library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ 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")
data("airquality")

#Mean

mean(airquality$Temp)
## [1] 77.88235

#Standard Deviation

sd(airquality$Wind)
## [1] 3.523001

#median

median(airquality$Temp)
## [1] 79

#Variance

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"

p1 <- 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")  #provide the data source
p1

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"

p3 <- 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"))
p3 

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"

p4 <- 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"))
p4

# Load necessary packages

library(ggplot2)
library(dplyr)

# Load the airquality dataset
data("airquality")

# Create a new date column
airquality$date <- as.Date(with(airquality, paste(2023, Month, Day, sep = "-")), "%Y-%m-%d")

# Verify the creation of the date column
str(airquality)
## 'data.frame':    153 obs. of  7 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 ...
##  $ date   : Date, format: "2023-05-01" "2023-05-02" ...
# Filter data for May
may_data <- airquality %>%
  filter(Month == 5)

# Display the first few rows of the filtered data
print(head(may_data))
##   Ozone Solar.R Wind Temp Month Day       date
## 1    41     190  7.4   67     5   1 2023-05-01
## 2    36     118  8.0   72     5   2 2023-05-02
## 3    12     149 12.6   74     5   3 2023-05-03
## 4    18     313 11.5   62     5   4 2023-05-04
## 5    NA      NA 14.3   56     5   5 2023-05-05
## 6    28      NA 14.9   66     5   6 2023-05-06
# Create the smooth line chart for May
ggplot(may_data, aes(x = date, y = Ozone)) +
  geom_line(color = "blue") +
  geom_point() +
  geom_smooth(method = "loess", se = FALSE, color = "red") +
  labs(title = "Ozone Levels in May", x = "Date", y = "Ozone Level (ppb)") +
  theme_minimal()
## `geom_smooth()` using formula = 'y ~ x'
## Warning: Removed 5 rows containing non-finite outside the scale range
## (`stat_smooth()`).
## Warning: Removed 5 rows containing missing values or values outside the scale range
## (`geom_point()`).