Statistics Descriptive In R
2026-10-10
Bakery Synthetic Dataset
library(readxl)
data_uts <- read_excel(
"C:/Users/acer/OneDrive/Dokumen/bakery_synthetic_dataset.xlsx",
col_names = TRUE
)
data_utsRingkasan Dataset
Ini adalah dataset retail bakery sintetis, dataset ini memiliki 16.569 catatan transaksi dalam periode 2 tahun dari januari 2023 sampai desember 2024. dataset ini mencakup 13 variabel data yang terdiri dari tanggal transaksi, umur customer, produk & kategori, quantity, harga jual per unit, persentase diskon, harga jual, total bayar, metode pembayaran,stok tersedia, jumlah produksi unit, unit terjual. dataset ini kita ambil dari kaggle yang dipublish oleh Anjali Jawale (2026) dan Shreyash Dodekar (2026) https://www.kaggle.com/datasets/shreyashdodekar/synthetic-bakery-sales-dataset/data
Statistika Deskriptif
Summary Data
summary(data_uts)## Date Customer_Age Product
## Min. :2023-01-01 00:00:00.00 Min. :16.00 Length:16569
## 1st Qu.:2023-07-06 00:00:00.00 1st Qu.:23.00 Class :character
## Median :2024-01-05 00:00:00.00 Median :30.00 Mode :character
## Mean :2024-01-04 00:36:45.75 Mean :34.48
## 3rd Qu.:2024-07-06 00:00:00.00 3rd Qu.:44.00
## Max. :2024-12-31 00:00:00.00 Max. :74.00
## Category Quantity Unit_Price Discount_Percentage
## Length:16569 Min. :1.000 Min. : 24.25 Min. : 0.000
## Class :character 1st Qu.:2.000 1st Qu.: 39.54 1st Qu.: 0.000
## Mode :character Median :2.000 Median : 50.81 Median : 3.800
## Mean :2.591 Mean : 85.69 Mean : 6.656
## 3rd Qu.:3.000 3rd Qu.: 71.91 3rd Qu.:10.200
## Max. :6.000 Max. :463.49 Max. :30.000
## Selling_Price Total_Bill Payment_Method Stock_Available
## Min. : 17.17 Min. : 17.61 Length:16569 Min. : 1.000
## 1st Qu.: 36.50 1st Qu.: 74.34 Class :character 1st Qu.: 2.000
## Median : 48.24 Median : 119.96 Mode :character Median : 2.000
## Mean : 79.96 Mean : 207.86 Mean : 2.748
## 3rd Qu.: 70.55 3rd Qu.: 209.11 3rd Qu.: 3.000
## Max. :463.30 Max. :2758.98 Max. :21.000
## Units_Produced Units_Sold Profit
## Min. : 2.000 Min. : 1.0 Min. :-2152.66
## 1st Qu.: 5.000 1st Qu.: 2.0 1st Qu.: -34.12
## Median : 7.000 Median : 4.0 Median : -0.42
## Mean : 7.647 Mean : 4.9 Mean : -13.90
## 3rd Qu.:10.000 3rd Qu.: 6.0 3rd Qu.: 25.14
## Max. :39.000 Max. :25.0 Max. : 898.42Modus dan Antimodus Data Kategorik
modus_Product <- names(which.max(table(data_uts$Product)))
paste("Modus data kolom Product :",modus_Product)## [1] "Modus data kolom Product : Bread"sedikit_Product <- names(which.min(table(data_uts$Product)))
paste("Product paling sedikit :", sedikit_Product)## [1] "Product paling sedikit : Honey"modus_Category <- names(which.max(table(data_uts$Category)))
paste("Modus data kolom Category :",modus_Category)## [1] "Modus data kolom Category : Beverages"sedikit_Category <- names(which.min(table(data_uts$Category)))
paste("Category paling sedikit :", sedikit_Category)## [1] "Category paling sedikit : Muffins"modus_Payment_Method <- names(which.max(table(data_uts$Payment_Method)))
paste("Modus data kolom Payment Method :",modus_Payment_Method)## [1] "Modus data kolom Payment Method : UPI"sedikit_Payment_Method <- names(which.min(table(data_uts$Payment_Method)))
paste("Payment Method paling sedikit :", sedikit_Payment_Method)## [1] "Payment Method paling sedikit : Wallet"Standar Deviasi Data Numerik
sd_CustomerAge <- sd(data_uts$Customer_Age, na.rm = TRUE)
paste("Standar Deviasi data kolom Customer Age :",sd_CustomerAge)## [1] "Standar Deviasi data kolom Customer Age : 15.2989973121483"sd_Quantity <- sd(data_uts$Quantity, na.rm = TRUE)
paste("Standar Deviasi kolom Quantity :",sd_Quantity)## [1] "Standar Deviasi kolom Quantity : 1.25165709836292"sd_Unit_Price <- sd(data_uts$Unit_Price, na.rm = TRUE)
paste("Standar Deviasi kolom Unit Price :",sd_Unit_Price)## [1] "Standar Deviasi kolom Unit Price : 96.9511935374476"sd_DiscountPercentage <- sd(data_uts$Discount_Percentage, na.rm = TRUE)
paste("Standar Deviasi kolom Discount Percentage :",sd_DiscountPercentage)## [1] "Standar Deviasi kolom Discount Percentage : 8.00023423563348"sd_Selling_Price <- sd(data_uts$Selling_Price, na.rm = TRUE)
paste("Standar Deviasi kolom Selling Price :",sd_Selling_Price)## [1] "Standar Deviasi kolom Selling Price : 91.0461599408723"sd_Total_Bill <- sd(data_uts$Total_Bill, na.rm = TRUE)
paste("Standar Deviasi kolom Total Bill :",sd_Total_Bill)## [1] "Standar Deviasi kolom Total Bill : 281.230169963612"sd_Stock_Available <- sd(data_uts$Stock_Available, na.rm = TRUE)
paste("Standar Deviasi kolom stock Available :",sd_Stock_Available)## [1] "Standar Deviasi kolom stock Available : 1.9003413356256"sd_Units_Produced <- sd(data_uts$Units_Produced, na.rm = TRUE)
paste("Standar Deviasi kolom Units Produced :",sd_Units_Produced)## [1] "Standar Deviasi kolom Units Produced : 4.43546590326741"sd_Units_Sold <- sd(data_uts$Units_Sold, na.rm = TRUE)
paste("Standar Deviasi kolom Units Sold :",sd_Units_Sold)## [1] "Standar Deviasi kolom Units Sold : 3.33244234115362"sd_Profit <- sd(data_uts$Profit, na.rm = TRUE)
paste("Standar Deviasi kolom Profit :",sd_Profit)## [1] "Standar Deviasi kolom Profit : 109.335028153946"Ringkasan Statistika Deskriptif Data
Variabel Kuantitatif
ringkasan_stat_deskriptif_quanti <- data.frame(
Variabel = c("Date","Costumer_Age","Quantity","Unit_Price","Discount_Percentage","Selling_Price","Total_Bill","Stock_Available","Units_Produced","Units_Sold","Profit"),
Min = c("2023-01-01 00:00:00",16.00,1.000,24.25,0.000,17.17,17.61,1.000,2.000,1.0,-2152.66),
Median = c("2024-01-05 00:00:00",30.00,2.000,50.81,3.800,48.24,119.96,2.000,7.000,4.0,-0.42),
Max = c("2024-12-31 00:00:00",74.00,6.000,463.49,30.000,463.30,2758.98,21.000,39.000,25.0,898.42))
ringkasan_stat_deskriptif_quantiVariabel Kualitatif
ringkasan_stat_deskriptif_quali <- data.frame(
Variabel = c("Product","Category","Payment_Method"),
Paling_Sedikit = c("Honey","Muffins","Wallet"),
Paling_Banyak = c("Bread","Beverages","UPI"))
ringkasan_stat_deskriptif_qualiVisualisasi
Visualisasi Kategori Selling Price
hist(data_uts$Selling_Price,
main = "Histogram Harga Jual Per Unit",
xlab = "Harga Jual",
ylab = "Frekuensi",
col = "green",
border = "black",
breaks = 30)
Karena dengan menggunakan histogram untuk variabel Selling price, menarik untuk dilihat grafik datanya karena informasi yang diperoleh dari grafik tersebut dapat memberikan insight yang bagus mengenai persebaran harga masing-masing produk agar dapat dipertimbangkan kembali dalam penetapan labelling harganya.
Visualisasi Kategori Profit
hist(data_uts$Profit,
main = "Histogram Keuntungan Penjualan",
xlab = "Keuntungan",
ylab = "Frekuensi",
col = "skyblue",
border = "black")
boxplot(data_uts$Profit,
main = "Boxplot Keuntungan Penjualan",
ylab = "Profit",
col = "skyblue",
border = "blue")
Pada kategori profit median dan meannya menghasilkan angka negatif yang artinya rata-rata dari distribusi data tersebut ada di rentang kerugian daripada keuntungan ditambah data minimumnya sangat jauh letaknya dengan rata-rata sehingga dengan melihat box plot dan histogramnya, kita dapat melihat dan mempertimbangkan distribusi datanya lebih lanjut dan mengidentifikasi outlier.
Visualisasi Total Penjualan Per Month
data_uts$Date <- as.Date(data_uts$Date)
data_uts$Month <- format(data_uts$Date, "%Y-%m")
total_bill_month <- aggregate(
Total_Bill ~ Month,
data = data_uts,
FUN = sum,
na.action = na.omit
)
plot(
x = seq_len(nrow(total_bill_month)),
y = total_bill_month$Total_Bill,
type = "o",
xaxt = "n",
main = "Total Bill per Month",
xlab = "Month",
ylab = "Total Bill",
col = "red"
)
axis(
1,
at = seq_len(nrow(total_bill_month)),
labels = total_bill_month$Month
)