Class Activity #4

Exploring and Understanding Data with R - data exploration example using used car data

getwd() #shows current work dirctory 

[1] "/cloud/project"

setwd("/cloud/project") #changes the work directory 

#Import the usedcars.csv file from the working directory into R as a data frame
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  7413 10926 7351 11613 8367 25125 27393 21026 32655 36116 ...
 $ color       : chr  "Yellow" "Gray" "Silver" "Gray" ...
 $ transmission: chr  "AUTO" "AUTO" "AUTO" "AUTO" ...

#Exploring numeric values

# 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          mileage      
 Min.   : 3800   Min.   :  4867  
 1st Qu.:10995   1st Qu.: 27200  
 Median :13592   Median : 36385  
 Mean   :12962   Mean   : 44261  
 3rd Qu.:14904   3rd Qu.: 55124  
 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))

[1] 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)

[1] 3122.482

var(usedcars$mileage)

[1] 728033954

sd(usedcars$mileage)

[1] 26982.1

#Exploring numeric variables p2

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

2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 
   3    1    1    1    3    2    6   11   14   42   49   16 
2012 
   1 

table(usedcars$model)

 SE SEL SES 
 78  23  49 

table(usedcars$color)

 Black   Blue   Gold   Gray  Green    Red Silver  White Yellow 
    35     17      1     16      5     25     32     16      3 

# 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   Blue   Gold   Gray  Green    Red Silver  White Yellow 
  23.3   11.3    0.7   10.7    3.3   16.7   21.3   10.7    2.0 

#Exploring relationship 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 

# The gmodels package is used for data exploration and analysis, particularly for creating detailed
# cross-tabulations and summary tables like (CrossTable); it is needed when analyzing relationships
# between categorical variables, but not required for basic data import or simple summaries
install.packages("gmodels")

# Crosstab of conservative by model
library(gmodels)

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

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

 
Total Observations in Table:  150 

 
               | usedcars$conservative 
usedcars$model |     FALSE |      TRUE | Row Total | 
---------------|-----------|-----------|-----------|
            SE |        27 |        51 |        78 | 
               |     0.009 |     0.004 |           | 
               |     0.346 |     0.654 |     0.520 | 
               |     0.529 |     0.515 |           | 
               |     0.180 |     0.340 |           | 
---------------|-----------|-----------|-----------|
           SEL |         7 |        16 |        23 | 
               |     0.086 |     0.044 |           | 
               |     0.304 |     0.696 |     0.153 | 
               |     0.137 |     0.162 |           | 
               |     0.047 |     0.107 |           | 
---------------|-----------|-----------|-----------|
           SES |        17 |        32 |        49 | 
               |     0.007 |     0.004 |           | 
               |     0.347 |     0.653 |     0.327 | 
               |     0.333 |     0.323 |           | 
               |     0.113 |     0.213 |           | 
---------------|-----------|-----------|-----------|
  Column Total |        51 |        99 |       150 | 
               |     0.340 |     0.660 |           | 
---------------|-----------|-----------|-----------|