UAS KOMSTAT

# Load Dataset
data("airquality")

# Hitung Statistik Deskriptif
summary(airquality$Ozone)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##    1.00   18.00   31.50   42.13   63.25  168.00      37

sd(airquality$Ozone, na.rm = TRUE)

## [1] 32.98788

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

# Load Dataset
data("mtcars")

# Buat Bar Chart
cyl_count <- table(mtcars$cyl)
barplot(cyl_count, main = "Jumlah Mobil Berdasarkan Cyl",
        xlab = "Cylinders", ylab = "Jumlah", col = "lightblue")

# 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

# Buat Scatter Plot dengan Warna Berdasarkan Species
library(ggplot2)

ggplot(iris, aes(x = Sepal.Length, y = Sepal.Width, color = Species)) +
  geom_point() +
  geom_smooth(method = "lm", se = FALSE) +
  labs(title = "Scatter Plot Sepal.Length vs Sepal.Width",
       x = "Sepal Length", y = "Sepal Width") +
  theme_minimal()

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

# Buat Tabel Kontingensi
chi_table <- table(mtcars$vs, mtcars$am)

# Uji Chi-Square
chi_result <- chisq.test(chi_table)
chi_result

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

# Model Regresi Linear
model <- lm(Temp ~ Solar.R, data = airquality)

# Ringkasan Model
summary(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

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

abline(model, col = "blue", lwd = 2)

# Nilai R Squared
summary(model)$r.squared

## [1] 0.07608786