Data=read.table(file.choose(), header = T)
Data
##               Provinsi Informal
## 1                 ACEH    63.91
## 2       SUMATERA_UTARA    57.26
## 3       SUMATERA_BARAT    64.33
## 4                 RIAU    52.00
## 5                JAMBI    57.27
## 6     SUMATERA_SELATAN    63.13
## 7             BENGKULU    65.17
## 8              LAMPUNG    64.72
## 9  KEP_BANGKA_BELITUNG    51.29
## 10            KEP_RIAU    34.25
## 11         DKI_JAKARTA    36.63
## 12          JAWA_BARAT    54.95
## 13         JAWA_TENGAH    58.79
## 14       DI_YOGYAKARTA    53.97
## 15          JAWA_TIMUR    61.73
## 16              BANTEN    45.12
## 17                BALI    50.47
## 18 NUSA_TENGGARA_BARAT    68.42
## 19 NUSA_TENGGARA_TIMUR    68.44
## 20    KALIMANTAN_BARAT    56.39
## 21   KALIMANTAN_TENGAH    50.15
## 22  KALIMANTAN_SELATAN    53.48
## 23    KALIMANTAN_TIMUR    43.22
## 24    KALIMANTAN_UTARA    48.44
## 25      SULAWESI_UTARA    54.56
## 26     SULAWESI_TENGAH    64.57
## 27    SULAWESI_SELATAN    60.45
## 28   SULAWESI_TENGGARA    61.13
## 29           GORONTALO    61.14
## 30      SULAWESI_BARAT    70.63
## 31              MALUKU    66.06
## 32        MALUKU_UTARA    64.51
## 33         PAPUA_BARAT    63.19
## 34    PAPUA_BARAT_DAYA    55.66
## 35               PAPUA    52.88
## 36       PAPUA_SELATAN    65.88
## 37        PAPUA_TENGAH    84.72
## 38    PAPUA_PEGUNUNGAN    95.30
length(Data$Informal)
## [1] 38
mean(Data$Informal)
## [1] 59.05816
median(Data$Informal)
## [1] 59.62
range(Data$Informal)
## [1] 34.25 95.30
max(Data$Informal) - min(Data$Informal)
## [1] 61.05
max(Data$Informal)
## [1] 95.3
min(Data$Informal)
## [1] 34.25
var(Data$Informal)
## [1] 127.1999
sd(Data$Informal)
## [1] 11.27829
quantile(Data$Informal)
##     0%    25%    50%    75%   100% 
## 34.250 53.030 59.620 64.555 95.300
library(ggplot2)
## Warning: package 'ggplot2' was built under R version 4.5.3
ggplot(Data, aes(x = Informal)) +
  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 = "Proporsi Lapangan Kerja Informal di Indonesia 2025",
    x = "Proporsi Informal (%)",
    y = "Frekuensi"
  ) +
  theme_classic() +
  theme(
    plot.title = element_text(hjust = 0.5, face = "bold")
  )

ggplot(Data, aes(x = "", y = Informal)) +
  geom_boxplot(fill = "red") +
  labs(
    title = "Box Plot Proporsi Lapangan Kerja Informal 2025",
    x = "",
    y = "Proporsi Informal (%)"
  ) +
  theme_minimal() +
  theme(
    plot.title = element_text(hjust = 0.5, face = "bold")
  )

library(dplyr)
## Warning: package 'dplyr' was built under R version 4.5.3
## 
## 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(stringr)
library(ggplot2)

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

Data_Kalimantan
##             Provinsi Informal
## 1   KALIMANTAN_BARAT    56.39
## 2  KALIMANTAN_TENGAH    50.15
## 3 KALIMANTAN_SELATAN    53.48
## 4   KALIMANTAN_TIMUR    43.22
## 5   KALIMANTAN_UTARA    48.44
ggplot(Data_Kalimantan, aes(x = reorder(Provinsi, -Informal),
                            y = Informal, fill = Provinsi)) +
  geom_col() +
  labs(
    title = "Proporsi Lapangan Kerja Informal di Pulau Kalimantan 2025",
    x = "Provinsi",
    y = "Proporsi Informal (%)"
  ) +
  theme_minimal() +
  theme(
    axis.text.x = element_text(angle = 45, hjust = 1),
    plot.title = element_text(hjust = 0.5, face = "bold"),
    legend.position = "none"
  )