n",
    "from flask import Flask, request, jsonify\n",
    "import joblib\n",
    "import pandas as pd\n",
    "\n",
    "# Create Flask App\n",
    "app = Flask(__name__)\n",
    "\n",
    "\n",
    "# Create API routing call\n",
    "@app.route('/predict', methods=['POST'])\n",
    "def predict():\n",
    "    \n",
    "    # Get JSON Request\n",
    "    feat_data = request.json\n",
    "    # Convert JSON request to Pandas DataFrame\n",
    "    df = pd.DataFrame(feat_data)\n",
    "    # Match Column Na,es\n",
    "    df = df.reindex(columns=col_names)\n",
    "    # Get prediction\n",
    "    prediction = list(model.predict(df))\n",
    "    # Return JSON version of Prediction\n",
    "    return jsonify({'prediction': str(prediction)})\n",
    "\n",
    "        \n",
    "\n",
    "if __name__ == '__main__':\n",
    "\n",
    "    # LOADS MODEL AND FEATURE COLUMNS\n",
    "    model = joblib.load(\"final_model.pkl\") \n",
    "    col_names = joblib.load(\"column_names.pkl\") \n",
    "\n",
    "    app.run(debug=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# JSON Post Request\n",
    "\n",
    "1. POST to: http://127.0.0.1:5000/predict\n",
    "2. Select Body\n",
    "3. Select Raw\n",
    "4. Select JSON(application/json)\n",
    "5. Supply JSON for Features:\n",
    "    [{\"TV\":230.1,\"radio\":37.8,\"newspaper\":69.2}]\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}