Exploring and Understanding Data with R
Data exploration example using used car data
getwd()## [1] "/cloud/project"I uploaded the file to the cloud “/cloud/project” and therefore I can access it directly from here. Assign the file to the variable usedcars
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 variables Summarize numeric variables
# summarize numeric variables
summary(usedcars$year)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2000 2008 2009 2009 2010 2012summary(usedcars$price)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 3800 10995 13592 12962 14904 21992summary(usedcars$mileage)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 4867 27200 36385 44261 55124 151479summary(usedcars[c("price", "mileage")])## price mileage
## Min. : 3800 Min. : 4867
## 1st Qu.:10995 1st Qu.: 27200
## Median :13592 Median : 36385
## Mean :12962 Mean : 44261
## 3rd Qu.:14904 3rd Qu.: 55124
## Max. :21992 Max. :151479Calculate the mean income
# calculate the mean income
(36000 + 44000 + 56000) / 3## [1] 45333.33mean(c(36000, 44000, 56000))## [1] 45333.33Calculate the median income
# the median income
median(c(36000, 44000, 56000))## [1] 44000Calculate the min/max of used car prices
# the min/max of used car prices
range(usedcars$price)## [1] 3800 21992Calculate the min/max of used car mileage
range(usedcars$mileage)## [1] 4867 151479Calculate the difference of the range
# the difference of the range
diff(range(usedcars$price))## [1] 18192Calculate IQR for used car prices
# IQR for used car prices
IQR(usedcars$price)## [1] 3909.5Use quantile to calculate five-number summary (price)
# use quantile to calculate five-number summary
quantile(usedcars$price)## 0% 25% 50% 75% 100%
## 3800.0 10995.0 13591.5 14904.5 21992.0Use quantile to calculate five-number summary (mileage)
quantile(usedcars$mileage)## 0% 25% 50% 75% 100%
## 4867.00 27200.25 36385.00 55124.50 151479.00Calculate the 99th percentile
# the 99th percentile
quantile(usedcars$price, probs = c(0.01, 0.99))## 1% 99%
## 5428.69 20505.00Quintiles of price (from 0 to 1)
# quintiles
quantile(usedcars$price, seq(from = 0, to = 1, by = 0.20))## 0% 20% 40% 60% 80% 100%
## 3800.0 10759.4 12993.8 13992.0 14999.0 21992.0Display boxplot of used car prices and mileage
# boxplot of used car prices and mileage
boxplot(usedcars$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
# histograms of used car prices and mileage
hist(usedcars$price, main = "Histogram of Used Car Prices",
xlab = "Price ($)")
hist(usedcars$mileage, main = "Histogram of Used Car Mileage",
xlab = "Odometer (mi.)")
Variance and standard deviation of the used car data
Variance of price
# variance and standard deviation of the used car data
var(usedcars$price)## [1] 9749892Standard deviation of price
sd(usedcars$price)## [1] 3122.482Variance of mileage
var(usedcars$mileage)## [1] 728033954Standard deviation of mileage
sd(usedcars$mileage)## [1] 26982.1Exploring numeric variables One-way tables for the used car data Year as columns
# one-way tables for the used car data
table(usedcars$year)##
## 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012
## 3 1 1 1 3 2 6 11 14 42 49 16 1Model as columns
table(usedcars$model)##
## SE SEL SES
## 78 23 49Color as columns
table(usedcars$color)##
## Black Blue Gold Gray Green Red Silver White Yellow
## 35 17 1 16 5 25 32 16 3Compute table proportions
# compute table proportions
model_table <- table(usedcars$model)
prop.table(model_table)##
## SE SEL SES
## 0.5200000 0.1533333 0.3266667Round the data
# round the data
color_table <- table(usedcars$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 2.0Exploring 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 ($)")
New variable indicating conservative colors
# new variable indicating conservative colors
usedcars$conservative <-
usedcars$color %in% c("Black", "Gray", "Silver", "White")# checking our variable
table(usedcars$conservative)##
## FALSE TRUE
## 51 99install.packages("gmodels")## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.5'
## (as 'lib' is unspecified)Crosstab of conservative by model
# 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 | |
## ---------------|-----------|-----------|-----------|
##
##