# MUHAMMAD FARID

# library ggplot2
library(ggplot2)

## Warning: package 'ggplot2' was built under R version 4.4.2

# 1. 
# Load dataset
data("airquality")

# a. Hitung mean, median, dan standar deviasi untuk Ozone
mean_ozone <- mean(airquality$Ozone)
median_ozone <- median(airquality$Ozone)
sd_ozone <- sd(airquality$Ozone, na.rm = TRUE)

# hasil rata2
mean_ozone

## [1] NA

# median
median_ozone

## [1] NA

# srandar deviasi
sd_ozone

## [1] 32.98788

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

# 2. dataset mtcars
data("mtcars")

# Hitung variabel cyl
cyl_counts <- table(mtcars$cyl)

# Buat bar chart
barplot(cyl_counts, 
        main = "Bar Chart Jumlah Tiap Kategori cyl",
        xlab = "cyl",
        ylab = "Jumlah",
        col = c("skyblue","yellow","red"))

# 3a. dataset iris
data("iris")

# Boxplot Petal.width berdasarkan Species
boxplot(Petal.Width ~ Species, data = iris,
        main = "Boxplot Petal.Width Berdasarkan Species",
        xlab = "Species",
        ylab = "Petal.Width",
        col = c("skyblue","yellow","red"))

# 3b. Hitung korelasi
hasil <- cor(iris$Sepal.Length, iris$Petal.Length)

# hasil
hasil

## [1] 0.8717538

# 3c. Scatter plot Sepal.Length vs Sepal.Width
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'

# 4. Uji Chi-Square antara vs dan am (mtcars)
hasil_chi_square <- chisq.test(mtcars$vs, mtcars$am)

# Tampilkan hasil
hasil_chi_square

## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  mtcars$vs and mtcars$am
## X-squared = 0.34754, df = 1, p-value = 0.5555

# 5a. 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

# Scatter plot dengan garis regresi
plot(airquality$Solar.R, airquality$Temp,
     main = "Scatter Plot Temp vs Solar.R",
     xlab = "Solar.R",
     ylab = "Temp",
     pch = 19, col = "blue")
abline(model, col = "red", lwd = 2)

# 5c. Interpretasi
## Signifikansi Koefisien Regresi
   ### P-value untuk Intercept (< 2e-16) dan Solar.R (0.000752)
   ### P-value untuk Solar.R lebih kecil dari 0.05, sehingga koefisien Solar.R signifikan secara statistik.Sehingga Solar.R berpengaruh signifikan terhadap Temp dalam model ini.
   ### T-value sebesar 3.444 > 0.05 menunjukkan bahwa efek Solar.R secara signifikan berbeda dari nol.

## R-Square
   ### Multiple R-squared = 0.07609 = 7.6% menunjukkan bahwa Solar.R hanya menjelaskan sebagian kecil dari variasi dalam Temp.
   ### Adjusted R-squared = 0.06967 = 6.9% memberikan Nilai rendah, dengan ini memperkuat indikasi bahwa model hanya memiliki kemampuan prediksi yang terbatas.