TM2.Komstat_ceisya artika firdasari devi

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.2.1     ✔ readr     2.2.0
## ✔ forcats   1.0.1     ✔ stringr   1.6.0
## ✔ ggplot2   4.0.3     ✔ tibble    3.3.1
## ✔ lubridate 1.9.5     ✔ tidyr     1.3.2
## ✔ purrr     1.2.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(ggplot2)
Data <- read_csv("Persentase Rumah Tangga yang Memiliki Akses terhadap Sumber Air Minum Layak Menurut Provinsi, 2025.csv",
                 skip = 3,
                 col_names = c("Provinsi", "Persentase")) %>%
  filter(!is.na(Provinsi) & Provinsi != "INDONESIA") %>%
  mutate(Persentase = as.numeric(Persentase))

## Rows: 39 Columns: 2
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (1): Provinsi
## dbl (1): Persentase
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

# BAGIAN 1: ANALISIS STATISTIKA DESKRIPTIF
length(Data$Persentase)

## [1] 38

mean(Data$Persentase)

## [1] 87.60789

median(Data$Persentase)

## [1] 89.935

range(Data$Persentase)

## [1] 32.89 99.98

max(Data$Persentase) - min(Data$Persentase)

## [1] 67.09

max(Data$Persentase)

## [1] 99.98

min(Data$Persentase)

## [1] 32.89

var(Data$Persentase)

## [1] 134.9053

sd(Data$Persentase)

## [1] 11.61487

quantile(Data$Persentase)

##      0%     25%     50%     75%    100% 
## 32.8900 83.2925 89.9350 94.8975 99.9800

# BAGIAN 2: VISUALISASI 1 - HISTOGRAM (NASIONAL)
ggplot(Data, aes(x = Persentase)) +
  geom_histogram(
    binwidth = 10,
    boundary = 30,
    fill = "pink",
    color = "black"
  ) +
  scale_x_continuous(
    breaks = seq(30, 100, by = 10),
    limits = c(30, 100)
  ) +
  labs(
    title = "Persentase Akses Air Minum Layak di Indonesia 2025",
    x = "Persentase (%)",
    y = "Freq"
  ) +
  theme_classic() +
  theme(
    axis.text.x = element_text(angle = 0, hjust = 0.5),
    plot.title = element_text(hjust = 0.5, face = "bold")
  )

# BAGIAN 3: VISUALISASI 2 - BOXPLOT (NASIONAL)
ggplot(Data, aes(x = "", y = Persentase)) +
  geom_boxplot(fill = "red") +
  labs(
    title = "Box Plot Akses Air Minum Layak Indonesia 2025",
    x = "",
    y = "Persentase (%)"
  ) +
  theme_minimal() +
  theme(
    plot.title = element_text(hjust = 0.5, face = "bold")
  )

# BAGIAN 4: VISUALISASI KHUSUS PROVINSI KALIMANTAN TIMUR
Rata_Kalimantan <- mean(Data$Persentase[str_starts(Data$Provinsi, "KALIMANTAN")])
Rata_Nasional   <- mean(Data$Persentase)
Kaltim_Val      <- Data$Persentase[Data$Provinsi == "KALIMANTAN TIMUR"]

Data_Kaltim_Comp <- data.frame(
  Kategori = c("Kalimantan Timur", "Rata-Rata Kalimantan", "Rata-Rata Nasional"),
  Persentase = c(Kaltim_Val, Rata_Kalimantan, Rata_Nasional)
)

Data_Kaltim_Comp

##               Kategori Persentase
## 1     Kalimantan Timur   88.45000
## 2 Rata-Rata Kalimantan   84.64200
## 3   Rata-Rata Nasional   87.60789

ggplot(Data_Kaltim_Comp, aes(x = reorder(Kategori, -Persentase), y = Persentase, fill = Kategori)) +
  geom_col(width = 0.5) +
  geom_text(aes(label = paste0(round(Persentase, 2), "%")), vjust = -0.5, fontface = "bold") +
  scale_y_continuous(limits = c(0, 105)) +
  labs(
    title = "Persentase Akses Air Minum Layak Kalimantan Timur Tahun 2025",
    x = "Kategori",
    y = "Persentase (%)"
  ) +
  theme_minimal() +
  theme(
    plot.title = element_text(hjust = 0.5, face = "bold"),
    legend.position = "none"
  )