Assignment 2 HW

Github Profile:

Plot 1

library(tidyverse)

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.2.1     ✔ readr     2.2.0
✔ forcats   1.0.1     ✔ stringr   1.6.0
✔ ggplot2   4.0.3     ✔ tibble    3.3.1
✔ lubridate 1.9.5     ✔ tidyr     1.3.2
✔ purrr     1.2.2     
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

data("airquality") 
head(airquality)

  Ozone Solar.R Wind Temp Month Day
1    41     190  7.4   67     5   1
2    36     118  8.0   72     5   2
3    12     149 12.6   74     5   3
4    18     313 11.5   62     5   4
5    NA      NA 14.3   56     5   5
6    28      NA 14.9   66     5   6

airquality1 <- airquality |>
  mutate(month_name = case_when(Month == 4 ~ "April",
                                Month == 5 ~ "May",
                                Month == 6 ~ "June",
                                Month == 7 ~ "July",
                                Month == 8 ~ "August",
                                Month == 9 ~ "September")) 

summary(airquality1$month_name)

   Length  N.unique   N.blank Min.nchar Max.nchar 
      153         5         0         3         9

airquality1$Month<-factor(airquality1$month_name, 
                          levels=c("May", "June","July", "August",
                                   "September"))

p1 <- airquality1 |>
  ggplot(aes(x=Temp, fill=month_name)) +
  geom_histogram(position="identity")+
  scale_fill_discrete(name = "Month", 
                      labels = c("May", "June","July", "August", "September")) +
  labs(x = "Monthly Temperatures from May - Sept", 
       y = "Frequency of Temps",
       title = "Histogram of Monthly Temperatures from May - Sept, 1973",
       caption = "New York State Department of Conservation and the National Weather Service")  #provide the data source 

p1

`stat_bin()` using `bins = 30`. Pick better value `binwidth`.

Plot 2

p2 <- airquality1 |>
  ggplot(aes(x=Temp, fill=month_name)) +
  geom_histogram(position="identity", alpha=0.5, binwidth = 5, color = "white")+
  scale_fill_discrete(name = "Month", labels = c("May", "June","July", "August", "September")) +
  labs(x = "Monthly Temperatures from May - Sept", 
       y = "Frequency of Temps",
       title = "Histogram of Monthly Temperatures from May - Sept, 1973",
       caption = "New York State Department of Conservation and the National Weather Service") 

p2

Plot 3

p3 <- airquality1 |>
  ggplot(aes(Month, Temp, fill =  month_name)) + 
  labs(x = "Months from May through September", y = "Temperatures", 
       title = "Side-by-Side Boxplot of Monthly Temperatures",
       caption = "New York State Department of Conservation and the National Weather Service") +
  geom_boxplot() +
  scale_fill_discrete(name = "Month", labels = c("May", "June","July", "August", "September")) 

p3

Plot 4

p4 <- airquality1 |>
  ggplot(aes(Month, Temp, fill = month_name)) + 
  labs(x = "Monthly Temperatures", y = "Temperatures", 
       title = "Side-by-Side Boxplot of Monthly Temperatures",
       caption = "New York State Department of Conservation and the National Weather Service") +
  geom_boxplot()+
  scale_fill_grey(name = "Month", labels = c("May", "June","July", "August", "September")) 

p4

Plot 5

p5 <- airquality1 |>
  ggplot(aes(Month, Temp, fill = month_name)) + 
  labs(x = "Months from April through July", 
       y = "Temperatures", 
       title = "Dot Plot of Monthly Temperatures",
       caption = "National Weather Service") +
  geom_dotplot(binaxis = "y", 
               stackdir = "center") +
  scale_fill_grey(name = "Month", 
                  labels = c("May", "June", "July", "August", "September"))

p5

Bin width defaults to 1/30 of the range of the data. Pick better value with
`binwidth`.