Projek BMBG
Import Data
##
## Attaching package: 'janitor'## The following objects are masked from 'package:stats':
##
## chisq.test, fisher.test##
## 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## Warning: package 'terra' was built under R version 4.4.3## terra 1.8.42##
## Attaching package: 'terra'## The following object is masked from 'package:janitor':
##
## crosstab## Warning: package 'exactextractr' was built under R version 4.4.3## Warning: package 'sf' was built under R version 4.4.3## Linking to GEOS 3.13.0, GDAL 3.10.1, PROJ 9.5.1; sf_use_s2() is TRUE# Load vektor dan raster
v <- vect("C:/Users/User/Documents/AKA/Tingkat 3/Semester 6/DMBG/Projek/Jawa_Kab.shp")
r <- rast("C:/Users/User/Downloads/NTL_Jawa.tif")
# Pastikan CRS sama
# Cek apakah CRS vektor dan raster sama
if (crs(v) != crs(r)) {
v <- project(v, crs(r))
}
# Ubah vektor ke format sf (karena exactextractr perlu sf)
v_sf <- sf::st_as_sf(v)
# Cek nama kolom ID kamu
names(v_sf) # pastikan nama kolomnya benar (harus ada kolom 'idkab')## [1] "fid" "idkab" "nmprov" "nmkab" "kdprov" "kdkab" "sumber"
## [8] "periode" "geometry"## | | | 0% | |= | 1% | |= | 2% | |== | 3% | |=== | 4% | |==== | 5% | |==== | 6% | |===== | 7% | |===== | 8% | |====== | 8% | |====== | 9% | |======= | 10% | |======== | 11% | |======== | 12% | |========= | 13% | |========== | 14% | |=========== | 15% | |=========== | 16% | |============ | 17% | |============ | 18% | |============= | 18% | |============== | 19% | |============== | 20% | |=============== | 21% | |=============== | 22% | |================ | 23% | |================ | 24% | |================= | 24% | |================== | 25% | |================== | 26% | |=================== | 27% | |=================== | 28% | |==================== | 29% | |===================== | 29% | |===================== | 30% | |====================== | 31% | |====================== | 32% | |======================= | 33% | |======================== | 34% | |========================= | 35% | |========================= | 36% | |========================== | 37% | |========================== | 38% | |=========================== | 39% | |============================ | 39% | |============================ | 40% | |============================= | 41% | |============================= | 42% | |============================== | 43% | |=============================== | 44% | |=============================== | 45% | |================================ | 45% | |================================ | 46% | |================================= | 47% | |================================== | 48% | |================================== | 49% | |=================================== | 50% | |==================================== | 51% | |==================================== | 52% | |===================================== | 53% | |====================================== | 54% | |====================================== | 55% | |======================================= | 55% | |======================================= | 56% | |======================================== | 57% | |========================================= | 58% | |========================================= | 59% | |========================================== | 60% | |========================================== | 61% | |=========================================== | 61% | |============================================ | 62% | |============================================ | 63% | |============================================= | 64% | |============================================= | 65% | |============================================== | 66% | |=============================================== | 67% | |================================================ | 68% | |================================================ | 69% | |================================================= | 70% | |================================================= | 71% | |================================================== | 71% | |=================================================== | 72% | |=================================================== | 73% | |==================================================== | 74% | |==================================================== | 75% | |===================================================== | 76% | |====================================================== | 76% | |====================================================== | 77% | |======================================================= | 78% | |======================================================= | 79% | |======================================================== | 80% | |======================================================== | 81% | |========================================================= | 82% | |========================================================== | 82% | |========================================================== | 83% | |=========================================================== | 84% | |=========================================================== | 85% | |============================================================ | 86% | |============================================================= | 87% | |============================================================== | 88% | |============================================================== | 89% | |=============================================================== | 90% | |================================================================ | 91% | |================================================================ | 92% | |================================================================= | 92% | |================================================================= | 93% | |================================================================== | 94% | |================================================================== | 95% | |=================================================================== | 96% | |==================================================================== | 97% | |===================================================================== | 98% | |===================================================================== | 99% | |======================================================================| 100%Data Cleaning
Cek Struktur Data
## [1] "tbl_df" "tbl" "data.frame"## tibble [119 × 6] (S3: tbl_df/tbl/data.frame)
## $ id : num [1:119] 3672 3673 3671 3674 3602 ...
## $ kode_prov: num [1:119] 36 36 36 36 36 36 36 36 34 34 ...
## $ Y : num [1:119] 8.44 4.51 9.18 6.55 3.75 ...
## $ X1 : num [1:119] 6.08 9.18 5.92 5.09 6.23 8.09 9.18 6.06 3.62 2.16 ...
## $ X2 : num [1:119] 6.61 7.88 7.16 9.06 10.39 ...
## $ X3 : num [1:119] 14294 14603 15641 17028 9631 ...Terdapat kesalahan tipe data unutk id dan kode_prov. Dimana dan kode_prov yang seharusnya dalam bentuk string/character teridentifikasi sebagai numeric
## [1] "sf" "data.frame"## Classes 'sf' and 'data.frame': 119 obs. of 10 variables:
## $ fid : num 25624 25630 25695 25760 25804 ...
## $ idkab : chr "3101" "3171" "3172" "3173" ...
## $ nmprov : chr "DKI JAKARTA" "DKI JAKARTA" "DKI JAKARTA" "DKI JAKARTA" ...
## $ nmkab : chr "KEPULAUAN SERIBU" "JAKARTA SELATAN" "JAKARTA TIMUR" "JAKARTA PUSAT" ...
## $ kdprov : chr "31" "31" "31" "31" ...
## $ kdkab : chr "01" "71" "72" "73" ...
## $ sumber : chr "BPS" "BPS" "BPS" "BPS" ...
## $ periode : chr "2020_1" "2020_1" "2020_1" "2020_1" ...
## $ geometry:sfc_GEOMETRY of length 119; first list element: List of 27
## ..$ :List of 1
## .. ..$ : num [1:7, 1:2] 106 106 106 106 106 ...
## ..$ :List of 1
## .. ..$ : num [1:4, 1:2] 106.49 106.49 106.49 106.49 -5.42 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:4, 1:2] 106.53 106.53 106.53 106.53 -5.57 ...
## ..$ :List of 1
## .. ..$ : num [1:4, 1:2] 106.5 106.5 106.5 106.5 -5.8 ...
## ..$ :List of 1
## .. ..$ : num [1:6, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:8, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:7, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:8, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:4, 1:2] 106.58 106.58 106.58 106.58 -5.63 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:7, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:7, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:6, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:6, 1:2] 107 107 107 107 107 ...
## ..- attr(*, "class")= chr [1:3] "XY" "MULTIPOLYGON" "sfg"
## $ mean_NTL: num 0.633 35.111 29.941 51.794 35.456 ...
## - attr(*, "sf_column")= chr "geometry"
## - attr(*, "agr")= Factor w/ 3 levels "constant","aggregate",..: NA NA NA NA NA NA NA NA NA
## ..- attr(*, "names")= chr [1:9] "fid" "idkab" "nmprov" "nmkab" ...Menyamakan bentuk ketegori peyimpanan dataset ke tibble Terdapat kesalahan tipe data unutk id . Dimana id yang seharusnya dalam bentuk string/character teridentifikasi sebagai numeric
Cek Missing Value
## id kode_prov Y X1 X2 X3
## 0 0 0 0 0 0## fid idkab nmprov nmkab kdprov kdkab sumber periode
## 0 0 0 0 0 0 0 0
## geometry X4
## 0 0## Warning: package 'skimr' was built under R version 4.4.3| Name | dataset |
| Number of rows | 119 |
| Number of columns | 6 |
| _______________________ | |
| Column type frequency: | |
| character | 2 |
| numeric | 4 |
| ________________________ | |
| Group variables | None |
Variable type: character
| skim_variable | n_missing | complete_rate | min | max | empty | n_unique | whitespace |
|---|---|---|---|---|---|---|---|
| id | 0 | 1 | 4 | 4 | 0 | 119 | 0 |
| kode_prov | 0 | 1 | 2 | 2 | 0 | 6 | 0 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| Y | 0 | 1 | 9.07 | 3.72 | 2.34 | 6.38 | 8.98 | 11.43 | 20.83 | ▃▇▅▂▁ |
| X1 | 0 | 1 | 5.04 | 1.83 | 1.56 | 3.70 | 4.91 | 6.26 | 9.18 | ▂▇▅▅▂ |
| X2 | 0 | 1 | 8.77 | 1.66 | 5.08 | 7.53 | 8.24 | 9.97 | 12.12 | ▁▇▆▂▅ |
| X3 | 0 | 1 | 12977.18 | 2937.19 | 8965.00 | 11000.00 | 12252.00 | 14152.50 | 25573.00 | ▇▅▂▁▁ |
## Warning: Couldn't find skimmers for class: sfc_GEOMETRY, sfc; No user-defined
## `sfl` provided. Falling back to `character`.| Name | bigdata |
| Number of rows | 119 |
| Number of columns | 10 |
| _______________________ | |
| Column type frequency: | |
| character | 8 |
| numeric | 2 |
| ________________________ | |
| Group variables | None |
Variable type: character
| skim_variable | n_missing | complete_rate | min | max | empty | n_unique | whitespace |
|---|---|---|---|---|---|---|---|
| idkab | 0 | 1 | 4 | 4 | 0 | 119 | 0 |
| nmprov | 0 | 1 | 6 | 13 | 0 | 6 | 0 |
| nmkab | 0 | 1 | 4 | 17 | 0 | 100 | 0 |
| kdprov | 0 | 1 | 2 | 2 | 0 | 6 | 0 |
| kdkab | 0 | 1 | 2 | 2 | 0 | 38 | 0 |
| sumber | 0 | 1 | 3 | 3 | 0 | 1 | 0 |
| periode | 0 | 1 | 6 | 6 | 0 | 1 | 0 |
| geometry | 0 | 1 | 1360 | 55924 | 0 | 119 | 0 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| fid | 0 | 1 | 38558.03 | 7661.93 | 25624.00 | 31713.50 | 39293.00 | 45010.00 | 50938.00 | ▆▇▇▆▇ |
| X4 | 0 | 1 | 7.13 | 9.40 | 0.63 | 1.73 | 2.72 | 9.09 | 51.79 | ▇▁▁▁▁ |
tidak terdapat
Cek Duplikasi data
## No variable names specified - using all columns.## No duplicate combinations found of: id, kode_prov, Y, X1, X2, X3## [1] 0## No variable names specified - using all columns.## No duplicate combinations found of: fid, idkab, nmprov, nmkab, kdprov, kdkab, sumber, periode, geometry, X4## [1] 0Selain itu dengan asumsi variabel id adalah primary keys akan diliat duplikasi dengan indikator variabel id
## No duplicate combinations found of: id## [1] 0## No duplicate combinations found of: idkab## [1] 0tidak terdapat duplikasi
Cek Konsistensi Data
## dataset.id dataset.kode_prov
## 1 3672 36
## 2 3673 36
## 3 3671 36
## 4 3674 36
## 5 3602 36
## 6 3601 36Dimana id merupakan dua digit pertama pada kode_prov
# Identifikasi variabel numerik
num_vars <- sapply(dataset, is.numeric)
# Definisikan aturan range untuk tiap variabel
rules <- list(
"Y" = c(0, 100),
"X1" = c(0, 100),
"X2" = c(0, 15),
"X3" = c(0, Inf) # hanya boleh > 0
)
# Loop cek konsistensi berdasarkan aturan
for (var in names(rules)) {
if (var %in% names(dataset)) {
cat("Checking", var, ":\n")
min_val <- rules[[var]][1]
max_val <- rules[[var]][2]
# Ambil nilai yang tidak NA dan tidak dalam range
if (is.infinite(max_val)) {
vals <- dataset[[var]][!is.na(dataset[[var]]) & dataset[[var]] <= min_val]
} else {
vals <- dataset[[var]][!is.na(dataset[[var]]) & (dataset[[var]] < min_val | dataset[[var]] > max_val)]
}
if (length(vals) > 0) {
cat(" Inconsistent values:\n")
print(unique(vals))
cat(" Count:", length(vals), "\n\n")
} else {
cat(" All values are consistent.\n\n")
}
} else {
cat("Variable", var, "not found in dataset.\n\n")
}
}## Checking Y :
## All values are consistent.
##
## Checking X1 :
## All values are consistent.
##
## Checking X2 :
## All values are consistent.
##
## Checking X3 :
## All values are consistent.# Identifikasi variabel numerik
num_vars <- sapply(bigdata, is.numeric)
# Definisikan aturan range untuk tiap variabel
rules <- list(
"X4" = c(0, 532)
)
# Loop cek konsistensi berdasarkan aturan
for (var in names(rules)) {
if (var %in% names(bigdata)) {
cat("Checking", var, ":\n")
min_val <- rules[[var]][1]
max_val <- rules[[var]][2]
# Ambil nilai yang tidak NA dan tidak dalam range
if (is.infinite(max_val)) {
vals <- bigdata[[var]][!is.na(bigdata[[var]]) & bigdata[[var]] <= min_val]
} else {
vals <- bigdata[[var]][!is.na(bigdata[[var]]) & (bigdata[[var]] < min_val | bigdata[[var]] > max_val)]
}
if (length(vals) > 0) {
cat(" Inconsistent values:\n")
print(unique(vals))
cat(" Count:", length(vals), "\n\n")
} else {
cat(" All values are consistent.\n\n")
}
} else {
cat("Variable", var, "not found in dataset.\n\n")
}
}## Checking X4 :
## All values are consistent.Data Validation
##
## Attaching package: 'validate'## The following objects are masked from 'package:terra':
##
## cells, compare, meta, origin, origin<-, values## The following object is masked from 'package:dplyr':
##
## exprval_dataset<-validator( "id"= is_unique(id)==T,
"kode_prov" = substr(id, 1, 2) == kode_prov,
"X1"= X1 >=0 & X1<=100,
"X2"= X2 >=0 & X2<=15,
"X3"= X3 >0
)
val_bigdata<-validator( "idkab"= is_unique(idkab)==T,
"X4"= X4 >=0 & X4<=52
)data_val_dataset <- confront(dataset, val_dataset, key ="id")
data_val_bigdata <- confront(bigdata, val_bigdata, key ="idkab")
summary(data_val_dataset)## name items passes fails nNA error warning
## 1 id 119 119 0 0 FALSE FALSE
## 2 kode_prov 119 119 0 0 FALSE FALSE
## 3 X1 119 119 0 0 FALSE FALSE
## 4 X2 119 119 0 0 FALSE FALSE
## 5 X3 119 119 0 0 FALSE FALSE
## expression
## 1 is_unique(id) == T
## 2 substr(id, 1, 2) == kode_prov
## 3 X1 - 0 >= -1e-08 & X1 - 100 <= 1e-08
## 4 X2 - 0 >= -1e-08 & X2 - 15 <= 1e-08
## 5 X3 > 0## name items passes fails nNA error warning
## 1 idkab 119 119 0 0 FALSE FALSE
## 2 X4 119 119 0 0 FALSE FALSE
## expression
## 1 is_unique(idkab) == T
## 2 X4 - 0 >= -1e-08 & X4 - 52 <= 1e-08
Tidak ada yang terlanggar pada data cleaning
Data Integration
# Misal, bigdata memiliki kolom "idkab" dan "X4"
# dataset memiliki kolom "id"
# Gabungkan kedua data frame berdasarkan ID yang sesuai
int_data <- merge(dataset, bigdata, by.x = "id", by.y = "idkab", all.x = TRUE)
# Cek hasil
head(int_data)## id kode_prov Y X1 X2 X3 fid nmprov nmkab
## 1 3101 31 13.03 7.93 9.26 14110 25624 DKI JAKARTA KEPULAUAN SERIBU
## 2 3171 31 3.03 5.22 11.95 25573 25630 DKI JAKARTA JAKARTA SELATAN
## 3 3172 31 4.09 6.95 11.99 19193 25695 DKI JAKARTA JAKARTA TIMUR
## 4 3173 31 4.63 6.24 11.61 18661 25760 DKI JAKARTA JAKARTA PUSAT
## 5 3174 31 3.94 6.18 11.24 22119 25804 DKI JAKARTA JAKARTA BARAT
## 6 3175 31 6.44 6.18 10.85 20032 25860 DKI JAKARTA JAKARTA UTARA
## kdprov kdkab sumber periode geometry X4
## 1 31 01 BPS 2020_1 MULTIPOLYGON (((106.4881 -5... 0.6328887
## 2 31 71 BPS 2020_1 POLYGON ((106.7374 -6.22393... 35.1112022
## 3 31 72 BPS 2020_1 POLYGON ((106.849 -6.207551... 29.9406319
## 4 31 73 BPS 2020_1 POLYGON ((106.8213 -6.13687... 51.7937012
## 5 31 74 BPS 2020_1 POLYGON ((106.6873 -6.09743... 35.4558067
## 6 31 75 BPS 2020_1 POLYGON ((106.9698 -6.09262... 33.4573936## 'data.frame': 119 obs. of 15 variables:
## $ id : chr "3101" "3171" "3172" "3173" ...
## $ kode_prov: chr "31" "31" "31" "31" ...
## $ Y : num 13.03 3.03 4.09 4.63 3.94 ...
## $ X1 : num 7.93 5.22 6.95 6.24 6.18 6.18 7.34 7.11 5.99 6.36 ...
## $ X2 : num 9.26 11.95 11.99 11.61 11.24 ...
## $ X3 : num 14110 25573 19193 18661 22119 ...
## $ fid : num 25624 25630 25695 25760 25804 ...
## $ nmprov : chr "DKI JAKARTA" "DKI JAKARTA" "DKI JAKARTA" "DKI JAKARTA" ...
## $ nmkab : chr "KEPULAUAN SERIBU" "JAKARTA SELATAN" "JAKARTA TIMUR" "JAKARTA PUSAT" ...
## $ kdprov : chr "31" "31" "31" "31" ...
## $ kdkab : chr "01" "71" "72" "73" ...
## $ sumber : chr "BPS" "BPS" "BPS" "BPS" ...
## $ periode : chr "2020_1" "2020_1" "2020_1" "2020_1" ...
## $ geometry :sfc_GEOMETRY of length 119; first list element: List of 27
## ..$ :List of 1
## .. ..$ : num [1:7, 1:2] 106 106 106 106 106 ...
## ..$ :List of 1
## .. ..$ : num [1:4, 1:2] 106.49 106.49 106.49 106.49 -5.42 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:4, 1:2] 106.53 106.53 106.53 106.53 -5.57 ...
## ..$ :List of 1
## .. ..$ : num [1:4, 1:2] 106.5 106.5 106.5 106.5 -5.8 ...
## ..$ :List of 1
## .. ..$ : num [1:6, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:8, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:7, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:8, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:4, 1:2] 106.58 106.58 106.58 106.58 -5.63 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:7, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:5, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:7, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:6, 1:2] 107 107 107 107 107 ...
## ..$ :List of 1
## .. ..$ : num [1:6, 1:2] 107 107 107 107 107 ...
## ..- attr(*, "class")= chr [1:3] "XY" "MULTIPOLYGON" "sfg"
## $ X4 : num 0.633 35.111 29.941 51.794 35.456 ...Data Redcution
## Y X1 X2 X3 X4
## 1 13.03 7.93 9.26 14110 0.6328887
## 2 3.03 5.22 11.95 25573 35.1112022
## 3 4.09 6.95 11.99 19193 29.9406319
## 4 4.63 6.24 11.61 18661 51.7937012
## 5 3.94 6.18 11.24 22119 35.4558067
## 6 6.44 6.18 10.85 20032 33.4573936## 'data.frame': 119 obs. of 5 variables:
## $ Y : num 13.03 3.03 4.09 4.63 3.94 ...
## $ X1: num 7.93 5.22 6.95 6.24 6.18 6.18 7.34 7.11 5.99 6.36 ...
## $ X2: num 9.26 11.95 11.99 11.61 11.24 ...
## $ X3: num 14110 25573 19193 18661 22119 ...
## $ X4: num 0.633 35.111 29.941 51.794 35.456 ...Data Transformation
## Y X1 X2 X3 X4
## 1 13.03 7.93 9.26 9.554639 0.6328887
## 2 3.03 5.22 11.95 10.149292 35.1112022
## 3 4.09 6.95 11.99 9.862301 29.9406319
## 4 4.63 6.24 11.61 9.834191 51.7937012
## 5 3.94 6.18 11.24 10.004192 35.4558067
## 6 6.44 6.18 10.85 9.905086 33.4573936