Python 0-Instructor.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Welcome to Python : An Introduction to Data Science\n",
    "\n",
    "Please sign in if you have not already. We use this data to improve our workshops!\n",
    "\n",
    "### About UF DSI\n",
    "\n",
    "We are an multi- and inter- disciplinary student organization that is dediated to promoting Data Science here at the Univeristy of Florida. We are partnered with the UF Informatics Institute who's aim is to foster informatics research and education.\n",
    "\n",
    "### What is Python?\n",
    "\n",
    "Python is an easy-to-use and robust **Object-Oriented** programming language. A lot of new software application are built with Python for this reason. It is used in other areas of computer science such and software engineering, digital arts, cybersecurity, and of course Data Science! \n",
    "\n",
    "This is a workshop that will introduce you to the basics of python and introduce you to Data Science and Visualization in Python. Due to the breadth of the language there are still many topics left for you to explore! Here we teach you the necessary skills. \n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Variables and Types"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Calculator\n",
    "\n",
    "Python can be used as a calculator. <code>Shift+Enter</code> runs the code block so you don't have to click run every time"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-3"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Addition and Subtraction\n",
    "(3+2)-8"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.2"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Multiplication and Division\n",
    "(3*2)/5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "729"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Exponentation\n",
    "3**6"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Variables can be given alphanumeric names beginning with an underscore or letter.  Variable types do not have to be declared and are inferred at run time."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'int'>\n"
     ]
    }
   ],
   "source": [
    "a = 1\n",
    "print(type(a)) # Built in function"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'float'>\n"
     ]
    }
   ],
   "source": [
    "b = 2.5 \n",
    "print(type(b))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Strings can be declared with either single or double quotes."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Go Gators\n",
      "<class 'str'>\n"
     ]
    }
   ],
   "source": [
    "c1 = \"Go \"\n",
    "c2 = 'Gators'\n",
    "c3 = c1 + c2\n",
    "print(c3)\n",
    "print(type(c3))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Modules and Import\n",
    "Files with a .py extension are known as Modules in Python.  Modules are used to store functions, variables, and class definitions.  \n",
    "\n",
    "Modules that are not part of the standard Python library are included in your program using the <code>import</code> statement."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'cos' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-7-5b8b9e4a0735>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;31m# To use Math, we must import it\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mmath\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 3\u001b[0;31m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcos\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m: name 'cos' is not defined"
     ]
    }
   ],
   "source": [
    "# To use Math, we must import it\n",
    "import math\n",
    "print(cos(0))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Whoops.  Importing the <code>math</code> module allows us access to all of its functions, but we must call them in this way"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1.0\n"
     ]
    }
   ],
   "source": [
    "print(math.cos(0))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Alternatively, you can use the <code>from</code> keyword"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "-1.0\n"
     ]
    }
   ],
   "source": [
    "from math import cos\n",
    "print(cos(math.pi)) # we only imported cos, not the pi constant"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Using the <code>from</code> statement we can import everything from the math module.  \n",
    "\n",
    "Disclaimer: many Pythonistas discourage doing this for performance reasons.  Just import what you need"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1.0\n"
     ]
    }
   ],
   "source": [
    "from math import *\n",
    "print(sin(pi/2)) # now we don't have to make a call to math"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Strings\n",
    "As you may expect, Python has a powerful, full featured string module.  \n",
    "\n",
    "### Substrings\n",
    "Python strings can be substringed using bracket syntax"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Come on Gators\n"
     ]
    }
   ],
   "source": [
    "mystring = \"Go Gators, Come on Gators, Get up and go!\"\n",
    "print(mystring[11:25])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Python is a 0-index based language.  Generally whenever forming a range of values in Python, the first argument is inclusive whereas the second is not, i.e. <code>mystring[11:25]</code> returns characters 11 through 24.\n",
    "\n",
    "You can omit the first or second argument"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Go Gators\n"
     ]
    }
   ],
   "source": [
    "print(mystring[:9]) # all characters before the 9th index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Get up and go!\n"
     ]
    }
   ],
   "source": [
    "print(mystring[27:]) # all characters at or after the 27th"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Go Gators, Come on Gators, Get up and go!\n"
     ]
    }
   ],
   "source": [
    "print(mystring[:]) # you can even omit both arguments"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Using negative values, you can count positions backwards"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "go\n"
     ]
    }
   ],
   "source": [
    "print(mystring[-3:-1])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### String Functions\n",
    "Here are some more useful string functions\n",
    "#### find"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "3\n"
     ]
    }
   ],
   "source": [
    "print(mystring.find(\"Gators\")) # returns the index of the first occurence of Gators"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Looks like nothing was found.  -1 is returned by default."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "-1\n"
     ]
    }
   ],
   "source": [
    "print (mystring.find(\"Seminoles\")) # no Seminoles here"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### lower and upper"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "go gators, come on gators, get up and go!\n",
      "GO GATORS, COME ON GATORS, GET UP AND GO!\n"
     ]
    }
   ],
   "source": [
    "print(mystring.lower())\n",
    "print(mystring.upper())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Go', 'Gators,', 'Come', 'on', 'Gators,', 'Get', 'up', 'and', 'go!']\n"
     ]
    }
   ],
   "source": [
    "print(mystring.split()) # returns a list of strings broken by a space by default"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Go Gators', ' Come on Gators', ' Get up and go!']\n"
     ]
    }
   ],
   "source": [
    "print(mystring.split(',')) # you can also define the separator"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### join\n",
    "\n",
    "The <code>join</code> is useful for building strings from lists or other iterables.  Call <code>join</code> on the desired separator"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Go Gators\n"
     ]
    }
   ],
   "source": [
    "print(' '.join([\"Go\", \"Gators\"]))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "For more information on string functions:\n",
    "\n",
    "https://docs.python.org/2/library/stdtypes.html#string-methods"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Lists\n",
    "The Python standard library does not have traditional C-style fixed-memory fixed-type arrays.  Instead, lists are used and can contain a mix of any type.\n",
    "\n",
    "Lists are created with square brackets []"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "mylist = [1, 2, 3, 4, 'five']\n",
    "print(mylist)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "mylist.append(6.0) # add an item to the end of the list\n",
    "print(mylist)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "mylist.insert(6, 7) # insert the number 7 at index 6\n",
    "print(mylist)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "mylist.remove('five') # removes the first matching occurence \n",
    "print(mylist)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "popped = mylist.pop() # by default, the last item in the list is removed and returned\n",
    "print(popped)\n",
    "print(mylist)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(len(mylist)) # returns the length of any iterable such as lists and strings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# default list sorting. When more complex objects are in the list, arguments can be used to customize how to sort\n",
    "mylist.sort()\n",
    "print(mylist)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "mylist.reverse() # reverse the list\n",
    "print(mylist)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "For more information on Lists:\n",
    "\n",
    "https://docs.python.org/2/tutorial/datastructures.html#more-on-lists"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Conditionals\n",
    "Python supports the standard if-else-if conditional expression. REMEMBER TO INDENT"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a = 1; b = 2\n",
    "\n",
    "if a > b:\n",
    "    print (\"a is greater than b\")\n",
    "elif a < b:\n",
    "    print (\"a is less than b\")\n",
    "else:\n",
    "    print(\"a is equal to b\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Loops\n",
    "Python supports for, foreach, and while loops\n",
    "### For (counting)\n",
    "Traditional counting loops are accomplished in Python with a combination of the <code>for</code> key word and the <code>range</code> function"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for x in range(10): # with one argument, range produces integers from 0 to 9\n",
    "    print (x)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for z in range(1, 12, 3): # with three arguments, range starts at 1 and goes in steps of 3 until greater than 12\n",
    "    print(z)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Foreach\n",
    "As it turns out, counting loops are just foreach loops in Python.  The <code>range</code> function returns a list of integers over which <code>for in</code> iterates.  This can be extended to any other iterable type"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for i in ['foo', 'bar']: # iterate over a list of strings\n",
    "    print (i)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Functions\n",
    "Functions in Python do not have a distinction between those that do and do not return a value.  If a value is returned, the type is not declared.\n",
    "\n",
    "Functions can be declared in any module without any distinction between static and non-static.  Functions can even be declared within other functions\n",
    "\n",
    "The syntax is the following"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def sayHello():\n",
    "    print (\"Hello there!\")\n",
    "    \n",
    "sayHello()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def player(name, number): # use some arguments\n",
    "    print (\"#\" + str(number), name) # cast number to a string when concatenating\n",
    "    \n",
    "player(\"Kasey Hill\", 0)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Functions can have optional arguments if a default value is provided in the function signature"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def player(name, number, team = 'Florida'): # optional team argument\n",
    "    print (\"#\" + str(number), name, team)\n",
    "    \n",
    "player(\"Kasey Hill\", 0) # no team argument supplied"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "player(\"Aaron Harrison\", 2, \"Kentucky\") # supplying all three arguments"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Python functions can be called using named arguments, instead of positional"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "player(number = 23, name = 'Chris Walker')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### return\n",
    "In Python functions, an arbitrary number of values can be returned"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def sum(x,y):\n",
    "    return x + y # return a single value\n",
    "\n",
    "print(sum(1,2))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Data Science Tutorial\n",
    "Now that we've covered some Python basics, we will begin a tutorial going through many tasks a data scientist may perform.  We will obtain real world data and go through the process of auditing, analyzing, visualing, and building classifiers from the data.\n",
    "\n",
    "We will use a database of selected professor salaries which can be found using this link: \n",
    "https://data.austintexas.gov/Health-and-Community-Services/Client-Demographics-for-the-Medical-Transportation/6jna-snvk\n",
    "\n",
    "This data covers the demographics of Medical Transport Program by the Ryan White Grants\n",
    "## Obtaining the Data\n",
    "Using the pandas library we can easily import data from a given link or from a file on our computer (must know syntax for filepath). In this case we will give it a link."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Client ID</th>\n",
       "      <th>Age Range</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Education Level</th>\n",
       "      <th>Insurance</th>\n",
       "      <th>Race</th>\n",
       "      <th>Hispanic Ethnicity</th>\n",
       "      <th>Language Primary</th>\n",
       "      <th>Living Situation</th>\n",
       "      <th>31 - Day Metro Pass</th>\n",
       "      <th>...</th>\n",
       "      <th>Disability Fare Card</th>\n",
       "      <th>Gas Voucher</th>\n",
       "      <th>Metro ACCESS book</th>\n",
       "      <th>STS ticket</th>\n",
       "      <th>Taxi Voucher</th>\n",
       "      <th>Van/Car Ride</th>\n",
       "      <th>Agency</th>\n",
       "      <th>Grant Year</th>\n",
       "      <th>Grant Dates</th>\n",
       "      <th>Grant Name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>10015</td>\n",
       "      <td>61 - 70</td>\n",
       "      <td>Female</td>\n",
       "      <td>Some college education</td>\n",
       "      <td>Medi-Cal/Medicaid</td>\n",
       "      <td>White</td>\n",
       "      <td>False</td>\n",
       "      <td>English</td>\n",
       "      <td>Rental housing</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>43.0</td>\n",
       "      <td>Community Action</td>\n",
       "      <td>2013</td>\n",
       "      <td>1/1/2013-12/31/2013</td>\n",
       "      <td>Ryan White Part C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>10015</td>\n",
       "      <td>61 - 70</td>\n",
       "      <td>Female</td>\n",
       "      <td>Some college education</td>\n",
       "      <td>Medi-Cal/Medicaid</td>\n",
       "      <td>White</td>\n",
       "      <td>False</td>\n",
       "      <td>English</td>\n",
       "      <td>Rental housing</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>52.0</td>\n",
       "      <td>Community Action</td>\n",
       "      <td>2014</td>\n",
       "      <td>1/1/2014-12/31/2014</td>\n",
       "      <td>Ryan White Part C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>10015</td>\n",
       "      <td>61 - 70</td>\n",
       "      <td>Female</td>\n",
       "      <td>Some college education</td>\n",
       "      <td>Medi-Cal/Medicaid</td>\n",
       "      <td>White</td>\n",
       "      <td>False</td>\n",
       "      <td>English</td>\n",
       "      <td>Rental housing</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>36.0</td>\n",
       "      <td>Community Action</td>\n",
       "      <td>2015</td>\n",
       "      <td>1/1/2015-12/31/2015</td>\n",
       "      <td>Ryan White Part C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>10015</td>\n",
       "      <td>61 - 70</td>\n",
       "      <td>Female</td>\n",
       "      <td>Some college education</td>\n",
       "      <td>Medi-Cal/Medicaid</td>\n",
       "      <td>White</td>\n",
       "      <td>False</td>\n",
       "      <td>English</td>\n",
       "      <td>Rental housing</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>9.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>21.0</td>\n",
       "      <td>Community Action</td>\n",
       "      <td>2015</td>\n",
       "      <td>1/1/2015-12/31/2015</td>\n",
       "      <td>Ryan White Part C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>10015</td>\n",
       "      <td>61 - 70</td>\n",
       "      <td>Female</td>\n",
       "      <td>Some college education</td>\n",
       "      <td>Medi-Cal/Medicaid</td>\n",
       "      <td>White</td>\n",
       "      <td>False</td>\n",
       "      <td>English</td>\n",
       "      <td>Rental housing</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>9.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>21.0</td>\n",
       "      <td>Community Action</td>\n",
       "      <td>2016</td>\n",
       "      <td>1/1/2016-12/31/2016</td>\n",
       "      <td>Ryan White Part C</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 21 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   Client ID Age Range  Gender         Education Level          Insurance  \\\n",
       "0      10015   61 - 70  Female  Some college education  Medi-Cal/Medicaid   \n",
       "1      10015   61 - 70  Female  Some college education  Medi-Cal/Medicaid   \n",
       "2      10015   61 - 70  Female  Some college education  Medi-Cal/Medicaid   \n",
       "3      10015   61 - 70  Female  Some college education  Medi-Cal/Medicaid   \n",
       "4      10015   61 - 70  Female  Some college education  Medi-Cal/Medicaid   \n",
       "\n",
       "    Race  Hispanic Ethnicity Language Primary Living Situation  \\\n",
       "0  White               False          English   Rental housing   \n",
       "1  White               False          English   Rental housing   \n",
       "2  White               False          English   Rental housing   \n",
       "3  White               False          English   Rental housing   \n",
       "4  White               False          English   Rental housing   \n",
       "\n",
       "   31 - Day Metro Pass        ...          Disability Fare Card  Gas Voucher  \\\n",
       "0                  NaN        ...                           NaN          NaN   \n",
       "1                  NaN        ...                           NaN          NaN   \n",
       "2                  NaN        ...                           NaN          6.0   \n",
       "3                  NaN        ...                           NaN          9.0   \n",
       "4                  NaN        ...                           NaN          9.0   \n",
       "\n",
       "   Metro ACCESS book  STS ticket  Taxi Voucher  Van/Car Ride  \\\n",
       "0                NaN         NaN           NaN          43.0   \n",
       "1                NaN         NaN           NaN          52.0   \n",
       "2                NaN         NaN           NaN          36.0   \n",
       "3                NaN         NaN           NaN          21.0   \n",
       "4                NaN         NaN           NaN          21.0   \n",
       "\n",
       "             Agency Grant Year          Grant Dates         Grant Name  \n",
       "0  Community Action       2013  1/1/2013-12/31/2013  Ryan White Part C  \n",
       "1  Community Action       2014  1/1/2014-12/31/2014  Ryan White Part C  \n",
       "2  Community Action       2015  1/1/2015-12/31/2015  Ryan White Part C  \n",
       "3  Community Action       2015  1/1/2015-12/31/2015  Ryan White Part C  \n",
       "4  Community Action       2016  1/1/2016-12/31/2016  Ryan White Part C  \n",
       "\n",
       "[5 rows x 21 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd # import the module and alias it as pd\n",
    "\n",
    "data = pd.read_csv('data.csv')\n",
    "data.head() # show the first few rows of the data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Accessing your data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    10015\n",
       "1    10015\n",
       "2    10015\n",
       "3    10015\n",
       "4    10015\n",
       "5    10015\n",
       "6    10016\n",
       "7    10016\n",
       "8    10016\n",
       "Name: Client ID, dtype: int64"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data[\"Client ID\"][:9]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    10015\n",
       "1    10015\n",
       "2    10015\n",
       "3    10015\n",
       "4    10015\n",
       "5    10015\n",
       "6    10016\n",
       "7    10016\n",
       "8    10016\n",
       "9    10016\n",
       "Name: Client ID, dtype: int64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Better way using loc\n",
    "data.loc[:9,'Client ID']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Looking at all the columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Client ID', 'Age Range', 'Gender', 'Education Level', 'Insurance',\n",
       "       'Race', 'Hispanic Ethnicity', 'Language Primary', 'Living Situation',\n",
       "       '31 - Day Metro Pass', '31-day Metro Pass - REDUCED',\n",
       "       'Disability Fare Card', 'Gas Voucher', 'Metro ACCESS book',\n",
       "       'STS ticket', 'Taxi Voucher', 'Van/Car Ride', 'Agency', 'Grant Year',\n",
       "       'Grant Dates', 'Grant Name'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.columns"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Check Unique Values and Types"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ nan,   6.,   9.,   5.,  12.,   3.,  21.,  14.,   7.,  10.,   2.,\n",
       "        22.,  27.,   4.,  11.,  50.,  51.,  53.,  15.,   1.,   8.,  13.,\n",
       "        45.,  24.,  38.,  16.,  25.,  17.,  34.,  48.,  58.,  39.,  60.,\n",
       "        28.,  40.,  19.,  29.,  36.,  18.,  20.,  26.,  35.,  31.,  46.,\n",
       "        54.,  65.,  71.,  66.,  72., 101.,  41.,  78.,  32.,  44.])"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.loc[:,'Gas Voucher'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Client ID\t\t\t<class 'numpy.int64'>\n",
      "Age Range\t\t\t<class 'str'>\n",
      "Gender\t\t\t<class 'str'>\n",
      "Education Level\t\t\t<class 'str'>\n",
      "Insurance\t\t\t<class 'str'>\n",
      "Race\t\t\t<class 'str'>\n",
      "Hispanic Ethnicity\t\t\t<class 'numpy.bool_'>\n",
      "Language Primary\t\t\t<class 'str'>\n",
      "Living Situation\t\t\t<class 'str'>\n",
      "31 - Day Metro Pass\t\t\t<class 'numpy.float64'>\n",
      "31-day Metro Pass - REDUCED\t\t\t<class 'numpy.float64'>\n",
      "Disability Fare Card\t\t\t<class 'numpy.float64'>\n",
      "Gas Voucher\t\t\t<class 'numpy.float64'>\n",
      "Metro ACCESS book\t\t\t<class 'numpy.float64'>\n",
      "STS ticket\t\t\t<class 'numpy.float64'>\n",
      "Taxi Voucher\t\t\t<class 'numpy.float64'>\n",
      "Van/Car Ride\t\t\t<class 'numpy.float64'>\n",
      "Agency\t\t\t<class 'str'>\n",
      "Grant Year\t\t\t<class 'numpy.int64'>\n",
      "Grant Dates\t\t\t<class 'str'>\n",
      "Grant Name\t\t\t<class 'str'>\n"
     ]
    }
   ],
   "source": [
    "# quick way to look at all the types\n",
    "for x in data.columns:\n",
    "    print(x + \"\\t\\t\\t\" + str(type(data.loc[:,x].unique()[0])))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Accessing Data using Index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['White', 'Black', 'American Indian or Native Alaskan', 'Asian',\n",
       "       'Pacific Islander', 'Other'], dtype=object)"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.iloc[:,5].unique()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Structurally, Pandas dataframes are a collection of Series objects sharing a common index.  In general, the Series object and Dataframe object share a large number of functions with some behavioral differences.  In other words, whatever computation you can do on a single column can generally be applied to the entire dataframe.\n",
    "\n",
    "Now we can use the dataframe version of <code>describe</code> to get an overview of all of our data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Client ID</th>\n",
       "      <th>31 - Day Metro Pass</th>\n",
       "      <th>31-day Metro Pass - REDUCED</th>\n",
       "      <th>Disability Fare Card</th>\n",
       "      <th>Gas Voucher</th>\n",
       "      <th>Metro ACCESS book</th>\n",
       "      <th>STS ticket</th>\n",
       "      <th>Taxi Voucher</th>\n",
       "      <th>Van/Car Ride</th>\n",
       "      <th>Grant Year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>2015.000000</td>\n",
       "      <td>942.000000</td>\n",
       "      <td>397.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>613.000000</td>\n",
       "      <td>73.000000</td>\n",
       "      <td>185.000000</td>\n",
       "      <td>222.000000</td>\n",
       "      <td>272.000000</td>\n",
       "      <td>2015.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>10414.268486</td>\n",
       "      <td>3.795117</td>\n",
       "      <td>4.463476</td>\n",
       "      <td>1.0</td>\n",
       "      <td>10.823817</td>\n",
       "      <td>6.369863</td>\n",
       "      <td>5.637838</td>\n",
       "      <td>3.306306</td>\n",
       "      <td>13.158088</td>\n",
       "      <td>2014.970720</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>255.210000</td>\n",
       "      <td>3.585521</td>\n",
       "      <td>3.608604</td>\n",
       "      <td>NaN</td>\n",
       "      <td>12.656405</td>\n",
       "      <td>6.417223</td>\n",
       "      <td>5.570075</td>\n",
       "      <td>3.820149</td>\n",
       "      <td>14.325706</td>\n",
       "      <td>1.391075</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>10012.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2013.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>10191.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>2014.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>10396.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>2015.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>10624.500000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>13.000000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>9.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>18.000000</td>\n",
       "      <td>2016.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>10909.000000</td>\n",
       "      <td>32.000000</td>\n",
       "      <td>24.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>101.000000</td>\n",
       "      <td>25.000000</td>\n",
       "      <td>29.000000</td>\n",
       "      <td>21.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>2017.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          Client ID  31 - Day Metro Pass  31-day Metro Pass - REDUCED  \\\n",
       "count   2015.000000           942.000000                   397.000000   \n",
       "mean   10414.268486             3.795117                     4.463476   \n",
       "std      255.210000             3.585521                     3.608604   \n",
       "min    10012.000000             1.000000                     1.000000   \n",
       "25%    10191.000000             1.000000                     1.000000   \n",
       "50%    10396.000000             2.000000                     3.000000   \n",
       "75%    10624.500000             5.000000                     8.000000   \n",
       "max    10909.000000            32.000000                    24.000000   \n",
       "\n",
       "       Disability Fare Card  Gas Voucher  Metro ACCESS book  STS ticket  \\\n",
       "count                   1.0   613.000000          73.000000  185.000000   \n",
       "mean                    1.0    10.823817           6.369863    5.637838   \n",
       "std                     NaN    12.656405           6.417223    5.570075   \n",
       "min                     1.0     1.000000           1.000000    1.000000   \n",
       "25%                     1.0     3.000000           1.000000    1.000000   \n",
       "50%                     1.0     7.000000           3.000000    3.000000   \n",
       "75%                     1.0    13.000000          10.000000    9.000000   \n",
       "max                     1.0   101.000000          25.000000   29.000000   \n",
       "\n",
       "       Taxi Voucher  Van/Car Ride   Grant Year  \n",
       "count    222.000000    272.000000  2015.000000  \n",
       "mean       3.306306     13.158088  2014.970720  \n",
       "std        3.820149     14.325706     1.391075  \n",
       "min        1.000000      1.000000  2013.000000  \n",
       "25%        1.000000      4.000000  2014.000000  \n",
       "50%        2.000000      8.000000  2015.000000  \n",
       "75%        3.000000     18.000000  2016.000000  \n",
       "max       21.000000    100.000000  2017.000000  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "## Visualizing the Data and EDA\n",
    "Another important tool in the data scientist's toolbox is the ability to create visualizations from data.  Visualizing data is often the most logical place to start getting a deeper intuition of the data.  This intuition will shape and drive your analysis.\n",
    "\n",
    "Even more important than visualizing data for your own personal benefit, it is often the job of the data scientist to use the data to tell a story.  Creating illustrative visuals that succinctly convey an idea are the best way to tell that story, especially to stakeholders with less technical skillsets.\n",
    "\n",
    "We'll be using the plotting library matplotlib, which stands for mathematical plotting library. It is the most widely used plotting library, and has a few other packages built on top of it (like a library called seaborn) to make your plots even more beautiful and easy to use. \n",
    "\n",
    "We'll start by doing a bit of setup."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "#importing matplotlib library with an alias as well as the seaborn library\n",
    "import matplotlib.pyplot as plt \n",
    "import seaborn as sns\n",
    "\n",
    "sns.set(style = 'darkgrid', color_codes = True)   # my personal style preferences\n",
    "\n",
    "# hack to make seaborn plots bigger on jupyter notebooks\n",
    "def setPlt(x = 25, y = 15):\n",
    "    f, ax = plt.subplots(figsize = (x,y))\n",
    "    sns.despine(f, left = True, bottom = True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "If the above does not work please follow these steps:\n",
    "\n",
    "MAC\n",
    "\n",
    "-Open terminal and type <code>conda remove seaborn</code> and press Enter. \n",
    "    \n",
    "-Then type <code>conda install seaborn==0.9.0</code>\n",
    "\n",
    "    \n",
    "Windows\n",
    "\n",
    "-Open Anaconda Prompt (Press Windows button and type \"Anaconda Prompt\")\n",
    "    \n",
    "-Type <code>conda remove seaborn</code>\n",
    "    \n",
    "-Then type <code>conda install seaborn==0.9.0</code>\n",
    "\n",
    "You may need to restart anaconda "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Lets look at at amount of gas vouchers given out."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABasAAAJVCAYAAADQuKkbAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvhp/UCwAAIABJREFUeJzs3X2w5mdd3/HP5pz7PieLy55NWU1iKkojl9iW0Cq2U22hGg0RNCCJKA8aKCi2WDtWrK0gD7Wdgp3ooBYsEFFTJHTDkyQEp9HqWIVOreCMmKt0JrYy2Q5rs7uespw9ZzfbP85JPHmCk+X3u7/n4fWaYXLfv3Pv97ruk0yGvOc312/fuXPnAgAAAAAAlS6o3gAAAAAAAIjVAAAAAACUE6sBAAAAACgnVgMAAAAAUE6sBgAAAACgnFgNAAAAAEA5sRoAAAAAgHJiNQAAAAAA5cRqAAAAAADKidUAAAAAAJQTqwEAAAAAKCdWAwAAAABQbr56A4/GsWPL56r3AAAAAADA53b48IF9j/bPuLMaAAAAAIByYjUAAAAAAOXEagAAAAAAyonVAAAAAACUE6sBAAAAACgnVgMAAAAAUE6sBgAAAACgnFgNAAAAAEA5sRoAAAAAgHJiNQAAAAAA5cRqAAAAAADKidUAAAAAAJQTqwEAAAAAKCdWAwAAAABQTqwGAAAAAKCcWA0AAAAAQDmxGgAAAACAcmI1AAAAAADlxGoAAAAAAMqJ1QAAAAAAlBOrAQAAAAAoJ1YDAAAAAFBOrAYAAAAAoJxYDQAAAABAObEaAAAAAIBy89Ub2O4uOriYuelk0JlnV9dyz8mVQWcCAAAAAOxkYvXnMTed5Nhb3jrozMMvf1kSsRoAAAAA4D6OAQEAAAAAoJxYDQAAAABAObEaAAAAAIByYjUAAAAAAOXEagAAAAAAyonVAAAAAACUE6sBAAAAACgnVgMAAAAAUE6sBgAAAACgnFgNAAAAAEA5sRoAAAAAgHJiNQAAAAAA5cRqAAAAAADKidUAAAAAAJQTqwEAAAAAKCdWAwAAAABQTqwGAAAAAKCcWA0AAAAAQDmxGgAAAACAcmI1AAAAAADlxGoAAAAAAMqJ1QAAAAAAlBOrAQAAAAAoJ1YDAAAAAFBOrAYAAAAAoNz8mMNbay9M8s833n6o9/4jrbWnJHlbkscm+e0kL++9nxlzHwAAAAAAbG+j3VndWtuf5E1JnpbkiiR/t7V2ZZKbkryi9/7EJPuSvGysPQAAAAAAsDOMeQzI3Mb8xySZbPxvLcmFvfePbHzmHUmuG3EPAAAAAADsAKMdA9J7X26tvTrJnUlOJfmtJKtJjm762NEkl2115qFD+zM/PzfoPqscPnygegsAAAAAANvGaLG6tfbkJC9J8vgkJ7N+/Me3JDm36WP7kty71ZnHj58acotbMlZUPnZseZS5AAAAAADVzqerjnkMyFVJ7ui9f7r3fjrrR348Pcklmz5zcZK7R9wDAAAAAAA7wJix+uNJrmytPaa1ti/Jt2X9KJCV1trXb3zmRUk+NOIeAAAAAADYAUaL1b33X0/yq0l+P8kfZv0Bi/8myQuS/HRr7c4kX5TkTWPtAQAAAACAnWG0M6uTpPf+hiRveNDljyf5ujHXBQAAAABgZxnzGBAAAAAAANgSsRoAAAAAgHJiNQAAAAAA5cRqAAAAAADKidUAAAAAAJQTqwEAAAAAKCdWAwAAAABQTqwGAAAAAKCcWA0AAAAAQDmxGgAAAACAcmI1AAAAAADlxGoAAAAAAMqJ1QAAAAAAlBOrAQAAAAAoJ1YDAAAAAFBOrAYAAAAAoJxYDQAAAABAObEaAAAAAIByYjUAAAAAAOXEagAAAAAAyonVAAAAAACUE6sBAAAAACgnVgMAAAAAUE6sBgAAAACgnFgNAAAAAEA5sRoAAAAAgHJiNQAAAAAA5cRqAAAAAADKidUAAAAAAJQTqwEAAAAAKCdWAwAAAABQTqwGAAAAAKCcWA0AAAAAQDmxGgAAAACAcmI1AAAAAADlxGoAAAAAAMqJ1QAAAAAAlBOrAQAAAAAoJ1YDAAAAAFBOrAYAAAAAoJxYDQAAAABAObEaAAAAAIByYjUAAAAAAOXEagAAAAAAyonVAAAAAACUE6sBAAAAACgnVgMAAAAAUE6sBgAAAACgnFgNAAAAAEA5sRoAAAAAgHJiNQAAAAAA5ebHGtxae2mSV2y69BVJfiXJ+5LckOTCJDf33l811h4AAAAAANgZRruzuvf+tt77U3rvT0nygiSfTvKGJDcmuSbJk5I8tbV29Vh7AAAAAABgZ5jVMSBvTvIvkjwhySd773f13s8kuSnJdTPaAwAAAAAA29Tosbq1dmWSC3vv/zHJpUmObvrx0SSXjb0HAAAAAAC2t9HOrN7k+7N+RnWyHsfPbfrZviT3bnXQoUP7Mz8/N+DW6hw+fKB6CwAAAAAA28aosbq1Nk3ytCTXb1z6VJJLNn3k4iR3b3Xe8eOnBtvbVo0VlY8dWx5lLgAAAABAtfPpqmPfWf3kJP+j9/6ZjfcfTdJaa5cnuSvJ87P+wEUAAAAAAPawsc+sfkLW76ZOkvTeV7J+l/UtST6R5M4kR0beAwAAAAAA29yod1b33t+d5N0PunZHkivGXBcAAAAAgJ1l7DurAQAAAADg8xKrAQAAAAAoJ1YDAAAAAFBOrAYAAAAAoJxYDQAAAABAObEaAAAAAIByYjUAAAAAAOXEagAAAAAAyonVAAAAAACUE6sBAAAAACgnVgMAAAAAUE6sBgAAAACgnFgNAAAAAEA5sRoAAAAAgHJiNQAAAAAA5cRqAAAAAADKidUAAAAAAJQTqwEAAAAAKCdWAwAAAABQTqwGAAAAAKCcWA0AAAAAQDmxGgAAAACAcmI1AAAAAADlxGoAAAAAAMqJ1QAAAAAAlBOrAQAAAAAoJ1YDAAAAAFBOrAYAAAAAoJxYDQAAAABAObEaAAAAAIByYjUAAAAAAOXEagAAAAAAyonVAAAAAACUE6sBAAAAACgnVgMAAAAAUE6sBgAAAACgnFgNAAAAAEA5sRoAAAAAgHJiNQAAAAAA5cRqAAAAAADKidUAAAAAAJQTqwEAAAAAKCdWAwAAAABQTqwGAAAAAKDcfPUGztdFBxczN50MOvPs6lruObky6EwAAAAAAD6/HRur56aTHHvzTYPOPPwDL0wiVgMAAAAAzJpjQAAAAAAAKCdWAwAAAABQTqwGAAAAAKCcWA0AAAAAQDmxGgAAAACAcmI1AAAAAADl5scc3lr7tiSvSfKYJL/ee/+h1tqVSW5IcmGSm3vvrxpzDwAAAAAAbH+j3VndWntCkrckeXaSJyf5m621q5PcmOSaJE9K8tSNawAAAAAA7GFjHgPynKzfOf2p3vtakuclOZXkk733u3rvZ5LclOS6EfcAAAAAAMAOMOYxIJcnWW2tfSDJlyX5YJI/SnJ002eOJrlsxD0AAAAAALADjBmr55P8vSRPT/L/knwgyWeTnNv0mX1J7t3qwEOH9md+fm7ALT7U4cMHRp0/63UAAAAAAHaCMWP1/0nyn3rvx5KktfberB/5cXbTZy5OcvdWBx4/fur+12PF3mPHlh/wflbrAAAAAADsFufTVceM1R9M8kuttaUky0muTnIkyY+11i5PcleS52f9gYsAAAAAAOxhoz1gsff+0SRvTPI7ST6R5H8leXOS65PcsnHtzqwHbAAAAAAA9rAx76xO7/3GPPTO6TuSXDHmugAAAAAA7Cyj3VkNAAAAAABbJVYDAAAAAFBOrAYAAAAAoJxYDQAAAABAObEaAAAAAIByYjUAAAAAAOXEagAAAAAAyonVAAAAAACUE6sBAAAAACgnVgMAAAAAUE6sBgAAAACgnFgNAAAAAEA5sRoAAAAAgHJiNQAAAAAA5cRqAAAAAADKidUAAAAAAJQTqwEAAAAAKCdWAwAAAABQTqwGAAAAAKCcWA0AAAAAQDmxGgAAAACAcmI1AAAAAADlxGoAAAAAAMqJ1QAAAAAAlBOrAQAAAAAoJ1YDAAAAAFBOrAYAAAAAoJxYDQAAAABAObEaAAAAAIByYjUAAAAAAOXEagAAAAAAyonVAAAAAACUE6sBAAAAACgnVgMAAAAAUE6sBgAAAACgnFgNAAAAAEA5sRoAAAAAgHJiNQAAAAAA5cRqAAAAAADKidUAAAAAAJQTqwEAAAAAKCdWAwAAAABQTqwGAAAAAKCcWA0AAAAAQDmxGgAAAACAcmI1AAAAAADlxGoAAAAAAMqJ1QAAAAAAlBOrAQAAAAAoJ1YDAAAAAFBuvnoDzN5FBxcyN50OOvPs6mruOXl60JkAAAAAwN4hVu9Bc9Npjv67Vw8685J/+C+TiNUAAAAAwPkZNVa31n4zyRcnWdu49P1J/kqSVyWZJPmZ3vvPj7kHAAAAAAC2v9FidWttX5InJnl87/3MxrUvTfKuJF+T9dtwf7e19pu990+MtQ8AAAAAALa/Me+sbht//fXW2l9K8tYky0l+o/d+T5K01o4kuTbJ60fcBwAAAAAA29wFI84+lOSOJM9J8k1JXp7ky5Ic3fSZo0kuG3EPAAAAAADsAKPdWd17/70kv3ff+9ba25PckOQnN31sX5J7tzrz0KH9mZ+fG2yPD+fw4QOjzp/1OrO0G78TAAAAADAbY55Z/Q1JFnrvd2xc2pfkT5JcsuljFye5e6szjx8/df/rscLosWPLD3g/q3VmaTd+JwAAAABg+zifBjnmmdVLSV7fWvs7SSZJvjfJC5Pc1Fo7nOQzSZ6b5PtG3AMAAAAAADvAaGdW994/mOTWJH+Q5PeT3Nh7/y9JfjzJbyb5WJJ39t7/61h7AAAAAABgZxjzzur03l+d5NUPuvbOJO8cc10AAAAAAHaW0e6sBgAAAACArRKrAQAAAAAoJ1YDAAAAAFBOrAYAAAAAoJxYDQAAAABAObEaAAAAAIByYjUAAAAAAOXEagAAAAAAyonVAAAAAACUE6sBAAAAACgnVgMAAAAAUE6sBgAAAACgnFgNAAAAAEA5sRoAAAAAgHJiNQAAAAAA5bYUq1trX/ow1756+O0AAAAAALAXzX+uH7bWLtp4eVtr7elJ9m28nyR5T5KvGm9rAAAAAADsFZ8zVif51STfvPH6/266fibJkVF2BAAAAADAnvM5Y3Xv/aokaa3d2Ht/yWy2BAAAAADAXvP57qxOkvTeX9Jae3ySi/IXR4Gk9/7fx9oYAAAAAAB7x5ZidWvtdUlemeTTSc5tXD6X5Akj7QsAAAAAgD1kS7E6yfckubz3fveYmwEAAAAAYG+6YIuf+1OhGgAAAACAsWz1zuo7WmtvTPL+JJ+976IzqwEAAAAAGMJWY/X1G3+9btM1Z1YDAAAAADCILcXq3vtXjL0RAAAAAAD2ri3F6tbaDz/c9d77DcNuBwAAAACAvWirx4D89U2vp0meluSO4bcDAAAAAMBetNVjQF68+X1r7dIkbx9lRwAAAAAA7DkXnM8f6r3fneTLh90KAAAAAAB71fmcWb0vydcm+fQoOwIAAAAAYM85nzOrzyX530leOfx2AAAAAADYix7VmdWttccnmfTe/+eouwIAAAAAYE/Z6jEglyd5f5JLk1zQWvuzJM/qvf/xmJsDAAAAAGBv2OoDFn8uyRt774d67weT/GSSnx9vWwAAAAAA7CVbjdVf0nv/pfve9N5/McnhcbYEAAAAAMBes9VYPd9au+i+N621x2X9QYsAAAAAAPAF29KZ1Ul+NslHWms3Zz1Sf1eSnx5tVwAAAAAA7ClbvbP6tqxH6mmSr07ypUneO9amAAAAAADYW7Yaq9+R5Od77/8syQuT/HiSG8faFAAAAAAAe8tWY/Xjeu9vSpLe+0rv/WeSXDLetgAAAAAA2EsezQMWL73vTWvtS5LsG2dLAAAAAADsNVt9wOINST7WWrs962dXX5nklaPtCgAAAACAPWVLd1b33m/MeqD+gyT/LclVvfd3jrkxAAAAAAD2jq3eWZ3e+x8m+cMR9wIAAAAAwB611TOrAQAAAABgNGI1AAAAAADlxGoAAAAAAMqJ1QAAAAAAlBOrAQAAAAAoJ1YDAAAAAFBOrAYAAAAAoNz82Au01v5tksf13q9vrT0lyduSPDbJbyd5ee/9zNh7AAAAAABgexv1zurW2jcl+d5Nl25K8ore+xOT7EvysjHXBwAAAABgZxgtVrfWLkryr5L86433j09yYe/9IxsfeUeS68ZaHwAAAACAnWPMO6t/IcmPJzm+8f7SJEc3/fxokstGXB8AAAAAgB1ilDOrW2svTfKnvfc7WmvXb1y+IMm5TR/bl+TeRzP30KH9mZ+fG2aTj+Dw4QOjzp/1OrO0G78TAAAAADAbYz1g8XlJLmmtfSzJRUm+KOuh+pJNn7k4yd2PZujx46fufz1WGD12bPkB72e1ziztxu8EAAAAAGwf59MgRzkGpPf+zb33v9Z7f0qSn0jygd77i5OstNa+fuNjL0ryoTHWBwAAAABgZxnzzOqH84IkP91auzPrd1u/acbrAwAAAACwDY11DMj9eu/vSPKOjdcfT/J1Y68JAAAAAMDOMus7qwEAAAAA4CFGv7Maxnbo4DTz04VBZ55ZPZ3jJ1cHnQkAAAAAPDKxmh1vfrqQT/7cNYPO/MpXvD+JWA0AAAAAs+IYEAAAAAAAyonVAAAAAACUE6sBAAAAACgnVgMAAAAAUE6sBgAAAACgnFgNAAAAAEA5sRoAAAAAgHJiNQAAAAAA5cRqAAAAAADKidUAAAAAAJSbr94A6y46uJi56WTQmWdX13LPyZVBZwIAAAAAjEGs3ibmppN8+i03DDrzi1/+w0nEagAAAABg+3MMCAAAAAAA5cRqAAAAAADKidUAAAAAAJQTqwEAAAAAKCdWAwAAAABQTqwGAAAAAKCcWA0AAAAAQDmxGgAAAACAcmI1AAAAAADlxGoAAAAAAMqJ1QAAAAAAlBOrAQAAAAAoJ1YDAAAAAFBOrAYAAAAAoJxYDQAAAABAObEaAAAAAIByYjUAAAAAAOXEagAAAAAAyonVAAAAAACUE6sBAAAAACgnVgMAAAAAUE6sBgAAAACgnFgNAAAAAEA5sRoAAAAAgHJiNQAAAAAA5cRqAAAAAADKidUAAAAAAJQTqwEAAAAAKCdWAwAAAABQTqwGAAAAAKCcWA0AAAAAQDmxGgAAAACAcmI1AAAAAADlxGoAAAAAAMrNV28AeKhDB6eZny4MOvPM6ukcP7k66EwAAAAAGIpYDdvQ/HQhH/n3zxp05t/+vg8mEasBAAAA2J4cAwIAAAAAQLlR76xurb0+ybVJziV5e+/9htbalUluSHJhkpt7768acw8AAAAAAGx/o91Z3Vp7WpJvTPLkJF+b5Adba1ckuTHJNUmelOSprbWrx9oDAAAAAAA7w2ixuvf+W0n+fu/9TJIvzvpd3EtJPtl7v2vj+k1JrhtrDwAAAAAA7Ayjnlnde19rrb0uySeS3JHk0iRHN33kaJLLxtwDAAAAAADb36hnVidJ7/01rbU3JPm1JE/M+vnV99mX5N6tzjp0aH/m5+cG3uEDHT58YNT5u3WdWa81Cw/3fe49s5oL5qeDrjPGzEey2/4eAQAAALB7jBarW2tflWSx9/6x3vup1tp7sv6wxbObPnZxkru3OvP48VP3vx4ruh07tvyA97ttnVmvNQuz/t19/M3fPug6V/zAB0r/eQAAAACAoZ1P3xrzzuonJHlda+0bsn439TVJfiHJT7XWLk9yV5LnZ/2BiwAAAAAA7GFjPmDxtiS3JvmDJL+f5Hd77+9Kcn2SW7J+jvWdSY6MtQcAAAAAAHaGUc+s7r2/NslrH3TtjiRXjLkuAAAAAAA7y2h3VgMAAAAAwFaJ1QAAAAAAlBOrAQAAAAAoJ1YDAAAAAFBOrAYAAAAAoJxYDQAAAABAObEaAAAAAIByYjUAAAAAAOXEagAAAAAAyonVAAAAAACUE6sBAAAAACgnVgMAAAAAUE6sBgAAAACg3Hz1BoC9YengNJPpwqAz11ZP58TJ1UFnAgAAAFBDrAZmYjJdyO1v/9ZBZz7jH9yWRKwGAAAA2A0cAwIAAAAAQDmxGgAAAACAcmI1AAAAAADlxGoAAAAAAMp5wCKjuejgNHPThUFnnl09nXtOeqAeAAAAAOw2YjWjmZsu5FM/99JBZ172irclEasBAAAAYLdxDAgAAAAAAOXEagAAAAAAyonVAAAAAACUE6sBAAAAACgnVgMAAAAAUE6sBgAAAACgnFgNAAAAAEA5sRoAAAAAgHJiNQAAAAAA5cRqAAAAAADKzVdvAKhz6OA089OFQWeeWT2d4ydXB50JAAAAwO4nVsMeNj9dyH9+6zMHnfn0l92aRKwGAAAA4NFxDAgAAAAAAOXEagAAAAAAyonVAAAAAACUE6sBAAAAACgnVgMAAAAAUE6sBgAAAACgnFgNAAAAAEA5sRoAAAAAgHJiNQAAAAAA5cRqAAAAAADKidUAAAAAAJQTqwEAAAAAKCdWAwAAAABQTqwGAAAAAKCcWA0AAAAAQDmxGgAAAACAcvPVGwDYiZYOTjOZLgw6c231dE6cXB10JgAAAMBOIVYDnIfJdCE3/+IzBp35vBffnkSsBgAAAPYmx4AAAAAAAFBu1DurW2uvSfKdG29v7b3/aGvtyiQ3JLkwyc2991eNuQcAAAAAALa/0e6s3ojS35LkbyR5SpKvaa19d5Ibk1yT5ElJntpau3qsPQAAAAAAsDOMeQzI0ST/tPe+2ntfS/LHSZ6Y5JO997t672eS3JTkuhH3AAAAAADADjDaMSC99z+673Vr7SuzfhzIz2Y9Yt/naJLLtjrz0KH9mZ+fG2yPD+fw4QOjzt+t68xyrd22zizX2m3rzHqtWdht3wcAAABgq0Y9szpJWmt/NcmtSV6Z5EzW766+z74k92511vHjp+5/PVbQOXZs+QHvd9s6s1xrt60zy7V22zqzXmsWdtv3AQAAABjS+bSTMY8BSWvt65PckeTHeu+/lORTSS7Z9JGLk9w95h4AAAAAANj+RruzurX2l5O8L8nzeu+/sXH5o+s/apcnuSvJ87P+wEUAAAAAAPawMY8B+ZEki0luaK3dd+0tSa5PcsvGz25LcmTEPQAAAAAAsAOM+YDFH0ryQ4/w4yvGWhcAAAAAgJ1n1DOrAQAAAABgK8Y8BgSAASwtTTKZLA46c21tJSdOrA06EwAAAOALIVYDbHOTyWJ++R1XDTrze67/cBKxGgAAANg+HAMCAAAAAEA5sRoAAAAAgHJiNQAAAAAA5cRqAAAAAADKidUAAAAAAJQTqwEAAAAAKCdWAwAAAABQTqwGAAAAAKCcWA0AAAAAQDmxGgAAAACAcmI1AAAAAADlxGoAAAAAAMqJ1QAAAAAAlBOrAQAAAAAoJ1YDAAAAAFBOrAYAAAAAoJxYDQAAAABAObEaAAAAAIByYjUAAAAAAOXEagAAAAAAyonVAAAAAACUE6sBAAAAACg3X70BgCEtHZxmMl0YdOba6umcOLk66EwAAAAAHkisBnaVyXQh77/x6kFnXvOSDyURqwEAAADG5BgQAAAAAADKidUAAAAAAJQTqwEAAAAAKCdWAwAAAABQTqwGAAAAAKCcWA0AAAAAQDmxGgAAAACAcmI1AAAAAADlxGoAAAAAAMqJ1QAAAAAAlJuv3gAA28PBpUmmk8VBZ66ureTkibVBZz4au/E7AQAAwG4lVgOQJJlOFvPWX75q0Jkv+54PJ6kLu9PJYt74q8N+px/97trvBAAAALuVY0AAAAAAACgnVgMAAAAAUE6sBgAAAACgnFgNAAAAAEA5sRoAAAAAgHJiNQAAAAAA5cRqAAAAAADKidUAAAAAAJQTqwEAAAAAKCdWAwAAAABQTqwGAAAAAKCcWA0AAAAAQDmxGgAAAACAcvNjL9Bae2yS303yrN77n7TWrkxyQ5ILk9zce3/V2HsAAAAAAGB7G/XO6tba30ryO0meuPH+wiQ3JrkmyZOSPLW1dvWYewAAAAAAYPsb+xiQlyX5R0nu3nj/dUk+2Xu/q/d+JslNSa4beQ8AAAAAAGxzox4D0nt/aZK01u67dGmSo5s+cjTJZVudd+jQ/szPzw22v4dz+PCBUefv1nVmudZuW2eWa+22dWa51m5bZ5ZrPXidM2dXMz83HXSNMWZ+LrP8+wQAAAB7xehnVj/IBUnObXq/L8m9W/3Dx4+fuv/1WKHg2LHlB7zfbevMcq3dts4s19pt68xyrd22zizXmuU6P/sfrhp0jR98wYdLf3cAAADAA53Pf5OPfQzIg30qySWb3l+cvzgiBAAAAACAPWrWd1Z/NElrrV2e5K4kz8/6AxcBAAAAANjDZnpnde99Jcn1SW5J8okkdyY5Mss9AAAAAACw/czkzure+5dven1HkitmsS4AAAAAADvDrM+sBgAAAACAhxCrAQAAAAAoJ1YDAAAAAFBOrAYAAAAAoJxYDQAAAABAObEaAAAAAIByYjUAAAAAAOXEagAAAAAAyonVAAAAAACUE6sBAAAAACgnVgMAAAAAUE6sBgAAAACgnFgNAAAAAEC5+eoNAMBO99ilaRYmC4POPL12On9+YnXQmdvRgaVpFgf+3a2snc7yHvjdcf4OLC1mcTIZdObK2lqWT6yUrAMAALuFWA0AX6CFyUJe8+5nDDrzdd95e5LdH1wXJwu5+v0vHnTmh675xSzvgd8d529xMsmzbrlx0JkffO5LspwHRuTFySTPOvIrw65z7Ysesg4AAOwWjgEBAAAAAKCcWA0AAAAAQDmxGgAAAACAcmI1AAAAAADlPGARAHiAA0vTLE4WBp+7snY6yyd294MPDywtZHEyHXTmytpqlk+cHnTmdnRgaTGLk8mgM1fW1rJ8wsMIAQBgpxCrAYAHWJws5Hnve8bgc29+9u1Zzu6O1YuTab71va8fdOZtz/mJLGf3x+rFySTPvOUtg8689bkvz3LEagAA2CkcAwIAAAAAQDmxGgAAAACAcmI1AAAAAADlxGoAAAAAAMp5wCIA7BCPXZpmYbIw6MzTa6fz5yd290MPk+TA0kIWJ9NBZ66srWb5xO5/8CHsZgckLEIfAAAciElEQVSWLsziZNj/JFpZO5PlE58ddCYAwF4hVgPADrEwWcg/ueUZg878mefenmT3x+rFyTTf+r5XDjrztmf/VJYjVsNOtjiZzzVHbh905vuvfUaWB50IALB3OAYEAAAAAIByYjUAAAAAAOXEagAAAAAAyonVAAAAAACU84BFAIAd6MDSYhYnk0FnrqytZfnEyqAzgXUHli7M4mTY//xaWTuT5ROfHXQmAEAlsRoAYAdanEzyzPf+1KAzb33OK7McsRrGsDiZz7OP/MagM9937TdmedCJAAC1HAMCAAAAAEA5sRoAAAAAgHJiNQAAAAAA5cRqAAAAAADKecAiAAAA29aBpf1ZnMwNOnNl7WyWT5wadOZWHVzan+nA32d17WxOFn2fJFlaekwmk2HvhVtbuzcnTnxm0JmPxm78TgA7gVgNAADAtrU4mct33vLHg85893OflOVBJ27ddDKX17737kFnvvY5lw4679GaTC7Ir7zn2KAzX/Qdhwed92hNJhfkw+/6s0FnXvVdjxt0HsBu5BgQAAAAAADKidUAAAAAAJQTqwEAAAAAKCdWAwAAAABQzgMWAQB4RAeWFrM4mQw6c2VtLcsnVgaduZcdWLowi5Nh/2/9ytqZLJ/4bNlas/xOu43f3fl77NL+LEzmBp15eu1s/vzEqUFnwvk4dPAxmZ8Oe7/imdV7c/zkZwadye5y0cH9mZsO++/Vs6tnc89J/17dzcRqAAAe0eJkkme+502Dzrz1O/5xliNWD2VxMp9nHXnXoDM/eO13ZfkR1vq2I0cGXevXrr32IWstTubz7Uc+MOg6H7j22x/2O+02i5P/3959h8tR1X8cfyf33iQQIKE3iYDAl06E0EH4SVBpUiUKIhhiQJqFIiUgRQIPCNIUeajSQUBFQA1V6QhKkfJVBAtSlSo1JPn9cc4Ne+ee2Xt398zdmHxez8ND7u7MfPbMzJlz5uzMbCc7XHt31mVet+OGc8S6G9rVwfjr/pF1mRfsMCrr8kSa1TlkMA9e8HLWZY4Zv0jW5cnsp2NIBy+d9vusy1z0m2tnXZ7MevQYEBERERERERERERFpOw1Wi4iIiIiIiIiIiEjbabBaRERERERERERERNpOg9UiIiIiIiIiIiIi0nb6gUURERERERFpyLwj52ZYV0fWZb43dRpvvf5O1mXO6UaMHM6QrrzXqH0wdTpvvP521mX218iRw+nKXJ6pU6fzepvKAzD/yOF0Zi7Th1On81qbyjT/iOF0Dsl/XeSHH0zntTd6lqmKrFTOAiPmpmNI3uPdtA+m8eobPY93VeQMZFYqZ6AsMGIuOobkHeKc9sGHvPrGu23Lmt1yGqHBahEREREREWnIsK4Odrr2oazLvGbHtXgr6xJlSNdgzvzZS1mXuf/2i2ZdXiO6ugbz82v+nXWZ2+20UNblNaqzazB3XvJK1mVuvNvCWZfXiM4hg3n8nLz7HMAqe/Xe7zqHDOaZ01/MmrPsNxbr9VrHkA5eOOn5rDmLH7JEMufF7z+dNQdgsYOWS2ed+ljenG+vlnV5jegY0slLZ9yVdZmLHrBRadbLZ96SNWuR/cemc866MW/Oflulc354Xd6cfXdoaX49BkRERERERERERERE2q4tV1ab2S7AJKALOM3df9iOzyEiIiIiIiIiIiIis4YBv7LazJYEjgc2AkYDE81s5YH+HCIiIiIiIiIiIiIy62jHY0DGAre5+6vu/jZwDbBTGz6HiIiIiIiIiIiIiMwiBs2YMWNAA83sMGC4u0+Kf08A1nH3iQP6QURERERERERERERkltGOK6sHA7Uj5IOA6W34HCIiIiIiIiIiIiIyi2jHYPVzwOI1fy8GPN+GzyEiIiIiIiIiIiIis4jONmTeAhxtZgsDbwM7AnoEiIiIiIiIiIiIiMgcbMCvrHb3fwFHALcDDwOXu/sDA/05RERERERERERERGTWMeA/sCgiIiIiIiIiIiIiUtSOZ1aLiIiIiIiIiIiIiPSgwWoRERERERERERERaTsNVouIiIiIiIiIiIhI22mwWkRERERERERERETarrPdHyAnM5sPuAfY2t3/VnhvNHAeMB/wO2Bvd/+wiYzvAjvHP29090OqyInLOhbYCZgBnO/up1aVFZf3fWAhd9+j8Poo4FJgEcCBXd39v00s//a4jKnxpb3c/f6a98cCpwJzAVe5+6RmyhGXtQ3wXWA4MMXdv1F4v+V1Z2YTgP1qXloGuMTd96uZJtd+92XgsPjnr9z9oML7WbZRXNahwFeB9wnb4ficWcV62p/t3kxm6nhgZl3Ar4Hj3P2OKnLMbCJwAKHePkjYzz9oNack6+uEfXAQcCNwiLvPKMyTZd3F1/cDdnL3TRPzjAQuA5YFXgF2dvcXGyzPhcBGwNtxkmPc/WeFeRquU4mc9YEfAPMCjwK7V7GNgJWByTVvLwnc7+5bt5qVKNNngJOBDuAPwIREmXJsoz2AQ4BpwG3AgcX132ROr7a1imNDWRte0bEhVabsx4d6/ZKcdbakPNnrbElOJXW2mAXcQQV1tqRM2etsSc4eVFNnk33U3HUplVNVO1uv3525LqXKVEVdSuVkr0slOVW1SamsPahgH4/zzTw36s/6z5FT89rFwG3uflFi+pw5WwFnufsyiemHAOcDY4B3gV3c/am+copZ8dg0Hngtvn2uu/+wMH2z/a7aHAPOAeYHXgS+6O6vFabPsS+sGXOGAP8Evuzurxemb3jdpc6VgU8Ak4Au4LTieovzNXpsSJ6T1xtLaSanTpm2os4YR84yxfeSYxzxvUaPd6nyLE+d8/RmcuI8vcYzKuobp3KqaJNSOVW0SaVjNDn7KGU5sRzZ+ih1cq4nUzvb6PhMFe1TymxzZbWZrQvcBaxQMsmlwH7uvgJhYOdrTWSMBT4DfBIYDaxlZtvnzolZmwCfBlYnNHL7xwY4e1bM2wzYveTtHwE/cvcVCRXuyCaWP4iwbdZw99Hxv9qB6rmAC4BtgZWAtc1si0Zz4rKWBX4MbEdYf2smltXyunP387rLAuwKvAwcnTvHzOYGzgA2AdYANo77Yq2Wt1HMGgvsAqxN2M/XNbMdcmUV62kD272hzNTxINafO4AN6szaUo6ZrQAcHDNWJxxj9201pyRrGeDbwDrAajFz89xlqnl9ZeDQOrN+D7jT3VcCzgVObyJnDPCpmmPEzxKzNlSnEuttPuA6YKK7rxIn2zMxa8vbyN1vqjlGfA54E/hWq1kl6+58wknZqsDcwFcSs7a0jWId+h6wmbuvRjhxOiBDTqpt/RKZjw1lbXhFx4ZU1nfIfHyo1y/JWWfr5GStsyU5u1NBnU1lAUNz19k66y5rna2zz1VRZ5N91Nx1qU5fOHs7W6/fnbkuleXkrkupnDXIXJfqlKeKNqksK/s+HvOK50b9Wf8t55jZEmb2S8JgXpkc5cHMFgW+TyhPygHA2zHnm8BFfeWUZI0h7A/d+3evAVea63fNzInnmtcDJ7r7GsAfSdfbHOvudOComONAr8FJGlx3qXNl4DngeMKg4WhgYjweFTVybEiek/djLKWhnDplGkbfYxxZyhTfqzfGAY0d71LleYy+z9MbyolZZeMZufvGZTm526RUzrZU0L8rG6PJ3UcpybmYzH2UOmNOWdrZRsZnqmqfysw2g9WEyrEv8HzxDTP7ODCXu98XX7oI+EITGS8Qvq3/wN2nAk8CoyrIwd1/C/yfh2+nFiFcBd/9zVbWLDNbgNAQTk681wV8CrimxZzuRmiKmT1i4QqVWusAf3H3Z2OZL20yB2B7wjdAz8XtNA6oHRjPtu5qnA0c7u7/riCng1BXhxM64V2Eb+i7c3JtIwgnub9x9zfdfRrhm8ftMmYV62mf273JzNTxYE/Ct4/3p2bIlPM+sE9cfzMIHZhRtTO0sA57ZLn7s8DK7v42MBIYARSv6siy7sxsKOEKkqPqzLcV4VtUgCuALWJ+v3LilzKjgAvM7FEzO8bMerRRTdapYnk2B+5190fj3/sDxSsFsmyjgpOBH7v7XzJkpXI6gPnMrINwIvBuYr6WthGh03Wvu78Q/76BmuNDCzmptnUF8h8bytrwKo4Nqaxh5D8+JMtUQZ0tW3e562wqZ2mqqbN1+3Tkq7NlObnrbNk+l73O1umjZq1LJTnvUUE7W1am3HWpJOddMtelkpzRZK5LdfaF7G1SSdY6VLCPF8+NGlj/LeVEuwK/AK4umy9TDoSrIo/pT467/w5Y2MIVgaVKssYAh8f9+ywzG1aYp+E6m8hZkzA4/Ov492QgNSieY911EK4mhTBIVHf/7ue6S50rjyVcvfhq7O9fQ2GQqIl2tuycvF4fttk+eK+svsY4cpap3hhHfL/R/S6VU/c8vckcSI9nvEP+vnEq5xHy9+9SOZ1Ud07WrXaMpor+fo8c4CWqGwuYmRPLk6udbWR8Jnv7VM9s8xgQd58AkP5ijiUInfhuLwAfayLj8e5/m9nyhFstN8ydU5M31cyOIXxb+1PgXxVlnQMcASyVeG8h4E3/6JaOZnPmB24lHIS6gDvMzN395vh+zvIsB3xgZtcTDg430PPbqqzbKX57Ope7/7TwVq797i0zOxJ4itBI/ZZwm0a3XNsIwi0kPzCzE2LW5+n5pVZLWYl62p911HBm6njgH93u/82S2VrOcfe/A3+Pry1MuGVnj1Zz6pRpqpl9jXBVzAPAw7nLFJ1A+Ib12TqzztyW7v6hmb0JLExJpzeRsxjh9t19gDcI9XZPwjeyvTJaKM9ywH/N7EpgReBu4MDCbNm2Ufx7eWBTYEJitlzbaB/C1QJvErbTNb1mbH0bPQKcamZLxXl2Imy3VnNSbeuZZD42lLXh3YORmY8NfWVlOT7U6ZdkrbMlORsT9utsdbYk5xQqqLP1+nQ562ydnL+Tsc7W2Ua35K6zcbpefdSK2tlizj9iW1tFO5vqd59C/vavmNNFNe1fMWcxqqlLqfWWvU0qyXoAmFzBPl48N+rv+m81B3c/GcDMNiqZJ0uOmR1A6PffVzJPj5you9z/qDNPjywzm4dwlfPBwNOEgZkj4zTdmqmzxTItB7xoZucTLr55knDeWVqmZtcd4c7GKWZ2GmGgdd16OYUyla27XufKwFWJZazTz5wyZefk9cZSmsmpl3VznTGObGUCJlI+xgGN73epbeSE/bnsPL2ZHEiPZzxO/vPmVM6F5G+TUjlvUdE5GfQeo6mij5LKoaKxgEROlna2kfGZitqnUrPTldX1DCY8M6bbIGB6swszs1WAm4GDvecVN1lzANz9u4SNuxQ9b63IkmXhGTj/dPdbSyYp5tBMjrvf6+5fcfc34jdB5wNb1slpZd11Er6J3hNYn9CBqL39J/d22ovwTJ+iXNtodcJz3j5OqPzT6Hm7WZZtBBD3g4sIB75fE24JqX32UbaskuWl1lHuzP5+lqZzzGxJQmfmfO/9PKys5XH3c4EFCc/mOzp3lpltDoxy9wv7mLR4C2lD+7u7P+Pu27v7C+7+DmGwcsvCZDnqVCfwWcKz5dYiXAlRvE009z43kXCr1/uJ93Jso8WAE4FVgcUJJ56pY1Kr2+jPhHV1PXAn4ZlsHyQmbSqntm0FnqGiY0OdNrxM09solVXF8aGw7pamojpbKI9XVWcL5am0zpbsD9nrbKFMb1FRnS1uIyqss3X6qGWaWnepnKra2ULWRCqqS4WczaqqS4WcYVRUlwo5R1Jhm1TI2oTM+3jJuVF/13+rOf3VUo6ZrQrsCBzXR05D+10qy93/6+5buvtTcXDmFPrev2k0h9BWbAqc7e5rEvoRLe13JetuLsJ57Fh3X5xwO//FidkbWncl58rH9mMZOXKK2yOl4WNQvaw+2o8cZbqavutXQ/tdSc4+1D9PbzgnSo1nLEv+vnEqZ+MK2qRUTtXnZGVjNGWazeqVU1EfZWZOxed+rZ5vt3S+Wfwgc4LnCBux22I0MbIPYGYbEna8Q939JxXmrGjhofXEg8R1hFuwc2eNAz5jZg8TGsTPm9kPat5/GRgRby8gZjacY2YbWXhmVLdBfPTDBJBx3REG7W5x91fc/V3C7SS130Ln3E5DCB3l6xNv58r5LHCru78cT5wvInTGumXZRgBmNi9wrbuv7uFHhN4H/lpFVtSfdZQ7s0yufX1FwjfqP3H31ElArpyl4vGI2Pm/kp7HiFxZXwJWiceI84AxZnZVYrp/Ea9mMrNOwg9l/Ke/IWa2mpntWPNS8RgBeerUi8B9Hm5tmkbozBavUsm9z21H2D4pObI2Bv7k7n919+mEKx82TUzX6jYaBjzg7p909w3i8v6amLThnETbWsmxoY82vExT2yiVVcXxIZFTSZ0t5lRVZxPlqazO1tkfstbZRE4ldTaxjSqps/3oo5ZpaN2V5VRUj1JZ65K5LpXkjMtdl0pyDiVzXSorD9Xs36msdci/j/c6NyLcZdGf9d9STuEcrJ5Wy7NnLM+DwE3AEmZ2Z2LeRo/hqTJdaGbja6ZJ7d+N1tlUmQ4i3Lr+YJzmCnrv39D6ursJeNfdH4jTnEN6/260zqbOlf/Wj2XkyCluj5Rm2vNU1pL9aD9ylOlB+q5fjR7vUjnbUf88veGcKDWeMZb8feNUzu4V9O9SOZOorn9Xb4ymTDN9h145FfVRijlVnvu1er7d0vlmrTlisNrD7YLvdQ/sALsBv2p0ORZuMfs54dd8e53E5MqJlgXONbOhcefclnCVa9Ysd9/c3Vf18MD2o4Dr3f1bNe9PJVypMC6+9JVmcgjP1D3ZzIbFAdHd6flMovsBM7PlYsXdpckcCLeVfNbMRsZlbQE81P1m5u20OvBnD88R6yFjziPAWDMbbuGHHbYBfl+Tk2sbQfh12V+YWaeZjSB0Zmc+kyhzFvRju1eQmZQjJ+7bU4BJ7n5KVTnRCOCyuJ8PItz6elftBDmy3H28u68UjxETgAfdfVxi0pv46IcdxhF+WKE/nd9ug4DTzGx+C8+1mkjhuWWZ6tQUwg+Pdd8SuDU1x4eYk22fM7OFCLdsJW8hz5T1J2AdCz+UBKG9+H1iula30XDgVjObN7ZL+xNuUW0pp6RtzX5s6KsNL9PMNkplVXF8SOVUUWdL1l32OluSU0mdLdsfctfZkpzsdbYkp5I6Sx991DJNbKdUzv1U086msqZU0P6lcn5L/vYvlTOR/HUplXMp1bRJqazbybyPl5wbfZX+rf9Wc1I/6JrSco67rxBf2xJ43t03rpdj4bbv99y99BEgqSzgEOAkM1sm9lf3pff+3dB+V5KzAeG50GvEybahsH8Xy0QT6w7YAVjKbOY9833u3/1Zd6TPlb8MbGZmC1v4bZcdCXe+1n7GRo8NfZ2TJzXZB09lPUIf7UemMh3VV/1q4niXyjmaOufpTeZAejzjGvKfN6dyfk7+NimVcyLVnZOVjtGUaTKrR06FYwHF8lR57tfquFyr55szzdaD1WZ2k5mNiX/uSngW71PAPIRfbW3UQYRb6E41s4fjf3tXkIO73wTcSHjG10PAPe5+ZRVZKWZ2npl9Pv65D+HXh58gfIszqdHlufsN9CzPBe5+b1yHS7j7e4Tn+VwLPEF47lPquTv9ybofOInQ8D1BeG7QhRWtu2UJ3z7NlDvH3acQrg54iHB7YxdwYu5tFLMeJWyDRwnPATzN3e+uIivmlW73qjKLMudMABYFDqw5RhxbQQ7u/ifCc2nvIXT83iHcWjmQ6+5YM9s7/nkksJ6ZPR4zU798XCrueycQnlf2BPCwu18Rc7LVKXf/J+E2ql/GZSwQc6tab72OEbmz3P1Jwvq/3cweJfyQ0UExJ+c2+g/hh5juI3SSbnP3yzPk9GpbCceFPch7bEi24WUTt7iNUmXaj/zHh0bL1Ox2SpVnA/LX2VTOVlRTZ8vWXe46myrTJuSvs6mcL1BBnS3ro5ZN3+y6S+UQnvWYvZ1tokxNrb+SnGPJXJdKci4hc10qyTmBCtqkkqzLqKZdSkmu/wpykgYwZ+/uOkW4/X9ozDmDMCDVEHd/hbjfEZ7vO4gK+qsertbcnjAQ+jjwaeLzbzP3hV4j9E+ujvv3eOCrMafpdVdyrnw34ZnLtxN+l+Zyj1d0t3BsSJ6Tl03fSh+8JOt4So61A1imZo93qZxjSJynt5ITs1LjGWeTuW9cknMm+dukVM5xVHdOluzLpbSYVcypaiygR06V537NjMtV1T4NmjGj+LgUEREREREREREREZGBNVtfWS0iIiIiIiIiIiIi/xs0WC0iIiIiIiIiIiIibafBahERERERERERERFpOw1Wi4iIiIiIiIiIiEjbabBaRERERERERERERNqus90fQERERESkncxsPLAXMC8wFHgGmOTu92dY9u7AYe6+YuH1RWPOsu7+Uqs5Ncs9GljI3ffLtUwRERERkYGiK6tFREREZI5lZpOB8cDO7r6yu38COAG4wcxGZYi4CljIzDYsvD4e+EXOgWoRERERkf91g2bMmNHuzyAiIiIiMuDi1c3PAp9w9xcK7+0GPOjuT5rZ1sDhwBBgEeAn7n6kmc0DXAgsD0wHHgL2cvfphWWdBCzo7nvGvwcBTwO7ufs9ZrYKcBawIDADOMXdLzazTYGz3H3VON/Mv82sEzgJ2Br4ELgH2Cd+zo2ADmBx4CXgi+7+gpktGXNGAV3Ale4+2cyWBu4EngSWBjYprg8RERERkYGgK6tFREREZE61PvBkamDW3S+JA9WDgAOB3d19DLAecJiZLQRsD8zr7qOBteOsyyZyzgZ2ioPbAGOBN+NAdSdwPXCmu68ObAFMNrP1+/js+wBrAWsAqxIeYTKu5jPsHB898howIb5+CXCBu68FrAOMNbOd43sfA45z9xU0UC0iIiIi7aJnVouIiIjInGoQ4UpmAMxsXsIVxgDzAFe7++Fmtg2wtZntAqwU5xsO3EUYWL4DuBk4zd2fLoa4+7NmdhewM3ABMJFwhTPACsAwd78uTvu8mV0LfA64vc5nHwtc4u7vxr/HxTIcDdzs7q/E1x8BFjGz4cAmwAJmdlxNGUcDDxCuzr63Tp6IiIiISOV0ZbWIiIiIzKnuB1Y0swUB3P0tdx8dr5S+FJgvDvL+EVgT+ANwMDAVGOTuzwLLEZ5xPR9wSxzYTvkRsKeZLQxsDFweX++gZsA8Gkx4TMcMwsB4tyE1//6QngPti5rZ4vHPqTXTdS+jI/5/g5oyrgdMjtO97+4flnx2EREREZEBocFqEREREZkjufvzwOnAT2t/TNHMPg5sCEwjPI96PmCSu/8S2BQYCnSY2dcJz6ye4u7fAX5DGNRO+RWwGHAEcGnNFdFPAVPNbIeYvQSwI+FK7VeAUWa2SHwcyRdrlncLsIuZDTWzwYRHjXypTlnfBO4Dvh1zRgJ3A9v2tZ5ERERERAaKBqtFREREZI7l7kcA5wOXm9kfzewZ4DpgCnAY8ChwA/CUmT0JbAM8Qbii+mLCFctPmNlDwAjgjJKc6cCPgf0IA8vdr08FtgO+YWaPEgahj3X32939CeAc4EHCQPOzNYs8h/CDjg8BjwEvlGXX2AVYz8weI1xVfoW7X9bnShIRERERGSCDZswo3nUoIiIiIiIiIiIiIjKwdGW1iIiIiIiIiIiIiLSdBqtFREREREREREREpO00WC0iIiIiIiIiIiIibafBahERERERERERERFpOw1Wi4iIiIiIiIiIiEjbabBaRERERERERERERNpOg9UiIiIiIiIiIiIi0nYarBYRERERERERERGRtvt/Qp4dY/He4CcAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 1800x720 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#create our first plot, a histogram of salaries\n",
    "\n",
    "setPlt(25,10)\n",
    "\n",
    "# two ways to do this\n",
    "\n",
    "hist = sns.countplot(data.loc[:,'Gas Voucher'])\n",
    "# hist = sns.countplot(x = 'Education Level', data= data)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    " Visualization is all about asking questions of the data. One thing that we could be curious the distrubution of genders "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1800x1080 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "setPlt()\n",
    "hist = sns.countplot(x = 'Gender', data = data)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Does insurance have anything to do with the amount of gas vouchers given out?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x114014a90>"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 792x648 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "setPlt(11,9)\n",
    "sns.boxenplot(y = 'Insurance', x = 'Gas Voucher', data = data, palette=\"Set2\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Looking at who has the highest amount of gas vouchers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Client ID</th>\n",
       "      <th>Age Range</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Education Level</th>\n",
       "      <th>Insurance</th>\n",
       "      <th>Race</th>\n",
       "      <th>Hispanic Ethnicity</th>\n",
       "      <th>Language Primary</th>\n",
       "      <th>Living Situation</th>\n",
       "      <th>31 - Day Metro Pass</th>\n",
       "      <th>...</th>\n",
       "      <th>Disability Fare Card</th>\n",
       "      <th>Gas Voucher</th>\n",
       "      <th>Metro ACCESS book</th>\n",
       "      <th>STS ticket</th>\n",
       "      <th>Taxi Voucher</th>\n",
       "      <th>Van/Car Ride</th>\n",
       "      <th>Agency</th>\n",
       "      <th>Grant Year</th>\n",
       "      <th>Grant Dates</th>\n",
       "      <th>Grant Name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>603</th>\n",
       "      <td>10030</td>\n",
       "      <td>51 - 60</td>\n",
       "      <td>Male</td>\n",
       "      <td>High school diploma/GED</td>\n",
       "      <td>Medicare</td>\n",
       "      <td>White</td>\n",
       "      <td>True</td>\n",
       "      <td>English</td>\n",
       "      <td>Rental housing</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>101.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Community Action</td>\n",
       "      <td>2015</td>\n",
       "      <td>1/1/2015-12/31/2015</td>\n",
       "      <td>Ryan White Part C</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1 rows × 21 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Client ID Age Range Gender          Education Level Insurance   Race  \\\n",
       "603      10030   51 - 60   Male  High school diploma/GED  Medicare  White   \n",
       "\n",
       "     Hispanic Ethnicity Language Primary Living Situation  \\\n",
       "603                True          English   Rental housing   \n",
       "\n",
       "     31 - Day Metro Pass        ...          Disability Fare Card  \\\n",
       "603                  NaN        ...                           NaN   \n",
       "\n",
       "     Gas Voucher  Metro ACCESS book  STS ticket  Taxi Voucher  Van/Car Ride  \\\n",
       "603        101.0                NaN         NaN           NaN           NaN   \n",
       "\n",
       "               Agency Grant Year          Grant Dates         Grant Name  \n",
       "603  Community Action       2015  1/1/2015-12/31/2015  Ryan White Part C  \n",
       "\n",
       "[1 rows x 21 columns]"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d = data[data['Gas Voucher']==101.0]\n",
    "d"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Compare different benefits?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1140ed1d0>"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 936x648 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#colored scatter plot\n",
    "setPlt(13,9)\n",
    "sns.scatterplot(x = 'Gas Voucher', y = 'Van/Car Ride', data = data)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "There is so much more that you can learn from this data and we urge you to practice the skills that you have learned by doing more exploration on this data set. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Thank You !"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}