PEKAN 1
Packages
lapply(c("tidyverse","rvest","kableExtra"),library,character.only=T)[[1]]## [1] "lubridate" "forcats" "stringr" "dplyr" "purrr" "readr"
## [7] "tidyr" "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [13] "grDevices" "utils" "datasets" "methods" "base"Kuliah
url <- "https://www.carsome.id/beli-mobil-bekas"
card <- read_html(url) %>% html_elements('.mod-card')
card %>%
html_element('.mod-card__high-tag-list') %>%
html_elements('span') %>%
html_text() %>%
paste(collapse = ',')## [1] "Plat Ganjil,Electric Parking Brake,360 Camera View,Plat Genap,Sports Mode,Map Navigator,Plat Ganjil,Keyless Push Start,Sports Mode,Plat Ganjil,Plat Genap,Jarak Tempuh Rendah,Retract Mirror,Plat Genap,Sports Mode,Plat Ganjil,Electric Parking Brake,Paddle Shift,Plat Ganjil,Panoramic Sun Roof,Electric Parking Brake,Plat Genap,Retract Mirror,Paddle Shift,Plat Ganjil,360 Camera View,Keyless Push Start,Plat Ganjil,Kamera Mundur,Retract Mirror,Plat Genap,Plat Genap,Sun Roof,Retract Mirror,Plat Genap,Retract Mirror,Plat Genap,Sports Mode,Plat Genap,Jarak Tempuh Rendah,Auto Retract Mirror,Plat Ganjil,Retract Mirror,Electric Parking Brake,Plat Ganjil"sapply(card,
function(card){
card %>%
html_element('.mod-card__high-tag-list') %>%
html_elements('span') %>%
html_text() %>%
paste(collapse = ',')
})## [1] "Plat Ganjil,Electric Parking Brake,360 Camera View"
## [2] "Plat Genap,Sports Mode,Map Navigator"
## [3] "Plat Ganjil,Keyless Push Start,Sports Mode"
## [4] "Plat Ganjil"
## [5] "Plat Genap,Jarak Tempuh Rendah,Retract Mirror"
## [6] "Plat Genap,Sports Mode"
## [7] "Plat Ganjil,Electric Parking Brake,Paddle Shift"
## [8] "Plat Ganjil,Panoramic Sun Roof,Electric Parking Brake"
## [9] "Plat Genap,Retract Mirror,Paddle Shift"
## [10] "Plat Ganjil,360 Camera View,Keyless Push Start"
## [11] "Plat Ganjil,Kamera Mundur,Retract Mirror"
## [12] "Plat Genap"
## [13] "Plat Genap,Sun Roof,Retract Mirror"
## [14] "Plat Genap,Retract Mirror"
## [15] "Plat Genap,Sports Mode"
## [16] "Plat Genap,Jarak Tempuh Rendah,Auto Retract Mirror"
## [17] "Plat Ganjil,Retract Mirror,Electric Parking Brake"
## [18] "Plat Ganjil"1 Page
url <- paste("https://www.carsome.id/beli-mobil-bekas?pageNo=",1,sep="")
card <- read_html(url) %>% html_elements('.mod-card')
Detail<-sapply(card,
function(card){
card %>%
html_element('.mod-card__high-tag-list') %>%
html_elements('span') %>%
html_text() %>%
paste(collapse = ',')
})
Harga.Kredit.Diskon<-card %>%
html_element('.mod-card__price__total')%>%
html_element("strong")%>%html_text2()
Harga.Cash.Diskon<-card %>%
html_element('.mod-card__price-cash')%>%html_text2()
Cicil<-card %>%
html_element('.mod-tooltipMonthPay')%>%
html_element("div")%>%html_text2()
Nama<-card %>%
html_element('a.mod-card__title')%>%html_text2()%>%gsub("\n","",.)
data<-cbind(Nama,Harga.Kredit.Diskon,Harga.Cash.Diskon,Cicil,
Detail);kable(head(data,15),caption="Tabel 1. Hasil Scraping Page 1")| Nama | Harga.Kredit.Diskon | Harga.Cash.Diskon | Cicil | Detail |
|---|---|---|---|---|
| 2019 WulingALMAZ LT LUX 1.5 | 198.000.000 | Rp 204.000.000 (Cash) | Rp 4,03 jt/bln | Plat Ganjil,Electric Parking Brake,360 Camera View |
| 2019 BMW3 20I (CKD) 2.0 | 474.000.000 | Rp 487.000.000 (Cash) | Rp 9,66 jt/bln | Plat Genap,Sports Mode,Map Navigator |
| 2018 ToyotaYARIS S TRD 1.5 | 199.000.000 | Rp 205.000.000 (Cash) | Rp 4,05 jt/bln | Plat Ganjil,Keyless Push Start,Sports Mode |
| 2019 DaihatsuAYLA R 1.2 | 113.500.000 | Rp 117.000.000 (Cash) | Rp 2,31 jt/bln | Plat Ganjil |
| 2022 ToyotaAVANZA G 1.5 | 211.000.000 | Rp 217.000.000 (Cash) | Rp 4,30 jt/bln | Plat Genap,Jarak Tempuh Rendah,Retract Mirror |
| 2020 HondaBRIO SATYA E 1.2 | 153.000.000 | Rp 158.000.000 (Cash) | Rp 3,12 jt/bln | Plat Genap,Sports Mode |
| 2016 HondaHR-V E 1.5 | 197.000.000 | Rp 203.000.000 (Cash) | Rp 4,01 jt/bln | Plat Ganjil,Electric Parking Brake,Paddle Shift |
| 2020 BMWX1 SDRIVE18I XLINE 1.5 | 554.000.000 | Rp 570.000.000 (Cash) | Rp 11,29 jt/bln | Plat Ganjil,Panoramic Sun Roof,Electric Parking Brake |
| 2018 ToyotaYARIS S TRD 1.5 | 192.000.000 | Rp 198.000.000 (Cash) | Rp 3,91 jt/bln | Plat Genap,Retract Mirror,Paddle Shift |
| 2015 NissanX-TRAIL 2.5 | 184.000.000 | Rp 190.000.000 (Cash) | Rp 3,75 jt/bln | Plat Ganjil,360 Camera View,Keyless Push Start |
| 2019 NissanLIVINA VL 1.5 | 192.000.000 | Rp 198.000.000 (Cash) | Rp 3,91 jt/bln | Plat Ganjil,Kamera Mundur,Retract Mirror |
| 2017 ToyotaAGYA G TRD 1.2 | 101.000.000 | Rp 104.500.000 (Cash) | Rp 2,06 jt/bln | Plat Genap |
| 2017 ChevroletTRAX TURBO LTZ 1.4 | 168.000.000 | Rp 173.000.000 (Cash) | Rp 3,42 jt/bln | Plat Genap,Sun Roof,Retract Mirror |
| 2021 ToyotaAVANZA G 1.3 | 186.000.000 | Rp 191.000.000 (Cash) | Rp 3,79 jt/bln | Plat Genap,Retract Mirror |
| 2017 ToyotaKIJANG INNOVA REBORN G 2.0 | 236.000.000 | Rp 243.000.000 (Cash) | Rp 4,81 jt/bln | Plat Genap,Sports Mode |
Looping
df<-data.frame()
for(hal in 1:10){
url <- paste("https://www.carsome.id/beli-mobil-bekas?pageNo=",hal,sep="")
card <- read_html(url) %>% html_elements('.mod-card')
card %>%
html_element('.mod-card__high-tag-list') %>%
html_elements('span') %>%
html_text() %>%
paste(collapse = ',')
Harga.Kredit.Diskon<-card %>%
html_element('.mod-card__price__total')%>%
html_element("strong")%>%html_text2()
Harga.Cash.Diskon<-card %>%
html_element('.mod-card__price-cash')%>%html_text2()
Cicil<-card %>%
html_element('.mod-tooltipMonthPay')%>%
html_element("div")%>%html_text2()
Nama<-card %>%
html_element('a.mod-card__title')%>%html_text2()%>%gsub("\n","",.)
Detail<-sapply(card,
function(card){
card %>%
html_element('.mod-card__high-tag-list') %>%
html_elements('span') %>%
html_text() %>%
paste(collapse = ',')
})
data<-cbind(Nama,Harga.Kredit.Diskon,Harga.Cash.Diskon,Cicil,
Detail)
df<-rbind(df,data)
cat("page",hal)
cat("\n")
}## page 1
## page 2
## page 3
## page 4
## page 5
## page 6
## page 7
## page 8
## page 9
## page 10kable(head(df,15),caption="Tabel 2. Hasil Scraping Page 1-10")| Nama | Harga.Kredit.Diskon | Harga.Cash.Diskon | Cicil | Detail |
|---|---|---|---|---|
| 2019 WulingALMAZ LT LUX 1.5 | 198.000.000 | Rp 204.000.000 (Cash) | Rp 4,03 jt/bln | Plat Ganjil,Electric Parking Brake,360 Camera View |
| 2019 BMW3 20I (CKD) 2.0 | 474.000.000 | Rp 487.000.000 (Cash) | Rp 9,66 jt/bln | Plat Genap,Sports Mode,Map Navigator |
| 2018 ToyotaYARIS S TRD 1.5 | 199.000.000 | Rp 205.000.000 (Cash) | Rp 4,05 jt/bln | Plat Ganjil,Keyless Push Start,Sports Mode |
| 2019 DaihatsuAYLA R 1.2 | 113.500.000 | Rp 117.000.000 (Cash) | Rp 2,31 jt/bln | Plat Ganjil |
| 2022 ToyotaAVANZA G 1.5 | 211.000.000 | Rp 217.000.000 (Cash) | Rp 4,30 jt/bln | Plat Genap,Jarak Tempuh Rendah,Retract Mirror |
| 2020 HondaBRIO SATYA E 1.2 | 153.000.000 | Rp 158.000.000 (Cash) | Rp 3,12 jt/bln | Plat Genap,Sports Mode |
| 2016 HondaHR-V E 1.5 | 197.000.000 | Rp 203.000.000 (Cash) | Rp 4,01 jt/bln | Plat Ganjil,Electric Parking Brake,Paddle Shift |
| 2020 BMWX1 SDRIVE18I XLINE 1.5 | 554.000.000 | Rp 570.000.000 (Cash) | Rp 11,29 jt/bln | Plat Ganjil,Panoramic Sun Roof,Electric Parking Brake |
| 2018 ToyotaYARIS S TRD 1.5 | 192.000.000 | Rp 198.000.000 (Cash) | Rp 3,91 jt/bln | Plat Genap,Retract Mirror,Paddle Shift |
| 2015 NissanX-TRAIL 2.5 | 184.000.000 | Rp 190.000.000 (Cash) | Rp 3,75 jt/bln | Plat Ganjil,360 Camera View,Keyless Push Start |
| 2019 NissanLIVINA VL 1.5 | 192.000.000 | Rp 198.000.000 (Cash) | Rp 3,91 jt/bln | Plat Ganjil,Kamera Mundur,Retract Mirror |
| 2017 ToyotaAGYA G TRD 1.2 | 101.000.000 | Rp 104.500.000 (Cash) | Rp 2,06 jt/bln | Plat Genap |
| 2017 ChevroletTRAX TURBO LTZ 1.4 | 168.000.000 | Rp 173.000.000 (Cash) | Rp 3,42 jt/bln | Plat Genap,Sun Roof,Retract Mirror |
| 2021 ToyotaAVANZA G 1.3 | 186.000.000 | Rp 191.000.000 (Cash) | Rp 3,79 jt/bln | Plat Genap,Retract Mirror |
| 2017 ToyotaKIJANG INNOVA REBORN G 2.0 | 236.000.000 | Rp 243.000.000 (Cash) | Rp 4,81 jt/bln | Plat Genap,Sports Mode |
Export Data Scraping
writexl::write_xlsx(df,"Data Scraping Mobil Bekas.xlsx")PEKAN 2
Packages
lapply(c("readxl","stringr","ggridges","hrbrthemes"),library,character.only=T)[[1]]## [1] "readxl" "kableExtra" "rvest" "lubridate" "forcats"
## [6] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [11] "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [16] "grDevices" "utils" "datasets" "methods" "base"Managing Data
Detail
Cleaning Detail menggunakan Excel
detail<-read_xlsx("Detail.xlsx")
df<-cbind(df,detail)
kable(head(df,15),caption="Tabel 3. Hasil Managing-Detail")| Nama | Harga.Kredit.Diskon | Harga.Cash.Diskon | Cicil | Detail | Plat | Detail1 | Detail2 |
|---|---|---|---|---|---|---|---|
| 2019 WulingALMAZ LT LUX 1.5 | 198.000.000 | Rp 204.000.000 (Cash) | Rp 4,03 jt/bln | Plat Ganjil,Electric Parking Brake,360 Camera View | Plat Genap | Sports Mode | Map Navigator |
| 2019 BMW3 20I (CKD) 2.0 | 474.000.000 | Rp 487.000.000 (Cash) | Rp 9,66 jt/bln | Plat Genap,Sports Mode,Map Navigator | Plat Ganjil | Panoramic Sun Roof | Electric Parking Brake |
| 2018 ToyotaYARIS S TRD 1.5 | 199.000.000 | Rp 205.000.000 (Cash) | Rp 4,05 jt/bln | Plat Ganjil,Keyless Push Start,Sports Mode | Plat Ganjil | Auto Cruise Control | Paddle Shift |
| 2019 DaihatsuAYLA R 1.2 | 113.500.000 | Rp 117.000.000 (Cash) | Rp 2,31 jt/bln | Plat Ganjil | Plat Ganjil | Electric Parking Brake | 360 Camera View |
| 2022 ToyotaAVANZA G 1.5 | 211.000.000 | Rp 217.000.000 (Cash) | Rp 4,30 jt/bln | Plat Genap,Jarak Tempuh Rendah,Retract Mirror | Plat Ganjil | Retract Mirror | Power Sliding Door |
| 2020 HondaBRIO SATYA E 1.2 | 153.000.000 | Rp 158.000.000 (Cash) | Rp 3,12 jt/bln | Plat Genap,Sports Mode | Plat Genap | Auto Retract Mirror | Auto Cruise Control |
| 2016 HondaHR-V E 1.5 | 197.000.000 | Rp 203.000.000 (Cash) | Rp 4,01 jt/bln | Plat Ganjil,Electric Parking Brake,Paddle Shift | Plat Ganjil | Auto Retract Mirror | Panoramic Sun Roof |
| 2020 BMWX1 SDRIVE18I XLINE 1.5 | 554.000.000 | Rp 570.000.000 (Cash) | Rp 11,29 jt/bln | Plat Ganjil,Panoramic Sun Roof,Electric Parking Brake | Plat Genap | Retract Mirror | Paddle Shift |
| 2018 ToyotaYARIS S TRD 1.5 | 192.000.000 | Rp 198.000.000 (Cash) | Rp 3,91 jt/bln | Plat Genap,Retract Mirror,Paddle Shift | Plat Ganjil | Keyless Push Start | Retract Mirror |
| 2015 NissanX-TRAIL 2.5 | 184.000.000 | Rp 190.000.000 (Cash) | Rp 3,75 jt/bln | Plat Ganjil,360 Camera View,Keyless Push Start | Plat Ganjil | 360 Camera View | Keyless Push Start |
| 2019 NissanLIVINA VL 1.5 | 192.000.000 | Rp 198.000.000 (Cash) | Rp 3,91 jt/bln | Plat Ganjil,Kamera Mundur,Retract Mirror | Plat Ganjil | Kamera Mundur | Retract Mirror |
| 2017 ToyotaAGYA G TRD 1.2 | 101.000.000 | Rp 104.500.000 (Cash) | Rp 2,06 jt/bln | Plat Genap | Plat Ganjil | Jarak Tempuh Rendah | Electric Parking Brake |
| 2017 ChevroletTRAX TURBO LTZ 1.4 | 168.000.000 | Rp 173.000.000 (Cash) | Rp 3,42 jt/bln | Plat Genap,Sun Roof,Retract Mirror | Plat Ganjil | 360 Camera View | Electric Parking Brake |
| 2021 ToyotaAVANZA G 1.3 | 186.000.000 | Rp 191.000.000 (Cash) | Rp 3,79 jt/bln | Plat Genap,Retract Mirror | Plat Genap | NA | NA |
| 2017 ToyotaKIJANG INNOVA REBORN G 2.0 | 236.000.000 | Rp 243.000.000 (Cash) | Rp 4,81 jt/bln | Plat Genap,Sports Mode | Plat Ganjil | Auto Retract Mirror | Keyless Push Start |
Harga Kredit Diskon
df$Harga.Kredit.Diskon<-str_remove_all(df$Harga.Kredit.Diskon,"[.]")%>%as.numeric();df$Harga.Kredit.Diskon## [1] 198000000 474000000 199000000 113500000 211000000 153000000 197000000
## [8] 554000000 192000000 184000000 192000000 101000000 168000000 186000000
## [15] 236000000 199000000 175000000 116500000 200000000 131000000 200000000
## [22] 104500000 192000000 260000000 188000000 143000000 136000000 151000000
## [29] 130000000 183000000 79500000 209000000 116500000 114500000 109500000
## [36] 217000000 189000000 118500000 199000000 116500000 155000000 109500000
## [43] 170000000 108500000 92000000 109500000 150000000 116500000 188000000
## [50] 116000000 139500000 340000000 111500000 167000000 120500000 102000000
## [57] 204000000 197000000 140000000 136000000 193000000 282000000 129500000
## [64] 193000000 197000000 211000000 210000000 218000000 229000000 213000000
## [71] 210000000 90000000 157000000 109500000 133500000 259000000 233000000
## [78] 287000000 143000000 143000000 203000000 257000000 199000000 114500000
## [85] 203000000 86000000 124500000 275000000 193000000 219000000 343000000
## [92] 257000000 245000000 157000000 193000000 124000000 237000000 110000000
## [99] 134000000 145000000 162000000 108000000 123500000 127000000 131000000
## [106] 110500000 140500000 195000000 119500000 204000000 124000000 209000000
## [113] 147000000 111000000 262000000 412000000 257000000 140000000 180000000
## [120] 113000000 123000000 370000000 429000000 220000000 195000000 166000000
## [127] 129000000 99000000 132000000 107000000 197000000 176000000 148000000
## [134] 222000000 232000000 170000000 278000000 109000000 100000000 206000000
## [141] 118000000 319000000 87000000 144000000 176000000 161000000 117000000
## [148] 211000000 140000000 204000000 149000000 230000000 213000000 219000000
## [155] 143000000 269000000 201000000 213000000 192000000 223000000 98000000
## [162] 185000000 164000000 190000000 360000000 119000000 139000000 207000000
## [169] 229000000 141000000 167000000 180000000 208000000 206000000 79000000
## [176] 236000000 184000000 134000000 188000000 394000000Harga Cash Diskon
df$Harga.Cash.Diskon<-str_remove_all(df$Harga.Cash.Diskon,"[.]")%>%
str_extract_all(.,"[0-9]+")%>%as.numeric();df$Harga.Cash.Diskon## [1] 204000000 487000000 205000000 117000000 217000000 158000000 203000000
## [8] 570000000 198000000 190000000 198000000 104500000 173000000 191000000
## [15] 243000000 205000000 180000000 120000000 206000000 135000000 206000000
## [22] 108000000 198000000 267000000 193000000 147000000 140500000 155000000
## [29] 134500000 188000000 82000000 215000000 120000000 118000000 113000000
## [36] 223000000 194000000 122000000 205000000 120000000 159000000 113000000
## [43] 175000000 112000000 94500000 113000000 154000000 120000000 193000000
## [50] 119500000 144000000 349000000 115000000 172000000 124000000 105500000
## [57] 210000000 203000000 144000000 139500000 199000000 290000000 133000000
## [64] 199000000 203000000 217000000 216000000 224000000 235000000 219000000
## [71] 216000000 92500000 162000000 113000000 137000000 266000000 240000000
## [78] 295000000 147000000 147000000 209000000 264000000 205000000 118000000
## [85] 209000000 88500000 128000000 283000000 199000000 225000000 352000000
## [92] 264000000 252000000 162000000 198000000 128000000 244000000 113500000
## [99] 138000000 149000000 166500000 111000000 127000000 131000000 135000000
## [106] 114000000 145000000 200000000 123000000 210000000 127500000 215000000
## [113] 151000000 114500000 269000000 423000000 264000000 144500000 185000000
## [120] 116500000 126500000 380000000 440500000 226000000 200500000 171000000
## [127] 132500000 102000000 136000000 110000000 203000000 181500000 152000000
## [134] 228500000 238500000 175000000 286000000 112500000 103000000 212000000
## [141] 122000000 328000000 89500000 148000000 181500000 166000000 121000000
## [148] 217000000 144000000 210000000 153500000 236000000 219000000 225000000
## [155] 147000000 276000000 206500000 219000000 197000000 229000000 101000000
## [162] 190500000 169000000 195000000 370000000 123000000 143000000 212500000
## [169] 235500000 145500000 172000000 185000000 214000000 212000000 81500000
## [176] 243000000 189500000 138000000 193000000 405000000Cicilan
df$Cicil<-str_replace_all(df$Cicil,",",".")%>%str_remove_all(.,"[A-Za-z]+")%>%
str_remove_all(.,"[/]")%>%as.numeric();df$Cicil## [1] 4.03 9.66 4.05 2.31 4.30 3.12 4.01 11.29 3.91 3.75 3.91 2.06
## [13] 3.42 3.79 4.81 4.05 3.57 2.37 4.08 2.67 4.08 2.13 3.91 5.30
## [25] 3.83 2.91 2.77 3.08 2.65 3.73 1.62 4.26 2.37 2.33 2.23 4.42
## [37] 3.85 2.41 4.05 2.37 3.16 2.23 3.46 2.21 1.87 2.23 3.06 2.37
## [49] 3.83 2.36 2.84 6.93 2.27 3.40 2.46 2.08 4.16 4.01 2.85 2.77
## [61] 3.93 5.75 2.64 3.93 4.01 4.30 4.28 4.44 4.67 4.34 4.28 1.83
## [73] 3.20 2.23 2.72 5.28 4.75 5.85 2.91 2.91 4.14 5.24 4.05 2.33
## [85] 4.14 1.75 2.54 5.60 3.93 4.46 6.99 5.24 4.99 3.20 3.93 2.53
## [97] 4.83 2.24 2.73 2.95 3.30 2.20 2.52 2.59 2.67 2.25 2.86 3.97
## [109] 2.43 4.16 2.53 4.26 3.00 2.26 5.34 8.39 5.24 2.85 3.67 2.30
## [121] 2.51 7.54 8.74 4.48 3.97 3.38 2.63 2.02 2.69 2.18 4.01 3.59
## [133] 3.02 4.52 4.73 3.46 5.66 2.22 2.04 4.20 2.40 6.50 1.77 2.93
## [145] 3.59 3.28 2.38 4.30 2.85 4.16 3.04 4.69 4.34 4.46 2.91 5.48
## [157] 4.10 4.34 3.91 4.54 2.00 3.77 3.34 3.87 7.33 2.42 2.83 4.22
## [169] 4.67 2.87 3.40 3.67 4.24 4.20 1.61 4.81 3.75 2.73 3.83 8.03colnames(df)[4]<-"Cicil (jt/bln)"Merek
Merek<-c("BMW","Chevrolet","Daihatsu","Datsun",
"Honda","Ford","Mazda","Mitsubishi","Nissan",
"Suzuki","Toyota","Wuling")
df$Merek<-unlist(str_extract_all(df$Nama,paste(Merek,collapse = "|")));df$Merek## [1] "Wuling" "BMW" "Toyota" "Daihatsu" "Toyota"
## [6] "Honda" "Honda" "BMW" "Toyota" "Nissan"
## [11] "Nissan" "Toyota" "Chevrolet" "Toyota" "Toyota"
## [16] "Toyota" "Honda" "Toyota" "Nissan" "Honda"
## [21] "Wuling" "Daihatsu" "Toyota" "Honda" "Mitsubishi"
## [26] "Honda" "Honda" "Daihatsu" "Suzuki" "Suzuki"
## [31] "Datsun" "Honda" "Toyota" "Daihatsu" "Daihatsu"
## [36] "Mitsubishi" "Wuling" "Toyota" "Wuling" "Toyota"
## [41] "Honda" "Daihatsu" "Honda" "Daihatsu" "Suzuki"
## [46] "Daihatsu" "Toyota" "Daihatsu" "Suzuki" "Daihatsu"
## [51] "Suzuki" "Honda" "Wuling" "Nissan" "Toyota"
## [56] "Nissan" "Wuling" "Nissan" "Toyota" "Honda"
## [61] "Daihatsu" "Honda" "Toyota" "Daihatsu" "Daihatsu"
## [66] "Honda" "Toyota" "Mitsubishi" "Mitsubishi" "Nissan"
## [71] "Mitsubishi" "Daihatsu" "Toyota" "Daihatsu" "Toyota"
## [76] "Honda" "Mitsubishi" "Toyota" "Honda" "Toyota"
## [81] "Mitsubishi" "Honda" "Wuling" "Suzuki" "Wuling"
## [86] "Daihatsu" "Honda" "Wuling" "Daihatsu" "Mitsubishi"
## [91] "Honda" "Honda" "Toyota" "Honda" "Toyota"
## [96] "Toyota" "Toyota" "Suzuki" "Suzuki" "Toyota"
## [101] "Suzuki" "Toyota" "Daihatsu" "Honda" "Daihatsu"
## [106] "Daihatsu" "Honda" "Daihatsu" "Suzuki" "Wuling"
## [111] "Honda" "Daihatsu" "Honda" "Daihatsu" "Honda"
## [116] "Mazda" "Honda" "Honda" "Honda" "Toyota"
## [121] "Toyota" "Toyota" "Mazda" "Honda" "Suzuki"
## [126] "Suzuki" "Suzuki" "Toyota" "Toyota" "Toyota"
## [131] "Toyota" "Toyota" "Suzuki" "Toyota" "Honda"
## [136] "Wuling" "Wuling" "Wuling" "Daihatsu" "Wuling"
## [141] "Daihatsu" "Toyota" "Toyota" "Suzuki" "Suzuki"
## [146] "Suzuki" "Daihatsu" "Mitsubishi" "Daihatsu" "Wuling"
## [151] "Daihatsu" "Wuling" "Toyota" "Toyota" "Honda"
## [156] "Honda" "Honda" "Honda" "Honda" "Honda"
## [161] "Daihatsu" "Honda" "Honda" "Toyota" "Toyota"
## [166] "Daihatsu" "Toyota" "Mitsubishi" "Toyota" "Honda"
## [171] "Daihatsu" "Wuling" "Wuling" "Wuling" "Datsun"
## [176] "Honda" "Honda" "Honda" "Mitsubishi" "Mitsubishi"Tahun
df$Tahun<-substr(df$Nama,1,4);df$Tahun## [1] "2019" "2019" "2018" "2019" "2022" "2020" "2016" "2020" "2018" "2015"
## [11] "2019" "2017" "2017" "2021" "2017" "2022" "2015" "2019" "2019" "2018"
## [21] "2019" "2018" "2018" "2019" "2016" "2019" "2018" "2015" "2014" "2022"
## [31] "2017" "2021" "2018" "2019" "2018" "2019" "2021" "2019" "2019" "2018"
## [41] "2018" "2018" "2019" "2017" "2019" "2018" "2014" "2019" "2022" "2019"
## [51] "2022" "2017" "2020" "2019" "2019" "2014" "2019" "2019" "2021" "2018"
## [61] "2019" "2021" "2015" "2019" "2018" "2018" "2019" "2019" "2020" "2021"
## [71] "2018" "2016" "2015" "2019" "2020" "2019" "2018" "2014" "2019" "2016"
## [81] "2016" "2018" "2019" "2018" "2019" "2015" "2018" "2021" "2019" "2019"
## [91] "2017" "2018" "2017" "2016" "2014" "2019" "2016" "2017" "2018" "2022"
## [101] "2018" "2016" "2020" "2014" "2020" "2018" "2018" "2021" "2013" "2019"
## [111] "2017" "2021" "2020" "2018" "2021" "2019" "2018" "2018" "2020" "2017"
## [121] "2019" "2016" "2019" "2017" "2019" "2019" "2018" "2017" "2019" "2016"
## [131] "2020" "2019" "2021" "2021" "2019" "2019" "2021" "2019" "2019" "2019"
## [141] "2019" "2017" "2014" "2019" "2019" "2019" "2018" "2018" "2020" "2019"
## [151] "2015" "2019" "2018" "2022" "2019" "2021" "2015" "2016" "2016" "2017"
## [161] "2017" "2020" "2020" "2018" "2022" "2018" "2017" "2017" "2020" "2016"
## [171] "2019" "2021" "2021" "2019" "2016" "2018" "2020" "2015" "2015" "2016"Hasil
kable(head(df,15),caption="Tabel 4. Hasil Managing Final")| Nama | Harga.Kredit.Diskon | Harga.Cash.Diskon | Cicil (jt/bln) | Detail | Plat | Detail1 | Detail2 | Merek | Tahun |
|---|---|---|---|---|---|---|---|---|---|
| 2019 WulingALMAZ LT LUX 1.5 | 198000000 | 204000000 | 4.03 | Plat Ganjil,Electric Parking Brake,360 Camera View | Plat Genap | Sports Mode | Map Navigator | Wuling | 2019 |
| 2019 BMW3 20I (CKD) 2.0 | 474000000 | 487000000 | 9.66 | Plat Genap,Sports Mode,Map Navigator | Plat Ganjil | Panoramic Sun Roof | Electric Parking Brake | BMW | 2019 |
| 2018 ToyotaYARIS S TRD 1.5 | 199000000 | 205000000 | 4.05 | Plat Ganjil,Keyless Push Start,Sports Mode | Plat Ganjil | Auto Cruise Control | Paddle Shift | Toyota | 2018 |
| 2019 DaihatsuAYLA R 1.2 | 113500000 | 117000000 | 2.31 | Plat Ganjil | Plat Ganjil | Electric Parking Brake | 360 Camera View | Daihatsu | 2019 |
| 2022 ToyotaAVANZA G 1.5 | 211000000 | 217000000 | 4.30 | Plat Genap,Jarak Tempuh Rendah,Retract Mirror | Plat Ganjil | Retract Mirror | Power Sliding Door | Toyota | 2022 |
| 2020 HondaBRIO SATYA E 1.2 | 153000000 | 158000000 | 3.12 | Plat Genap,Sports Mode | Plat Genap | Auto Retract Mirror | Auto Cruise Control | Honda | 2020 |
| 2016 HondaHR-V E 1.5 | 197000000 | 203000000 | 4.01 | Plat Ganjil,Electric Parking Brake,Paddle Shift | Plat Ganjil | Auto Retract Mirror | Panoramic Sun Roof | Honda | 2016 |
| 2020 BMWX1 SDRIVE18I XLINE 1.5 | 554000000 | 570000000 | 11.29 | Plat Ganjil,Panoramic Sun Roof,Electric Parking Brake | Plat Genap | Retract Mirror | Paddle Shift | BMW | 2020 |
| 2018 ToyotaYARIS S TRD 1.5 | 192000000 | 198000000 | 3.91 | Plat Genap,Retract Mirror,Paddle Shift | Plat Ganjil | Keyless Push Start | Retract Mirror | Toyota | 2018 |
| 2015 NissanX-TRAIL 2.5 | 184000000 | 190000000 | 3.75 | Plat Ganjil,360 Camera View,Keyless Push Start | Plat Ganjil | 360 Camera View | Keyless Push Start | Nissan | 2015 |
| 2019 NissanLIVINA VL 1.5 | 192000000 | 198000000 | 3.91 | Plat Ganjil,Kamera Mundur,Retract Mirror | Plat Ganjil | Kamera Mundur | Retract Mirror | Nissan | 2019 |
| 2017 ToyotaAGYA G TRD 1.2 | 101000000 | 104500000 | 2.06 | Plat Genap | Plat Ganjil | Jarak Tempuh Rendah | Electric Parking Brake | Toyota | 2017 |
| 2017 ChevroletTRAX TURBO LTZ 1.4 | 168000000 | 173000000 | 3.42 | Plat Genap,Sun Roof,Retract Mirror | Plat Ganjil | 360 Camera View | Electric Parking Brake | Chevrolet | 2017 |
| 2021 ToyotaAVANZA G 1.3 | 186000000 | 191000000 | 3.79 | Plat Genap,Retract Mirror | Plat Genap | NA | NA | Toyota | 2021 |
| 2017 ToyotaKIJANG INNOVA REBORN G 2.0 | 236000000 | 243000000 | 4.81 | Plat Genap,Sports Mode | Plat Ganjil | Auto Retract Mirror | Keyless Push Start | Toyota | 2017 |
Visualisasi
ggplot(df,aes(x=`Cicil (jt/bln)`,y=Merek,fill=Merek))+geom_density_ridges()+
scale_fill_brewer(palette="RdBu")+theme_modern_rc(axis_title_just = "center",
axis_title_size = 12)+
theme(plot.title = element_text(hjust=0.5),legend.position = "none")+
labs(x="\nMerek",y="Cicilan/Bulan (Juta Rupiah)\n",title="Sebaran Harga Cicilan/Bulan Tiap Merek Mobil")
ggplot(df,aes(x=`Cicil (jt/bln)`,y=Tahun,fill=Tahun))+geom_density_ridges()+
scale_fill_brewer(palette="Oranges")+theme_modern_rc(axis_title_just = "center",
axis_title_size = 12)+
theme(plot.title = element_text(hjust=0.5),legend.position = "none")+
labs(x="\nMerek",y="Cicilan/Bulan (Juta Rupiah)\n",title="Sebaran Harga Cicilan/Bulan Tiap Tahun")
ggplot(df,aes(x=Tahun,y=df$`Cicil (jt/bln)`,fill=Merek))+geom_violin(aes(group=Tahun),col="coral")+geom_boxplot()+
scale_fill_brewer(palette="Spectral")+theme_modern_rc(axis_title_just = "center",
axis_title_size = 12)+
theme(plot.title = element_text(hjust=0.5),legend.position = "bottom",
plot.subtitle = element_text(hjust=0.5,color="white"))+
labs(x="\nTahun",y="Cicilan/Bulan (Juta Rupiah)\n",title="Sebaran Harga Cicilan/bulan Tiap Merek Mobil",
subtitle="Selama 10 Tahun Terakhir")
PEKAN 3
Packages
lapply(c("car","lmtest"),library,character.only=T)[[1]]## [1] "car" "carData" "hrbrthemes" "ggridges" "readxl"
## [6] "kableExtra" "rvest" "lubridate" "forcats" "stringr"
## [11] "dplyr" "purrr" "readr" "tidyr" "tibble"
## [16] "ggplot2" "tidyverse" "stats" "graphics" "grDevices"
## [21] "utils" "datasets" "methods" "base"Jadikan peubah kategorik sebagai faktor
df$Merek<-as.factor(df$Merek)
df$Tahun<-as.factor(df$Tahun)Relevel Factor sebagai kategori referensi
DF<-df%>%mutate(Merek = relevel(df$Merek, ref = "Daihatsu"));DF$Merek;DF$Tahun## [1] Wuling BMW Toyota Daihatsu Toyota Honda
## [7] Honda BMW Toyota Nissan Nissan Toyota
## [13] Chevrolet Toyota Toyota Toyota Honda Toyota
## [19] Nissan Honda Wuling Daihatsu Toyota Honda
## [25] Mitsubishi Honda Honda Daihatsu Suzuki Suzuki
## [31] Datsun Honda Toyota Daihatsu Daihatsu Mitsubishi
## [37] Wuling Toyota Wuling Toyota Honda Daihatsu
## [43] Honda Daihatsu Suzuki Daihatsu Toyota Daihatsu
## [49] Suzuki Daihatsu Suzuki Honda Wuling Nissan
## [55] Toyota Nissan Wuling Nissan Toyota Honda
## [61] Daihatsu Honda Toyota Daihatsu Daihatsu Honda
## [67] Toyota Mitsubishi Mitsubishi Nissan Mitsubishi Daihatsu
## [73] Toyota Daihatsu Toyota Honda Mitsubishi Toyota
## [79] Honda Toyota Mitsubishi Honda Wuling Suzuki
## [85] Wuling Daihatsu Honda Wuling Daihatsu Mitsubishi
## [91] Honda Honda Toyota Honda Toyota Toyota
## [97] Toyota Suzuki Suzuki Toyota Suzuki Toyota
## [103] Daihatsu Honda Daihatsu Daihatsu Honda Daihatsu
## [109] Suzuki Wuling Honda Daihatsu Honda Daihatsu
## [115] Honda Mazda Honda Honda Honda Toyota
## [121] Toyota Toyota Mazda Honda Suzuki Suzuki
## [127] Suzuki Toyota Toyota Toyota Toyota Toyota
## [133] Suzuki Toyota Honda Wuling Wuling Wuling
## [139] Daihatsu Wuling Daihatsu Toyota Toyota Suzuki
## [145] Suzuki Suzuki Daihatsu Mitsubishi Daihatsu Wuling
## [151] Daihatsu Wuling Toyota Toyota Honda Honda
## [157] Honda Honda Honda Honda Daihatsu Honda
## [163] Honda Toyota Toyota Daihatsu Toyota Mitsubishi
## [169] Toyota Honda Daihatsu Wuling Wuling Wuling
## [175] Datsun Honda Honda Honda Mitsubishi Mitsubishi
## 11 Levels: Daihatsu BMW Chevrolet Datsun Honda Mazda Mitsubishi ... Wuling## [1] 2019 2019 2018 2019 2022 2020 2016 2020 2018 2015 2019 2017 2017 2021 2017
## [16] 2022 2015 2019 2019 2018 2019 2018 2018 2019 2016 2019 2018 2015 2014 2022
## [31] 2017 2021 2018 2019 2018 2019 2021 2019 2019 2018 2018 2018 2019 2017 2019
## [46] 2018 2014 2019 2022 2019 2022 2017 2020 2019 2019 2014 2019 2019 2021 2018
## [61] 2019 2021 2015 2019 2018 2018 2019 2019 2020 2021 2018 2016 2015 2019 2020
## [76] 2019 2018 2014 2019 2016 2016 2018 2019 2018 2019 2015 2018 2021 2019 2019
## [91] 2017 2018 2017 2016 2014 2019 2016 2017 2018 2022 2018 2016 2020 2014 2020
## [106] 2018 2018 2021 2013 2019 2017 2021 2020 2018 2021 2019 2018 2018 2020 2017
## [121] 2019 2016 2019 2017 2019 2019 2018 2017 2019 2016 2020 2019 2021 2021 2019
## [136] 2019 2021 2019 2019 2019 2019 2017 2014 2019 2019 2019 2018 2018 2020 2019
## [151] 2015 2019 2018 2022 2019 2021 2015 2016 2016 2017 2017 2020 2020 2018 2022
## [166] 2018 2017 2017 2020 2016 2019 2021 2021 2019 2016 2018 2020 2015 2015 2016
## Levels: 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022Model Regresi dengan peubah dummy
model<-lm(`Cicil (jt/bln)`~Merek+Tahun,DF);model;summary(model)##
## Call:
## lm(formula = `Cicil (jt/bln)` ~ Merek + Tahun, data = DF)
##
## Coefficients:
## (Intercept) MerekBMW MerekChevrolet MerekDatsun
## 2.31431 7.85866 0.40453 -1.33278
## MerekHonda MerekMazda MerekMitsubishi MerekNissan
## 1.21335 5.85839 1.91724 0.91946
## MerekSuzuki MerekToyota MerekWuling Tahun2014
## 0.11569 0.74859 1.12731 0.06956
## Tahun2015 Tahun2016 Tahun2017 Tahun2018
## 0.05729 0.56578 0.70116 0.24898
## Tahun2019 Tahun2020 Tahun2021 Tahun2022
## 0.39230 0.21175 1.23751 1.36069##
## Call:
## lm(formula = `Cicil (jt/bln)` ~ Merek + Tahun, data = DF)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.7441 -0.7239 -0.0709 0.5319 3.9113
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.31431 1.08821 2.127 0.034977 *
## MerekBMW 7.85866 0.76728 10.242 < 2e-16 ***
## MerekChevrolet 0.40453 1.08455 0.373 0.709646
## MerekDatsun -1.33278 0.78241 -1.703 0.090429 .
## MerekHonda 1.21335 0.24843 4.884 2.50e-06 ***
## MerekMazda 5.85839 0.76634 7.645 1.83e-12 ***
## MerekMitsubishi 1.91724 0.35886 5.343 3.10e-07 ***
## MerekNissan 0.91946 0.44448 2.069 0.040190 *
## MerekSuzuki 0.11569 0.33176 0.349 0.727764
## MerekToyota 0.74859 0.25604 2.924 0.003960 **
## MerekWuling 1.12731 0.31953 3.528 0.000547 ***
## Tahun2014 0.06956 1.13663 0.061 0.951275
## Tahun2015 0.05729 1.12442 0.051 0.959426
## Tahun2016 0.56578 1.11036 0.510 0.611074
## Tahun2017 0.70116 1.10094 0.637 0.525119
## Tahun2018 0.24898 1.08175 0.230 0.818260
## Tahun2019 0.39230 1.07682 0.364 0.716105
## Tahun2020 0.21175 1.10893 0.191 0.848808
## Tahun2021 1.23751 1.10223 1.123 0.263235
## Tahun2022 1.36069 1.11621 1.219 0.224631
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.036 on 160 degrees of freedom
## Multiple R-squared: 0.567, Adjusted R-squared: 0.5156
## F-statistic: 11.03 on 19 and 160 DF, p-value: < 2.2e-16avPlots(model)
Uji Asumsi
Fungsi Uji Normal
uji.normal<-function(x, object.name="x", graph=TRUE, graph.transformed=TRUE){
lapply(c("fitdistrplus", "kSamples", "rcompanion"), library, character.only=T)
if(any(x<0))x<-x-min(x)+1
mean <- fitdist(x, "norm")$estimate[1]; sd <- fitdist(x, "norm")$estimate[2]
uji<-ks.test(x, "pnorm", mean=mean, sd=sd)
uji1<- ad.test(x, rnorm(length(x), mean=mean, sd=sd))
pvalue<-uji$p.value
PVALUE1<-uji1$ad[1,3]
PVALUE2<-uji1$ad[2,3]
t<-transformTukey(x,quiet = TRUE,plotit = FALSE)
pt<-ks.test(t, "pnorm", mean=fitdist(t,"norm")$estimate[1],
sd=fitdist(t,"norm")$estimate[2])$p.value
lambda<-transformTukey(x,returnLambda =TRUE,quiet=TRUE,plotit = FALSE)
if(graph==TRUE){
if(graph.transformed==FALSE){
par(mfrow=c(1,2))
hist(x, freq=F, col="steelblue", border="white",
main=paste("Histogram of ",object.name),xlab=object.name)
lines(density(x),lwd=2, col="coral")
qqnorm(x,col="coral");qqline(x,col="steelblue",lwd=2)
}
else{
par(mfrow=c(2,2))
hist(x, freq=F, col="steelblue", border="white",
main=paste("Histogram of ",object.name),xlab=object.name)
lines(density(x),lwd=2, col="coral")
hist(t, main=paste("Histogram of ",object.name,"transformed"),
xlab=paste(object.name,"transformed"), freq=F,
col="steelblue",border = "white")
lines(density(t),lwd=2, col="coral")
qqnorm(x,col="coral");qqline(x,col="steelblue",lwd=2)
qqnorm(t, col="coral");qqline(t,col="steelblue", lwd=2)
}
}
z<-ifelse((PVALUE1>=0.05 & PVALUE2<0.05 ||PVALUE1<0.05 & PVALUE2>=0.05),
ifelse(pvalue>=0.05,
return(`Hasil Uji Kolmogorov Smirnov`=data.frame(`P-Value`=pvalue,
Keputusan="Terima H0, data menyebar normal")),
return(list(`Hasil Uji Kolmogorov Smirnov`=data.frame(`P-Value`=pvalue,
Keputusan="Tolak H0, data tidak menyebar normal"),
`lambda transformasi`=lambda,
`Data Hasil Transformasi Tukey`= t,
`Setelah transformasi~Uji Kolmogorov-Smirnov`=data.frame(`P-Value`=pt,
`Keputusan`=ifelse(pt>=0.05,
"Terima H0, data menyebar normal",
"Tolak H0, data tidak menyebar normal"))))),
ifelse(((pvalue >= 0.05)&(PVALUE1 >= 0.05||PVALUE2>= 0.05)),
return(list(`Hasil Uji Kolmogorov Smirnov`=data.frame(`P-Value`=pvalue,
Keputusan="Terima H0, data menyebar normal"),
`Hasil Uji Anderson`=
data.frame(`P-Value`=
rbind(`Versi 1`=PVALUE1, `Versi 2`=PVALUE2),
Keputusan=rep("Terima H0, data menyebar normal", 2)))),
ifelse((pvalue >= 0.05&(PVALUE1 < 0.05||PVALUE2 < 0.05)),
return(list(`Hasil Uji Kolmogorov Smirnov`= data.frame(`P-Value`=pvalue,
Keputusan="Terima H0, data menyebar normal"),
`Hasil Uji Anderson`=data.frame(`P-Value`=
rbind(`Versi 1`=PVALUE1,`Versi 2`=PVALUE2),
Keputusan= rep("Tolak H0, data tidak menyebar normal",2)),
`lambda transformasi`=lambda,
`Data Hasil Transformasi Tukey`= t,
`Setelah transformasi~Uji Kolmogorov-Smirnov`=
data.frame(`P-Value`=pt,
`Keputusan`=ifelse(pt>=0.05,
"Terima H0, data menyebar normal",
"Tolak H0, data tidak menyebar normal")))),
ifelse(pvalue < 0.05&(PVALUE1 >= 0.05||PVALUE2 >= 0.05),
return(list(`Hasil Uji Kolmogorov Smirnov`=data.frame(`P-Value`=pvalue,
Keputusan="Tolak H0, data tidak menyebar normal"),
`Hasil Uji Anderson`=data.frame(`P-Value`= rbind(`Versi 1`=PVALUE1,`Versi 2`=PVALUE2),
Keputusan=rep("Terima H0, data menyebar normal",2)),
`lambda transformasi`=lambda,
`Data Hasil Transformasi Tukey`= t,
`Setelah transformasi~Uji Kolmogorov-Smirnov`=data.frame(`P-Value`=pt,
`Keputusan`=ifelse(pt>=0.05,
"Terima H0, data menyebar normal",
"Tolak H0, data tidak menyebar normal")))),
return(list(`Hasil Uji Kolmogorov Smirnov`=data.frame(`P-Value`=pvalue,
Keputusan="Tolak H0, data tidak menyebar normal"),
`Hasil Uji Anderson`=data.frame(`P-Value`=rbind(`Versi 1`=PVALUE1,
`Versi 2`=PVALUE2),
Keputusan=rep("Tolak H0, data tidak menyebar normal",2)),
`lambda transformasi`=lambda,
`Data Hasil Transformasi Tukey`= t,
`Setelah transformasi~Uji Kolmogorov-Smirnov`=data.frame(`P-Value`=pt,
`Keputusan`=ifelse(pt>=0.05,
"Terima H0, data menyebar normal",
"Tolak H0, data tidak menyebar normal"))))))))
return(z)
}
uji.normal1<-function(x, object.name="x", graph=TRUE, graph.transformed=TRUE){
lapply(c("fitdistrplus", "kSamples", "rcompanion"), library, character.only=T)
if(any(x<0))x<-x-min(x)+1
mean <- mean(x); sd <- sd(x)
uji<-ks.test(x, "pnorm", mean=mean, sd=sd)
uji1<- ad.test(x, rnorm(length(x), mean=mean, sd=sd))
pvalue<-uji$p.value
PVALUE1<-uji1$ad[1,3]
PVALUE2<-uji1$ad[2,3]
t<-transformTukey(x,quiet = TRUE,plotit = FALSE)
pt<-ks.test(t, "pnorm", mean=mean(t),
sd=sd(t))$p.value
lambda<-transformTukey(x,returnLambda =TRUE,quiet=TRUE,plotit = FALSE)
if(graph==TRUE){
if(graph.transformed==FALSE){
par(mfrow=c(1,2))
hist(x, freq=F, col="steelblue", border="white",
main=paste("Histogram of ",object.name),xlab=object.name)
lines(density(x),lwd=2, col="coral")
qqnorm(x,col="coral");qqline(x,col="steelblue",lwd=2)
}
else{
par(mfrow=c(2,2))
hist(x, freq=F, col="steelblue", border="white",
main=paste("Histogram of ",object.name),xlab=object.name)
lines(density(x),lwd=2, col="coral")
hist(t, main=paste("Histogram of ",object.name,"transformed"),
xlab=paste(object.name,"transformed"), freq=F,
col="steelblue",border = "white")
lines(density(t),lwd=2, col="coral")
qqnorm(x,col="coral");qqline(x,col="steelblue",lwd=2)
qqnorm(t, col="coral");qqline(t,col="steelblue", lwd=2)
}
}
z<-ifelse((PVALUE1>=0.05 & PVALUE2<0.05 ||PVALUE1<0.05 & PVALUE2>=0.05),
ifelse(pvalue>=0.05,
return(`Hasil Uji Kolmogorov Smirnov`=data.frame(`P-Value`=pvalue,
Keputusan="Terima H0, data menyebar normal")),
return(list(`Hasil Uji Kolmogorov Smirnov`=data.frame(`P-Value`=pvalue,
Keputusan="Tolak H0, data tidak menyebar normal"),
`lambda transformasi`=lambda,
`Data Hasil Transformasi Tukey`= t,
`Setelah transformasi~Uji Kolmogorov-Smirnov`=data.frame(`P-Value`=pt,
`Keputusan`=ifelse(pt>=0.05,
"Terima H0, data menyebar normal",
"Tolak H0, data tidak menyebar normal"))))),
ifelse(((pvalue >= 0.05)&(PVALUE1 >= 0.05||PVALUE2>= 0.05)),
return(list(`Hasil Uji Kolmogorov Smirnov`=data.frame(`P-Value`=pvalue,
Keputusan="Terima H0, data menyebar normal"),
`Hasil Uji Anderson`=
data.frame(`P-Value`=
rbind(`Versi 1`=PVALUE1, `Versi 2`=PVALUE2),
Keputusan=rep("Terima H0, data menyebar normal", 2)))),
ifelse((pvalue >= 0.05&(PVALUE1 < 0.05||PVALUE2 < 0.05)),
return(list(`Hasil Uji Kolmogorov Smirnov`= data.frame(`P-Value`=pvalue,
Keputusan="Terima H0, data menyebar normal"),
`Hasil Uji Anderson`=data.frame(`P-Value`=
rbind(`Versi 1`=PVALUE1,`Versi 2`=PVALUE2),
Keputusan= rep("Tolak H0, data tidak menyebar normal",2)),
`lambda transformasi`=lambda,
`Data Hasil Transformasi Tukey`= t,
`Setelah transformasi~Uji Kolmogorov-Smirnov`=
data.frame(`P-Value`=pt,
`Keputusan`=ifelse(pt>=0.05,
"Terima H0, data menyebar normal",
"Tolak H0, data tidak menyebar normal")))),
ifelse(pvalue < 0.05&(PVALUE1 >= 0.05||PVALUE2 >= 0.05),
return(list(`Hasil Uji Kolmogorov Smirnov`=data.frame(`P-Value`=pvalue,
Keputusan="Tolak H0, data tidak menyebar normal"),
`Hasil Uji Anderson`=data.frame(`P-Value`= rbind(`Versi 1`=PVALUE1,`Versi 2`=PVALUE2),
Keputusan=rep("Terima H0, data menyebar normal",2)),
`lambda transformasi`=lambda,
`Data Hasil Transformasi Tukey`= t,
`Setelah transformasi~Uji Kolmogorov-Smirnov`=data.frame(`P-Value`=pt,
`Keputusan`=ifelse(pt>=0.05,
"Terima H0, data menyebar normal",
"Tolak H0, data tidak menyebar normal")))),
return(list(`Hasil Uji Kolmogorov Smirnov`=data.frame(`P-Value`=pvalue,
Keputusan="Tolak H0, data tidak menyebar normal"),
`Hasil Uji Anderson`=data.frame(`P-Value`=rbind(`Versi 1`=PVALUE1,
`Versi 2`=PVALUE2),
Keputusan=rep("Tolak H0, data tidak menyebar normal",2)),
`lambda transformasi`=lambda,
`Data Hasil Transformasi Tukey`= t,
`Setelah transformasi~Uji Kolmogorov-Smirnov`=data.frame(`P-Value`=pt,
`Keputusan`=ifelse(pt>=0.05,
"Terima H0, data menyebar normal",
"Tolak H0, data tidak menyebar normal"))))))))
return(z)
}Normalitas
uji.normal(model$residuals,"residuals",graph.transformed = F)
## $`Hasil Uji Kolmogorov Smirnov`
## P.Value Keputusan
## 1 0.353 Terima H0, data menyebar normal
##
## $`Hasil Uji Anderson`
## P.Value Keputusan
## Versi 1 0.10401 Terima H0, data menyebar normal
## Versi 2 0.10441 Terima H0, data menyebar normalNormalitas sisaan terpenuhi (p-value > 0,05)
Homoskedastisitas dan Non-Autokorelasi
par(mfrow=c(1,2));plot(model,c(1,3))
gqtest(model);bgtest(model)##
## Goldfeld-Quandt test
##
## data: model
## GQ = 1.6863, df1 = 70, df2 = 70, p-value = 0.01516
## alternative hypothesis: variance increases from segment 1 to 2##
## Breusch-Godfrey test for serial correlation of order up to 1
##
## data: model
## LM test = 1.4281, df = 1, p-value = 0.2321Homoskedastisitas dan non-autokorelasi pada sisaan terpenuhi (p-value > 0,05)
PEKAN 4
Packages
library(leaps)Metode Forward
forward<-regsubsets(`Cicil (jt/bln)`~Merek+Tahun,DF,method="forward")
sf<-summary(forward);sf## Subset selection object
## Call: regsubsets.formula(`Cicil (jt/bln)` ~ Merek + Tahun, DF, method = "forward")
## 19 Variables (and intercept)
## Forced in Forced out
## MerekBMW FALSE FALSE
## MerekChevrolet FALSE FALSE
## MerekDatsun FALSE FALSE
## MerekHonda FALSE FALSE
## MerekMazda FALSE FALSE
## MerekMitsubishi FALSE FALSE
## MerekNissan FALSE FALSE
## MerekSuzuki FALSE FALSE
## MerekToyota FALSE FALSE
## MerekWuling FALSE FALSE
## Tahun2014 FALSE FALSE
## Tahun2015 FALSE FALSE
## Tahun2016 FALSE FALSE
## Tahun2017 FALSE FALSE
## Tahun2018 FALSE FALSE
## Tahun2019 FALSE FALSE
## Tahun2020 FALSE FALSE
## Tahun2021 FALSE FALSE
## Tahun2022 FALSE FALSE
## 1 subsets of each size up to 8
## Selection Algorithm: forward
## MerekBMW MerekChevrolet MerekDatsun MerekHonda MerekMazda
## 1 ( 1 ) "*" " " " " " " " "
## 2 ( 1 ) "*" " " " " " " "*"
## 3 ( 1 ) "*" " " " " " " "*"
## 4 ( 1 ) "*" " " " " " " "*"
## 5 ( 1 ) "*" " " " " "*" "*"
## 6 ( 1 ) "*" " " " " "*" "*"
## 7 ( 1 ) "*" " " " " "*" "*"
## 8 ( 1 ) "*" " " " " "*" "*"
## MerekMitsubishi MerekNissan MerekSuzuki MerekToyota MerekWuling
## 1 ( 1 ) " " " " " " " " " "
## 2 ( 1 ) " " " " " " " " " "
## 3 ( 1 ) "*" " " " " " " " "
## 4 ( 1 ) "*" " " " " " " " "
## 5 ( 1 ) "*" " " " " " " " "
## 6 ( 1 ) "*" " " " " " " " "
## 7 ( 1 ) "*" " " " " " " "*"
## 8 ( 1 ) "*" " " " " "*" "*"
## Tahun2014 Tahun2015 Tahun2016 Tahun2017 Tahun2018 Tahun2019 Tahun2020
## 1 ( 1 ) " " " " " " " " " " " " " "
## 2 ( 1 ) " " " " " " " " " " " " " "
## 3 ( 1 ) " " " " " " " " " " " " " "
## 4 ( 1 ) " " " " " " " " " " " " " "
## 5 ( 1 ) " " " " " " " " " " " " " "
## 6 ( 1 ) " " " " " " " " " " " " " "
## 7 ( 1 ) " " " " " " " " " " " " " "
## 8 ( 1 ) " " " " " " " " " " " " " "
## Tahun2021 Tahun2022
## 1 ( 1 ) " " " "
## 2 ( 1 ) " " " "
## 3 ( 1 ) " " " "
## 4 ( 1 ) "*" " "
## 5 ( 1 ) "*" " "
## 6 ( 1 ) "*" "*"
## 7 ( 1 ) "*" "*"
## 8 ( 1 ) "*" "*"par(mfrow=c(2,2))
plot(sf$rsq, xlab="Jumlah Variabel", ylab="R2",type="l");points(1:8,sf$rsq,col=ifelse(sf$rsq==sf$rsq[which.max(sf$rsq)],"coral","steelblue"),cex=1.5,pch=16)
plot(sf$adjr2, xlab="Jumlah Variabel", ylab="Adj R2",type="l");points(1:8,sf$adjr2,col=ifelse(sf$adjr2==sf$adjr2[which.max(sf$adjr2)],"coral","steelblue"),cex=1.5,pch=16)
plot(sf$bic, xlab="Jumlah Variabel", ylab="BIC",type="l");points(1:8,sf$bic,col=ifelse(sf$bic==sf$bic[which.min(sf$bic)],"coral","steelblue"),cex=1.5,pch=16)
plot(sf$cp, xlab="Jumlah Variabel", ylab="CP",type="l");points(1:8,sf$cp,col=ifelse(sf$cp==sf$cp[which.min(sf$cp)],"coral","steelblue"),cex=1.5,pch=16)
Jumlah dummy variabel yang digunakan sebanyak 8 jika berdasarkan R2
Metode Backward
backward<-regsubsets(`Cicil (jt/bln)`~Merek+Tahun,DF,method="backward")
sb<-summary(backward);sb## Subset selection object
## Call: regsubsets.formula(`Cicil (jt/bln)` ~ Merek + Tahun, DF, method = "backward")
## 19 Variables (and intercept)
## Forced in Forced out
## MerekBMW FALSE FALSE
## MerekChevrolet FALSE FALSE
## MerekDatsun FALSE FALSE
## MerekHonda FALSE FALSE
## MerekMazda FALSE FALSE
## MerekMitsubishi FALSE FALSE
## MerekNissan FALSE FALSE
## MerekSuzuki FALSE FALSE
## MerekToyota FALSE FALSE
## MerekWuling FALSE FALSE
## Tahun2014 FALSE FALSE
## Tahun2015 FALSE FALSE
## Tahun2016 FALSE FALSE
## Tahun2017 FALSE FALSE
## Tahun2018 FALSE FALSE
## Tahun2019 FALSE FALSE
## Tahun2020 FALSE FALSE
## Tahun2021 FALSE FALSE
## Tahun2022 FALSE FALSE
## 1 subsets of each size up to 8
## Selection Algorithm: backward
## MerekBMW MerekChevrolet MerekDatsun MerekHonda MerekMazda
## 1 ( 1 ) "*" " " " " " " " "
## 2 ( 1 ) "*" " " " " " " "*"
## 3 ( 1 ) "*" " " " " " " "*"
## 4 ( 1 ) "*" " " " " "*" "*"
## 5 ( 1 ) "*" " " " " "*" "*"
## 6 ( 1 ) "*" " " " " "*" "*"
## 7 ( 1 ) "*" " " " " "*" "*"
## 8 ( 1 ) "*" " " " " "*" "*"
## MerekMitsubishi MerekNissan MerekSuzuki MerekToyota MerekWuling
## 1 ( 1 ) " " " " " " " " " "
## 2 ( 1 ) " " " " " " " " " "
## 3 ( 1 ) "*" " " " " " " " "
## 4 ( 1 ) "*" " " " " " " " "
## 5 ( 1 ) "*" " " " " " " "*"
## 6 ( 1 ) "*" " " " " "*" "*"
## 7 ( 1 ) "*" " " " " "*" "*"
## 8 ( 1 ) "*" " " " " "*" "*"
## Tahun2014 Tahun2015 Tahun2016 Tahun2017 Tahun2018 Tahun2019 Tahun2020
## 1 ( 1 ) " " " " " " " " " " " " " "
## 2 ( 1 ) " " " " " " " " " " " " " "
## 3 ( 1 ) " " " " " " " " " " " " " "
## 4 ( 1 ) " " " " " " " " " " " " " "
## 5 ( 1 ) " " " " " " " " " " " " " "
## 6 ( 1 ) " " " " " " " " " " " " " "
## 7 ( 1 ) " " " " " " " " " " " " " "
## 8 ( 1 ) " " " " " " " " " " " " " "
## Tahun2021 Tahun2022
## 1 ( 1 ) " " " "
## 2 ( 1 ) " " " "
## 3 ( 1 ) " " " "
## 4 ( 1 ) " " " "
## 5 ( 1 ) " " " "
## 6 ( 1 ) " " " "
## 7 ( 1 ) "*" " "
## 8 ( 1 ) "*" "*"par(mfrow=c(2,2))
plot(sb$rsq, xlab="Jumlah Variabel", ylab="R2",type="l");points(1:8,sb$rsq,col=ifelse(sb$rsq==sb$rsq[which.max(sb$rsq)],"coral","steelblue"),cex=1.5,pch=16)
plot(sb$adjr2, xlab="Jumlah Variabel", ylab="Adj R2",type="l");points(1:8,sb$adjr2,col=ifelse(sb$adjr2==sb$adjr2[which.max(sb$adjr2)],"coral","steelblue"),cex=1.5,pch=16)
plot(sb$bic, xlab="Jumlah Variabel", ylab="BIC",type="l");points(1:8,sb$bic,col=ifelse(sb$bic==sb$bic[which.min(sb$bic)],"coral","steelblue"),cex=1.5,pch=16)
plot(sb$cp, xlab="Jumlah Variabel", ylab="CP",type="l");points(1:8,sb$cp,col=ifelse(sb$cp==sb$cp[which.min(sb$cp)],"coral","steelblue"),cex=1.5,pch=16)
Jumlah dummy variabel yang digunakan sebanyak 8 jika berdasarkan R2
Model Final
coef(backward,8)## (Intercept) MerekBMW MerekHonda MerekMazda MerekMitsubishi
## 2.7553536 7.7196464 1.1174198 5.8096464 1.8588131
## MerekToyota MerekWuling Tahun2021 Tahun2022
## 0.6794349 1.0486764 0.9226860 1.0062496PEKAN 5
Packages
lapply(c("glmnet","lmridge"),library,character.only=T)[[1]]## [1] "glmnet" "Matrix" "leaps" "rcompanion" "kSamples"
## [6] "SuppDists" "fitdistrplus" "survival" "MASS" "lmtest"
## [11] "zoo" "car" "carData" "hrbrthemes" "ggridges"
## [16] "readxl" "kableExtra" "rvest" "lubridate" "forcats"
## [21] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [26] "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [31] "grDevices" "utils" "datasets" "methods" "base"Regresi Ridge (glmnet)
Peubah
x<-data.matrix(economics[, c('pop', 'psavert', 'uempmed', 'pce')])
y<-economics$unemployCV
cv.r<-cv.glmnet(x,y,alpha=0);plot(cv.r)
Best Model
best.lr<-cv.r$lambda.min
bestridge<-glmnet(x,y,alpha=0,lambda=best.lr);coef(bestridge)## 5 x 1 sparse Matrix of class "dgCMatrix"
## s0
## (Intercept) -1.445024e+03
## pop 2.093831e-02
## psavert 3.951673e+01
## uempmed 4.704123e+02
## pce -1.154226e-01Fungsi R-Square
rsq<-function(bestmodel,bestlambda,x,y){
#y duga
y.duga <- predict(bestmodel, s = bestlambda, newx = x)
#JKG dan JKT
jkt <- sum((y - mean(y))^2)
jkg <- sum((y.duga- y)^2)
#find R-Squared
rsq <- 1 - jkg/jkt
return(rsq)
}R-Square Ridge
rsq(bestridge,best.lr,x,y)## [1] 0.7666784Regresi Lasso (glmnet)
CV
cv.l<-cv.glmnet(x,y,alpha=1);plot(cv.l)
Best Model
best.ll<-cv.l$lambda.min
bestlasso<-glmnet(x,y,alpha=1,lambda=best.ll);coef(bestlasso)## 5 x 1 sparse Matrix of class "dgCMatrix"
## s0
## (Intercept) -3.266128e+04
## pop 1.612626e-01
## psavert 1.734076e+02
## uempmed 5.779452e+02
## pce -1.555702e+00R-Square Lasso
rsq(bestlasso,best.ll,x,y)## [1] 0.855554Regresi Ridge (lmridge)
lmr<-lmridge(`Cicil (jt/bln)`~Merek+Tahun,DF,scaling="centered");plot(lmr);vif(lmr)
## MerekBMW MerekChevrolet MerekDatsun MerekHonda MerekMazda MerekMitsubishi
## k=0 0.54809 1.09507 0.56991 0.05746 0.54674 0.11989
## MerekNissan MerekSuzuki MerekToyota MerekWuling Tahun2014 Tahun2015
## k=0 0.18393 0.10247 0.06103 0.09505 1.20277 1.17707
## Tahun2016 Tahun2017 Tahun2018 Tahun2019 Tahun2020 Tahun2021 Tahun2022
## k=0 1.14782 1.12842 1.08943 1.07951 1.14485 1.13107 1.15994summary(lmr)##
## Call:
## lmridge.default(formula = `Cicil (jt/bln)` ~ Merek + Tahun, data = DF,
## scaling = "centered")
##
##
## Coefficients: for Ridge parameter K= 0
## Estimate Estimate (Sc) StdErr (Sc) t-value (Sc) Pr(>|t|)
## Intercept 2.3143 2.3143 0.4705 4.9192 <2e-16 ***
## MerekBMW 7.8587 7.8587 0.7649 10.2742 <2e-16 ***
## MerekChevrolet 0.4045 0.4045 1.0812 0.3742 0.7088
## MerekDatsun -1.3328 -1.3328 0.7800 -1.7087 0.0894 .
## MerekHonda 1.2133 1.2134 0.2477 4.8994 <2e-16 ***
## MerekMazda 5.8584 5.8584 0.7640 7.6685 <2e-16 ***
## MerekMitsubishi 1.9172 1.9172 0.3577 5.3592 <2e-16 ***
## MerekNissan 0.9195 0.9195 0.4431 2.0751 0.0396 *
## MerekSuzuki 0.1157 0.1157 0.3307 0.3498 0.7269
## MerekToyota 0.7486 0.7486 0.2552 2.9329 0.0039 **
## MerekWuling 1.1273 1.1273 0.3185 3.5391 0.0005 ***
## Tahun2014 0.0696 0.0696 1.1331 0.0614 0.9511
## Tahun2015 0.0573 0.0573 1.1209 0.0511 0.9593
## Tahun2016 0.5658 0.5658 1.1069 0.5111 0.6100
## Tahun2017 0.7012 0.7012 1.0975 0.6389 0.5238
## Tahun2018 0.2490 0.2490 1.0784 0.2309 0.8177
## Tahun2019 0.3923 0.3923 1.0735 0.3655 0.7153
## Tahun2020 0.2118 0.2117 1.1055 0.1915 0.8483
## Tahun2021 1.2375 1.2375 1.0988 1.1262 0.2618
## Tahun2022 1.3607 1.3607 1.1127 1.2228 0.2232
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Ridge Summary
## R2 adj-R2 DF ridge F AIC BIC
## 0.56700 0.51860 19.00020 11.09653 29.67161 1025.07066
## Ridge minimum MSE= 14.56072 at K= 0
## P-value for F-test ( 19.0002 , 161.0001 ) = 1.023754e-20
## -------------------------------------------------------------------