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 ...
Summary statistics
mean(airquality$Temp)
## [1] 77.88235
mean(airquality[,4])
## [1] 77.88235
Standard Deviation
sd(airquality$Wind)
## [1] 3.523001
var(airquality$Wind)
## [1] 12.41154
Change Months 5-9
airquality$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"
Summary statistics
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
##
Reorder Month
airquality$Month<-factor(airquality$Month, levels=c("May", "June","July", "August", "September"))
Plot 1 - Histogram categorized by Month, qplot
p1 <- qplot(data = airquality,Temp,fill = Month,geom = "histogram", bins = 30)
p1

Plot 2 - Histogram with ggplot
p2 <- airquality %>%
ggplot(aes(x=Temp, fill=Month)) +
geom_histogram(position="identity", alpha=0.5, binwidth = 5, color = "black")+
scale_fill_discrete(name = "Month", labels = c("May", "June","July", "August", "September"))
p2

Plot 3 - Boxplots categorized by Month
p3 <- airquality %>%
ggplot(aes(Month, Temp, fill = Month)) +
ggtitle("Temperatures") +
xlab("Month") +
ylab("Temperature") +
geom_boxplot() +
scale_fill_discrete(name = "Month", labels = c("May", "June","July", "August", "September"))
p3

Plot 4 - Box plots in grey scale
p4 <- airquality %>%
ggplot(aes(Month, Temp, fill = Month)) +
ggtitle("Temperatures") +
xlab("Month") +
ylab("Temperature") +
geom_boxplot()+
scale_fill_grey(name = "Month", labels = c("May", "June","July", "August", "September"))
p4

Plot 5 - (a) Ozone Levels vs Month
p5 <- airquality %>%
ggplot(aes(Month, Ozone,fill = Month)) +
ggtitle("Ozone") +
xlab("Month") +
ylab("Ozone") +
geom_boxplot() +
scale_fill_discrete(name = "Month", labels = c("May", "June","July", "August", "September"))
p5
## Warning: Removed 37 rows containing non-finite values (stat_boxplot).

Plot 5 (b) Ozone level vs Wind speed and Month
p5 <- airquality %>%
ggplot(aes(Wind, Ozone, fill = Month, color = Month)) +
ggtitle("Ozone vs Wind and Month") +
xlab("Wind") +
ylab("Ozone") +
geom_point() +
scale_fill_discrete(name = "Month", labels = c("May", "June","July", "August", "September"))
p5
## Warning: Removed 37 rows containing missing values (geom_point).
