DATA110_Fernandez_Maira_Airquality_Assignment2

library(ggplot2)

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
✔ lubridate 1.9.5     ✔ tibble    3.3.1
✔ purrr     1.2.2     ✔ tidyr     1.3.2
── 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

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`.

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")#provide the data source

p2

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

p4<-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_grey(name= "Month", labels= c("May", "June", "July", "August", "September"))

p4

p5 <-airquality1 |>
  ggplot(aes(x = Temp, y = Ozone, color=Ozone)) +
  geom_point() +
  labs(
    x = "Temperature",
    y = "Ozone",
    title = "Scatterplot of Temperature and Ozone",
    caption = "New York State Department of Conservation and the National Weather Service"
  )

p5

Warning: Removed 37 rows containing missing values or values outside the scale range
(`geom_point()`).

This graph represents how the Ozone line deteriorates as the temperature rises. I tried to change the color but when I added red the graph change to red dotes, so I returned to the first version. I tried to do graph with the Wind and Temperature, but were confusing. I used the code that we practice in previous class, because after trying many times with different graphs, I could not make it, so I decided to use the one that I already know.