visualisasi

Lihat sebaran penghasilan pelanggan, apakah condong ke rendah atau tinggi

library(ggplot2)

df <- read.csv("df_customer.csv")

ggplot(df, aes(x = Penghasilan)) +
  geom_histogram(bins = 30, fill = "steelblue", color = "white") +
  labs(
    title = "Distribusi Penghasilan Pelanggan",
    x = "Penghasilan",
    y = "Jumlah Pelanggan"
  ) +
  theme_minimal()

Bandingin perilaku belanja antara laki-laki dan perempuan

ggplot(df, aes(x = Jenis_Kelamin, y = Total_Belanja, fill = Jenis_Kelamin)) +
  stat_summary(fun = mean, geom = "bar") +
  labs(
    title = "Rata-rata Total Belanja Berdasarkan Jenis Kelamin",
    x = "Jenis Kelamin",
    y = "Rata-rata Total Belanja"
  ) +
  theme_minimal() +
  guides(fill = "none")

Apakah penghasilan tinggi selalu belanja lebih besar?

ggplot(df, aes(x = Penghasilan, y = Total_Belanja)) +
  geom_point(alpha = 0.6) +
  geom_smooth(method = "lm", se = FALSE) +
  labs(
    title = "Hubungan Penghasilan dan Total Belanja",
    x = "Penghasilan",
    y = "Total Belanja"
  ) +
  theme_minimal()

## `geom_smooth()` using formula = 'y ~ x'

Bandingin pola belanja pelanggan Desa vs Kota

ggplot(df, aes(x = Tempat_Tinggal, y = Total_Belanja, fill = Tempat_Tinggal)) +
  geom_boxplot() +
  labs(
    title = "Distribusi Total Belanja Berdasarkan Tempat Tinggal",
    x = "Tempat Tinggal",
    y = "Total Belanja"
  ) +
  theme_minimal() +
  guides(fill = "none")

Lihat proporsi pelanggan berdasarkan gender

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

df %>%
  count(Jenis_Kelamin) %>%
  ggplot(aes(x = "", y = n, fill = Jenis_Kelamin)) +
  geom_col(width = 1) +
  coord_polar("y") +
  labs(title = "Proporsi Jenis Kelamin Pelanggan") +
  theme_void()