w3 homework

1. R의 내장 데이터셋인 airquality를 이용하여, 적합한 3가지 이상의 그래프 유형을 ggplot2을 사용해서 그려보자.

knitr::opts_chunk$set(echo = TRUE)
library(ggplot2)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

# 데이터 확인
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

summary(airquality)

##      Ozone           Solar.R           Wind             Temp      
##  Min.   :  1.00   Min.   :  7.0   Min.   : 1.700   Min.   :56.00  
##  1st Qu.: 18.00   1st Qu.:115.8   1st Qu.: 7.400   1st Qu.:72.00  
##  Median : 31.50   Median :205.0   Median : 9.700   Median :79.00  
##  Mean   : 42.13   Mean   :185.9   Mean   : 9.958   Mean   :77.88  
##  3rd Qu.: 63.25   3rd Qu.:258.8   3rd Qu.:11.500   3rd Qu.:85.00  
##  Max.   :168.00   Max.   :334.0   Max.   :20.700   Max.   :97.00  
##  NA's   :37       NA's   :7                                       
##      Month            Day      
##  Min.   :5.000   Min.   : 1.0  
##  1st Qu.:6.000   1st Qu.: 8.0  
##  Median :7.000   Median :16.0  
##  Mean   :6.993   Mean   :15.8  
##  3rd Qu.:8.000   3rd Qu.:23.0  
##  Max.   :9.000   Max.   :31.0  
## 

# 1. 산점도
ggplot(airquality, aes(x = Wind, y = Ozone)) +
  geom_point(color = "steelblue", alpha = 0.7) +
  labs(title = "WindvsOzone",
       x = "Wind (mph)",
       y = "Ozone (ppb)") +
  theme_minimal() +
  theme(plot.title = element_text(size = 14, face = "bold", hjust = 0.5))

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

# 2. 박스플롯
ggplot(airquality, aes(x = factor(Month), y = Temp)) +
  geom_boxplot(fill = "tomato", alpha = 0.6) +
  labs(title = "Monthly Temperature Distribution",
       x = "Month",
       y = "Temperature (°F)") +
  theme_light() +
  theme(plot.title = element_text(size = 14, face = "bold", hjust = 0.5))

# 3. 히스토그램
ggplot(airquality, aes(x = Temp)) +
  geom_histogram(binwidth = 5, fill = "skyblue", color = "black") +
  labs(title = "Temperature Distribution Histogram",
       x = "Temperature (°F)",
       y = "Frequency") +
  theme_classic() +
  theme(plot.title = element_text(size = 14, face = "bold", hjust = 0.5))

## 2. 각 그래프를 통해 데이터에서 어떠한 정보를 얻을 수 있는지 간단히 R markdown을 이용해서 설명해보자.

knitr::opts_chunk$set(echo = TRUE)
#scatterplot(산점도): shows the negative correlation between wind speed and ozone levels
#boxplot:Compares temperature distributions across months, showing a general trend of temperature increasing from may to july, and slightly decreasing afterwards
#Histogram: Shows how frequently different temperature ranges occurred.