Week 2 assignment

Week 2 Assignment

load tidyverse package

for the first time, install tidyverse

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.2     ✔ readr     2.1.4
## ✔ forcats   1.0.0     ✔ stringr   1.5.0
## ✔ ggplot2   3.4.3     ✔ tibble    3.2.1
## ✔ lubridate 1.9.2     ✔ tidyr     1.3.0
## ✔ purrr     1.0.2     
## ── 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

mean(airquality$Temp)

## [1] 77.88235

mean(airquality[,4])

## [1] 77.88235

median(airquality$Temp)

## [1] 79

sd(airquality$Wind)

## [1] 3.523001

var(airquality$Wind)

## [1] 12.41154

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(airquality$Month)

##    Length     Class      Mode 
##       153 character character

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

#####This histogram shows the monthly temperature frequency distribution from May to September of 1973, providing information on the range and changes in temperature in New York during the summer.

plot1 <- airquality |>
  ggplot(aes(x=Temp, fill=Month)) +
  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
print(plot1)

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

#####From May through September of 1973, this histogram shows the frequency distribution of the monthly temperatures.

plot2 <- 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")) +
  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")
print(plot2)

#####This side-by-side boxplot shows the monthly temperature distribution from May to September, allowing for a comparison of temperature variations and central tendencies in New York during the summer.
plot3 <- airquality |>
  ggplot(aes(Month, Temp, fill = Month)) + 
  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"))
print(plot3)

#####This boxplot compares and contrasts the monthly temperature distribution from May to September to show variances and central tendencies. 
plot4 <- airquality |>
  ggplot(aes(Month, Temp, fill = Month)) + 
  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"))
print(plot4)

#####A visual comparison of ozone fluctuations over the course of the year is made possible by this faceted scatter plot, which shows ozone levels by day and assigns a distinctive hue to each month.
airquality <- na.omit(airquality)
plot5 <- airquality |>
  ggplot(aes(x = Day, y = Ozone, color = factor(Month))) +  
  geom_point() +
  labs(x = "Day",y = "Ozone (ppb)",
       title = "Day-by-Day Ozone levels (Faceted by Month)",
       caption = "New York State Department of Conservation and the National Weather Service") +
  facet_wrap(~ Month, ncol = 3) + 
  theme_minimal()

print(plot5)