library(dplyr) df <- read.csv(“df_customer.csv”) head(df)
frec1 <- df %>% filter(Total_Belanja > 5000000) %>% count(ID_Pelanggan, sort = TRUE)
head(frec1, n=3)
frec2 <- df %>% group_by(ID_Pelanggan, Jenis_Kelamin, Tempat_Tinggal) %>% summarise(frec = n(), .groups = ‘drop’)
ffrec2 <- frec2 %>% filter(frec > 5 & Tempat_Tinggal == ‘Kota’ & Jenis_Kelamin == ‘Perempuan’)
nrow(ffrec2) ffrec2
frec3 <- df %>% group_by(ID_Pelanggan, Penghasilan) %>% filter(Penghasilan > 5000000) %>% summarise(frec = n(), .groups = ‘drop’)
head(arrange(frec3, desc(frec)), n=1)
summ4 <- df %>% group_by(Jenis_Kelamin, Tempat_Tinggal, Total_Belanja) %>% filter(Total_Belanja > 5000000) %>% summarise(.groups = ‘drop’)
head(arrange(summ4), n = 1) head(arrange(summ4, desc(Jenis_Kelamin)), n = 1)
summ5 <- df %>% group_by(Penghasilan, Tempat_Tinggal, Total_Belanja) %>% filter(Total_Belanja > 5000000) %>% summarise(.groups = ‘drop’)
head(summ5) min(summ5\(Penghasilan) max(summ5\)Penghasilan)