Exploring and Understanding Data with R

Exploring and understanding data ——————–

data exploration example using used car data

getwd()

[1] "C:/Users/npenaper/Downloads"

setwd("C:/Users/npenaper/Documents")

usedcars <- read.csv("usedcars.csv", stringsAsFactors = FALSE)

# get structure of used car data
str(usedcars)

'data.frame':   150 obs. of  6 variables:
 $ year        : int  2011 2011 2011 2011 2012 2010 2011 2010 2011 2010 ...
 $ model       : chr  "SEL" "SEL" "SEL" "SEL" ...
 $ price       : int  21992 20995 19995 17809 17500 17495 17000 16995 16995 16995
$ mileage     : int   ...
 $ color        chr  "Yellow" "Gray" "Silver" "Gray" ...
 $ transmission: chr  "AUTO" "AUTO" "AUTO" "AUTO" ...

Exploring numeric variables —–

# summarize numeric variables
summary(usedcars$year)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
   2000    2008    2009    2009    2010    2012 

summary(usedcars[c("price", "mileage")])

     price      
 Min.   : 3800   Min.   :  4867  
 1st Qu.:10995   1st Qu.: 27200  
 Median :13592   Median : 36385  
 Mean   :12962   Mean   : 44261  
 3rd Qu.:14904  
 Max.   :21992   Max.   :151479  

# calculate the mean income
(36000 + 44000 + 56000) / 3

[1] 45333.33

mean(c(36000, 44000, 56000))

[1] 45333.33

# the median income
median(c(36000, 44000, 56000))

[1] 44000

# the min/max of used car prices
range(usedcars$price)

[1]  3800 21992

# the difference of the range
diff(range(usedcars$price))

 18192

# IQR for used car prices
IQR(usedcars$price)

[1] 3909.5

# use quantile to calculate five-number summary
quantile(usedcars$price)

     0%     25%     50%     75%    100% 
 3800.0 10995.0 13591.5 14904.5 21992.0 

# the 99th percentile
quantile(usedcars$price, probs = c(0.01, 0.99))

      1%      99% 
 5428.69 20505.00 

# quintiles
quantile(usedcars$price, seq(from = 0, to = 1, by = 0.20))

     0%     20%     40%     60%     80%    100% 
 3800.0 10759.4 12993.8 13992.0 14999.0 21992.0 

# boxplot of used car prices and mileage
boxplot(usedcars$price, main="Boxplot of Used Car Prices",
      ylab="Price ($)")

boxplot(usedcars$mileage, main="Boxplot of Used Car Mileage",
      ylab="Odometer (mi.)")

# histograms of used car prices and mileage
hist(usedcars$price, main = "Histogram of Used Car Prices",
     xlab = "Price ($)")

hist(usedcars$mileage, main = "Histogram of Used Car Mileage",
     xlab = "Odometer (mi.)")

# variance and standard deviation of the used car data
var(usedcars$price)

[1] 9749892

sd(usedcars$price)

 3122.482

var(usedcars$mileage)

[1] 728033954

sd(usedcars$mileage)

[1] 26982.1

Exploring numeric variables —–

# one-way tables for the used car data
table(usedcars$year)

2000 2001 2002 2003 2004 2005 2007 2008 2009 2010 2011 2012 
   1    1    1    3    6   11   14   42   49   16    1 

table(usedcars$model)

 SE SEL SES 
 23  49 

table(usedcars$color)

 Black   Blue   Gold   Gray  Green    Red Silver  White 
    35     17     16      5     32     16 

# compute table proportions
model_table <- table(usedcars$model)
prop.table(model_table)

       SE       SEL       SES 
0.5200000 0.1533333 0.3266667 

# round the data
color_table <- table(usedcars$color)
color_pct <- prop.table(color_table) * 100
round(color_pct, digits = 1)

 Black   Gold   Gray    Red Silver Yellow 
  11.3    0.7    3.3   16.7   10.7    2.0 

Exploring relationships between variables —–

# scatterplot of price vs. mileage
plot(x = usedcars$mileage, y = usedcars$price,
     main = "Scatterplot of Price vs. Mileage",
     xlab = "Used Car Odometer (mi.)",
     ylab = "Used Car Price ($)")

# new variable indicating conservative colors
usedcars$conservative <-
  usedcars$color %in% c("Black", "Gray", "Silver", "White")

# checking our variable
table(usedcars$conservative)

FALSE  TRUE    51    99 

install.packages("gmodels")

WARNING: Rtools is required to build R packages but is not currently installed. Please download and install the appropriate version of Rtools before proceeding:

https://cran.rstudio.com/bin/windows/Rtools/
Installing package into ‘C:/Users/npenaper/AppData/Local/R/win-library/4.2’
(as ‘lib’ is unspecified)
also installing the dependency ‘gdata’

trying URL 'https://cran.rstudio.com/bin/windows/contrib/4.2/gdata_3.0.0.zip'
Content type 'application/zip' length 495777 bytes (484 KB)
downloaded 484 KB

trying URL 'https://cran.rstudio.com/bin/windows/contrib/4.2/gmodels_2.18.1.1.zip'
Content type 'application/zip' length 114240 bytes (111 KB)
downloaded 111 KB

package ‘gdata’ successfully unpacked and MD5 sums checked
package ‘gmodels’ successfully unpacked and MD5 sums checked

# Crosstab of conservative by model
library(gmodels)

Warning: package ‘gmodels’ was built under R version 4.2.3

CrossTable(x = usedcars$model, y = usedcars$conservative)

 
   Cell Contents
|-------------------------|
|                       N |
| Chi-square contribution |
|           N / Col Total |
|         N / Table Total |

 
Total Observations in Table:  150 

 
              | usedcars$conservative 
usedcars$model |     FALSE |      TRUE | Row Total | 
---------------|-----------|-----------|-----------
            SE |        27 |        51 |        78
               |  |     0.004 |  | 
               |  |     0.654 |     0.520
                  0.529 |  |           |                |     0.180    0.340 |           | ---------------|----------------------||
           SEL        7 |        16 |  | 
               |     0.086 |     0.044          | 
 |     0.304 |  |     0.153
                  0.137 |  |           |                |  |     0.107          | ---------------||----------------------|
           SES       17 |        32       49 | 
               |     0.007 |     0.004          | 
                  0.347 |     0.653    0.327 | 
               |     0.323 |  | 
                  0.113 |     0.213 |           | ---------------|----------------------|-----------|
 |        51       99 |  | 
                  0.340 |     0.660          | 
|----------------------|-----------|