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, uniondf_customer <- read.csv("C:/Users/User/Downloads/df_customer.csv")
head(df_customer)## X ID_Pelanggan Jenis_Kelamin Tempat_Tinggal Penghasilan Total_Belanja
## 1 1 ID00031 Laki-laki Desa 2227350 2563031
## 2 2 ID00079 Perempuan Kota 9047608 8369550
## 3 3 ID00051 Perempuan Kota 9735540 8053033
## 4 4 ID00014 Laki-laki Kota 13510126 9799876
## 5 5 ID00067 Perempuan Desa 7773498 6982081
## 6 6 ID00042 Laki-laki Desa 6666740 4782002str(df_customer)## 'data.frame': 300 obs. of 6 variables:
## $ X : int 1 2 3 4 5 6 7 8 9 10 ...
## $ ID_Pelanggan : chr "ID00031" "ID00079" "ID00051" "ID00014" ...
## $ Jenis_Kelamin : chr "Laki-laki" "Perempuan" "Perempuan" "Laki-laki" ...
## $ Tempat_Tinggal: chr "Desa" "Kota" "Kota" "Kota" ...
## $ Penghasilan : int 2227350 9047608 9735540 13510126 7773498 6666740 5658721 7637656 6776730 10412102 ...
## $ Total_Belanja : int 2563031 8369550 8053033 9799876 6982081 4782002 4286283 4779797 6315967 5106141 ...summary(df_customer)## X ID_Pelanggan Jenis_Kelamin Tempat_Tinggal
## Min. : 1.00 Length :300 Length :300 Length :300
## 1st Qu.: 75.75 N.unique : 94 N.unique : 2 N.unique : 2
## Median :150.50 N.blank : 0 N.blank : 0 N.blank : 0
## Mean :150.50 Min.nchar: 7 Min.nchar: 9 Min.nchar: 4
## 3rd Qu.:225.25 Max.nchar: 7 Max.nchar: 9 Max.nchar: 4
## Max. :300.00
## Penghasilan Total_Belanja
## Min. : 901314 Min. : 2534171
## 1st Qu.: 6426148 1st Qu.: 5360644
## Median : 8630042 Median : 6552757
## Mean : 8656732 Mean : 6679163
## 3rd Qu.:10921107 3rd Qu.: 7895702
## Max. :16145151 Max. :11626302unique(df_customer$ID_Pelanggan)## [1] "ID00031" "ID00079" "ID00051" "ID00014" "ID00067" "ID00042" "ID00050"
## [8] "ID00043" "ID00025" "ID00090" "ID00091" "ID00069" "ID00057" "ID00092"
## [15] "ID00009" "ID00093" "ID00099" "ID00072" "ID00026" "ID00007" "ID00083"
## [22] "ID00036" "ID00078" "ID00081" "ID00076" "ID00015" "ID00032" "ID00041"
## [29] "ID00074" "ID00023" "ID00027" "ID00060" "ID00053" "ID00096" "ID00038"
## [36] "ID00089" "ID00034" "ID00063" "ID00013" "ID00082" "ID00097" "ID00021"
## [43] "ID00047" "ID00095" "ID00016" "ID00094" "ID00006" "ID00086" "ID00039"
## [50] "ID00004" "ID00052" "ID00022" "ID00087" "ID00035" "ID00040" "ID00030"
## [57] "ID00012" "ID00064" "ID00071" "ID00085" "ID00037" "ID00008" "ID00098"
## [64] "ID00084" "ID00046" "ID00017" "ID00062" "ID00054" "ID00024" "ID00005"
## [71] "ID00070" "ID00055" "ID00075" "ID00048" "ID00077" "ID00056" "ID00068"
## [78] "ID00001" "ID00088" "ID00020" "ID00049" "ID00059" "ID00011" "ID00066"
## [85] "ID00044" "ID00045" "ID00033" "ID00010" "ID00058" "ID00061" "ID00029"
## [92] "ID00073" "ID00018" "ID00002"#3. Siapa pelanggan yang sering beelanja
# melihat pelanggan yang sering belanja
sort(table(df_customer$ID_Pelanggan), decreasing = TRUE)[1-3]##
## ID00007 ID00089 ID00093 ID00026 ID00032 ID00009 ID00014 ID00023 ID00024 ID00031
## 9 7 7 6 6 5 5 5 5 5
## ID00042 ID00053 ID00054 ID00063 ID00072 ID00074 ID00079 ID00084 ID00090 ID00006
## 5 5 5 5 5 5 5 5 5 4
## ID00016 ID00017 ID00027 ID00036 ID00040 ID00046 ID00057 ID00067 ID00071 ID00082
## 4 4 4 4 4 4 4 4 4 4
## ID00085 ID00087 ID00091 ID00094 ID00002 ID00008 ID00013 ID00030 ID00033 ID00035
## 4 4 4 4 3 3 3 3 3 3
## ID00037 ID00039 ID00041 ID00045 ID00048 ID00049 ID00050 ID00052 ID00055 ID00060
## 3 3 3 3 3 3 3 3 3 3
## ID00069 ID00076 ID00077 ID00081 ID00083 ID00086 ID00097 ID00001 ID00004 ID00005
## 3 3 3 3 3 3 3 2 2 2
## ID00010 ID00011 ID00020 ID00021 ID00022 ID00029 ID00034 ID00038 ID00043 ID00051
## 2 2 2 2 2 2 2 2 2 2
## ID00058 ID00061 ID00064 ID00066 ID00070 ID00075 ID00092 ID00096 ID00098 ID00099
## 2 2 2 2 2 2 2 2 2 2
## ID00012 ID00015 ID00018 ID00044 ID00047 ID00056 ID00059 ID00062 ID00068 ID00073
## 1 1 1 1 1 1 1 1 1 1
## ID00078 ID00088 ID00095
## 1 1 1#4. Rata-rata penghasilan pelanggan berdasarkan jenis kelamin.
# melihat rata-rata penghasilan
aggregate(Penghasilan ~ Jenis_Kelamin, data = df_customer, mean)## Jenis_Kelamin Penghasilan
## 1 Laki-laki 8880902
## 2 Perempuan 8505199#5. Rata-Rata total belanja pelanggan berdasarkan jenis kelamin.
# rata-rata total belanja
aggregate(Total_Belanja ~ Jenis_Kelamin, data = df_customer, mean)## Jenis_Kelamin Total_Belanja
## 1 Laki-laki 6034728
## 2 Perempuan 7114786#6. Rata-rata penghasilan pelanggan berdasarkan tempat tinggal (Kota vs Desa)
# rata-rata penghasilan pelanggan
aggregate(Penghasilan ~ Tempat_Tinggal, data = df_customer, mean)## Tempat_Tinggal Penghasilan
## 1 Desa 6249122
## 2 Kota 9878685#7. Rata-rata total belanja pelanggan berdasarkan tempat tinggal
aggregate(Total_Belanja ~ Tempat_Tinggal, data = df_customer, mean)## Tempat_Tinggal Total_Belanja
## 1 Desa 5022231
## 2 Kota 7520118#8. Siapa lima pelanggan dengan total belanja tertinggi?
head(df_customer[order(-df_customer$Total_Belanja), c("ID_Pelanggan", "Total_Belanja")], 5)## ID_Pelanggan Total_Belanja
## 76 ID00034 11626302
## 175 ID00011 11527638
## 228 ID00057 11031197
## 287 ID00093 10984825
## 33 ID00007 10846012#9. Distribusi jumlah transaksi berdasarkan jenis kelamin.
table(df_customer$Jenis_Kelamin)##
## Laki-laki Perempuan
## 121 179#10. Buat kategori penghasilan
df_customer$Kategori_Penghasilan <- cut( df_customer$Penghasilan,
breaks = c(-Inf, 5000000, 10000000, Inf),
labels = c("Rendah", "Menengah", "Tinggi"))
table(df_customer$Kategori_Penghasilan)##
## Rendah Menengah Tinggi
## 27 175 98Q1 <- df_customer %>%
filter(Total_Belanja > 5000000) %>%
count(ID_Pelanggan, sort = TRUE)
Q1## ID_Pelanggan n
## 1 ID00007 7
## 2 ID00025 7
## 3 ID00026 6
## 4 ID00089 6
## 5 ID00053 5
## 6 ID00079 5
## 7 ID00084 5
## 8 ID00090 5
## 9 ID00093 5
## 10 ID00006 4
## 11 ID00009 4
## 12 ID00016 4
## 13 ID00023 4
## 14 ID00024 4
## 15 ID00031 4
## 16 ID00032 4
## 17 ID00036 4
## 18 ID00057 4
## 19 ID00063 4
## 20 ID00067 4
## 21 ID00074 4
## 22 ID00087 4
## 23 ID00091 4
## 24 ID00002 3
## 25 ID00013 3
## 26 ID00014 3
## 27 ID00030 3
## 28 ID00035 3
## 29 ID00037 3
## 30 ID00039 3
## 31 ID00040 3
## 32 ID00042 3
## 33 ID00045 3
## 34 ID00046 3
## 35 ID00052 3
## 36 ID00055 3
## 37 ID00060 3
## 38 ID00069 3
## 39 ID00071 3
## 40 ID00072 3
## 41 ID00082 3
## 42 ID00085 3
## 43 ID00094 3
## 44 ID00004 2
## 45 ID00008 2
## 46 ID00010 2
## 47 ID00017 2
## 48 ID00021 2
## 49 ID00022 2
## 50 ID00033 2
## 51 ID00034 2
## 52 ID00038 2
## 53 ID00041 2
## 54 ID00048 2
## 55 ID00049 2
## 56 ID00050 2
## 57 ID00051 2
## 58 ID00054 2
## 59 ID00058 2
## 60 ID00066 2
## 61 ID00075 2
## 62 ID00076 2
## 63 ID00083 2
## 64 ID00086 2
## 65 ID00092 2
## 66 ID00096 2
## 67 ID00097 2
## 68 ID00001 1
## 69 ID00005 1
## 70 ID00011 1
## 71 ID00012 1
## 72 ID00015 1
## 73 ID00018 1
## 74 ID00027 1
## 75 ID00029 1
## 76 ID00043 1
## 77 ID00044 1
## 78 ID00047 1
## 79 ID00056 1
## 80 ID00059 1
## 81 ID00061 1
## 82 ID00064 1
## 83 ID00070 1
## 84 ID00073 1
## 85 ID00077 1
## 86 ID00078 1
## 87 ID00088 1
## 88 ID00095 1
## 89 ID00098 1
## 90 ID00099 1