Skip to content

Instantly share code, notes, and snippets.

@pybokeh

pybokeh/gist:5b65e2bb2636c00c50cd

Last active August 29, 2015 14:07
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save pybokeh/5b65e2bb2636c00c50cd to your computer and use it in GitHub Desktop.
Save pybokeh/5b65e2bb2636c00c50cd to your computer and use it in GitHub Desktop.
Download ZIP
Fuel_Economy
Raw
gistfile1.txt
{
"metadata": {
"name": "",
"signature": "sha256:0ae2bb4e7582025a1823781701129b0c175718b3384245ded6dd1058497747f5"
},
"nbformat": 3,
"nbformat_minor": 0,
"worksheets": [
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<center><h1>Analyzing Automobile Fuel Economy Data</h1><h3>Using Python</h3></center>"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Data source: [http://www.fueleconomy.gov/feg/ws/index.shtml](http://www.fueleconomy.gov/feg/ws/index.shtml)<br>\n",
"Data file: [www.fueleconomy.gov/feq/epadata/vehicles.csv.zip](www.fueleconomy.gov/feq/epadata/vehicles.csv.zip)<br>\n",
"Data meta data: [http://www.fueleconomy.gov/feg/ws/index.shtml#vehicle](http://www.fueleconomy.gov/feg/ws/index.shtml#vehicle)<br>\n",
"Python environment: Python 3.4.1 in virtual environment created using Miniconda3 on Xubuntu 14.04"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### I've installed the usual packages for data analyis and plotting:"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"import pandas as pd\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sbn"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 304
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### If you are like me, I like to see all the data if I have enough RAM:"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"pd.options.display.max_rows = 999\n",
"pd.options.display.max_columns = 999"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 305
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"vehicles = pd.read_csv('vehicles.csv') # Absolute path isn't necessary if you launched the\n",
" # ipython notebook in the same directory as the csv file"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 306
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"vehicles.head()"
],
"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>barrels08</th>\n",
" <th>barrelsA08</th>\n",
" <th>charge120</th>\n",
" <th>charge240</th>\n",
" <th>city08</th>\n",
" <th>city08U</th>\n",
" <th>cityA08</th>\n",
" <th>cityA08U</th>\n",
" <th>cityCD</th>\n",
" <th>cityE</th>\n",
" <th>cityUF</th>\n",
" <th>co2</th>\n",
" <th>co2A</th>\n",
" <th>co2TailpipeAGpm</th>\n",
" <th>co2TailpipeGpm</th>\n",
" <th>comb08</th>\n",
" <th>comb08U</th>\n",
" <th>combA08</th>\n",
" <th>combA08U</th>\n",
" <th>combE</th>\n",
" <th>combinedCD</th>\n",
" <th>combinedUF</th>\n",
" <th>cylinders</th>\n",
" <th>displ</th>\n",
" <th>drive</th>\n",
" <th>engId</th>\n",
" <th>eng_dscr</th>\n",
" <th>feScore</th>\n",
" <th>fuelCost08</th>\n",
" <th>fuelCostA08</th>\n",
" <th>fuelType</th>\n",
" <th>fuelType1</th>\n",
" <th>ghgScore</th>\n",
" <th>ghgScoreA</th>\n",
" <th>highway08</th>\n",
" <th>highway08U</th>\n",
" <th>highwayA08</th>\n",
" <th>highwayA08U</th>\n",
" <th>highwayCD</th>\n",
" <th>highwayE</th>\n",
" <th>highwayUF</th>\n",
" <th>hlv</th>\n",
" <th>hpv</th>\n",
" <th>id</th>\n",
" <th>lv2</th>\n",
" <th>lv4</th>\n",
" <th>make</th>\n",
" <th>model</th>\n",
" <th>mpgData</th>\n",
" <th>phevBlended</th>\n",
" <th>pv2</th>\n",
" <th>pv4</th>\n",
" <th>range</th>\n",
" <th>rangeCity</th>\n",
" <th>rangeCityA</th>\n",
" <th>rangeHwy</th>\n",
" <th>rangeHwyA</th>\n",
" <th>trany</th>\n",
" <th>UCity</th>\n",
" <th>UCityA</th>\n",
" <th>UHighway</th>\n",
" <th>UHighwayA</th>\n",
" <th>VClass</th>\n",
" <th>year</th>\n",
" <th>youSaveSpend</th>\n",
" <th>guzzler</th>\n",
" <th>trans_dscr</th>\n",
" <th>tCharger</th>\n",
" <th>sCharger</th>\n",
" <th>atvType</th>\n",
" <th>fuelType2</th>\n",
" <th>rangeA</th>\n",
" <th>evMotor</th>\n",
" <th>mfrCode</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td> 15.689436</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 19</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td>-1</td>\n",
" <td>-1</td>\n",
" <td> 0</td>\n",
" <td> 423.190476</td>\n",
" <td> 21</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 4</td>\n",
" <td> 2.0</td>\n",
" <td> Rear-Wheel Drive</td>\n",
" <td> 9011</td>\n",
" <td> (FFS)</td>\n",
" <td>-1</td>\n",
" <td> 2400</td>\n",
" <td> 0</td>\n",
" <td> Regular</td>\n",
" <td> Regular Gasoline</td>\n",
" <td>-1</td>\n",
" <td>-1</td>\n",
" <td> 25</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 1</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> Alfa Romeo</td>\n",
" <td> Spider Veloce 2000</td>\n",
" <td> Y</td>\n",
" <td> False</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> Manual 5-spd</td>\n",
" <td> 23.3333</td>\n",
" <td> 0</td>\n",
" <td> 35.0000</td>\n",
" <td> 0</td>\n",
" <td> Two Seaters</td>\n",
" <td> 1985</td>\n",
" <td> -1000</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td> 29.950562</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 9</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td>-1</td>\n",
" <td>-1</td>\n",
" <td> 0</td>\n",
" <td> 807.909091</td>\n",
" <td> 11</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 12</td>\n",
" <td> 4.9</td>\n",
" <td> Rear-Wheel Drive</td>\n",
" <td> 22020</td>\n",
" <td> (GUZZLER)</td>\n",
" <td>-1</td>\n",
" <td> 4550</td>\n",
" <td> 0</td>\n",
" <td> Regular</td>\n",
" <td> Regular Gasoline</td>\n",
" <td>-1</td>\n",
" <td>-1</td>\n",
" <td> 14</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 10</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> Ferrari</td>\n",
" <td> Testarossa</td>\n",
" <td> N</td>\n",
" <td> False</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> Manual 5-spd</td>\n",
" <td> 11.0000</td>\n",
" <td> 0</td>\n",
" <td> 19.0000</td>\n",
" <td> 0</td>\n",
" <td> Two Seaters</td>\n",
" <td> 1985</td>\n",
" <td>-11750</td>\n",
" <td> T</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td> 12.195570</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 23</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td>-1</td>\n",
" <td>-1</td>\n",
" <td> 0</td>\n",
" <td> 329.148148</td>\n",
" <td> 27</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 4</td>\n",
" <td> 2.2</td>\n",
" <td> Front-Wheel Drive</td>\n",
" <td> 2100</td>\n",
" <td> (FFS)</td>\n",
" <td>-1</td>\n",
" <td> 1850</td>\n",
" <td> 0</td>\n",
" <td> Regular</td>\n",
" <td> Regular Gasoline</td>\n",
" <td>-1</td>\n",
" <td>-1</td>\n",
" <td> 33</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 19</td>\n",
" <td> 77</td>\n",
" <td> 100</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> Dodge</td>\n",
" <td> Charger</td>\n",
" <td> Y</td>\n",
" <td> False</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> Manual 5-spd</td>\n",
" <td> 29.0000</td>\n",
" <td> 0</td>\n",
" <td> 47.0000</td>\n",
" <td> 0</td>\n",
" <td> Subcompact Cars</td>\n",
" <td> 1985</td>\n",
" <td> 1750</td>\n",
" <td> NaN</td>\n",
" <td> SIL</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td> 29.950562</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 10</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td>-1</td>\n",
" <td>-1</td>\n",
" <td> 0</td>\n",
" <td> 807.909091</td>\n",
" <td> 11</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 8</td>\n",
" <td> 5.2</td>\n",
" <td> Rear-Wheel Drive</td>\n",
" <td> 2850</td>\n",
" <td> NaN</td>\n",
" <td>-1</td>\n",
" <td> 4550</td>\n",
" <td> 0</td>\n",
" <td> Regular</td>\n",
" <td> Regular Gasoline</td>\n",
" <td>-1</td>\n",
" <td>-1</td>\n",
" <td> 12</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 1000</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> Dodge</td>\n",
" <td> B150/B250 Wagon 2WD</td>\n",
" <td> N</td>\n",
" <td> False</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> Automatic 3-spd</td>\n",
" <td> 12.2222</td>\n",
" <td> 0</td>\n",
" <td> 16.6667</td>\n",
" <td> 0</td>\n",
" <td> Vans</td>\n",
" <td> 1985</td>\n",
" <td>-11750</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td> 17.337486</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 17</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td>-1</td>\n",
" <td>-1</td>\n",
" <td> 0</td>\n",
" <td> 467.736842</td>\n",
" <td> 19</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 4</td>\n",
" <td> 2.2</td>\n",
" <td> 4-Wheel or All-Wheel Drive</td>\n",
" <td> 66031</td>\n",
" <td> (FFS,TRBO)</td>\n",
" <td>-1</td>\n",
" <td> 2950</td>\n",
" <td> 0</td>\n",
" <td> Premium</td>\n",
" <td> Premium Gasoline</td>\n",
" <td>-1</td>\n",
" <td>-1</td>\n",
" <td> 23</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 10000</td>\n",
" <td> 0</td>\n",
" <td> 14</td>\n",
" <td> Subaru</td>\n",
" <td> Legacy AWD Turbo</td>\n",
" <td> N</td>\n",
" <td> False</td>\n",
" <td> 0</td>\n",
" <td> 90</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> 0</td>\n",
" <td> Manual 5-spd</td>\n",
" <td> 21.0000</td>\n",
" <td> 0</td>\n",
" <td> 32.0000</td>\n",
" <td> 0</td>\n",
" <td> Compact Cars</td>\n",
" <td> 1993</td>\n",
" <td> -3750</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> T</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"metadata": {},
"output_type": "pyout",
"prompt_number": 307,
"text": [
" barrels08 barrelsA08 charge120 charge240 city08 city08U cityA08 \\\n",
"0 15.689436 0 0 0 19 0 0 \n",
"1 29.950562 0 0 0 9 0 0 \n",
"2 12.195570 0 0 0 23 0 0 \n",
"3 29.950562 0 0 0 10 0 0 \n",
"4 17.337486 0 0 0 17 0 0 \n",
"\n",
" cityA08U cityCD cityE cityUF co2 co2A co2TailpipeAGpm \\\n",
"0 0 0 0 0 -1 -1 0 \n",
"1 0 0 0 0 -1 -1 0 \n",
"2 0 0 0 0 -1 -1 0 \n",
"3 0 0 0 0 -1 -1 0 \n",
"4 0 0 0 0 -1 -1 0 \n",
"\n",
" co2TailpipeGpm comb08 comb08U combA08 combA08U combE combinedCD \\\n",
"0 423.190476 21 0 0 0 0 0 \n",
"1 807.909091 11 0 0 0 0 0 \n",
"2 329.148148 27 0 0 0 0 0 \n",
"3 807.909091 11 0 0 0 0 0 \n",
"4 467.736842 19 0 0 0 0 0 \n",
"\n",
" combinedUF cylinders displ drive engId \\\n",
"0 0 4 2.0 Rear-Wheel Drive 9011 \n",
"1 0 12 4.9 Rear-Wheel Drive 22020 \n",
"2 0 4 2.2 Front-Wheel Drive 2100 \n",
"3 0 8 5.2 Rear-Wheel Drive 2850 \n",
"4 0 4 2.2 4-Wheel or All-Wheel Drive 66031 \n",
"\n",
" eng_dscr feScore fuelCost08 fuelCostA08 fuelType fuelType1 \\\n",
"0 (FFS) -1 2400 0 Regular Regular Gasoline \n",
"1 (GUZZLER) -1 4550 0 Regular Regular Gasoline \n",
"2 (FFS) -1 1850 0 Regular Regular Gasoline \n",
"3 NaN -1 4550 0 Regular Regular Gasoline \n",
"4 (FFS,TRBO) -1 2950 0 Premium Premium Gasoline \n",
"\n",
" ghgScore ghgScoreA highway08 highway08U highwayA08 highwayA08U \\\n",
"0 -1 -1 25 0 0 0 \n",
"1 -1 -1 14 0 0 0 \n",
"2 -1 -1 33 0 0 0 \n",
"3 -1 -1 12 0 0 0 \n",
"4 -1 -1 23 0 0 0 \n",
"\n",
" highwayCD highwayE highwayUF hlv hpv id lv2 lv4 make \\\n",
"0 0 0 0 0 0 1 0 0 Alfa Romeo \n",
"1 0 0 0 0 0 10 0 0 Ferrari \n",
"2 0 0 0 19 77 100 0 0 Dodge \n",
"3 0 0 0 0 0 1000 0 0 Dodge \n",
"4 0 0 0 0 0 10000 0 14 Subaru \n",
"\n",
" model mpgData phevBlended pv2 pv4 range rangeCity \\\n",
"0 Spider Veloce 2000 Y False 0 0 0 0 \n",
"1 Testarossa N False 0 0 0 0 \n",
"2 Charger Y False 0 0 0 0 \n",
"3 B150/B250 Wagon 2WD N False 0 0 0 0 \n",
"4 Legacy AWD Turbo N False 0 90 0 0 \n",
"\n",
" rangeCityA rangeHwy rangeHwyA trany UCity UCityA \\\n",
"0 0 0 0 Manual 5-spd 23.3333 0 \n",
"1 0 0 0 Manual 5-spd 11.0000 0 \n",
"2 0 0 0 Manual 5-spd 29.0000 0 \n",
"3 0 0 0 Automatic 3-spd 12.2222 0 \n",
"4 0 0 0 Manual 5-spd 21.0000 0 \n",
"\n",
" UHighway UHighwayA VClass year youSaveSpend guzzler \\\n",
"0 35.0000 0 Two Seaters 1985 -1000 NaN \n",
"1 19.0000 0 Two Seaters 1985 -11750 T \n",
"2 47.0000 0 Subcompact Cars 1985 1750 NaN \n",
"3 16.6667 0 Vans 1985 -11750 NaN \n",
"4 32.0000 0 Compact Cars 1993 -3750 NaN \n",
"\n",
" trans_dscr tCharger sCharger atvType fuelType2 rangeA evMotor mfrCode \n",
"0 NaN NaN NaN NaN NaN NaN NaN NaN \n",
"1 NaN NaN NaN NaN NaN NaN NaN NaN \n",
"2 SIL NaN NaN NaN NaN NaN NaN NaN \n",
"3 NaN NaN NaN NaN NaN NaN NaN NaN \n",
"4 NaN T NaN NaN NaN NaN NaN NaN "
]
}
],
"prompt_number": 307
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### If you rather observe the columns vertically, we can transpose the dataframe:"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"df1 = vehicles.head(1)\n",
"df1.transpose()"
],
"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>0</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>barrels08</th>\n",
" <td> 15.68944</td>\n",
" </tr>\n",
" <tr>\n",
" <th>barrelsA08</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>charge120</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>charge240</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>city08</th>\n",
" <td> 19</td>\n",
" </tr>\n",
" <tr>\n",
" <th>city08U</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>cityA08</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>cityA08U</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>cityCD</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>cityE</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>cityUF</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>co2</th>\n",
" <td> -1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>co2A</th>\n",
" <td> -1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>co2TailpipeAGpm</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>co2TailpipeGpm</th>\n",
" <td> 423.1905</td>\n",
" </tr>\n",
" <tr>\n",
" <th>comb08</th>\n",
" <td> 21</td>\n",
" </tr>\n",
" <tr>\n",
" <th>comb08U</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>combA08</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>combA08U</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>combE</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>combinedCD</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>combinedUF</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>cylinders</th>\n",
" <td> 4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>displ</th>\n",
" <td> 2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>drive</th>\n",
" <td> Rear-Wheel Drive</td>\n",
" </tr>\n",
" <tr>\n",
" <th>engId</th>\n",
" <td> 9011</td>\n",
" </tr>\n",
" <tr>\n",
" <th>eng_dscr</th>\n",
" <td> (FFS)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>feScore</th>\n",
" <td> -1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>fuelCost08</th>\n",
" <td> 2400</td>\n",
" </tr>\n",
" <tr>\n",
" <th>fuelCostA08</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>fuelType</th>\n",
" <td> Regular</td>\n",
" </tr>\n",
" <tr>\n",
" <th>fuelType1</th>\n",
" <td> Regular Gasoline</td>\n",
" </tr>\n",
" <tr>\n",
" <th>ghgScore</th>\n",
" <td> -1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>ghgScoreA</th>\n",
" <td> -1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>highway08</th>\n",
" <td> 25</td>\n",
" </tr>\n",
" <tr>\n",
" <th>highway08U</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>highwayA08</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>highwayA08U</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>highwayCD</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>highwayE</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>highwayUF</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>hlv</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>hpv</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>id</th>\n",
" <td> 1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>lv2</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>lv4</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>make</th>\n",
" <td> Alfa Romeo</td>\n",
" </tr>\n",
" <tr>\n",
" <th>model</th>\n",
" <td> Spider Veloce 2000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mpgData</th>\n",
" <td> Y</td>\n",
" </tr>\n",
" <tr>\n",
" <th>phevBlended</th>\n",
" <td> False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>pv2</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>pv4</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>range</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>rangeCity</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>rangeCityA</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>rangeHwy</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>rangeHwyA</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trany</th>\n",
" <td> Manual 5-spd</td>\n",
" </tr>\n",
" <tr>\n",
" <th>UCity</th>\n",
" <td> 23.3333</td>\n",
" </tr>\n",
" <tr>\n",
" <th>UCityA</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>UHighway</th>\n",
" <td> 35</td>\n",
" </tr>\n",
" <tr>\n",
" <th>UHighwayA</th>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>VClass</th>\n",
" <td> Two Seaters</td>\n",
" </tr>\n",
" <tr>\n",
" <th>year</th>\n",
" <td> 1985</td>\n",
" </tr>\n",
" <tr>\n",
" <th>youSaveSpend</th>\n",
" <td> -1000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>guzzler</th>\n",
" <td> NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trans_dscr</th>\n",
" <td> NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>tCharger</th>\n",
" <td> NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>sCharger</th>\n",
" <td> NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>atvType</th>\n",
" <td> NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>fuelType2</th>\n",
" <td> NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>rangeA</th>\n",
" <td> NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>evMotor</th>\n",
" <td> NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mfrCode</th>\n",
" <td> NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"metadata": {},
"output_type": "pyout",
"prompt_number": 308,
"text": [
" 0\n",
"barrels08 15.68944\n",
"barrelsA08 0\n",
"charge120 0\n",
"charge240 0\n",
"city08 19\n",
"city08U 0\n",
"cityA08 0\n",
"cityA08U 0\n",
"cityCD 0\n",
"cityE 0\n",
"cityUF 0\n",
"co2 -1\n",
"co2A -1\n",
"co2TailpipeAGpm 0\n",
"co2TailpipeGpm 423.1905\n",
"comb08 21\n",
"comb08U 0\n",
"combA08 0\n",
"combA08U 0\n",
"combE 0\n",
"combinedCD 0\n",
"combinedUF 0\n",
"cylinders 4\n",
"displ 2\n",
"drive Rear-Wheel Drive\n",
"engId 9011\n",
"eng_dscr (FFS)\n",
"feScore -1\n",
"fuelCost08 2400\n",
"fuelCostA08 0\n",
"fuelType Regular\n",
"fuelType1 Regular Gasoline\n",
"ghgScore -1\n",
"ghgScoreA -1\n",
"highway08 25\n",
"highway08U 0\n",
"highwayA08 0\n",
"highwayA08U 0\n",
"highwayCD 0\n",
"highwayE 0\n",
"highwayUF 0\n",
"hlv 0\n",
"hpv 0\n",
"id 1\n",
"lv2 0\n",
"lv4 0\n",
"make Alfa Romeo\n",
"model Spider Veloce 2000\n",
"mpgData Y\n",
"phevBlended False\n",
"pv2 0\n",
"pv4 0\n",
"range 0\n",
"rangeCity 0\n",
"rangeCityA 0\n",
"rangeHwy 0\n",
"rangeHwyA 0\n",
"trany Manual 5-spd\n",
"UCity 23.3333\n",
"UCityA 0\n",
"UHighway 35\n",
"UHighwayA 0\n",
"VClass Two Seaters\n",
"year 1985\n",
"youSaveSpend -1000\n",
"guzzler NaN\n",
"trans_dscr NaN\n",
"tCharger NaN\n",
"sCharger NaN\n",
"atvType NaN\n",
"fuelType2 NaN\n",
"rangeA NaN\n",
"evMotor NaN\n",
"mfrCode NaN"
]
}
],
"prompt_number": 308
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"vehicles.fuelType.value_counts()"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 309,
"text": [
"Regular 24056\n",
"Premium 8950\n",
"Gasoline or E85 1092\n",
"Diesel 1058\n",
"Premium or E85 103\n",
"Electricity 68\n",
"CNG 59\n",
"Midgrade 52\n",
"Gasoline or natural gas 18\n",
"Regular Gas and Electricity 11\n",
"Premium Gas or Electricity 10\n",
"Gasoline or propane 8\n",
"Premium and Electricity 5\n",
"dtype: int64"
]
}
],
"prompt_number": 309
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"vehicles.fuelType1.value_counts() # or you can do: vehicles[\"fuelType1\"].value_counts()"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 310,
"text": [
"Regular Gasoline 25185\n",
"Premium Gasoline 9068\n",
"Diesel 1058\n",
"Electricity 68\n",
"Natural Gas 59\n",
"Midgrade Gasoline 52\n",
"dtype: int64"
]
}
],
"prompt_number": 310
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"vehicles.make.value_counts()"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 311,
"text": [
"Chevrolet 3630\n",
"Ford 2941\n",
"Dodge 2460\n",
"GMC 2299\n",
"Toyota 1827\n",
"BMW 1491\n",
"Nissan 1261\n",
"Mercedes-Benz 1145\n",
"Volkswagen 1055\n",
"Mitsubishi 999\n",
"Mazda 914\n",
"Pontiac 893\n",
"Audi 842\n",
"Honda 837\n",
"Subaru 793\n",
"Jeep 778\n",
"Porsche 754\n",
"Volvo 708\n",
"Chrysler 684\n",
"Mercury 609\n",
"Buick 594\n",
"Hyundai 576\n",
"Plymouth 526\n",
"Suzuki 515\n",
"Cadillac 470\n",
"Oldsmobile 462\n",
"Isuzu 434\n",
"Saab 432\n",
"Kia 416\n",
"Lexus 343\n",
"Jaguar 305\n",
"Infiniti 297\n",
"Saturn 278\n",
"Acura 277\n",
"MINI 256\n",
"Lincoln 236\n",
"Ferrari 183\n",
"Eagle 161\n",
"Rolls-Royce 157\n",
"Geo 147\n",
"Aston Martin 128\n",
"Land Rover 125\n",
"Bentley 100\n",
"Peugeot 98\n",
"Lamborghini 97\n",
"Maserati 97\n",
"Scion 74\n",
"Daewoo 67\n",
"Renault 56\n",
"Lotus 55\n",
"Roush Performance 47\n",
"Alfa Romeo 44\n",
"J.K. Motors 36\n",
"Ram 36\n",
"Wallace Environmental 32\n",
"Maybach 31\n",
"American Motors Corporation 27\n",
"Fiat 26\n",
"smart 22\n",
"Hummer 19\n",
"CX Automotive 17\n",
"Daihatsu 17\n",
"Merkur 14\n",
"Federal Coach 14\n",
"Import Trade Services 13\n",
"Spyker 13\n",
"Sterling 12\n",
"Dabryan Coach Builders Inc 9\n",
"Yugo 8\n",
"Bugatti 8\n",
"Bertone 7\n",
"McLaren Automotive 7\n",
"AM General 6\n",
"Pininfarina 6\n",
"Tecstar, LP 6\n",
"Mcevoy Motors 6\n",
"Tesla 6\n",
"Saleen 5\n",
"VPG 5\n",
"Saleen Performance 5\n",
"Bitter Gmbh and Co. Kg 5\n",
"Vector 4\n",
"Grumman Olson 4\n",
"Texas Coach Company 4\n",
"Autokraft Limited 4\n",
"Kenyon Corporation Of America 4\n",
"TVR Engineering Ltd 4\n",
"Panther Car Company Limited 4\n",
"Bill Dovell Motor Car Company 4\n",
"Ruf Automobile Gmbh 3\n",
"Evans Automobiles 3\n",
"Dacia 3\n",
"BYD 3\n",
"Consulier Industries Inc 3\n",
"Morgan 3\n",
"BMW Alpina 3\n",
"Quantum Technologies 2\n",
"Red Shift Ltd. 2\n",
"PAS, Inc 2\n",
"PAS Inc - GMC 2\n",
"CODA Automotive 2\n",
"Avanti Motor Corporation 2\n",
"SRT 2\n",
"Laforza Automobile Inc 2\n",
"Mobility Ventures LLC 2\n",
"Azure Dynamics 2\n",
"CCC Engineering 2\n",
"Excalibur Autos 1\n",
"Environmental Rsch and Devp Corp 1\n",
"Isis Imports Ltd 1\n",
"Qvale 1\n",
"Grumman Allied Industries 1\n",
"London Taxi 1\n",
"Import Foreign Auto Sales Inc 1\n",
"Aurora Cars Ltd 1\n",
"S and S Coach Company E.p. Dutton 1\n",
"Fisker 1\n",
"Panoz Auto-Development 1\n",
"Goldacre 1\n",
"ASC Incorporated 1\n",
"London Coach Co Inc 1\n",
"E. P. Dutton, Inc. 1\n",
"Volga Associated Automobile 1\n",
"Shelby 1\n",
"Lambda Control Systems 1\n",
"General Motors 1\n",
"Superior Coaches Div E.p. Dutton 1\n",
"JBA Motorcars, Inc. 1\n",
"Mahindra 1\n",
"Panos 1\n",
"Vixen Motor Company 1\n",
"Length: 131, dtype: int64"
]
}
],
"prompt_number": 311
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Let's say you are wondering how the overall fuel economy (highway + city) has improved with each successive model year of gasoline-based automobiles, how would you find out?"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Looking at the data [metadata](http://www.fueleconomy.gov/feg/ws/index.shtml#vehicle), looks like I need to filter based off of \"fuelType1\", \"fuelType2\", and \"atvType\"."
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"vehicles.fuelType1.value_counts()"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 312,
"text": [
"Regular Gasoline 25185\n",
"Premium Gasoline 9068\n",
"Diesel 1058\n",
"Electricity 68\n",
"Natural Gas 59\n",
"Midgrade Gasoline 52\n",
"dtype: int64"
]
}
],
"prompt_number": 312
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"vehicles.fuelType2.value_counts()"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 313,
"text": [
"E85 1195\n",
"Electricity 26\n",
"Natural Gas 18\n",
"Propane 8\n",
"dtype: int64"
]
}
],
"prompt_number": 313
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"vehicles.atvType.value_counts()"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 314,
"text": [
"FFV 1195\n",
"Diesel 986\n",
"Hybrid 388\n",
"EV 68\n",
"CNG 49\n",
"Plug-in Hybrid 26\n",
"Bifuel (CNG) 18\n",
"Bifuel (LPG) 8\n",
"dtype: int64"
]
}
],
"prompt_number": 314
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"# Ensure automobile only takes gasoline as fuel\n",
"criteria1 = vehicles.fuelType1.isin(['Regular Gasoline','Premium Gasoline','Midgrade Gasoline'])\n",
"# Ensure it doesn't have a secondary fuel source\n",
"criteria2 = vehicles.fuelType2.isnull()\n",
"# Ensure car is not a hybrid\n",
"criteria3 = vehicles.atvType != 'Hybrid'"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 315
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"# Apply the criteria\n",
"vehicle_non_hybrid = vehicles[criteria1 & criteria2 & criteria3]"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 316
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"# Group the data by model year\n",
"grouped = vehicle_non_hybrid.groupby(['year'])"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 317
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"# Get the average mpg for each model year\n",
"average = grouped['comb08'].agg(np.mean)"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 320
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"# Let's plot the average mpg with each model year\n",
"average.plot()\n",
"plt.title(\"Average Overall MPG by Model Year\")\n",
"plt.show()"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "display_data",
"png": "iVBORw0KGgoAAAANSUhEUgAAAfQAAAFwCAYAAABO94lEAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nKugiIiIRoIIuIiISASroIiIiEfD/CbnXJqOryloAAAAASUVORK5CYII=\n",
"text": [
"<matplotlib.figure.Figure at 0xa1a9b82c>"
]
}
],
"prompt_number": 323
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Let's compare average overall mpg of gasonline-based Hondas vs Toyotas"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"# Ensure automobile only takes gasoline as fuel\n",
"criteria1 = vehicles.fuelType1.isin(['Regular Gasoline','Premium Gasoline','Midgrade Gasoline'])\n",
"# Ensure it doesn't have a secondary fuel source\n",
"criteria2 = vehicles.fuelType2.isnull()\n",
"# Ensure car is not a hybrid\n",
"criteria3 = vehicles.atvType != 'Hybrid'\n",
"criteria4 = vehicles.make.isin(['Honda'])\n",
"\n",
"honda_vehicle_non_hybrid = vehicles[criteria1 & criteria2 & criteria3 & criteria4]"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 324
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"criteria1 = vehicles.fuelType1.isin(['Regular Gasoline','Premium Gasoline','Midgrade Gasoline'])\n",
"criteria2 = vehicles.fuelType2.isnull()\n",
"criteria3 = vehicles.atvType != 'Hybrid'\n",
"criteria4 = vehicles.make.isin(['Toyota'])\n",
"\n",
"toyota_vehicle_non_hybrid = vehicles[criteria1 & criteria2 & criteria3 & criteria4]"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 325
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"honda_grouped = honda_vehicle_non_hybrid.groupby(['year'])\n",
"honda_average = honda_grouped['comb08'].agg(np.mean)"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 326
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"toyota_grouped = toyota_vehicle_non_hybrid.groupby(['year'])\n",
"toyota_average = toyota_grouped['comb08'].agg(np.mean)"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 327
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"fig = plt.figure()\n",
"axes = fig.add_axes([0.1, 0.1, 0.8, 0.8])\n",
"axes.plot(honda_average.index, honda_average.values, label=\"Honda\")\n",
"axes.plot(toyota_average.index, toyota_average.values, label=\"Toyota\")\n",
"plt.legend()\n",
"plt.title(\"Honda vs Toyota Overall MPG by Model Year\")\n",
"plt.show()"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "display_data",
"png": "iVBORw0KGgoAAAANSUhEUgAAAfkAAAFrCAYAAADSGPCsAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nEEIIN/X/AW9PaZxGTOztAAAAAElFTkSuQmCC\n",
"text": [
"<matplotlib.figure.Figure at 0xa14d756c>"
]
}
],
"prompt_number": 333
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Is there a way I could've made this chart above from just one dataframe?"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"criteria1 = vehicles.fuelType1.isin(['Regular Gasoline','Premium Gasoline','Midgrade Gasoline'])\n",
"criteria2 = vehicles.fuelType2.isnull()\n",
"criteria3 = vehicles.atvType != 'Hybrid'\n",
"criteria4 = vehicles.make.isin(['Honda','Toyota'])\n",
"\n",
"honda_toyota_vehicle_non_hybrid = vehicles[criteria1 & criteria2 & criteria3 & criteria4]"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 342
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"honda_toyota_grouped = honda_toyota_vehicle_non_hybrid.groupby(['year','make'])\n",
"honda_toyota_average = honda_toyota_grouped['comb08'].agg(np.mean)"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 343
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"print(honda_toyota_average)"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"year make \n",
"1984 Honda 28.083333\n",
" Toyota 23.044118\n",
"1985 Honda 26.906250\n",
" Toyota 22.925926\n",
"1986 Honda 27.650000\n",
" Toyota 21.660714\n",
"1987 Honda 27.750000\n",
" Toyota 21.875000\n",
"1988 Honda 27.791667\n",
" Toyota 21.422535\n",
"1989 Honda 26.800000\n",
" Toyota 20.969697\n",
"1990 Honda 25.954545\n",
" Toyota 20.620690\n",
"1991 Honda 25.500000\n",
" Toyota 20.155172\n",
"1992 Honda 27.500000\n",
" Toyota 19.948276\n",
"1993 Honda 27.545455\n",
" Toyota 19.118644\n",
"1994 Honda 25.225806\n",
" Toyota 20.081633\n",
"1995 Honda 24.939394\n",
" Toyota 20.596774\n",
"1996 Honda 23.533333\n",
" Toyota 21.236364\n",
"1997 Honda 23.615385\n",
" Toyota 20.907407\n",
"1998 Honda 23.047619\n",
" Toyota 20.890909\n",
"1999 Honda 22.720000\n",
" Toyota 21.714286\n",
"2000 Honda 22.739130\n",
" Toyota 20.603774\n",
"2001 Honda 23.272727\n",
" Toyota 20.560000\n",
"2002 Honda 23.714286\n",
" Toyota 20.591837\n",
"2003 Honda 24.047619\n",
" Toyota 20.946429\n",
"2004 Honda 24.047619\n",
" Toyota 20.927273\n",
"2005 Honda 23.954545\n",
" Toyota 21.519231\n",
"2006 Honda 21.700000\n",
" Toyota 20.431818\n",
"2007 Honda 22.772727\n",
" Toyota 20.434783\n",
"2008 Honda 22.920000\n",
" Toyota 20.217391\n",
"2009 Honda 23.000000\n",
" Toyota 20.634615\n",
"2010 Honda 23.076923\n",
" Toyota 20.961538\n",
"2011 Honda 23.800000\n",
" Toyota 21.000000\n",
"2012 Honda 25.125000\n",
" Toyota 21.061224\n",
"2013 Honda 25.739130\n",
" Toyota 21.333333\n",
"2014 Honda 25.900000\n",
" Toyota 22.021739\n",
"2015 Honda 27.727273\n",
" Toyota 22.439024\n",
"Name: comb08, Length: 64, dtype: float64\n"
]
}
],
"prompt_number": 344
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"honda_toyota_average.plot(by='make')"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 346,
"text": [
"<matplotlib.axes._subplots.AxesSubplot at 0xa13423ec>"
]
},
{
"metadata": {},
"output_type": "display_data",
"png": "iVBORw0KGgoAAAANSUhEUgAAAf4AAAFhCAYAAACRX8izAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nxATx/wEqDDew7B60vwAAAABJRU5ErkJggg==\n",
"text": [
"<matplotlib.figure.Figure at 0xa1348e4c>"
]
}
],
"prompt_number": 346
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### This didn't work!"
]
}
],
"metadata": {}
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment