df_customer <- read.csv("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 4782002
nrow(df_customer)
## [1] 300
length(unique(df_customer$ID_Pelanggan))
## [1] 94
unique(df_customer$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"
sort(table(df_customer$ID_Pelanggan), decreasing = TRUE) [1:3]
##
## ID00007 ID00025 ID00089
## 9 7 7
aggregate(Penghasilan ~ Jenis_Kelamin, data = df_customer, mean)
## Jenis_Kelamin Penghasilan
## 1 Laki-laki 8880902
## 2 Perempuan 8505199
aggregate(Total_Belanja ~ Jenis_Kelamin, data = df_customer, mean)
## Jenis_Kelamin Total_Belanja
## 1 Laki-laki 6034728
## 2 Perempuan 7114786
aggregate(Penghasilan ~ Tempat_Tinggal, data = df_customer, mean)
## Tempat_Tinggal Penghasilan
## 1 Desa 6249122
## 2 Kota 9878685
aggregate(Total_Belanja ~ Tempat_Tinggal, data= df_customer, mean)
## Tempat_Tinggal Total_Belanja
## 1 Desa 5022231
## 2 Kota 7520118
df_customer [order(-df_customer$Total_Belanja), c("ID_Pelanggan", "Total_Belanja")]
## ID_Pelanggan Total_Belanja
## 76 ID00034 11626302
## 175 ID00011 11527638
## 228 ID00057 11031197
## 287 ID00093 10984825
## 33 ID00007 10846012
## 208 ID00023 10739381
## 26 ID00036 10641105
## 252 ID00064 10615150
## 204 ID00074 10556216
## 72 ID00039 10344433
## 101 ID00079 10241993
## 11 ID00090 10137674
## 57 ID00025 9945372
## 278 ID00045 9928570
## 275 ID00061 9924147
## 167 ID00093 9890886
## 86 ID00087 9872391
## 132 ID00005 9817378
## 4 ID00014 9799876
## 224 ID00090 9796996
## 64 ID00060 9758749
## 264 ID00025 9710543
## 164 ID00048 9695153
## 113 ID00046 9689403
## 246 ID00084 9639414
## 49 ID00069 9594128
## 282 ID00053 9589712
## 126 ID00023 9531823
## 182 ID00046 9516174
## 15 ID00057 9484196
## 42 ID00053 9466583
## 142 ID00089 9423949
## 211 ID00057 9287318
## 12 ID00091 9275845
## 75 ID00050 9201734
## 135 ID00024 9144955
## 19 ID00099 9141069
## 107 ID00050 9080252
## 179 ID00085 9009507
## 174 ID00084 8951249
## 111 ID00076 8931677
## 239 ID00026 8922412
## 298 ID00002 8895933
## 168 ID00036 8895365
## 193 ID00040 8798502
## 270 ID00018 8798501
## 79 ID00069 8784311
## 122 ID00087 8768903
## 92 ID00030 8685167
## 279 ID00092 8612837
## 244 ID00026 8604458
## 30 ID00076 8595100
## 40 ID00053 8582735
## 116 ID00046 8578249
## 39 ID00060 8558413
## 283 ID00063 8500700
## 125 ID00079 8492008
## 61 ID00041 8371463
## 2 ID00079 8369550
## 87 ID00035 8307214
## 99 ID00067 8304569
## 273 ID00006 8268965
## 21 ID00026 8232816
## 300 ID00063 8211115
## 127 ID00026 8161496
## 90 ID00012 8098488
## 223 ID00087 8072625
## 3 ID00051 8053033
## 222 ID00025 7994421
## 235 ID00090 7993933
## 78 ID00013 7946382
## 140 ID00036 7942215
## 288 ID00017 7936955
## 243 ID00060 7915300
## 89 ID00030 7896921
## 220 ID00026 7895296
## 32 ID00032 7884152
## 274 ID00071 7876640
## 123 ID00007 7857641
## 63 ID00090 7826544
## 269 ID00045 7825427
## 236 ID00058 7808366
## 294 ID00024 7804955
## 23 ID00042 7798760
## 201 ID00007 7780053
## 191 ID00087 7760180
## 261 ID00074 7731739
## 16 ID00092 7720654
## 137 ID00021 7717504
## 59 ID00021 7714018
## 221 ID00007 7655665
## 84 ID00032 7640093
## 55 ID00097 7636699
## 20 ID00072 7627379
## 143 ID00039 7622355
## 284 ID00071 7616089
## 68 ID00006 7566649
## 66 ID00016 7515644
## 157 ID00030 7512473
## 69 ID00072 7490116
## 170 ID00022 7485827
## 118 ID00035 7484242
## 117 ID00054 7476936
## 194 ID00040 7410923
## 218 ID00025 7379123
## 163 ID00075 7365112
## 214 ID00053 7299584
## 285 ID00084 7261831
## 105 ID00051 7261072
## 266 ID00055 7214061
## 150 ID00077 7194070
## 18 ID00093 7188080
## 77 ID00004 7187773
## 241 ID00085 7184097
## 172 ID00042 7166426
## 106 ID00074 7154243
## 250 ID00093 7140298
## 169 ID00052 7122143
## 147 ID00071 7121152
## 226 ID00084 7117614
## 290 ID00002 7097745
## 47 ID00034 7064321
## 54 ID00082 7021800
## 5 ID00067 6982081
## 151 ID00083 6974488
## 81 ID00052 6971142
## 233 ID00091 6935452
## 253 ID00037 6931584
## 129 ID00007 6921826
## 291 ID00049 6919859
## 44 ID00096 6911517
## 43 ID00027 6901502
## 195 ID00010 6899791
## 14 ID00091 6841960
## 183 ID00070 6805522
## 267 ID00089 6787182
## 173 ID00059 6749874
## 88 ID00040 6745396
## 141 ID00083 6741328
## 188 ID00045 6730077
## 299 ID00037 6719412
## 272 ID00031 6699765
## 249 ID00031 6686485
## 131 ID00042 6678890
## 209 ID00026 6663821
## 205 ID00024 6661848
## 176 ID00055 6646206
## 13 ID00069 6582132
## 70 ID00086 6566917
## 83 ID00089 6556704
## 219 ID00052 6548809
## 185 ID00044 6527872
## 281 ID00053 6524073
## 202 ID00058 6514985
## 197 ID00072 6500860
## 260 ID00004 6476914
## 296 ID00067 6462534
## 22 ID00007 6448525
## 190 ID00016 6446238
## 230 ID00023 6436205
## 146 ID00009 6390543
## 213 ID00010 6347690
## 166 ID00067 6344949
## 110 ID00086 6339596
## 215 ID00054 6329024
## 9 ID00014 6315967
## 152 ID00056 6314093
## 60 ID00079 6296779
## 234 ID00001 6288533
## 238 ID00029 6280030
## 138 ID00055 6262374
## 52 ID00063 6261498
## 65 ID00095 6259431
## 242 ID00007 6243561
## 231 ID00014 6229499
## 29 ID00043 6226134
## 67 ID00094 6224021
## 280 ID00063 6201985
## 198 ID00082 6194282
## 62 ID00047 6172545
## 85 ID00025 6168863
## 232 ID00006 6134541
## 128 ID00032 6122424
## 36 ID00074 6119057
## 27 ID00078 6117587
## 177 ID00008 6100858
## 17 ID00009 6096816
## 292 ID00002 6090917
## 45 ID00038 6084854
## 100 ID00023 6033115
## 247 ID00006 6027924
## 186 ID00032 6011391
## 56 ID00091 5990469
## 251 ID00017 5988984
## 145 ID00090 5987338
## 119 ID00094 5983600
## 31 ID00015 5977619
## 34 ID00009 5955753
## 103 ID00037 5952935
## 256 ID00035 5952082
## 187 ID00036 5946104
## 120 ID00079 5944523
## 112 ID00084 5892759
## 161 ID00088 5826813
## 46 ID00089 5776859
## 180 ID00066 5731064
## 192 ID00033 5704286
## 171 ID00049 5695306
## 121 ID00024 5654997
## 82 ID00022 5602663
## 91 ID00031 5581822
## 293 ID00013 5581775
## 73 ID00031 5581673
## 148 ID00098 5535035
## 254 ID00057 5530567
## 229 ID00073 5490472
## 258 ID00033 5476852
## 24 ID00009 5448759
## 53 ID00013 5438461
## 134 ID00016 5436492
## 160 ID00016 5433512
## 80 ID00025 5423813
## 268 ID00085 5411875
## 124 ID00093 5383301
## 97 ID00096 5369782
## 149 ID00048 5333229
## 257 ID00089 5259961
## 153 ID00039 5249938
## 35 ID00041 5228866
## 196 ID00089 5221740
## 289 ID00097 5214133
## 286 ID00082 5164174
## 259 ID00066 5157567
## 10 ID00025 5106141
## 58 ID00038 5094570
## 265 ID00008 5052071
## 248 ID00094 5043885
## 139 ID00075 5002921
## 178 ID00046 4993380
## 51 ID00076 4968714
## 189 ID00014 4947617
## 104 ID00008 4922220
## 255 ID00020 4877976
## 159 ID00089 4797439
## 133 ID00070 4785421
## 154 ID00068 4784177
## 6 ID00042 4782002
## 8 ID00043 4779797
## 212 ID00029 4723412
## 297 ID00082 4720756
## 95 ID00014 4698681
## 158 ID00094 4695264
## 200 ID00007 4677575
## 102 ID00085 4672343
## 207 ID00054 4622512
## 199 ID00009 4605777
## 114 ID00017 4520756
## 41 ID00007 4498392
## 203 ID00061 4444803
## 38 ID00027 4389470
## 25 ID00083 4381195
## 262 ID00097 4292393
## 7 ID00050 4286283
## 109 ID00074 4252327
## 144 ID00054 4240845
## 155 ID00001 4230664
## 216 ID00077 4224491
## 165 ID00020 4222089
## 210 ID00033 4173259
## 96 ID00093 4171074
## 237 ID00081 4141607
## 184 ID00072 4111994
## 295 ID00049 4086854
## 48 ID00093 4072657
## 28 ID00081 4062511
## 225 ID00032 4026738
## 71 ID00086 4000684
## 271 ID00042 3999429
## 245 ID00041 3856989
## 108 ID00098 3834102
## 263 ID00005 3810681
## 37 ID00023 3777745
## 98 ID00071 3749631
## 276 ID00048 3627563
## 93 ID00064 3624444
## 136 ID00032 3616787
## 156 ID00040 3565274
## 227 ID00024 3527189
## 162 ID00054 3396041
## 74 ID00081 3358968
## 240 ID00027 3321927
## 130 ID00027 3224369
## 277 ID00017 3196313
## 115 ID00062 3159885
## 206 ID00063 3098677
## 181 ID00077 3006345
## 217 ID00011 2886327
## 94 ID00099 2752967
## 1 ID00031 2563031
## 50 ID00072 2534171
head(10)
## [1] 10
table(df_customer$Jenis_Kelamin)
##
## Laki-laki Perempuan
## 121 179
df_customer$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 98
1. Pelanggan yang paling sering membeli dengan total belanja >
5.000.000
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
q11 <- df_customer %>%
filter(Total_Belanja > 5000000) %>%
count(ID_Pelanggan, sort = TRUE) %>%
slice_head(n=5)
q11
## ID_Pelanggan n
## 1 ID00007 7
## 2 ID00025 7
## 3 ID00026 6
## 4 ID00089 6
## 5 ID00053 5
2. Ada berapa banyak perempuan di kota yang berbelanja lebih dari
5x
q22 <- df_customer %>%
filter(Jenis_Kelamin == "Perempuan", Tempat_Tinggal == "Kota") %>%
count(ID_Pelanggan) %>%
filter(n > 5) %>%
summarise(jumlah = n())
q22
## jumlah
## 1 0
3. Pelanggan yang paling sering membeli dengan penghasilan >
5.000.000
q33 <- df_customer %>%
filter(Penghasilan > 5000000) %>%
count(ID_Pelanggan, sort = TRUE) %>%
slice_head(n=1)
q33
## ID_Pelanggan n
## 1 ID00007 9
4. Berjenis kelamin apa pelanggan yang tinggal di desa dengan total
belanja > 5.000.000
q44 <- df_customer %>%
filter(Tempat_Tinggal == "Desa", Total_Belanja > 5000000) %>%
count(Jenis_Kelamin)
q44
## Jenis_Kelamin n
## 1 Laki-laki 10
## 2 Perempuan 37
5. Berpenghasilan berapa pelanggan yang tinggal di desa namun
memiliki total belanja > 5.000.000
q55 <- df_customer %>%
filter(Tempat_Tinggal == "Desa", Total_Belanja > 5000000) %>%
select(ID_Pelanggan, Penghasilan) %>%
head(10)
q55
## ID_Pelanggan Penghasilan
## 1 ID00067 7773498
## 2 ID00014 6776730
## 3 ID00027 8108645
## 4 ID00089 9032981
## 5 ID00034 5616450
## 6 ID00013 4481204
## 7 ID00091 6128487
## 8 ID00038 5947963
## 9 ID00041 9231091
## 10 ID00047 5940612