Homework Airquality

library(tidyverse)

## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --

## v ggplot2 3.3.5     v purrr   0.3.4
## v tibble  3.1.4     v dplyr   1.0.7
## v tidyr   1.1.3     v stringr 1.4.0
## v readr   2.0.1     v forcats 0.5.1

## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

Showing 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 ...

airquality <- airquality

Calulating summary statistics

One way of calculating “mean”

mean(airquality$Temp)

## [1] 77.88235

Another way of calculating “mean”

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

Changing 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"

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 ...

Plot 1: Histogram Categorized by Month with qplot

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

Plot 2: 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: 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: Same as previous Side-by-Side Boxplots, but in grey-scale

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: Scatterplot using plot

plot(airquality$Temp, airquality$Wind, main = 'Shows no strong correlation between Temperature and Wind', xlab = 'Temperatures', ylab='Wind')
abline(lm(Wind ~ Temp, data = airquality), col='red')

#plot(airquality)

airquality %>%
  ggplot(aes(Temp,Wind, color=Ozone))+
  geom_point(size=3)+
  labs(x="Temperature",y="Wind",title="Correlation between Temperature and Wind")+
  geom_smooth(method="lm", color='red')+
  theme_bw()

## `geom_smooth()` using formula 'y ~ x'