Assignment 1.ipynb

{
 "metadata": {
  "name": "Assignment 1"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "heading",
     "level": 1,
     "metadata": {},
     "source": [
      "Question 1\n",
      "What are the column names of the dataset?"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "What are the column names of the dataset?"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import pandas as pd\n",
      "df = pd.read_csv(\"hw1_data.csv\")\n",
      "df.columns"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 17,
       "text": [
        "Index([Ozone, Solar.R, Wind, Temp, Month, Day], dtype=object)"
       ]
      }
     ],
     "prompt_number": 17
    },
    {
     "cell_type": "heading",
     "level": 1,
     "metadata": {},
     "source": [
      "Question 2"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Extract the first 2 rows of the data frame and print them to the console. What does the output look like?"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df[:2]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>Ozone</th>\n",
        "      <th>Solar.R</th>\n",
        "      <th>Wind</th>\n",
        "      <th>Temp</th>\n",
        "      <th>Month</th>\n",
        "      <th>Day</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 41</td>\n",
        "      <td> 190</td>\n",
        "      <td> 7.4</td>\n",
        "      <td> 67</td>\n",
        "      <td> 5</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 36</td>\n",
        "      <td> 118</td>\n",
        "      <td> 8.0</td>\n",
        "      <td> 72</td>\n",
        "      <td> 5</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "output_type": "pyout",
       "prompt_number": 7,
       "text": [
        "   Ozone  Solar.R  Wind  Temp  Month  Day\n",
        "0     41      190   7.4    67      5    1\n",
        "1     36      118   8.0    72      5    2"
       ]
      }
     ],
     "prompt_number": 7
    },
    {
     "cell_type": "heading",
     "level": 1,
     "metadata": {},
     "source": [
      "Question 3"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "How many observations (i.e. rows) are in this data frame?"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "len(df)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 9,
       "text": [
        "153"
       ]
      }
     ],
     "prompt_number": 9
    },
    {
     "cell_type": "heading",
     "level": 1,
     "metadata": {},
     "source": [
      "Question 4"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Extract the last 2 rows of the data frame and print them to the console. What does the output look like?"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df[-2:]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>Ozone</th>\n",
        "      <th>Solar.R</th>\n",
        "      <th>Wind</th>\n",
        "      <th>Temp</th>\n",
        "      <th>Month</th>\n",
        "      <th>Day</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>151</th>\n",
        "      <td> 18</td>\n",
        "      <td> 131</td>\n",
        "      <td>  8.0</td>\n",
        "      <td> 76</td>\n",
        "      <td> 9</td>\n",
        "      <td> 29</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>152</th>\n",
        "      <td> 20</td>\n",
        "      <td> 223</td>\n",
        "      <td> 11.5</td>\n",
        "      <td> 68</td>\n",
        "      <td> 9</td>\n",
        "      <td> 30</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "output_type": "pyout",
       "prompt_number": 14,
       "text": [
        "     Ozone  Solar.R  Wind  Temp  Month  Day\n",
        "151     18      131   8.0    76      9   29\n",
        "152     20      223  11.5    68      9   30"
       ]
      }
     ],
     "prompt_number": 14
    },
    {
     "cell_type": "heading",
     "level": 1,
     "metadata": {},
     "source": [
      "Question 5"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "What is the value of Ozone in the 47th row?"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "#Notice the differenct rowcount from python to R\n",
      "df.Ozone[46]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 19,
       "text": [
        "21.0"
       ]
      }
     ],
     "prompt_number": 19
    },
    {
     "cell_type": "heading",
     "level": 1,
     "metadata": {},
     "source": [
      "Question 6"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "How many missing values are in the Ozone column of this data frame?"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "#one option, there might be others for this\n",
      "len(df.Ozone[df.Ozone.isnull()==True])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 38,
       "text": [
        "37"
       ]
      }
     ],
     "prompt_number": 38
    },
    {
     "cell_type": "heading",
     "level": 1,
     "metadata": {},
     "source": [
      "Question 7"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "What is the mean of the Ozone column in this dataset? Exclude missing values (coded as NA) from this calculation."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.Ozone.mean()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 39,
       "text": [
        "42.129310344827587"
       ]
      }
     ],
     "prompt_number": 39
    },
    {
     "cell_type": "heading",
     "level": 1,
     "metadata": {},
     "source": [
      "Question 8"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Extract the subset of rows of the data frame where Ozone values are above 31 and Temp values are above 90. What is the mean of Solar.R in this subset?"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df[\"Solar.R\"][(df.Temp>90) &(df.Ozone>31)].mean()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 56,
       "text": [
        "212.80000000000001"
       ]
      }
     ],
     "prompt_number": 56
    },
    {
     "cell_type": "heading",
     "level": 1,
     "metadata": {},
     "source": [
      "Question 9"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "What is the mean of \"Temp\" when \"Month\" is equal to 6?"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.Temp[df.Month==6].mean()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 57,
       "text": [
        "79.099999999999994"
       ]
      }
     ],
     "prompt_number": 57
    },
    {
     "cell_type": "heading",
     "level": 1,
     "metadata": {},
     "source": [
      "Question 10"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "What was the maximum ozone value in the month of May (i.e. Month = 5)?"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.Ozone[df.Month==5].max()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 58,
       "text": [
        "115.0"
       ]
      }
     ],
     "prompt_number": 58
    }
   ],
   "metadata": {}
  }
 ]
}