# Load in the Dataset.
## The airquality dataset has been pre-loaded
## 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
## If you want to look at specific statistics, here are some variations on coding. Here are 2 different ways to calculate “mean.”
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 change 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
## Qplot stands for “Quick-Plot” (in the ggplot2 package)
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 the 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.
# BOX PLOTS
## A “boxplot”, or “box-and-whiskers plot” is a graphical summary of a distribution; the box in the middle indicates “hinges” (close to the first and third quartiles) and median. The lines (“whiskers”) show the largest or smallest observation that falls within a distance of 1.5 times the box size from the nearest hinge. If any observations fall farther away, the additional points are considered “extreme” values and are shown separately. A boxplot can often give a good idea of the data distribution.
boxplot(airquality$Wind)
boxplot(airquality[,1:4])
# only for the numerical variables
boxplot(airquality$Wind ~ airquality$Month)
## We can also write the same command using a slightly more readable language:
# boxplot(Temp ~ Month, data = airquality)
p5 <- 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"))
p5
