Load library

library(ggplot2)
library(readxl)
library(ggthemes)
library(gridExtra)

Import Data

setwd("C:/Users/Dell 7490/Documents/statistika")
data <- read_excel("used_car_sales.xlsx")
head(data)

## # A tibble: 6 × 25
##   ID     `Distributor Name` Location   `Car Name` `Manufacturer Name` `Car Type`
##   <chr>  <chr>              <chr>      <chr>      <chr>               <chr>     
## 1 O2KE17 Carmudi            California Fortuner   Toyota              SUV       
## 2 EPMPC8 Carousell          Philadelp… Creta      Hyundai             Hatchback 
## 3 SQKXAP Carsome            North Car… Scorpio    Mahindra            SUV       
## 4 PWP2QK Trivett            North Car… Plato      Prazo               Convertib…
## 5 FNDDKM Zupps              Portland   Dzire      Maruti              Sedan     
## 6 I5D584 Zupps              Denver     Fortuner   Toyota              SUV       
## # ℹ 19 more variables: Color <chr>, Gearbox <chr>, `Number of Seats` <dbl>,
## #   `Number of Doors` <dbl>, Energy <chr>, `Manufactured Year` <dbl>,
## #   `Price-$` <dbl>, `Mileage-KM` <dbl>, `Engine Power-HP` <dbl>,
## #   `Purchased Date` <dttm>, `Car Sale Status` <chr>, `Sold Date` <dttm>,
## #   `Purchased Price-$` <dbl>, `Sold Price-$` <dbl>, `Margin-%` <dbl>,
## #   `Sales Agent Name` <chr>, `Sales Rating` <dbl>, `Sales Commission-$` <dbl>,
## #   Feedback <chr>

print(data)

## # A tibble: 10,000 × 25
##    ID     `Distributor Name` Location  `Car Name` `Manufacturer Name` `Car Type`
##    <chr>  <chr>              <chr>     <chr>      <chr>               <chr>     
##  1 O2KE17 Carmudi            Californ… Fortuner   Toyota              SUV       
##  2 EPMPC8 Carousell          Philadel… Creta      Hyundai             Hatchback 
##  3 SQKXAP Carsome            North Ca… Scorpio    Mahindra            SUV       
##  4 PWP2QK Trivett            North Ca… Plato      Prazo               Convertib…
##  5 FNDDKM Zupps              Portland  Dzire      Maruti              Sedan     
##  6 I5D584 Zupps              Denver    Fortuner   Toyota              SUV       
##  7 KPRE75 Cars24             New York  Thar       Mahindra            SUV       
##  8 8C1O0B Ahg                Denver    Etriga     Maruti              Hatchback 
##  9 KCVVNQ Olx                Detroit   Yodha      Tata                Truck     
## 10 HGW6RK Nufor              Tennessee Creta      Hyundai             Hatchback 
## # ℹ 9,990 more rows
## # ℹ 19 more variables: Color <chr>, Gearbox <chr>, `Number of Seats` <dbl>,
## #   `Number of Doors` <dbl>, Energy <chr>, `Manufactured Year` <dbl>,
## #   `Price-$` <dbl>, `Mileage-KM` <dbl>, `Engine Power-HP` <dbl>,
## #   `Purchased Date` <dttm>, `Car Sale Status` <chr>, `Sold Date` <dttm>,
## #   `Purchased Price-$` <dbl>, `Sold Price-$` <dbl>, `Margin-%` <dbl>,
## #   `Sales Agent Name` <chr>, `Sales Rating` <dbl>, …

1. Pie Chart

pie_chart <- ggplot(data, aes(x = " ", fill = `Car Name`)) +
  geom_bar(width = 1) +
  coord_polar("y", start = 0) +
  theme_minimal() +
  labs(title = "Lokasi") +
  theme(axis.text.x = element_blank())

pie_chart

2. Bar Chart

bar_chart <- ggplot(data, aes(x = `Location`, fill = `Location`)) +
  geom_bar() +
  theme_minimal() +
  labs(title = "Lokasi Penjualan", x = "Lokasi Penjualan", y = "Frekuensi")

bar_chart

3. Histogram

# 3. Histogram
histogram <- ggplot(data, aes(x = `Manufactured Year`)) +
  geom_histogram(binwidth = 5, fill = "blue", color = "black", alpha = 0.7) +
  theme_minimal() +
  labs(title = "Histogram: Tahun Dibuat Mobil", x = "Tahun", y = "Jumlah Kendaraan")

histogram

4. Bloxplot

boxplot_data <- ggplot(data) +
  geom_boxplot(aes(y = `Price-$`, fill = "Harga"), alpha = 0.6) +
  theme_minimal() +
  labs(title = "Boxplot: Harga ($)", fill = "Harga")

boxplot_data

5. Density

density_plot <- ggplot(data, aes(x = `Engine Power-HP`,fill = "Engine Power-HP")) +
  geom_density(alpha = 0.5) +
  theme_minimal() +
  labs(title = "Density Plot: Engine Power", x = "Horse Power", y = "Density")
density_plot

6. Penyebaran Data

# Menghitung Statistik Deskriptif
# Misalnya, kita akan menghitung untuk kolom `Price-$` dan `Manufactured Year`

# 1. Mean (Rata-rata)
mean_price <- mean(data$`Price-$`, na.rm = TRUE)
mean_year <- mean(data$`Manufactured Year`, na.rm = TRUE)

# 2. Median
median_price <- median(data$`Price-$`, na.rm = TRUE)
median_year <- median(data$`Manufactured Year`, na.rm = TRUE)

# 3. Modus (Mode)
# Fungsi untuk menghitung modus
get_mode <- function(x) {
  ux <- unique(x)
  ux[which.max(tabulate(match(x, ux)))]
}
mode_price <- get_mode(data$`Price-$`)
mode_year <- get_mode(data$`Manufactured Year`)

# 4. Kuartil 1 (Q1)
q1_price <- quantile(data$`Price-$`, probs = 0.25, na.rm = TRUE)
q1_year <- quantile(data$`Manufactured Year`, probs = 0.25, na.rm = TRUE)

# 5. Kuartil 3 (Q3)
q3_price <- quantile(data$`Price-$`, probs = 0.75, na.rm = TRUE)
q3_year <- quantile(data$`Manufactured Year`, probs = 0.75, na.rm = TRUE)

# 6. Range (Jangkauan)
range_price <- range(data$`Price-$`, na.rm = TRUE)
range_year <- range(data$`Manufactured Year`, na.rm = TRUE)

# Menampilkan Hasil
cat("Statistik Deskriptif untuk Harga ($):\n")

## Statistik Deskriptif untuk Harga ($):

cat("Mean:", mean_price, "\n")

## Mean: 7975.1

cat("Median:", median_price, "\n")

## Median: 7900

cat("Modus:", mode_price, "\n")

## Modus: 7700

cat("Q1:", q1_price, "\n")

## Q1: 7200

cat("Q3:", q3_price, "\n")

## Q3: 8700

cat("Range:", range_price[1], "-", range_price[2], "\n\n")

## Range: 6000 - 10900

cat("Statistik Deskriptif untuk Tahun Pembuatan:\n")

## Statistik Deskriptif untuk Tahun Pembuatan:

cat("Mean:", mean_year, "\n")

## Mean: 2019.525

cat("Median:", median_year, "\n")

## Median: 2020

cat("Modus:", mode_year, "\n")

## Modus: 2024

cat("Q1:", q1_year, "\n")

## Q1: 2017

cat("Q3:", q3_year, "\n")

## Q3: 2022

cat("Range:", range_year[1], "-", range_year[2], "\n")

## Range: 2015 - 2024

# Menghitung Varians
var_year <- var(data$`Manufactured Year`, na.rm = TRUE)
print(paste("Varians Manufactured Year:", var_year))

## [1] "Varians Manufactured Year: 8.33299825982598"

# Menghitung Standar Deviasi
sd_year <- sd(data$`Manufactured Year`, na.rm = TRUE)
print(paste("Standar Deviasi Manufactured Year:", sd_year))

## [1] "Standar Deviasi Manufactured Year: 2.88669330893082"

menampilkan semua data

grid.arrange(pie_chart, bar_chart, histogram, boxplot_data, density_plot, ncol = 2)

Statistika_Deskriptif

Aditya Putra Hertanto

2025-03-07

Load library

Import Data

1. Pie Chart

2. Bar Chart

3. Histogram

4. Bloxplot

5. Density

6. Penyebaran Data

menampilkan semua data