Load in the Dataset.

Because airquality is a pre-built dataset, we can write it to our data directory to store it for later use.

# install.packages("tidyverse")
library(tidyverse)
## -- Attaching packages --------------------------------------- tidyverse 1.3.0 --
## v ggplot2 3.3.1     v purrr   0.3.4
## v tibble  3.0.1     v dplyr   1.0.0
## v tidyr   1.1.0     v stringr 1.4.0
## v readr   1.3.1     v forcats 0.5.0
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

Show the data

Look at the structure of the data

str(airquality)
## 'data.frame':    153 obs. of  6 variables:
##  $ Ozone  : int  41 36 12 18 NA 28 23 19 8 NA ...
##  $ Solar.R: int  190 118 149 313 NA NA 299 99 19 194 ...
##  $ Wind   : num  7.4 8 12.6 11.5 14.3 14.9 8.6 13.8 20.1 8.6 ...
##  $ Temp   : int  67 72 74 62 56 66 65 59 61 69 ...
##  $ Month  : int  5 5 5 5 5 5 5 5 5 5 ...
##  $ Day    : int  1 2 3 4 5 6 7 8 9 10 ...

Calculating Summary Statistics

mean(airquality$Temp)
## [1] 77.88235
mean(airquality[,4])
## [1] 77.88235

Calculate Median, Standard Deviation, and Variance

median(airquality$Temp)
## [1] 79
sd(airquality$Wind)
## [1] 3.523001
var(airquality$Wind)
## [1] 12.41154

Change the Months from 5 - 9 to May through September

airquality$Month[airquality$Month == 5]<- "May"
airquality$Month[airquality$Month == 6]<- "June"
airquality$Month[airquality$Month == 7]<- "July"
airquality$Month[airquality$Month == 8]<- "August"
airquality$Month[airquality$Month == 9]<- "September"

Look at the summary statistics of the dataset, and see how Month has changed to have characters instead of numbers

str(airquality)
## 'data.frame':    153 obs. of  6 variables:
##  $ Ozone  : int  41 36 12 18 NA 28 23 19 8 NA ...
##  $ Solar.R: int  190 118 149 313 NA NA 299 99 19 194 ...
##  $ Wind   : num  7.4 8 12.6 11.5 14.3 14.9 8.6 13.8 20.1 8.6 ...
##  $ Temp   : int  67 72 74 62 56 66 65 59 61 69 ...
##  $ Month  : chr  "May" "May" "May" "May" ...
##  $ Day    : int  1 2 3 4 5 6 7 8 9 10 ...
summary(airquality)
##      Ozone           Solar.R           Wind             Temp      
##  Min.   :  1.00   Min.   :  7.0   Min.   : 1.700   Min.   :56.00  
##  1st Qu.: 18.00   1st Qu.:115.8   1st Qu.: 7.400   1st Qu.:72.00  
##  Median : 31.50   Median :205.0   Median : 9.700   Median :79.00  
##  Mean   : 42.13   Mean   :185.9   Mean   : 9.958   Mean   :77.88  
##  3rd Qu.: 63.25   3rd Qu.:258.8   3rd Qu.:11.500   3rd Qu.:85.00  
##  Max.   :168.00   Max.   :334.0   Max.   :20.700   Max.   :97.00  
##  NA's   :37       NA's   :7                                       
##     Month                Day      
##  Length:153         Min.   : 1.0  
##  Class :character   1st Qu.: 8.0  
##  Mode  :character   Median :16.0  
##                     Mean   :15.8  
##                     3rd Qu.:23.0  
##                     Max.   :31.0  
##

Month is a categorical variable with different levels, called factors.

Reorder the Months so they do not default to alphabetical

airquality$Month<-factor(airquality$Month, levels=c("May", "June","July", "August", "September"))

Plot 1: Create a histogram categorized by Month with qplot

p1 <- qplot(data = airquality, Temp, fill = Month, geom = "histogram", bins = 20)
p1

Plot 2: Make a histogram using ggplot

ggplot is more sophisticated than qplot, but still uses ggplot2 package

Reorder the legend so that it is not the default (alphabetical), but rather in order that months come

Outline the bars in white using the color = “white” command

p2 <- airquality %>% 
  ggplot(aes(x=Temp, fill=Month)) +
  geom_histogram(position="identity", alpha=0.5, binwidth = 5, color = "white")+
  scale_fill_discrete(name = "Month", labels = c("May", "June", "July", "August", "September"))
p2

Plot 3: Create side-by-side boxplots categorized by Month

fill=Month command fills each boxplot with a different color in aesthetics

scale_fill_discrete makes the legend on the side for discrete color values

p3 <- airquality %>% 
  ggplot(aes(Month, Temp, fill = Month)) +
  ggtitle("Temperatures") +
  xlab("Months") +
  ylab("Frequency") +
  geom_boxplot() +
  scale_fill_discrete(name = "Month", labels = c("May", "June", "July", "August", "September"))
p3

Plot 4: Make the same side-by-side boxplots, but in grey-scale

Use the scale_fill_grey command for the grey-scale legend, and again, use fill=Month in the aesthetics

p4 <- airquality %>% 
  ggplot(aes(Month, Temp, fill = Month)) +
  ggtitle("Temperatures") +
  xlab("Temperatures") +
  ylab("Frequency") +
  geom_boxplot() +
  scale_fill_grey(name = "Month", labels = c("May", "June", "July", "August", "September"))
p4

Plot 5: Now make one plot on your own of any of the variables in this dataset. It may be a scatterplot, histogram or boxplot.

# tried Wind qplot
p5 <- qplot(data = airquality, Wind, fill = Month, geom = "histogram", bins = 20)
p5

# tried Ozone qplot
p6 <- qplot(data = airquality, Ozone, fill = Month, geom = "histogram", bins = 20)
p6
## Warning: Removed 37 rows containing non-finite values (stat_bin).

# tried wind qplot with fill = Day, did not work so well
p7 <- qplot(data = airquality, Wind, fill = Day, geom = "histogram", bins = 20)
p7

# tried wind qplot with fill = Day, changed bins to 100 and still no color but a bit clearer
p8 <- qplot(data = airquality, Wind, fill = Day, geom = "histogram", bins = 100)
p8

#tried qplot with ozone and different bin number
p9 <- qplot(data = airquality, Ozone, fill = Month, geom = "histogram", bins = 50)
p9
## Warning: Removed 37 rows containing non-finite values (stat_bin).

#ggplot with Ozone
p10 <- airquality %>% 
  ggplot(aes(x=Ozone, fill=Month)) +
  geom_histogram(position="identity", alpha=0.5, binwidth = 5, color = "white")+
  scale_fill_discrete(name = "Month", labels = c("May", "June", "July", "August", "September"))
p10
## Warning: Removed 37 rows containing non-finite values (stat_bin).

# ggplot with Ozone larger binwidth than p10
p11 <- airquality %>% 
  ggplot(aes(x=Ozone, fill=Month)) +
  geom_histogram(position="identity", alpha=0.5, binwidth = 10, color = "white")+
  scale_fill_discrete(name = "Month", labels = c("May", "June", "July", "August", "September"))
p11
## Warning: Removed 37 rows containing non-finite values (stat_bin).

# ggplot wind, comparing binwidth with p 13
p12 <- airquality %>% 
  ggplot(aes(x=Wind, fill=Month)) +
  geom_histogram(position="identity", alpha=0.5, binwidth = 10, color = "white")+
  scale_fill_discrete(name = "Month", labels = c("May", "June", "July", "August", "September"))
p12

# ggplot wind, compare binwidth with p12
p13 <- airquality %>% 
  ggplot(aes(x=Wind, fill=Month)) +
  geom_histogram(position="identity", alpha=0.5, binwidth = 5, color = "white")+
  scale_fill_discrete(name = "Month", labels = c("May", "June", "July", "August", "September"))
p13

# ggplot wind, compare binwith with p12 and 13
p14 <- airquality %>% 
  ggplot(aes(x=Wind, fill=Month)) +
  geom_histogram(position="identity", alpha=0.5, binwidth = 0.5, color = "white")+
  scale_fill_discrete(name = "Month", labels = c("May", "June", "July", "August", "September"))
p14

# boxplot with ozone
p14 <- airquality %>% 
  ggplot(aes(Month, Ozone, fill = Month)) +
  ggtitle("Ozone") +
  xlab("Months") +
  ylab("Frequency") +
  geom_boxplot() +
  scale_fill_discrete(name = "Month", labels = c("May", "June", "July", "August", "September"))
p14
## Warning: Removed 37 rows containing non-finite values (stat_boxplot).

# boxplot with wind
p15 <- airquality %>% 
  ggplot(aes(Month, Wind, fill = Month)) +
  ggtitle("Wind") +
  xlab("Months") +
  ylab("Frequency") +
  geom_boxplot() +
  scale_fill_discrete(name = "Month", labels = c("May", "June", "July", "August", "September"))
p15

# Boxplot with Ozone greyscale
p16 <- airquality %>% 
  ggplot(aes(Month, Ozone, fill = Month)) +
  ggtitle("Ozone") +
  xlab("Month") +
  ylab("Frequency") +
  geom_boxplot() +
  scale_fill_grey(name = "Month", labels = c("May", "June", "July", "August", "September"))
p16
## Warning: Removed 37 rows containing non-finite values (stat_boxplot).

# boxplot with wind greyscale
p17 <- airquality %>% 
  ggplot(aes(Month, Wind, fill = Month)) +
  ggtitle("Wind") +
  xlab("Months") +
  ylab("Frequency") +
  geom_boxplot() +
  scale_fill_grey(name = "Month", labels = c("May", "June", "July", "August", "September"))
p17

# histogram Ozone
p18 <- qplot(data = airquality, Ozone, fill = Month, geom = "histogram", bins = 20)
p18
## Warning: Removed 37 rows containing non-finite values (stat_bin).

# histogram Ozone, attempted a fill of Temp instead of Month... not so successful
p19 <- airquality %>% 
  ggplot(aes(x=Ozone, fill=Temp)) +
  geom_histogram(position="identity", alpha=0.5, binwidth = 5, color = "white")+
  scale_fill_grey(name = "Temp", labels = c("65", "72", "56", "67", "55"))
p19
## Warning: Removed 37 rows containing non-finite values (stat_bin).

## Trying to overlay other variables than month, like temp with Ozone, or temp with Wind, etc.
# Scatterplot of Wind and Ozone, not clear how to add color to this...
plot20 <- airquality %>%
  ggplot(aes(Wind, Ozone))+
  geom_point()+
  xlab("Ozone")+
  ylab("Wind mph")+
  ggtitle("Scatterplot of Wind versus Ozone")
plot20
## Warning: Removed 37 rows containing missing values (geom_point).

# Scatterplot of Wind and temperature, not clear how to add color to this...
plot20 <- airquality %>%
  ggplot(aes(Wind, Temp))+
  geom_point()+
  xlab("Ozone")+
  ylab("Temperature")+
  ggtitle("Scatterplot of Wind versus Temperature")
plot20