TM 2 KOMSTAT

Data <- read.table(file.choose(), header = T)
Data

##               Provinsi   SMA
## 1                 ACEH 74.46
## 2       SUMATERA_UTARA 74.43
## 3       SUMATERA_BARAT 68.64
## 4                 RIAU 67.79
## 5                JAMBI 66.62
## 6     SUMATERA_SELATAN 64.81
## 7             BENGKULU 63.41
## 8              LAMPUNG 64.54
## 9  KEP.BANGKA_BELITUNG 68.96
## 10            KEP.RIAU 78.97
## 11         DKI_JAKARTA 88.10
## 12          JAWA_BARAT 66.47
## 13         JAWA_TENGAH 58.35
## 14       DI_YOGYAKARTA 89.69
## 15          JAWA_TIMUR 68.65
## 16              BANTEN 70.07
## 17                BALI 76.51
## 18 NUSA_TENGGARA_BARAT 63.66
## 19 NUSA_TENGGARA_TIMUR 43.46
## 20    KALIMANTAN_BARAT 55.58
## 21   KALIMANTAN_TENGAH 63.93
## 22  KALIMANTAN_SELATAN 68.35
## 23    KALIMANTAN_TIMUR 73.63
## 24    KALIMANTAN_UTARA 59.50
## 25      SULAWESI_UTARA 67.57
## 26     SULAWESI_TENGAH 55.69
## 27    SULAWESI_SELATAN 67.41
## 28   SULAWESI_TENGGARA 68.28
## 29           GORONTALO 46.19
## 30      SULAWESI_BARAT 54.79
## 31              MALUKU 75.01
## 32        MALUKU_UTARA 64.61
## 33         PAPUA_BARAT 59.99
## 34    PAPUA_BARAT_DAYA    NA
## 35               PAPUA 39.50
## 36       PAPUA_SELATAN    NA
## 37        PAPUA_TENGAH    NA
## 38    PAPUA_PEGUNUNGAN    NA

Data_Clean <- na.omit(Data$SMA)
length(Data_Clean)

## [1] 34

mean(Data_Clean)

## [1] 65.81235

median(Data_Clean)

## [1] 67.015

range(Data_Clean)

## [1] 39.50 89.69

max(Data_Clean) - min(Data_Clean)

## [1] 50.19

max(Data_Clean)

## [1] 89.69

min(Data_Clean)

## [1] 39.5

var(Data_Clean)

## [1] 114.2291

sd(Data_Clean)

## [1] 10.6878

quantile(Data_Clean)

##      0%     25%     50%     75%    100% 
## 39.5000 60.8450 67.0150 69.7925 89.6900

library(ggplot2)
Data_Plot <- na.omit(Data)
ggplot(Data_Plot, aes(x = SMA)) +
  geom_histogram(
    binwidth = 10,
    boundary = 30,
    fill = "skyblue",
    color = "black"
  ) +
  scale_x_continuous(
    breaks = seq(30, 90, by = 10),
    limits = c(30, 90)
  ) +
  labs(
    title = "Tingkat Penyelesaian Pendidikan SMA 2023",
    x = "Persentase Penyelesaian (%)",
    y = "Frekuensi"
  ) +
  theme_classic() +
  theme(
    plot.title = element_text(hjust = 0.5, face = "bold")
  )

library(ggplot2)
ggplot(Data_Plot, aes(x = "", y = SMA)) +
  geom_boxplot(fill = "orange") +
  labs(
    title = "Box Plot Penyelesaian SMA 2023",
    x = "",
    y = "Persentase (%)"
  ) +
  theme_minimal() +
  theme(plot.title = element_text(hjust = 0.5, face = "bold"))

library(dplyr)

## 
## 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)

## ── 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   SMA
## 1   KALIMANTAN_BARAT 55.58
## 2  KALIMANTAN_TENGAH 63.93
## 3 KALIMANTAN_SELATAN 68.35
## 4   KALIMANTAN_TIMUR 73.63
## 5   KALIMANTAN_UTARA 59.50

ggplot(Data_Kalimantan, aes(x = Provinsi, y = SMA, fill = Provinsi)) +
  geom_col() +
  labs(
    title = "Penyelesaian Pendidikan SMA Pulau Kalimantan 2023",
    x = "Provinsi",
    y = "Persentase (%)"
  ) +
  theme_minimal() +
  theme(
    axis.text.x = element_text(angle = 45, hjust = 1),
    plot.title = element_text(hjust = 0.5, face = "bold"),
    legend.position = "none"
  )