#1. distribusi diskrit dan kontinu

#parameter distribusi diskrit
n_trials <- 20
prob_success <- 0.5 
#generate data 
x_discrete <- 0:n_trials
y_discrete <- dbinom(x_discrete, size = n_trials, prob = prob_success)
#plot
barplot(y_discrete, names.arg = x_discrete, 
        main = "Simulasi Distribusi Binomial (n=20, p=0.5)",
        xlab = "Jumlah Sukses (Gambar)", 
        ylab = "Probabilitas",
        col = "skyblue", border = "white")

#parameter distribusi kontinu
mu <- 100    
sigma <- 15
#generate data random
set.seed(123) 
data_kontinu <- rnorm(10000, mean = mu, sd = sigma)
#plot menggunakan histogram
hist(data_kontinu, breaks = 50, probability = TRUE,
     main = "Simulasi Distribusi Normal (IQ)",
     xlab = "Skor IQ", ylab = "Densitas",
     col = "lightgreen", border = "white")

#menambahkan garis kurva halus
curve(dnorm(x, mean = 10, sd = 2), from = 0, to = 20, col = "blue")

#2. Studi Kasus

#load library
if(!require(ggplot2)) install.packages("ggplot2")
## Loading required package: ggplot2
library(ggplot2)
#permintaan harian (distribusi poisson)
pesanan_harian <- rpois(365, lambda = 50)
#waktu pengiriman (distribusi gamma)
waktu_kirim <- rgamma(1000, shape = 9, rate = 3)
#barang retur (distribusi binomial)
barang_retur <- rbinom(365, size = 100, prob = 0.02)
#visualisasi
par(mfrow=c(1,3))
hist(pesanan_harian, col="orange", main="Permintaan Barang/Hari", 
     xlab="Jumlah Pesanan", ylab="Frekuensi (Hari)")
hist(waktu_kirim, col="skyblue", main="Waktu Pengiriman (Lead Time)", 
     xlab="Hari", ylab="Kepadatan", probability = TRUE)
lines(density(waktu_kirim), lwd=2)
hist(barang_retur, col="pink", main="Simulasi Retur per 100 Item", 
     xlab="Jumlah Barang Retur", ylab="Frekuensi")