# Load dataset
data(airquality)

# Hitung statistik deskriptif untuk variabel Ozone
mean_ozone <- mean(airquality$Ozone, na.rm = TRUE)
median_ozone <- median(airquality$Ozone, na.rm = TRUE)
sd_ozone <- sd(airquality$Ozone, na.rm = TRUE)

# Tampilkan hasil
mean_ozone

## [1] 42.12931

median_ozone

## [1] 31.5

sd_ozone

## [1] 32.98788

# Scatter plot antara Wind dan Temp
plot(airquality$Wind, airquality$Temp,
     main = "Scatter Plot antara Wind dan Temp",
     xlab = "Wind", ylab = "Temp",
     col = "blue", pch = 19)

# Load dataset
data(mtcars)

# Buat bar chart untuk variabel cyl
barplot(table(mtcars$cyl),
        main = "Bar Chart Variabel cyl",
        xlab = "Jumlah Silinder (cyl)",
        ylab = "Frekuensi",
        col = "skyblue")

# Tambahkan label jumlah pada masing-masing kategori
text(x = 1:length(table(mtcars$cyl)),
     y = table(mtcars$cyl),
     labels = table(mtcars$cyl), pos = 3)

# Load dataset
data(iris)

# Buat boxplot
boxplot(Petal.Width ~ Species, data = iris,
        main = "Boxplot Petal.Width Berdasarkan Species",
        xlab = "Species", ylab = "Petal.Width",
        col = c("red", "green", "blue"))

# Hitung korelasi
correlation <- cor(iris$Sepal.Length, iris$Petal.Length)
correlation

## [1] 0.8717538

# Interpretasi hasil
if (correlation > 0) {
  print("Korelasi positif: Sepal.Length dan Petal.Length meningkat bersama.")
} else {
  print("Korelasi negatif: Sepal.Length meningkat, tetapi Petal.Length menurun.")
}

## [1] "Korelasi positif: Sepal.Length dan Petal.Length meningkat bersama."

# Buat scatter plot dengan warna berdasarkan Species
plot(iris$Sepal.Length, iris$Sepal.Width,
     col = as.factor(iris$Species),
     pch = 19, 
     main = "Scatter Plot Sepal.Length vs Sepal.Width",
     xlab = "Sepal.Length", ylab = "Sepal.Width")

# Tambahkan legenda
legend("topright", legend = levels(iris$Species),
       col = 1:3, pch = 19)

# Tambahkan garis regresi untuk masing-masing spesies
library(ggplot2)

## Warning: package 'ggplot2' was built under R version 4.3.3

ggplot(iris, aes(x = Sepal.Length, y = Sepal.Width, color = Species)) +
  geom_point() +
  geom_smooth(method = "lm", se = FALSE) +
  ggtitle("Scatter Plot dengan Garis Regresi per Species")

## `geom_smooth()` using formula = 'y ~ x'

# Membuat tabel kontingensi
contingency_table <- table(mtcars$vs, mtcars$am)

# Lakukan uji Chi-Square
chi_test <- chisq.test(contingency_table)

# Tampilkan hasil
chi_test

## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  contingency_table
## X-squared = 0.34754, df = 1, p-value = 0.5555

# Bangun model regresi: Temp ~ Solar.R
linear_model <- lm(Temp ~ Solar.R, data = airquality)

# Tampilkan ringkasan model
summary(linear_model)

## 
## Call:
## lm(formula = Temp ~ Solar.R, data = airquality)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -22.3787  -4.9572   0.8932   5.9111  18.4013 
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)    
## (Intercept) 72.863012   1.693951  43.014  < 2e-16 ***
## Solar.R      0.028255   0.008205   3.444 0.000752 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 8.898 on 144 degrees of freedom
##   (7 observations deleted due to missingness)
## Multiple R-squared:  0.07609,    Adjusted R-squared:  0.06967 
## F-statistic: 11.86 on 1 and 144 DF,  p-value: 0.0007518

# Scatter plot
plot(airquality$Solar.R, airquality$Temp,
     main = "Scatter Plot Solar.R vs Temp dengan Garis Regresi",
     xlab = "Solar.R", ylab = "Temp",
     col = "blue", pch = 19)

# Tambahkan garis regresi
abline(linear_model, col = "red", lwd = 2)