{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## First, let's test the ping method (GET /ping)\n",
    "\n",
    "This method will be used by Sagemaker for health check our model. It must return a code **200**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "from urllib import request\n",
    "\n",
    "base_url='http://localhost:8080'\n",
    "\n",
    "resp = request.urlopen(\"%s/ping\" % base_url)\n",
    "print(\"Response code: %d\" % resp.getcode() )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Then we can the predictions (POST /invocations)\n",
    "\n",
    "This method will be used by Sagemaker for the predictions. Here we're simulating the header parameter related to the CustomAttributes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%%time\n",
    "import pandas as pd\n",
    "\n",
    "def predict(test_df, content_type='text/csv', accept='text/csv'):\n",
    "    headers = {\n",
    "        'Content-type': content_type,\n",
    "        'Accept': accept\n",
    "    }\n",
    "    \n",
    "    if content_type == 'text/csv':\n",
    "        payload = test_df.to_csv(index=False).encode('utf-8')\n",
    "    else:\n",
    "        payload = test_df.to_json().encode('utf-8')\n",
    "        \n",
    "    req = request.Request(\"%s/invocations\" % base_url, data=payload, headers=headers)\n",
    "    resp = request.urlopen(req)\n",
    "    body = resp.read().decode('utf-8')\n",
    "    print(\"Response code: %d, Prediction: %s\\n\" % (resp.getcode(), body))\n",
    "    for i in resp.headers:\n",
    "        print(i, resp.headers[i])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Get the first 10 records from test dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Get the first 10 records\n",
    "test_df = pd.read_csv('test.csv').head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Test all the different input and output formats"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "predict(test_df, 'text/csv', 'text/csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "predict(test_df, 'text/csv', 'application/json')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "predict(test_df, 'application/json', 'application/json')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "predict(test_df, 'application/json', 'text/csv')"
   ]
  }
 ],
 "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
}