TM.KOMSTAT_Mardiana Syakira Mulkani Putri

Data=read.table(file.choose(),header = TRUE)
Data

##               Provinsi      Luas
## 1                 ACEH  56835.02
## 2       SUMATERA_UTARA  72437.76
## 3       SUMATERA_BARAT  42107.67
## 4                 RIAU  89900.78
## 5                JAMBI  49023.04
## 6     SUMATERA_SELATAN  86771.92
## 7             BENGKULU  20122.21
## 8              LAMPUNG  33570.76
## 9  KEP_BANGKA_BELITUNG  16670.23
## 10            KEP_RIAU   8170.38
## 11         DKI_JAKARTA    661.53
## 12          JAWA_BARAT  37053.33
## 13         JAWA_TENGAH  34347.43
## 14       DI_YOGYAKARTA   3170.36
## 15          JAWA_TIMUR  48055.88
## 16              BANTEN   9355.76
## 17                BALI   5582.83
## 18 NUSA_TENGGARA_BARAT  19631.99
## 19 NUSA_TENGGARA_TIMUR  48378.11
## 20    KALIMANTAN_BARAT 147018.06
## 21   KALIMANTAN_TENGAH 153430.36
## 22  KALIMANTAN_SELATAN  37125.43
## 23    KALIMANTAN_TIMUR 126951.78
## 24    KALIMANTAN_UTARA  69900.89
## 25      SULAWESI_UTARA  14488.43
## 26     SULAWESI_TENGAH  61496.98
## 27    SULAWESI_SELATAN  45323.98
## 28   SULAWESI_TENGGARA  36139.30
## 29           GORONTALO  12024.98
## 30      SULAWESI_BARAT  16590.67
## 31              MALUKU  46133.83
## 32        MALUKU_UTARA  31465.98
## 33         PAPUA_BARAT  60308.59
## 34    PAPUA_BARAT_DAYA  39103.06
## 35               PAPUA  81383.32
## 36       PAPUA_SELATAN 117858.97
## 37        PAPUA_TENGAH  61079.59
## 38    PAPUA_PEGUNUNGAN  52508.66

length(Data$Luas)

## [1] 38

mean(Data$Luas)

## [1] 49794.21

median(Data$Luas)

## [1] 43715.82

range(Data$Luas)

## [1]    661.53 153430.36

max(Data$Luas)-min(Data$Luas)

## [1] 152768.8

max(Data$Luas)

## [1] 153430.4

min(Data$Luas)

## [1] 661.53

var(Data$Luas) 

## [1] 1465787583

sd(Data$Luas)

## [1] 38285.61

quantile(Data$Luas)

##        0%       25%       50%       75%      100% 
##    661.53  19754.54  43715.82  61392.63 153430.36

library(ggplot2)

## Warning: package 'ggplot2' was built under R version 4.6.1

ggplot(Data, aes(x = Luas)) +
  geom_histogram(
    binwidth = 20000,
    boundary = 0,
    fill = "pink",
    color = "black"
  ) +
  scale_x_continuous(
    breaks = seq(0, 160000, by = 20000),
    labels = function(x) format(x, scientific = FALSE, big.mark = ".")
  ) +
  labs(
    title = "Luas Daerah Provinsi di Indonesia Tahun 2025",
    x = "Luas Daerah (km²)",
    y = "Freq"
  ) +
  theme_classic() +
  theme(
    axis.text.x = element_text(angle = 45, hjust = 1),
    plot.title = element_text(
      hjust = 0.5,
      face = "bold"
    )
  )

## Warning in prettyNum(.Internal(format(x, trim, digits, nsmall, width, 3L, :
## 'big.mark' and 'decimal.mark' are both '.', which could be confusing

ggplot(Data, aes(x = "", y = Luas)) +
  geom_boxplot(fill = "red") +
  labs(title = "Box Plot Luas Daerah Provinsi Indonesia 2025", x = "", y = "Luas Daerah (km²)") +
  theme_minimal() +
  theme(plot.title = element_text(hjust = 0.5, face = "bold"))

library(dplyr)

## Warning: package 'dplyr' was built under R version 4.6.1

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(tidyverse)

## Warning: package 'tidyverse' was built under R version 4.6.1

## Warning: package 'tibble' was built under R version 4.6.1

## Warning: package 'tidyr' was built under R version 4.6.1

## Warning: package 'readr' was built under R version 4.6.1

## Warning: package 'purrr' was built under R version 4.6.1

## Warning: package 'forcats' was built under R version 4.6.1

## Warning: package 'lubridate' was built under R version 4.6.1

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats   1.0.1     ✔ stringr   1.6.0
## ✔ lubridate 1.9.5     ✔ tibble    3.3.1
## ✔ purrr     1.2.2     ✔ tidyr     1.3.2
## ✔ readr     2.2.0

## ── 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_Kalimantan <- Data %>%
  filter(str_starts(Provinsi, "KALIMANTAN"))
Data_Kalimantan

##             Provinsi      Luas
## 1   KALIMANTAN_BARAT 147018.06
## 2  KALIMANTAN_TENGAH 153430.36
## 3 KALIMANTAN_SELATAN  37125.43
## 4   KALIMANTAN_TIMUR 126951.78
## 5   KALIMANTAN_UTARA  69900.89

ggplot(Data_Kalimantan, aes(x = Provinsi, y = Luas, fill = Provinsi)) +
  geom_col() +
  labs(
    title = "Luas Daerah Pulau Kalimantan Tahun 2025",
    x = "Provinsi",
    y = "Luas Daerah (km²)"
  ) +
  theme_minimal() +
  theme(
    axis.text.x = element_text(angle = 45, hjust = 1),
    plot.title = element_text(hjust = 0.5, face = "bold"),
    legend.position = "none"
  )