Chapter10_Introducing_pandas.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Setting up a fancy stylesheet"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<link href='http://fonts.googleapis.com/css?family=Alegreya+Sans:100,300,400,500,700,800,900,100italic,300italic,400italic,500italic,700italic,800italic,900italic' rel='stylesheet' type='text/css'>\n",
       "<link href='http://fonts.googleapis.com/css?family=Arvo:400,700,400italic' rel='stylesheet' type='text/css'>\n",
       "<link href='http://fonts.googleapis.com/css?family=PT+Mono' rel='stylesheet' type='text/css'>\n",
       "<link href='http://fonts.googleapis.com/css?family=Shadows+Into+Light' rel='stylesheet' type='text/css'>\n",
       "<link href='http://fonts.googleapis.com/css?family=Philosopher:400,700,400italic,700italic' rel='stylesheet' type='text/css'>\n",
       "\n",
       "<style>\n",
       "\n",
       "@font-face {\n",
       "    font-family: \"Computer Modern\";\n",
       "    src: url('http://mirrors.ctan.org/fonts/cm-unicode/fonts/otf/cmunss.otf');\n",
       "}\n",
       "\n",
       "#notebook_panel { /* main background */\n",
       "    background: #ddd;\n",
       "    color: #000000;\n",
       "}\n",
       "\n",
       "\n",
       "div.text_cell_render{\n",
       "    font-family: 'Arvo' sans-serif;\n",
       "    line-height: 130%;\n",
       "    font-size: 115%;\n",
       "    width:1000px;\n",
       "    margin-left:auto;\n",
       "    margin-right:auto;\n",
       "}\n",
       "\n",
       "\n",
       "/* Formatting for header cells */\n",
       ".text_cell_render h1 {\n",
       "    font-family: 'Philosopher', sans-serif;\n",
       "    font-weight: 400;\n",
       "    font-size: 2.2em;\n",
       "    line-height: 100%;\n",
       "    color: rgb(0, 80, 120);\n",
       "    margin-bottom: 0.1em;\n",
       "    margin-top: 0.1em;\n",
       "    display: block;\n",
       "}\t\n",
       ".text_cell_render h2 {\n",
       "    font-family: 'Philosopher', serif;\n",
       "    font-weight: 400;\n",
       "    font-size: 1.9em;\n",
       "    line-height: 100%;\n",
       "    color: rgb(200,100,0);\n",
       "    margin-bottom: 0.1em;\n",
       "    margin-top: 0.1em;\n",
       "    display: block;\n",
       "}\t\n",
       "\n",
       ".text_cell_render h3 {\n",
       "    font-family: 'Philosopher', serif;\n",
       "    margin-top:12px;\n",
       "    margin-bottom: 3px;\n",
       "    font-style: italic;\n",
       "    color: rgb(94,127,192);\n",
       "}\n",
       "\n",
       ".text_cell_render h4 {\n",
       "    font-family: 'Philosopher', serif;\n",
       "}\n",
       "\n",
       ".text_cell_render h5 {\n",
       "    font-family: 'Alegreya Sans', sans-serif;\n",
       "    font-weight: 300;\n",
       "    font-size: 16pt;\n",
       "    color: grey;\n",
       "    font-style: italic;\n",
       "    margin-bottom: .1em;\n",
       "    margin-top: 0.1em;\n",
       "    display: block;\n",
       "}\n",
       "\n",
       ".text_cell_render h6 {\n",
       "    font-family: 'PT Mono', sans-serif;\n",
       "    font-weight: 300;\n",
       "    font-size: 10pt;\n",
       "    color: grey;\n",
       "    margin-bottom: 1px;\n",
       "    margin-top: 1px;\n",
       "}\n",
       "\n",
       ".CodeMirror{\n",
       "        font-family: \"PT Mono\";\n",
       "        font-size: 100%;\n",
       "}\n",
       "\n",
       "</style>\n",
       "\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from IPython.core.display import HTML\n",
    "css_file = 'style.css'\n",
    "HTML(open(css_file, 'r').read())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Setting up the required python &#8482; environment"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "#import numpy as np\n",
    "import pandas as pd\n",
    "from scipy.stats import norm\n",
    "#from math import factorial\n",
    "#import scikits.bootstrap as bs\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "from warnings import filterwarnings\n",
    "\n",
    "%matplotlib inline\n",
    "filterwarnings('ignore')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Pandas"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Introduction"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<p>*pandas* is a python library that is a monster at data manipulation.  Dare I say: **I love *pandas*!**</p>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Some basic *pandas*"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "values_1 = [12.3, 14.2, 15.2, 13.2, 15.4, 11, 12.8, 18.3, 14.3, 15.9, 9.9, 11.9, 17.9]\n",
    "# Some values in an array"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "data_1 = pd.Series(values_1) # Taking the values in values_1 and adding them to the computer\n",
    "# variable data_1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0     12.3\n",
       "1     14.2\n",
       "2     15.2\n",
       "3     13.2\n",
       "4     15.4\n",
       "5     11.0\n",
       "6     12.8\n",
       "7     18.3\n",
       "8     14.3\n",
       "9     15.9\n",
       "10     9.9\n",
       "11    11.9\n",
       "12    17.9\n",
       "dtype: float64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_1 # Each value is now part of an ordered list, each attached to an index value (starting\n",
    "# at 0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "list"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(values_1) # Whereas values_1 is a computer variable that is a list..."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "pandas.core.series.Series"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(data_1) # ... is a pandas Series object"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    13.000000\n",
       "mean     14.023077\n",
       "std       2.516994\n",
       "min       9.900000\n",
       "25%      12.300000\n",
       "50%      14.200000\n",
       "75%      15.400000\n",
       "max      18.300000\n",
       "dtype: float64"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_1.describe() # The simplest way to describe a column of values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x108a76ba8>"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXwAAAECCAYAAAD9z2x7AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nB/p25W9aufG6AAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x108a76908>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.distplot(data_1) # A quick histogram and kernel density estimate of the values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "values_2 = pd.Series(norm.rvs(loc = 18, scale = 4, size = 13)) # Creating another series, this\n",
    "# time containing 13 random values from a normal distribution with a mean of 18 and a\n",
    "# standrad deviation of 4\n",
    "# I imported the norm function from the scipy.stats library"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "data_2 = pd.DataFrame() # A new (empty)  pandas DataFrame"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "data_2['var_1'] = values_1 # Making a new column, calling it var_1 and adding the values in\n",
    "# values_1 to it"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>var_1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>12.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>14.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>15.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>13.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>15.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>11.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>12.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>18.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>14.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>15.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>9.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>11.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>17.9</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    var_1\n",
       "0    12.3\n",
       "1    14.2\n",
       "2    15.2\n",
       "3    13.2\n",
       "4    15.4\n",
       "5    11.0\n",
       "6    12.8\n",
       "7    18.3\n",
       "8    14.3\n",
       "9    15.9\n",
       "10    9.9\n",
       "11   11.9\n",
       "12   17.9"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "data_2['var_2'] = values_2 # Adding another column to the DataFrame and adding the values in\n",
    "# values_2 to it"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>var_1</th>\n",
       "      <th>var_2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>12.3</td>\n",
       "      <td>21.515040</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>14.2</td>\n",
       "      <td>20.012435</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>15.2</td>\n",
       "      <td>23.513542</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>13.2</td>\n",
       "      <td>14.871926</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>15.4</td>\n",
       "      <td>20.694091</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>11.0</td>\n",
       "      <td>21.867815</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>12.8</td>\n",
       "      <td>16.358531</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>18.3</td>\n",
       "      <td>15.531141</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>14.3</td>\n",
       "      <td>21.665154</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>15.9</td>\n",
       "      <td>18.233597</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>9.9</td>\n",
       "      <td>20.001324</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>11.9</td>\n",
       "      <td>10.677342</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>17.9</td>\n",
       "      <td>18.258056</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    var_1      var_2\n",
       "0    12.3  21.515040\n",
       "1    14.2  20.012435\n",
       "2    15.2  23.513542\n",
       "3    13.2  14.871926\n",
       "4    15.4  20.694091\n",
       "5    11.0  21.867815\n",
       "6    12.8  16.358531\n",
       "7    18.3  15.531141\n",
       "8    14.3  21.665154\n",
       "9    15.9  18.233597\n",
       "10    9.9  20.001324\n",
       "11   11.9  10.677342\n",
       "12   17.9  18.258056"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>var_1</th>\n",
       "      <th>var_2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>13.000000</td>\n",
       "      <td>13.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>14.023077</td>\n",
       "      <td>18.707692</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>2.516994</td>\n",
       "      <td>3.562157</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>9.900000</td>\n",
       "      <td>10.677342</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>12.300000</td>\n",
       "      <td>16.358531</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>14.200000</td>\n",
       "      <td>20.001324</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>15.400000</td>\n",
       "      <td>21.515040</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>18.300000</td>\n",
       "      <td>23.513542</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           var_1      var_2\n",
       "count  13.000000  13.000000\n",
       "mean   14.023077  18.707692\n",
       "std     2.516994   3.562157\n",
       "min     9.900000  10.677342\n",
       "25%    12.300000  16.358531\n",
       "50%    14.200000  20.001324\n",
       "75%    15.400000  21.515040\n",
       "max    18.300000  23.513542"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_2.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>var_1</th>\n",
       "      <th>var_2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>15.2</td>\n",
       "      <td>23.513542</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>15.4</td>\n",
       "      <td>20.694091</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>18.3</td>\n",
       "      <td>15.531141</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>15.9</td>\n",
       "      <td>18.233597</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>17.9</td>\n",
       "      <td>18.258056</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    var_1      var_2\n",
       "2    15.2  23.513542\n",
       "4    15.4  20.694091\n",
       "7    18.3  15.531141\n",
       "9    15.9  18.233597\n",
       "12   17.9  18.258056"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_3 = data_2[data_2['var_1'] > 15] # Creating a new DataFrame only including rows (for all\n",
    "# columns) where the values in the var_1 column is greater than 15\n",
    "data_3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "data_2['groups'] = ['A', 'A', 'B', 'A', 'B', 'A', 'B', 'B', 'B', 'A', 'A', 'B', 'A']\n",
    "# The data_2 DataFrame now has a new column called groups"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>var_1</th>\n",
       "      <th>var_2</th>\n",
       "      <th>groups</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>12.3</td>\n",
       "      <td>21.515040</td>\n",
       "      <td>A</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>14.2</td>\n",
       "      <td>20.012435</td>\n",
       "      <td>A</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>15.2</td>\n",
       "      <td>23.513542</td>\n",
       "      <td>B</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>13.2</td>\n",
       "      <td>14.871926</td>\n",
       "      <td>A</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>15.4</td>\n",
       "      <td>20.694091</td>\n",
       "      <td>B</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>11.0</td>\n",
       "      <td>21.867815</td>\n",
       "      <td>A</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>12.8</td>\n",
       "      <td>16.358531</td>\n",
       "      <td>B</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>18.3</td>\n",
       "      <td>15.531141</td>\n",
       "      <td>B</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>14.3</td>\n",
       "      <td>21.665154</td>\n",
       "      <td>B</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>15.9</td>\n",
       "      <td>18.233597</td>\n",
       "      <td>A</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>9.9</td>\n",
       "      <td>20.001324</td>\n",
       "      <td>A</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>11.9</td>\n",
       "      <td>10.677342</td>\n",
       "      <td>B</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>17.9</td>\n",
       "      <td>18.258056</td>\n",
       "      <td>A</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    var_1      var_2 groups\n",
       "0    12.3  21.515040      A\n",
       "1    14.2  20.012435      A\n",
       "2    15.2  23.513542      B\n",
       "3    13.2  14.871926      A\n",
       "4    15.4  20.694091      B\n",
       "5    11.0  21.867815      A\n",
       "6    12.8  16.358531      B\n",
       "7    18.3  15.531141      B\n",
       "8    14.3  21.665154      B\n",
       "9    15.9  18.233597      A\n",
       "10    9.9  20.001324      A\n",
       "11   11.9  10.677342      B\n",
       "12   17.9  18.258056      A"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "data_4 = data_2.groupby('groups')\n",
    "# Creating a new DataFrame by splitting up DataFrame data_2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>var_1</th>\n",
       "      <th>var_2</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>groups</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"8\" valign=\"top\">A</th>\n",
       "      <th>count</th>\n",
       "      <td>7.000000</td>\n",
       "      <td>7.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>13.485714</td>\n",
       "      <td>19.251456</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>2.779346</td>\n",
       "      <td>2.391433</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>9.900000</td>\n",
       "      <td>14.871926</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>11.650000</td>\n",
       "      <td>18.245827</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>13.200000</td>\n",
       "      <td>20.001324</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>15.050000</td>\n",
       "      <td>20.763737</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>17.900000</td>\n",
       "      <td>21.867815</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"8\" valign=\"top\">B</th>\n",
       "      <th>count</th>\n",
       "      <td>6.000000</td>\n",
       "      <td>6.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>14.650000</td>\n",
       "      <td>18.073300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>2.249222</td>\n",
       "      <td>4.763809</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>11.900000</td>\n",
       "      <td>10.677342</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>13.175000</td>\n",
       "      <td>15.737989</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>14.750000</td>\n",
       "      <td>18.526311</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>15.350000</td>\n",
       "      <td>21.422388</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>18.300000</td>\n",
       "      <td>23.513542</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  var_1      var_2\n",
       "groups                            \n",
       "A      count   7.000000   7.000000\n",
       "       mean   13.485714  19.251456\n",
       "       std     2.779346   2.391433\n",
       "       min     9.900000  14.871926\n",
       "       25%    11.650000  18.245827\n",
       "       50%    13.200000  20.001324\n",
       "       75%    15.050000  20.763737\n",
       "       max    17.900000  21.867815\n",
       "B      count   6.000000   6.000000\n",
       "       mean   14.650000  18.073300\n",
       "       std     2.249222   4.763809\n",
       "       min    11.900000  10.677342\n",
       "       25%    13.175000  15.737989\n",
       "       50%    14.750000  18.526311\n",
       "       75%    15.350000  21.422388\n",
       "       max    18.300000  23.513542"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_4.describe() # Now this is magic!"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Importing spreadsheet files"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "data_5 = pd.read_csv('MOOC_Mock.csv') # Creating a computer variable called data_5, attatching\n",
    "# to it a comma seperated value file, which makes it a DataFrame"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "pandas.core.frame.DataFrame"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(data_5) # Yes, it's a DataFrame object"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>File</th>\n",
       "      <th>Age</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Delay</th>\n",
       "      <th>Stay</th>\n",
       "      <th>ICU</th>\n",
       "      <th>RVD</th>\n",
       "      <th>CD4</th>\n",
       "      <th>HR</th>\n",
       "      <th>Temp</th>\n",
       "      <th>CRP</th>\n",
       "      <th>WCC</th>\n",
       "      <th>HB</th>\n",
       "      <th>Rupture</th>\n",
       "      <th>Histo</th>\n",
       "      <th>Comp</th>\n",
       "      <th>MASS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>38</td>\n",
       "      <td>Female</td>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>NaN</td>\n",
       "      <td>97</td>\n",
       "      <td>35.2</td>\n",
       "      <td>NaN</td>\n",
       "      <td>10.49</td>\n",
       "      <td>10.4</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>32</td>\n",
       "      <td>Male</td>\n",
       "      <td>6</td>\n",
       "      <td>10</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>57</td>\n",
       "      <td>109</td>\n",
       "      <td>38.8</td>\n",
       "      <td>45.3</td>\n",
       "      <td>7.08</td>\n",
       "      <td>19.8</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>19</td>\n",
       "      <td>Female</td>\n",
       "      <td>1</td>\n",
       "      <td>16</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>NaN</td>\n",
       "      <td>120</td>\n",
       "      <td>36.3</td>\n",
       "      <td>10.7</td>\n",
       "      <td>13.00</td>\n",
       "      <td>8.7</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>20</td>\n",
       "      <td>Female</td>\n",
       "      <td>2</td>\n",
       "      <td>9</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>NaN</td>\n",
       "      <td>120</td>\n",
       "      <td>35.7</td>\n",
       "      <td>77.8</td>\n",
       "      <td>4.45</td>\n",
       "      <td>8.8</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>28</td>\n",
       "      <td>Female</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>491</td>\n",
       "      <td>115</td>\n",
       "      <td>37.1</td>\n",
       "      <td>51.6</td>\n",
       "      <td>21.98</td>\n",
       "      <td>13.4</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   File  Age  Gender  Delay  Stay ICU  RVD  CD4   HR  Temp   CRP    WCC    HB  \\\n",
       "0     1   38  Female      3     6  No   No  NaN   97  35.2   NaN  10.49  10.4   \n",
       "1     2   32    Male      6    10  No  Yes   57  109  38.8  45.3   7.08  19.8   \n",
       "2     3   19  Female      1    16  No   No  NaN  120  36.3  10.7  13.00   8.7   \n",
       "3     4   20  Female      2     9  No  Yes  NaN  120  35.7  77.8   4.45   8.8   \n",
       "4     5   28  Female      3     3  No  Yes  491  115  37.1  51.6  21.98  13.4   \n",
       "\n",
       "  Rupture Histo Comp  MASS  \n",
       "0      No   Yes  Yes     5  \n",
       "1      No    No  Yes     8  \n",
       "2      No    No   No     3  \n",
       "3      No    No   No     0  \n",
       "4      No   Yes   No     7  "
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_5.head() # Showing the first few (default is 5) rows"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Age</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Delay</th>\n",
       "      <th>Stay</th>\n",
       "      <th>ICU</th>\n",
       "      <th>RVD</th>\n",
       "      <th>CD4</th>\n",
       "      <th>HR</th>\n",
       "      <th>Temp</th>\n",
       "      <th>CRP</th>\n",
       "      <th>WCC</th>\n",
       "      <th>HB</th>\n",
       "      <th>Rupture</th>\n",
       "      <th>Histo</th>\n",
       "      <th>Comp</th>\n",
       "      <th>MASS</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>File</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>38</td>\n",
       "      <td>Female</td>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>NaN</td>\n",
       "      <td>97</td>\n",
       "      <td>35.2</td>\n",
       "      <td>NaN</td>\n",
       "      <td>10.49</td>\n",
       "      <td>10.4</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>32</td>\n",
       "      <td>Male</td>\n",
       "      <td>6</td>\n",
       "      <td>10</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>57</td>\n",
       "      <td>109</td>\n",
       "      <td>38.8</td>\n",
       "      <td>45.3</td>\n",
       "      <td>7.08</td>\n",
       "      <td>19.8</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>19</td>\n",
       "      <td>Female</td>\n",
       "      <td>1</td>\n",
       "      <td>16</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>NaN</td>\n",
       "      <td>120</td>\n",
       "      <td>36.3</td>\n",
       "      <td>10.7</td>\n",
       "      <td>13.00</td>\n",
       "      <td>8.7</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      Age  Gender  Delay  Stay ICU  RVD  CD4   HR  Temp   CRP    WCC    HB  \\\n",
       "File                                                                         \n",
       "1      38  Female      3     6  No   No  NaN   97  35.2   NaN  10.49  10.4   \n",
       "2      32    Male      6    10  No  Yes   57  109  38.8  45.3   7.08  19.8   \n",
       "3      19  Female      1    16  No   No  NaN  120  36.3  10.7  13.00   8.7   \n",
       "\n",
       "     Rupture Histo Comp  MASS  \n",
       "File                           \n",
       "1         No   Yes  Yes     5  \n",
       "2         No    No  Yes     8  \n",
       "3         No    No   No     3  "
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_5.set_index('File').head(3) # Changing the default index column to the File column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>File</th>\n",
       "      <th>Age</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Delay</th>\n",
       "      <th>Stay</th>\n",
       "      <th>ICU</th>\n",
       "      <th>RVD</th>\n",
       "      <th>CD4</th>\n",
       "      <th>HR</th>\n",
       "      <th>Temp</th>\n",
       "      <th>CRP</th>\n",
       "      <th>WCC</th>\n",
       "      <th>HB</th>\n",
       "      <th>Rupture</th>\n",
       "      <th>Histo</th>\n",
       "      <th>Comp</th>\n",
       "      <th>MASS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>147</th>\n",
       "      <td>148</td>\n",
       "      <td>54</td>\n",
       "      <td>Male</td>\n",
       "      <td>5</td>\n",
       "      <td>11</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>NaN</td>\n",
       "      <td>115</td>\n",
       "      <td>38.2</td>\n",
       "      <td>NaN</td>\n",
       "      <td>17.64</td>\n",
       "      <td>15.7</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>148</th>\n",
       "      <td>149</td>\n",
       "      <td>29</td>\n",
       "      <td>Male</td>\n",
       "      <td>4</td>\n",
       "      <td>6</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>45</td>\n",
       "      <td>133</td>\n",
       "      <td>41.2</td>\n",
       "      <td>163.5</td>\n",
       "      <td>15.50</td>\n",
       "      <td>19.2</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>149</th>\n",
       "      <td>150</td>\n",
       "      <td>55</td>\n",
       "      <td>Female</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>78</td>\n",
       "      <td>95</td>\n",
       "      <td>40.6</td>\n",
       "      <td>NaN</td>\n",
       "      <td>24.22</td>\n",
       "      <td>16.5</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     File  Age  Gender  Delay  Stay  ICU  RVD  CD4   HR  Temp    CRP    WCC  \\\n",
       "147   148   54    Male      5    11  Yes  Yes  NaN  115  38.2    NaN  17.64   \n",
       "148   149   29    Male      4     6   No  Yes   45  133  41.2  163.5  15.50   \n",
       "149   150   55  Female      5     2  Yes  Yes   78   95  40.6    NaN  24.22   \n",
       "\n",
       "       HB Rupture Histo Comp  MASS  \n",
       "147  15.7     Yes   Yes   No     1  \n",
       "148  19.2     Yes   Yes  Yes     9  \n",
       "149  16.5     Yes   Yes   No     4  "
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_5.tail(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.4.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}