Load in Dataset

library("tidyverse")
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.0 ──
## ✓ ggplot2 3.3.3     ✓ purrr   0.3.4
## ✓ tibble  3.0.6     ✓ dplyr   1.0.4
## ✓ tidyr   1.1.2     ✓ stringr 1.4.0
## ✓ readr   1.4.0     ✓ forcats 0.5.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

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

Calculate Median,SD and Variance

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

Change months from int to char

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"

Month change to char 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 statistics of dataset

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 Months so they do not default to alphabetical order

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

Plot:1 Create histogram categorized by Month with qplot

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

Plot 2:Make histogram using ggplot

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

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:Create side-by-side boxplots categorized by Month in grey scale

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

Plot 5 : Scatter plot using ggplot

ggplot(data = airquality) +
  geom_point(mapping = aes(x=Temp,y=Ozone,color = Month))
## Warning: Removed 37 rows containing missing values (geom_point).