{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Coursera Capstone: \"Battle of the Neighborhoods\"\n",
    "\n",
    "## Identifying Optimal Places for a Pizza Truck to Set Up Shop in San Diego"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "> Introduction / Business Problem"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Food trucks have become increasingly popular as a way to serve unique cuisine in different places, especially in large cities. Ample opportunities exist to make a net profit provided they visit the right places, i.e., those that attract significant crowds of hungry people. Determining the best areas to set up shop and sell the most food requires knowledge of the type and popularity of other places to eat/drink nearby, which areas are low on food options, when and where large events occur that attract a lot of hungry people, etc. These efforts will focus on identifying good places for a pizza truck to visit in San Diego, California, with particular emphasis on bars and events."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "> Data Plan & Description"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "   This project will retrieve, clean, and process data from the Foursquare API. It will then apply various machine learning techniques - including classification and clustering algorithms - to identify optimal places for a pizza truck to set up shop in San Diego. Intuition suggests seeking out bars, and other trending areas with large events, that don't offer food or have other popular established restaurants nearby. In other words, I seek to isolate venues where people would have a big crazing for pizza while minimizing the competition. Real-world data extracted from Foursquare are as of June 2019. From the Foursquare \"venues\" group, I will query the following endpoints: \"search\" to find existing venues in San Diego, \"trending\" and \"likes\" as a metric of their popularity, \"categories\" to determine their type, \"timeseries\" to see how their stats have vary throughout the year, \"similar\" to find similar venues, \"events\" to determine when they are likely to be busy with a lot of people, and \"menu\" to determine what items they offer. If I deem it necessary, I will also seek out other datasets to find recurring events such as Farmer's Markets that also attract large numbers of hungry people."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Hello Capstone Project Course!\n"
     ]
    }
   ],
   "source": [
    "print('Hello Capstone Project Course')"
   ]
  }
 ],
 "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": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}