Dataframe terdiri dari banyak kolom dengan tiap kolom berisi list atau vector yang sama panjangnya. Setiap kolom merepresentasikan satu variabel, sedangkan setiap baris merepresentasikan satu observasi. Dataframe dapat berisi berbagai jenis data, seperti numerik, karakter, dan logika.

head(data_ssn)
## # A tibble: 6 × 118
##    URUT R101      R102 R105     R401 R403    R404    R405     R407 R408     R409
##   <dbl> <dbl+lb> <dbl> <dbl+l> <dbl> <dbl+l> <dbl+l> <dbl+l> <dbl> <dbl+l> <dbl>
## 1     1 18 [Lam…     7 2 [Per…     4 5 [Men… 2 [Kaw… 1 [Lak…    26  1 [Ya]    23
## 2     2 19 [Kep…     3 1 [Per…     5 3 [Ana… 1 [Bel… 1 [Lak…     9 NA         NA
## 3     7 16 [Sum…    71 1 [Per…     1 1 [Kep… 2 [Kaw… 1 [Lak…    39  1 [Ya]    26
## 4    23 16 [Sum…    71 1 [Per…     4 3 [Ana… 1 [Bel… 2 [Per…     9 NA         NA
## 5    27 15 [Jam…     5 2 [Per…     4 3 [Ana… 1 [Bel… 1 [Lak…     8 NA         NA
## 6    28 52 [Nus…     6 2 [Per…     3 3 [Ana… 3 [Cer… 2 [Per…    37 NA         28
## # ℹ 107 more variables: R406A <dbl>, R406B <dbl>, R406C <dbl>, R410 <dbl>,
## #   R601 <dbl>, R602 <dbl>, R603 <dbl>, R604 <dbl>, R605 <dbl+lbl>,
## #   R606 <dbl+lbl>, R607 <dbl+lbl>, R608 <dbl+lbl>, R609 <dbl+lbl>,
## #   R610 <dbl+lbl>, R611 <dbl+lbl>, R612 <dbl+lbl>, R613 <dbl+lbl>,
## #   R614 <dbl+lbl>, R615 <dbl+lbl>, R616 <dbl+lbl>, R617 <dbl>, R618 <dbl>,
## #   R619 <dbl+lbl>, R620 <dbl+lbl>, R621 <dbl+lbl>, R1101_A <chr>,
## #   R1101_B <chr>, R1101_C <chr>, R1101_D <chr>, R1101_E <chr>, …
#str(data_ssn)       # Melihat ringkasan struktur dari suatu objek data
#summary(data_ssn)   # Melihat ringkasan statistik dasar

1 Check Missing Values

Missing Value dituliskan dengan NA. Untuk menguji NA, gunakan is.na().


colSums(is.na(df_ori))

sum(is.na(df_ori$varA))


sum(is.na(data_ssn$R105))
## [1] 0

2 Making New Variable

Untuk menjaga data asli, lebih baik membuat kolom baru daripada menimpa kolom asli. Membuat variabel baru dalam data frame dapat dilakukan seperti membuat vektor.


base
df_ori$var_baru <- ekspresi

df_ori[,"var_baru"] <- ekspresi

dplyr
library(dplyr)
df_baru <- df_ori %>%
  mutate(var_baru = ifelse(condition, "Label 1", "Label 2"))
print(df_baru[,c("var_baru")])

Menggunakan syntax base

data_ssn$tambah <- 1
head(data_ssn[,"tambah"],8)
## # A tibble: 8 × 1
##   tambah
##    <dbl>
## 1      1
## 2      1
## 3      1
## 4      1
## 5      1
## 6      1
## 7      1
## 8      1
data_ssn[,"Var_baru"] <- 1
head(data_ssn[,"Var_baru"],6)
## # A tibble: 6 × 1
##   Var_baru
##      <dbl>
## 1        1
## 2        1
## 3        1
## 4        1
## 5        1
## 6        1

Menggunakan mutate()

Library dplyr menyediakan fungsi mutate() untuk menambah/memodifikasi kolom dalam data frame.

Fungsi ini memungkinkan untuk melakukan penghitungan/transformasi pada kolom yang ada, dan menambahkan hasilnya sebagai kolom baru ke dalam data frame.

library(dplyr)
data <- data_ssn %>%
  mutate(status = ifelse(R407 < 18, "Anak-anak", "Dewasa")) #Variabel baru bernama status
print(data[,c("status")])
## # A tibble: 48,797 × 1
##    status   
##    <chr>    
##  1 Dewasa   
##  2 Anak-anak
##  3 Dewasa   
##  4 Anak-anak
##  5 Anak-anak
##  6 Dewasa   
##  7 Dewasa   
##  8 Dewasa   
##  9 Dewasa   
## 10 Dewasa   
## # ℹ 48,787 more rows

3 Sort Cases

  • Dilakukan untuk mengurutkan data berdasarkan beberapa variabel tertentu

  • Dilakukan dengan membuat vektor logika untuk melakukan pengurutan data

  • Fungsi yang sering digunakan: arrange (...), order(...)

  • Dalam library dplyr, fungsi arrange() otomatis mengurutkan secara ascending tanpa memerlukan fungsi tambahan seperti asc(). Hanya perlu menggunakan desc() untuk mengurutkan secara descending.


base
df_sorted_asc  <- df_ori[order(df_ori$varA, decreasing = FALSE), ]

df_sorted_desc <- df_ori[order(df_ori$varA, decreasing = TRUE), ]

dplyr
library(dplyr)
df_sort <- df_ori %>%
                  arrange(varA) #Ascending
library(dplyr)
df_sort <- df_ori %>%
                  arrange(desc(varA) #Descending

1. Menyortir 1 Variabel dengan arrange()

library(dplyr)
data_sorted111 <- data_ssn %>%
                  arrange(R101) # Sort kolom R101 secara Ascending
print(data_sorted111)
## # A tibble: 48,797 × 120
##      URUT R101       R102 R105        R401 R403    R404    R405     R407 R408   
##     <dbl> <dbl+lbl> <dbl> <dbl+lbl>  <dbl> <dbl+l> <dbl+l> <dbl+l> <dbl> <dbl+l>
##  1 300062 11 [Aceh]     3 2 [Perdes…     2 2 [Ist… 2 [Kaw… 2 [Per…    58  1 [Ya]
##  2 300235 11 [Aceh]    74 1 [Perkot…     4 3 [Ana… 1 [Bel… 2 [Per…    17 NA     
##  3 300240 11 [Aceh]    74 2 [Perdes…     6 3 [Ana… 1 [Bel… 2 [Per…     3 NA     
##  4 300411 11 [Aceh]    15 2 [Perdes…     4 3 [Ana… 1 [Bel… 1 [Lak…     0 NA     
##  5 300576 11 [Aceh]    14 2 [Perdes…     1 1 [Kep… 2 [Kaw… 1 [Lak…    61  1 [Ya]
##  6 300606 11 [Aceh]     4 1 [Perkot…     2 2 [Ist… 2 [Kaw… 2 [Per…    37  1 [Ya]
##  7 300632 11 [Aceh]     3 2 [Perdes…     4 5 [Men… 2 [Kaw… 2 [Per…    38  1 [Ya]
##  8 300748 11 [Aceh]    75 2 [Perdes…     2 2 [Ist… 2 [Kaw… 2 [Per…    44  1 [Ya]
##  9 301149 11 [Aceh]     9 2 [Perdes…     4 3 [Ana… 1 [Bel… 1 [Lak…    19 NA     
## 10 301179 11 [Aceh]    17 2 [Perdes…     4 3 [Ana… 1 [Bel… 2 [Per…    25 NA     
## # ℹ 48,787 more rows
## # ℹ 110 more variables: R409 <dbl>, R406A <dbl>, R406B <dbl>, R406C <dbl>,
## #   R410 <dbl>, R601 <dbl>, R602 <dbl>, R603 <dbl>, R604 <dbl>, R605 <dbl+lbl>,
## #   R606 <dbl+lbl>, R607 <dbl+lbl>, R608 <dbl+lbl>, R609 <dbl+lbl>,
## #   R610 <dbl+lbl>, R611 <dbl+lbl>, R612 <dbl+lbl>, R613 <dbl+lbl>,
## #   R614 <dbl+lbl>, R615 <dbl+lbl>, R616 <dbl+lbl>, R617 <dbl>, R618 <dbl>,
## #   R619 <dbl+lbl>, R620 <dbl+lbl>, R621 <dbl+lbl>, R1101_A <chr>, …
data_sorted_desc112 <- data_ssn %>%
                       arrange(desc(R101))
print(data_sorted_desc112)
## # A tibble: 48,797 × 120
##      URUT R101        R102 R105       R401 R403    R404    R405     R407 R408   
##     <dbl> <dbl+lbl>  <dbl> <dbl+lbl> <dbl> <dbl+l> <dbl+l> <dbl+l> <dbl> <dbl+l>
##  1 300131 94 [Papua]    19 2 [Perde…     5 3 [Ana… 1 [Bel… 2 [Per…    10 NA     
##  2 301416 94 [Papua]    12 1 [Perko…     3 3 [Ana… 1 [Bel… 2 [Per…    20 NA     
##  3 301449 94 [Papua]     1 2 [Perde…     2 2 [Ist… 2 [Kaw… 2 [Per…    40  1 [Ya]
##  4 301540 94 [Papua]    12 1 [Perko…     3 3 [Ana… 1 [Bel… 1 [Lak…    10 NA     
##  5 301758 94 [Papua]     4 2 [Perde…     2 2 [Ist… 2 [Kaw… 2 [Per…    47  1 [Ya]
##  6 302124 94 [Papua]     1 1 [Perko…     1 1 [Kep… 3 [Cer… 1 [Lak…    62 NA     
##  7 302233 94 [Papua]    12 1 [Perko…     3 3 [Ana… 1 [Bel… 1 [Lak…    22 NA     
##  8 302405 94 [Papua]     4 1 [Perko…     3 3 [Ana… 1 [Bel… 2 [Per…    18 NA     
##  9 302501 94 [Papua]    12 2 [Perde…     3 3 [Ana… 1 [Bel… 1 [Lak…    25 NA     
## 10 303359 94 [Papua]    20 2 [Perde…     1 1 [Kep… 2 [Kaw… 1 [Lak…    40  1 [Ya]
## # ℹ 48,787 more rows
## # ℹ 110 more variables: R409 <dbl>, R406A <dbl>, R406B <dbl>, R406C <dbl>,
## #   R410 <dbl>, R601 <dbl>, R602 <dbl>, R603 <dbl>, R604 <dbl>, R605 <dbl+lbl>,
## #   R606 <dbl+lbl>, R607 <dbl+lbl>, R608 <dbl+lbl>, R609 <dbl+lbl>,
## #   R610 <dbl+lbl>, R611 <dbl+lbl>, R612 <dbl+lbl>, R613 <dbl+lbl>,
## #   R614 <dbl+lbl>, R615 <dbl+lbl>, R616 <dbl+lbl>, R617 <dbl>, R618 <dbl>,
## #   R619 <dbl+lbl>, R620 <dbl+lbl>, R621 <dbl+lbl>, R1101_A <chr>, …
glimpse(data_sorted_desc112)
## Rows: 48,797
## Columns: 120
## $ URUT     <dbl> 300131, 301416, 301449, 301540, 301758, 302124, 302233, 30240…
## $ R101     <dbl+lbl> 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 9…
## $ R102     <dbl> 19, 12, 1, 12, 4, 1, 12, 4, 12, 20, 29, 10, 32, 16, 16, 16, 1…
## $ R105     <dbl+lbl> 2, 1, 2, 1, 2, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, …
## $ R401     <dbl> 5, 3, 2, 3, 2, 1, 3, 3, 3, 1, 5, 1, 6, 1, 2, 2, 4, 7, 2, 1, 5…
## $ R403     <dbl+lbl> 3, 3, 2, 3, 2, 1, 3, 3, 3, 1, 3, 1, 3, 1, 3, 2, 3, 3, 2, …
## $ R404     <dbl+lbl> 1, 1, 2, 1, 2, 3, 1, 1, 1, 2, 1, 2, 1, 4, 1, 2, 1, 1, 2, …
## $ R405     <dbl+lbl> 2, 2, 2, 1, 2, 1, 1, 2, 1, 1, 1, 1, 1, 2, 2, 2, 1, 2, 2, …
## $ R407     <dbl> 10, 20, 40, 10, 47, 62, 22, 18, 25, 40, 3, 39, 9, 43, 22, 43,…
## $ R408     <dbl+lbl> NA, NA,  1, NA,  1, NA, NA, NA, NA,  1, NA,  1, NA, NA, N…
## $ R409     <dbl> NA, NA, 24, NA, 20, 24, NA, NA, NA, 24, NA, 30, NA, 20, NA, 1…
## $ R406A    <dbl> 28, 15, 9, 11, 7, 26, 15, 31, 11, 2, 29, 3, 28, 1, 1, 17, 4, …
## $ R406B    <dbl> 7, 12, 8, 5, 5, 5, 10, 8, 12, 7, 8, 5, 7, 7, 7, 7, 6, 2, 10, …
## $ R406C    <dbl> 2012, 2002, 1982, 2012, 1975, 1960, 2000, 2004, 1997, 1982, 2…
## $ R410     <dbl> 1, 2, 2, 2, 2, 1, 2, 1, 2, 2, 1, 1, 1, 1, 1, 2, 2, 1, 1, 1, 2…
## $ R601     <dbl> 94, 94, 53, 91, 73, 73, 73, 73, 81, 94, 94, 94, 94, 94, 94, 9…
## $ R602     <dbl> 19, 12, 9, 1, 71, 71, 8, 8, 72, 2, 29, 10, 32, 16, 16, 16, 13…
## $ R603     <dbl> 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, NA, 94, 94, 94, 94, 9…
## $ R604     <dbl> 19, 12, 1, 12, 4, 1, 12, 4, 12, 20, NA, 10, 32, 16, 16, 16, 1…
## $ R605     <dbl+lbl>  3, NA, NA,  4, NA, NA, NA, NA, NA, NA,  4, NA,  4, NA, N…
## $ R606     <dbl+lbl>  4, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
## $ R607     <dbl+lbl>  1,  1,  1,  1,  1,  1,  1,  1,  1,  1, NA,  1,  1,  5,  …
## $ R608     <dbl+lbl>  5,  5,  5,  1,  5,  5,  5,  5,  5,  5, NA,  5,  5,  5,  …
## $ R609     <dbl+lbl>  5,  5,  5,  5,  5,  5,  5,  5,  5,  5, NA,  5,  5,  5,  …
## $ R610     <dbl+lbl>  2,  2,  3,  2,  3,  3,  2,  2,  3,  3, NA,  1,  2,  1,  …
## $ R611     <dbl+lbl>  1,  2, NA,  1, NA, NA,  1,  1, NA, NA, NA, NA,  1, NA, N…
## $ R612     <dbl+lbl>  3, 13, 13,  3,  3,  8, 21, 21,  8,  3, NA, NA,  3, NA, N…
## $ R613     <dbl+lbl>  5,  3,  8,  5,  8,  8,  2,  2,  8,  8, NA, NA,  4, NA, N…
## $ R614     <dbl+lbl> 25,  8, 13, 25,  3,  8, 13, 13,  8,  3, NA, NA, 25, NA, N…
## $ R615     <dbl+lbl>  5,  5, NA,  5, NA, NA,  5,  5,  5, NA, NA, NA,  2, NA, N…
## $ R616     <dbl+lbl>  5,  5, NA,  5, NA, NA,  5,  5,  5, NA, NA, NA,  1, NA, N…
## $ R617     <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 225000, NA, N…
## $ R618     <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 1, NA, NA, NA…
## $ R619     <dbl+lbl>  2,  2, NA,  2, NA, NA,  2,  2, NA, NA, NA, NA,  2, NA, N…
## $ R620     <dbl+lbl>  3, 13, NA,  3, NA, NA, 21, 21, NA, NA, NA, NA,  3, NA, N…
## $ R621     <dbl+lbl>  4,  2, NA,  4, NA, NA,  1,  1, NA, NA, NA, NA,  3, NA, N…
## $ R1101_A  <chr> "", "", "A", "", "A", "", "", "", "A", "A", "", "", "", "", "…
## $ R1101_B  <chr> "", "", "", "B", "", "", "", "B", "", "", "", "", "", "", "",…
## $ R1101_C  <chr> "C", "", "", "", "", "", "", "", "", "", "C", "", "C", "C", "…
## $ R1101_D  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1101_E  <chr> "", "", "", "", "", "", "E", "", "", "", "", "", "", "", "", …
## $ R1101_X  <chr> "", "X", "", "", "", "X", "", "", "", "", "", "X", "", "", ""…
## $ R1102    <dbl+lbl> 5, 5, 5, 5, 5, 5, 5, 1, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, …
## $ R1103    <dbl+lbl> NA, NA, NA, NA, NA, NA, NA,  5, NA, NA, NA, NA, NA, NA, N…
## $ R1104    <dbl+lbl> NA, NA, NA, NA, NA, NA, NA,  1, NA, NA, NA, NA, NA, NA, N…
## $ R1105    <dbl+lbl> NA, NA, NA, NA, NA, NA, NA,  5, NA, NA, NA, NA, NA, NA, N…
## $ R1106    <dbl+lbl> NA, NA, NA, NA, NA, NA, NA,  5, NA, NA, NA, NA, NA, NA, N…
## $ R1107_A  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1107_B  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1107_C  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1107_D  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1107_E  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1107_F  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1107_G  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1107_H  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1108    <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
## $ R1109_A  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1109_B  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1109_C  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1109_D  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1109_E  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1109_X  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1110_A  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1110_B  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1110_C  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1110_D  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1110_E  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1110_F  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1110_G  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1110_H  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1110_I  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1201    <dbl+lbl> 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, …
## $ R1202_A  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1202_B  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1202_C  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1202_D  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1202_E  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1202_F  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1202_G  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1203    <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
## $ R1204_A  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1204_B  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1204_C  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1204_D  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1204_E  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1204_X  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1205_A  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1205_B  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1205_C  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1205_D  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1205_E  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1205_F  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1205_G  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1205_H  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1205_I  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "…
## $ R1206    <dbl+lbl>  5,  5,  5,  5,  5,  5,  5,  5,  5,  5, NA,  5,  5,  5,  …
## $ R1207    <dbl+lbl>  5,  5,  5,  5,  5,  1,  5,  5,  8,  5, NA,  5,  5,  5,  …
## $ R1208    <dbl> NA, NA, NA, NA, NA, 84, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
## $ R1209    <dbl+lbl>  5,  5,  5,  5,  5,  1,  5,  5, NA,  5, NA,  5,  5,  5,  …
## $ FWT      <dbl> 18.677762, 8.387459, 89.970590, 90.586172, 54.131840, 235.579…
## $ R301     <dbl> 5, 6, 6, 3, 4, 2, 4, 5, 5, 2, 5, 2, 7, 3, 3, 4, 6, 8, 4, 10, …
## $ R302     <dbl> 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0…
## $ R303     <dbl> 5, 5, 5, 3, 4, 2, 4, 5, 5, 2, 4, 2, 7, 3, 3, 4, 5, 8, 4, 9, 5…
## $ R304     <dbl> 5, 4, 4, 3, 3, 2, 4, 4, 5, 2, 3, 2, 5, 3, 3, 4, 2, 8, 4, 8, 5…
## $ R305     <dbl> 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1…
## $ EXPEND   <dbl> 20158990, 6701536, 6334490, 4396231, 6277762, 7281107, 125883…
## $ KAPITA   <dbl> 4031798.1, 1116922.6, 1055748.4, 1465410.3, 1569440.5, 364055…
## $ WERT     <dbl> 18.677762, 8.387459, 89.970590, 90.586172, 54.131840, 235.579…
## $ WEIND    <dbl> 93.38881, 50.32476, 539.82354, 271.75852, 216.52736, 471.1592…
## $ NKS      <chr> "100080", "150402", "100396", "150090", "100146", "150137", "…
## $ NURT     <dbl> 3, 13, 12, 15, 6, 7, 12, 3, 11, 6, 2, 8, 4, 6, 6, 1, 10, 10, …
## $ GK       <dbl> 661946, 743289, 661946, 743289, 661946, 743289, 743289, 74328…
## $ MISKIN   <dbl+lbl> 2, 2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 2, 2, 2, 2, 1, 1, 2, 2, …
## $ MISKINWB <dbl+lbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, …
## $ KABU     <dbl+lbl> 9419, 9412, 9401, 9412, 9404, 9401, 9412, 9404, 9412, 942…
## $ Z101     <dbl+lbl> 94, 96, 95, 96, 96, 95, 96, 96, 96, 94, 97, 96, 97, 97, 9…
## $ Z102     <dbl> 19, 1, 1, 1, 4, 1, 1, 4, 1, 20, 1, 5, 6, 7, 7, 7, 2, 6, 1, 4,…
## $ zkabu    <dbl+lbl> 9419, 9601, 9501, 9601, 9604, 9501, 9601, 9604, 9601, 942…
## $ tambah   <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1…
## $ Var_baru <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1…
#Menggunakan order() dari Base R
data_sorted121 <- data_ssn[order(data_ssn$R405), ]
head(data_sorted121)
## # A tibble: 6 × 120
##    URUT R101      R102 R105     R401 R403    R404    R405     R407 R408     R409
##   <dbl> <dbl+lb> <dbl> <dbl+l> <dbl> <dbl+l> <dbl+l> <dbl+l> <dbl> <dbl+l> <dbl>
## 1     1 18 [Lam…     7 2 [Per…     4 5 [Men… 2 [Kaw… 1 [Lak…    26  1 [Ya]    23
## 2     2 19 [Kep…     3 1 [Per…     5 3 [Ana… 1 [Bel… 1 [Lak…     9 NA         NA
## 3     7 16 [Sum…    71 1 [Per…     1 1 [Kep… 2 [Kaw… 1 [Lak…    39  1 [Ya]    26
## 4    27 15 [Jam…     5 2 [Per…     4 3 [Ana… 1 [Bel… 1 [Lak…     8 NA         NA
## 5    51 18 [Lam…     7 2 [Per…     3 3 [Ana… 1 [Bel… 1 [Lak…    23 NA         NA
## 6    61 52 [Nus…     5 1 [Per…     3 3 [Ana… 1 [Bel… 1 [Lak…    20 NA         NA
## # ℹ 109 more variables: R406A <dbl>, R406B <dbl>, R406C <dbl>, R410 <dbl>,
## #   R601 <dbl>, R602 <dbl>, R603 <dbl>, R604 <dbl>, R605 <dbl+lbl>,
## #   R606 <dbl+lbl>, R607 <dbl+lbl>, R608 <dbl+lbl>, R609 <dbl+lbl>,
## #   R610 <dbl+lbl>, R611 <dbl+lbl>, R612 <dbl+lbl>, R613 <dbl+lbl>,
## #   R614 <dbl+lbl>, R615 <dbl+lbl>, R616 <dbl+lbl>, R617 <dbl>, R618 <dbl>,
## #   R619 <dbl+lbl>, R620 <dbl+lbl>, R621 <dbl+lbl>, R1101_A <chr>,
## #   R1101_B <chr>, R1101_C <chr>, R1101_D <chr>, R1101_E <chr>, …
data_sorted_desc122 <- data_ssn[order(data_ssn$R405, decreasing = TRUE), ]
head(data_sorted_desc122)
## # A tibble: 6 × 120
##    URUT R101      R102 R105     R401 R403    R404    R405     R407 R408     R409
##   <dbl> <dbl+lb> <dbl> <dbl+l> <dbl> <dbl+l> <dbl+l> <dbl+l> <dbl> <dbl+l> <dbl>
## 1    23 16 [Sum…    71 1 [Per…     4 3 [Ana… 1 [Bel… 2 [Per…     9 NA         NA
## 2    28 52 [Nus…     6 2 [Per…     3 3 [Ana… 3 [Cer… 2 [Per…    37 NA         28
## 3    51 18 [Lam…     7 2 [Per…     2 2 [Ist… 2 [Kaw… 2 [Per…    52  1 [Ya]    15
## 4    58 21 [Kep…     1 1 [Per…     2 2 [Ist… 2 [Kaw… 2 [Per…    46  1 [Ya]    23
## 5    82 16 [Sum…    10 1 [Per…     2 2 [Ist… 2 [Kaw… 2 [Per…    52  1 [Ya]    20
## 6    84 63 [Kal…     4 1 [Per…     5 3 [Ana… 1 [Bel… 2 [Per…    13 NA         NA
## # ℹ 109 more variables: R406A <dbl>, R406B <dbl>, R406C <dbl>, R410 <dbl>,
## #   R601 <dbl>, R602 <dbl>, R603 <dbl>, R604 <dbl>, R605 <dbl+lbl>,
## #   R606 <dbl+lbl>, R607 <dbl+lbl>, R608 <dbl+lbl>, R609 <dbl+lbl>,
## #   R610 <dbl+lbl>, R611 <dbl+lbl>, R612 <dbl+lbl>, R613 <dbl+lbl>,
## #   R614 <dbl+lbl>, R615 <dbl+lbl>, R616 <dbl+lbl>, R617 <dbl>, R618 <dbl>,
## #   R619 <dbl+lbl>, R620 <dbl+lbl>, R621 <dbl+lbl>, R1101_A <chr>,
## #   R1101_B <chr>, R1101_C <chr>, R1101_D <chr>, R1101_E <chr>, …

2. Menyortir berdasarkan 2 Variabel

library(dplyr)
data_sorted211 <- data_ssn %>%
                  arrange(R101, desc(R610)) 
#Sort R101 secara naik, dan jika ada nilai yang sama pada R101, sortir 610 dengan menurun.
print(data_sorted211[,c("R101","R610")])
## # A tibble: 48,797 × 2
##    R101      R610                     
##    <dbl+lbl> <dbl+lbl>                
##  1 11 [Aceh] 3 [Tidak bersekolah lagi]
##  2 11 [Aceh] 3 [Tidak bersekolah lagi]
##  3 11 [Aceh] 3 [Tidak bersekolah lagi]
##  4 11 [Aceh] 3 [Tidak bersekolah lagi]
##  5 11 [Aceh] 3 [Tidak bersekolah lagi]
##  6 11 [Aceh] 3 [Tidak bersekolah lagi]
##  7 11 [Aceh] 3 [Tidak bersekolah lagi]
##  8 11 [Aceh] 3 [Tidak bersekolah lagi]
##  9 11 [Aceh] 3 [Tidak bersekolah lagi]
## 10 11 [Aceh] 3 [Tidak bersekolah lagi]
## # ℹ 48,787 more rows
#Menggunakan order() dari Base R
data_sorted212 <- data_ssn[order(data_ssn$R101, -data_ssn$R407), ]
print(data_sorted212[,c("R101","R407")])
## # A tibble: 48,797 × 2
##    R101       R407
##    <dbl+lbl> <dbl>
##  1 11 [Aceh]    91
##  2 11 [Aceh]    88
##  3 11 [Aceh]    87
##  4 11 [Aceh]    83
##  5 11 [Aceh]    83
##  6 11 [Aceh]    82
##  7 11 [Aceh]    82
##  8 11 [Aceh]    81
##  9 11 [Aceh]    81
## 10 11 [Aceh]    79
## # ℹ 48,787 more rows

3. Menyortir Berdasarkan 3 atau lebih Variabel

library(dplyr)
data_sorted311 <- data_ssn %>%
                  arrange(R101, desc(R610), R404)
print(data_sorted311[,c("R101","R610", "R404")])
## # A tibble: 48,797 × 3
##    R101      R610                      R404           
##    <dbl+lbl> <dbl+lbl>                 <dbl+lbl>      
##  1 11 [Aceh] 3 [Tidak bersekolah lagi] 1 [Belum kawin]
##  2 11 [Aceh] 3 [Tidak bersekolah lagi] 1 [Belum kawin]
##  3 11 [Aceh] 3 [Tidak bersekolah lagi] 1 [Belum kawin]
##  4 11 [Aceh] 3 [Tidak bersekolah lagi] 1 [Belum kawin]
##  5 11 [Aceh] 3 [Tidak bersekolah lagi] 1 [Belum kawin]
##  6 11 [Aceh] 3 [Tidak bersekolah lagi] 1 [Belum kawin]
##  7 11 [Aceh] 3 [Tidak bersekolah lagi] 1 [Belum kawin]
##  8 11 [Aceh] 3 [Tidak bersekolah lagi] 1 [Belum kawin]
##  9 11 [Aceh] 3 [Tidak bersekolah lagi] 1 [Belum kawin]
## 10 11 [Aceh] 3 [Tidak bersekolah lagi] 1 [Belum kawin]
## # ℹ 48,787 more rows
#Menggunakan order() dari Base R
data_sorted312 <- data_ssn[order(data_ssn$R101, -data_ssn$R401, data_ssn$R407), ]
print(data_sorted312[,c("R101","R401", "R407")])
## # A tibble: 48,797 × 3
##    R101       R401  R407
##    <dbl+lbl> <dbl> <dbl>
##  1 11 [Aceh]    15     0
##  2 11 [Aceh]    10     6
##  3 11 [Aceh]    10    44
##  4 11 [Aceh]     9    16
##  5 11 [Aceh]     9    34
##  6 11 [Aceh]     8     0
##  7 11 [Aceh]     8     0
##  8 11 [Aceh]     8     1
##  9 11 [Aceh]     8     2
## 10 11 [Aceh]     8     5
## # ℹ 48,787 more rows

4 Select Variables

Manipulasi data select variables digunakan untuk memilih kolom/variabel.


base
data_selected <- df_ori[, c("var 1","var 2","var 3","...","var-n")]

data_selected <- df_ori[, c(posisi A, posisi B, ..., posisi-n)]

dplyr
library(dplyr)
data_selected1 <- df_ori %>% 
                  select(var1, var2, ..., var-n)
                  
data_selected2 <- df_ori %>% 
                  select(-c(var1, var2, ..., var-n))    

data_selected3 <- df_ori %>% 
                  select(starts_with("partname"))
                  
data_selected4 <- df_ori %>% 
                  select(contains("partname"))

Dalam operasi ini bisa dilakukan proses drop and keep variabel yang digunakan.

1. Menyebut Nama-Nama Kolom

Memilih variabel berdasarkan nama kolom/variabel.

# Memilih variabel tertentu
data_selected1 <- data_ssn[, c("R101","R105","R407","FWT","R1102")]
head(data_selected1)
## # A tibble: 6 × 5
##   R101                           R105           R407   FWT R1102    
##   <dbl+lbl>                      <dbl+lbl>     <dbl> <dbl> <dbl+lbl>
## 1 18 [Lampung]                   2 [Perdesaan]    26 293.  5 [Tidak]
## 2 19 [Kepulauan Bangka Belitung] 1 [Perkotaan]     9  40.5 5 [Tidak]
## 3 16 [Sumatera Selatan]          1 [Perkotaan]    39 521.  5 [Tidak]
## 4 16 [Sumatera Selatan]          1 [Perkotaan]     9 239.  5 [Tidak]
## 5 15 [Jambi]                     2 [Perdesaan]     8 277.  5 [Tidak]
## 6 52 [Nusa Tenggara Barat]       2 [Perdesaan]    37 143.  5 [Tidak]

2. Menggunakan Indeks Kolom

Memilih variabel berdasarkan posisi urutan kolom variabel tersebut.

# Memilih variabel berdasarkan indeks kolom
data_selected2 <- data_ssn[, c(1, 2, 3, 5)]  # Memilih kolom 1, 2, 3, dan 5
head(data_selected2)
## # A tibble: 6 × 4
##    URUT R101                            R102  R401
##   <dbl> <dbl+lbl>                      <dbl> <dbl>
## 1     1 18 [Lampung]                       7     4
## 2     2 19 [Kepulauan Bangka Belitung]     3     5
## 3     7 16 [Sumatera Selatan]             71     1
## 4    23 16 [Sumatera Selatan]             71     4
## 5    27 15 [Jambi]                         5     4
## 6    28 52 [Nusa Tenggara Barat]           6     3

3. Menggunakan Operator select()

Menggunakan fungsi select() untuk menyeleksi kolom dengan cara yang lebih efisien dan elegan.

library(dplyr)
data_selected3 <- data_ssn %>% 
                  select(R101, R105, R407, FWT, R1102)
head(data_selected3)
## # A tibble: 6 × 5
##   R101                           R105           R407   FWT R1102    
##   <dbl+lbl>                      <dbl+lbl>     <dbl> <dbl> <dbl+lbl>
## 1 18 [Lampung]                   2 [Perdesaan]    26 293.  5 [Tidak]
## 2 19 [Kepulauan Bangka Belitung] 1 [Perkotaan]     9  40.5 5 [Tidak]
## 3 16 [Sumatera Selatan]          1 [Perkotaan]    39 521.  5 [Tidak]
## 4 16 [Sumatera Selatan]          1 [Perkotaan]     9 239.  5 [Tidak]
## 5 15 [Jambi]                     2 [Perdesaan]     8 277.  5 [Tidak]
## 6 52 [Nusa Tenggara Barat]       2 [Perdesaan]    37 143.  5 [Tidak]

4. Mengecualikan Variabel Tertentu

Mengecualikan variabel tertentu dengan memberi tanda minus (-)

data_selected4 <- data_ssn %>% 
                  select(-MISKIN)
head(data_selected4)
## # A tibble: 6 × 119
##    URUT R101      R102 R105     R401 R403    R404    R405     R407 R408     R409
##   <dbl> <dbl+lb> <dbl> <dbl+l> <dbl> <dbl+l> <dbl+l> <dbl+l> <dbl> <dbl+l> <dbl>
## 1     1 18 [Lam…     7 2 [Per…     4 5 [Men… 2 [Kaw… 1 [Lak…    26  1 [Ya]    23
## 2     2 19 [Kep…     3 1 [Per…     5 3 [Ana… 1 [Bel… 1 [Lak…     9 NA         NA
## 3     7 16 [Sum…    71 1 [Per…     1 1 [Kep… 2 [Kaw… 1 [Lak…    39  1 [Ya]    26
## 4    23 16 [Sum…    71 1 [Per…     4 3 [Ana… 1 [Bel… 2 [Per…     9 NA         NA
## 5    27 15 [Jam…     5 2 [Per…     4 3 [Ana… 1 [Bel… 1 [Lak…     8 NA         NA
## 6    28 52 [Nus…     6 2 [Per…     3 3 [Ana… 3 [Cer… 2 [Per…    37 NA         28
## # ℹ 108 more variables: R406A <dbl>, R406B <dbl>, R406C <dbl>, R410 <dbl>,
## #   R601 <dbl>, R602 <dbl>, R603 <dbl>, R604 <dbl>, R605 <dbl+lbl>,
## #   R606 <dbl+lbl>, R607 <dbl+lbl>, R608 <dbl+lbl>, R609 <dbl+lbl>,
## #   R610 <dbl+lbl>, R611 <dbl+lbl>, R612 <dbl+lbl>, R613 <dbl+lbl>,
## #   R614 <dbl+lbl>, R615 <dbl+lbl>, R616 <dbl+lbl>, R617 <dbl>, R618 <dbl>,
## #   R619 <dbl+lbl>, R620 <dbl+lbl>, R621 <dbl+lbl>, R1101_A <chr>,
## #   R1101_B <chr>, R1101_C <chr>, R1101_D <chr>, R1101_E <chr>, …

5. Memilih Variabel dengan Pola Nama

# Memilih variabel yang diawali dengan huruf "R10"
data_selected5 <- data_ssn %>% 
                  select(starts_with("R10"))
head(data_selected5)
## # A tibble: 6 × 3
##   R101                            R102 R105         
##   <dbl+lbl>                      <dbl> <dbl+lbl>    
## 1 18 [Lampung]                       7 2 [Perdesaan]
## 2 19 [Kepulauan Bangka Belitung]     3 1 [Perkotaan]
## 3 16 [Sumatera Selatan]             71 1 [Perkotaan]
## 4 16 [Sumatera Selatan]             71 1 [Perkotaan]
## 5 15 [Jambi]                         5 2 [Perdesaan]
## 6 52 [Nusa Tenggara Barat]           6 2 [Perdesaan]
# Memilih variabel yang mengandung kata "R4"
data_selected6 <- data_ssn %>% 
                  select(contains("R4"))
head(data_selected6)
## # A tibble: 6 × 11
##    R401 R403         R404    R405     R407 R408     R409 R406A R406B R406C  R410
##   <dbl> <dbl+lbl>    <dbl+l> <dbl+l> <dbl> <dbl+l> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1     4 5 [Menantu]  2 [Kaw… 1 [Lak…    26  1 [Ya]    23    12     9  1996     2
## 2     5 3 [Anak kan… 1 [Bel… 1 [Lak…     9 NA         NA    16     9  2013     1
## 3     1 1 [Kepala r… 2 [Kaw… 1 [Lak…    39  1 [Ya]    26    27    10  1983     2
## 4     4 3 [Anak kan… 1 [Bel… 2 [Per…     9 NA         NA     6     2  2014     1
## 5     4 3 [Anak kan… 1 [Bel… 1 [Lak…     8 NA         NA    10     1  2015     2
## 6     3 3 [Anak kan… 3 [Cer… 2 [Per…    37 NA         28     1     1  1986     2

5 Select Cases


base
df_ori[df_ori$varX == 1,] # Misalnya memilih yang berkode 1 dari var X

df_ori[df_ori$varX == 2 | df_ori$varX > 1500,] # Misalnya memilih yang berkode 2 atau >1500 dari var X

dplyr
Select Single
library(dplyr)
df_select <- subset(df_ori, var-n)

df_select <- df_ori %>%
                   filter(kondisi)

Select Multiple
pilihan <- c(32, 11, 62)
df_select <- df_ori %>%
                    filter(var-n %in% 
                      pilihan)

5.1 Select Cases: Single

1. Menggunakan Operator Subsetting Dasar [ ]

data_jawa_barat <- data_ssn[data_ssn$R101==32, ]

2. Menggunakan subset()

data_jawa_barat <- subset(data_ssn, R101 == 32)

3. Menggunakan filter ()

library(dplyr)
data_jawa_barat <- data_ssn %>%
                   filter(R101 == 32)

4. Memilih berdasarkan >1 kriteria

data_jabar_bandung <- data_ssn %>%
                      filter(R101 == 32 & R403 == 1)
data_jawa_barat_tengah <- data_ssn %>%
                          filter(R101 == 32 | R101 == 33)

5.2 Select Cases: Multiple

1. Menggunakan Operator Subsetting Dasar [ ] dengan %in%

# daftar provinsi yang ingin dipilih
provinsi_pilihan <- c(32, 11, 62)

# Memilih data untuk provinsi-provinsi yang ada di daftar
data_provinsi_pilihan1 <- data_ssn[data_ssn$R101 %in% 
                                    provinsi_pilihan, ]

2. Menggunakan fungsi subset() dengan %in%

data_provinsi_pilihan2 <- subset(data_ssn, R101 %in% 
                                  provinsi_pilihan)

3. Menggunakan dplyr dengan filter() dan %in%

library(dplyr)
data_provinsi_pilihan3 <- data_ssn %>%
                            filter(R101%in% 
                                  provinsi_pilihan)
head(data_provinsi_pilihan3, 10)
## # A tibble: 10 × 120
##     URUT R101           R102 R105     R401 R403    R404    R405     R407 R408   
##    <dbl> <dbl+lbl>     <dbl> <dbl+l> <dbl> <dbl+l> <dbl+l> <dbl+l> <dbl> <dbl+l>
##  1   172 62 [Kalimant…    71 1 [Per…     3 3 [Ana… 1 [Bel… 1 [Lak…    17 NA     
##  2   248 62 [Kalimant…     5 2 [Per…     4 3 [Ana… 1 [Bel… 1 [Lak…     7 NA     
##  3   301 62 [Kalimant…     2 1 [Per…     5 3 [Ana… 1 [Bel… 1 [Lak…     9 NA     
##  4   360 62 [Kalimant…     9 2 [Per…     1 1 [Kep… 2 [Kaw… 1 [Lak…    47  1 [Ya]
##  5   378 62 [Kalimant…     4 2 [Per…     4 3 [Ana… 1 [Bel… 1 [Lak…    13 NA     
##  6   793 62 [Kalimant…    13 1 [Per…     1 1 [Kep… 2 [Kaw… 1 [Lak…    48  1 [Ya]
##  7  1050 62 [Kalimant…    71 1 [Per…     3 3 [Ana… 1 [Bel… 2 [Per…    17 NA     
##  8  1340 62 [Kalimant…     7 2 [Per…     6 6 [Cuc… 1 [Bel… 2 [Per…     4 NA     
##  9  1384 62 [Kalimant…     8 2 [Per…     2 2 [Ist… 2 [Kaw… 2 [Per…    33  1 [Ya]
## 10  1450 62 [Kalimant…     2 1 [Per…     2 2 [Ist… 2 [Kaw… 2 [Per…    26  1 [Ya]
## # ℹ 110 more variables: R409 <dbl>, R406A <dbl>, R406B <dbl>, R406C <dbl>,
## #   R410 <dbl>, R601 <dbl>, R602 <dbl>, R603 <dbl>, R604 <dbl>, R605 <dbl+lbl>,
## #   R606 <dbl+lbl>, R607 <dbl+lbl>, R608 <dbl+lbl>, R609 <dbl+lbl>,
## #   R610 <dbl+lbl>, R611 <dbl+lbl>, R612 <dbl+lbl>, R613 <dbl+lbl>,
## #   R614 <dbl+lbl>, R615 <dbl+lbl>, R616 <dbl+lbl>, R617 <dbl>, R618 <dbl>,
## #   R619 <dbl+lbl>, R620 <dbl+lbl>, R621 <dbl+lbl>, R1101_A <chr>,
## #   R1101_B <chr>, R1101_C <chr>, R1101_D <chr>, R1101_E <chr>, …

4. Menggunakan Logika OR

library(dplyr)
data_provinsi_pilihan4 <- data_ssn %>%
                            filter(R101 == 32 | R101 == 33  | R101 == 31)
head(data_provinsi_pilihan4, 10)
## # A tibble: 10 × 120
##     URUT R101           R102 R105     R401 R403    R404    R405     R407 R408   
##    <dbl> <dbl+lbl>     <dbl> <dbl+l> <dbl> <dbl+l> <dbl+l> <dbl+l> <dbl> <dbl+l>
##  1    70 31 [DKI Jaka…    71 1 [Per…     5 3 [Ana… 1 [Bel… 1 [Lak…    13 NA     
##  2    71 31 [DKI Jaka…    72 1 [Per…     1 1 [Kep… 2 [Kaw… 1 [Lak…    50  1 [Ya]
##  3   244 33 [Jawa Ten…    15 2 [Per…     1 1 [Kep… 2 [Kaw… 1 [Lak…    51  1 [Ya]
##  4   300 33 [Jawa Ten…    25 1 [Per…     2 2 [Ist… 2 [Kaw… 2 [Per…    54  1 [Ya]
##  5   303 33 [Jawa Ten…    75 1 [Per…     3 3 [Ana… 1 [Bel… 2 [Per…    16 NA     
##  6   339 31 [DKI Jaka…    72 1 [Per…     1 1 [Kep… 4 [Cer… 2 [Per…    74 NA     
##  7   370 31 [DKI Jaka…    72 1 [Per…     2 2 [Ist… 2 [Kaw… 2 [Per…    38  1 [Ya]
##  8   371 33 [Jawa Ten…     2 1 [Per…     2 2 [Ist… 2 [Kaw… 2 [Per…    33  1 [Ya]
##  9   375 33 [Jawa Ten…    27 2 [Per…     4 3 [Ana… 1 [Bel… 2 [Per…     6 NA     
## 10   401 33 [Jawa Ten…    14 2 [Per…     5 3 [Ana… 1 [Bel… 2 [Per…     3 NA     
## # ℹ 110 more variables: R409 <dbl>, R406A <dbl>, R406B <dbl>, R406C <dbl>,
## #   R410 <dbl>, R601 <dbl>, R602 <dbl>, R603 <dbl>, R604 <dbl>, R605 <dbl+lbl>,
## #   R606 <dbl+lbl>, R607 <dbl+lbl>, R608 <dbl+lbl>, R609 <dbl+lbl>,
## #   R610 <dbl+lbl>, R611 <dbl+lbl>, R612 <dbl+lbl>, R613 <dbl+lbl>,
## #   R614 <dbl+lbl>, R615 <dbl+lbl>, R616 <dbl+lbl>, R617 <dbl>, R618 <dbl>,
## #   R619 <dbl+lbl>, R620 <dbl+lbl>, R621 <dbl+lbl>, R1101_A <chr>,
## #   R1101_B <chr>, R1101_C <chr>, R1101_D <chr>, R1101_E <chr>, …

6 Filter Data


base
data_filter <- df_ori[kondisi df_ori$var, ]

data_filter <- subset(df_ori, kondisi var)

dplyr
library(dplyr)
df_filter <- df_ori %>%
                   filter(kondisi)
library(dplyr)
pilihan <- c(32, 11, 62)
df_filter <- df_ori %>%
                    filter(var-n %in% 
                      pilihan)

Berikut merupakan cara untuk memfilter data menurut kondisi tertentu

1. Menggunakan Subset Operator [ ]

# Memilih variabel umur lebih besar dari 15
data_filtered11 <- data_ssn[data_ssn$R407 >=15, ]

# Memilih variabel tamat pendidikan tertentu
data_filtered12 <- data_ssn[data_ssn$R614>=5 & data_ssn$R614<=7, ]

2. Menggunakan subset()

# Memilih variabel umur lebih besar dari 15
data_filtered21 <- subset(data_ssn, R407 >=15)

# Memilih data dimanavariabel tamat pendidikan tertentu
data_filtered22 <- subset(data_ssn, R614 >= 15 & R614<=17)

# Memilih data dimana umur lebih dari 30 dan pengeluaran lebih dari 5 juta
data_filtered23 <- subset(data_ssn, R407 > 30 & EXPEND > 5000)

3. Menggunakan filter()

library(dplyr)

# Memilih data dimana variabel umur lebih besar dari 30
data_filtered31 <- data_ssn %>% 
                   filter(R407 > 30)


# Memilih data dimana variabel tamat pendidikan tertentu
data_filtered32 <- data_ssn %>% 
                   filter(R614 >= 1 & R614<=4)

# Memilih data dimana umur lebih dari 30 dan pengeluaran lebih dari 5 juta
data_filtered33 <- data_ssn %>% 
                  filter(R407 > 30, EXPEND > 5000000)

4. Menggabungkan Kondisi dengan Operator Logika

# Memilih data dimana umur lebih dari 30 dan tamat pendidikan sama dengan SD/SEDERAJAT
data_filtered41 <- data_ssn %>% 
                   filter(R407 > 30 & R614>=1 & R614<=4)

# Memilih data dimana umur lebih dari 30 atau tamat pendidikan sama dengan SD/SEDERAJAT
data_filtered42 <- data_ssn %>% 
                   filter(R407 > 30 | R614>=1 & R614<=4)

# Memilih data dimana umur tidak lebih dari 30
data_filtered43 <- data_ssn %>% 
                   filter(!(R407 > 30))

7 Recode Variables

Recoding berfungsi untuk membuat nilai baru dari nilai variabel yang sudah ada.


base
df_ori$recode <- ifelse(df_ori$kondisi_var, "Label 1","Label 2")

car
library(car)
recode(df_ori$varA,'kondisi1=nilai1; else=nilai2')

dplyr
library(dplyr)
df_recode <- df_ori %>%
  mutate(kelum = case_when(
    condition1 ~ value1,
    condition2 ~ value2,
    TRUE ~ default_value
  ))

Digunakan untuk membuat nilai baru dari variabel yang sudah ada

Fungsi yang biasa digunakan: fungsi if else(...), recode(...), case_when(...)

1. Menggunakan ifelse()

Fungsi ifelse() adalah fungsi yang sering digunakan untuk merecode variabel dalam satu baris kode.

data_ssn$educ_recoded <- ifelse(data_ssn$R614 >= 1 & data_ssn$R614 <= 4, "SD",
                               ifelse(data_ssn$R614 >= 5 & data_ssn$R614 <= 8, "SMP",
                               ifelse(data_ssn$R614 >= 9, "SMA+", NA)))
table(data_ssn$educ_recoded)
## 
##    SD  SMA+   SMP 
## 10648 23945  7471

2. Menggunakan recode()

Jika memiliki nilai yang ingin direkode satu per satu:

library(dplyr)
data_recode1 <- data_ssn %>%
  mutate(R610 = as_factor(R610)) %>%  # Konversi ke faktor
  mutate(pendidikan_recoded = recode(R610,
                                     `1` = 1,
                                     `2` = 2,
                                     `3` = 1))
print(data_recode1)
## # A tibble: 48,797 × 122
##     URUT R101           R102 R105     R401 R403    R404    R405     R407 R408   
##    <dbl> <dbl+lbl>     <dbl> <dbl+l> <dbl> <dbl+l> <dbl+l> <dbl+l> <dbl> <dbl+l>
##  1     1 18 [Lampung]      7 2 [Per…     4 5 [Men… 2 [Kaw… 1 [Lak…    26  1 [Ya]
##  2     2 19 [Kepulaua…     3 1 [Per…     5 3 [Ana… 1 [Bel… 1 [Lak…     9 NA     
##  3     7 16 [Sumatera…    71 1 [Per…     1 1 [Kep… 2 [Kaw… 1 [Lak…    39  1 [Ya]
##  4    23 16 [Sumatera…    71 1 [Per…     4 3 [Ana… 1 [Bel… 2 [Per…     9 NA     
##  5    27 15 [Jambi]        5 2 [Per…     4 3 [Ana… 1 [Bel… 1 [Lak…     8 NA     
##  6    28 52 [Nusa Ten…     6 2 [Per…     3 3 [Ana… 3 [Cer… 2 [Per…    37 NA     
##  7    51 18 [Lampung]      7 2 [Per…     2 2 [Ist… 2 [Kaw… 2 [Per…    52  1 [Ya]
##  8    51 18 [Lampung]      7 2 [Per…     3 3 [Ana… 1 [Bel… 1 [Lak…    23 NA     
##  9    58 21 [Kepulaua…     1 1 [Per…     2 2 [Ist… 2 [Kaw… 2 [Per…    46  1 [Ya]
## 10    61 52 [Nusa Ten…     5 1 [Per…     3 3 [Ana… 1 [Bel… 1 [Lak…    20 NA     
## # ℹ 48,787 more rows
## # ℹ 112 more variables: R409 <dbl>, R406A <dbl>, R406B <dbl>, R406C <dbl>,
## #   R410 <dbl>, R601 <dbl>, R602 <dbl>, R603 <dbl>, R604 <dbl>, R605 <dbl+lbl>,
## #   R606 <dbl+lbl>, R607 <dbl+lbl>, R608 <dbl+lbl>, R609 <dbl+lbl>, R610 <fct>,
## #   R611 <dbl+lbl>, R612 <dbl+lbl>, R613 <dbl+lbl>, R614 <dbl+lbl>,
## #   R615 <dbl+lbl>, R616 <dbl+lbl>, R617 <dbl>, R618 <dbl>, R619 <dbl+lbl>,
## #   R620 <dbl+lbl>, R621 <dbl+lbl>, R1101_A <chr>, R1101_B <chr>, …

3. Menggunakan Paket car

Sama seperti recode() dari dplyr, car juga untuk recoding langsung.

library(car)
data_ssn <- data.frame(R404 = c("Belum kawin", "Kawin", "Cerai Hidup", "Cerai Mati"))

# Merecode kolom 'R404'
data_ssn$status_recoded <- recode(data_ssn$R404, "'Belum kawin' = 1; 'Kawin' = 2; 'Cerai Hidup' = 3; 'Cerai Mati' = 4")
print(data_ssn$status_recoded)
## [1] 1 2 3 4

4. Menggunakan case_when()

Digunakan jika ingin melakukan merekoding berdasarkan rentang nilai, kondisi logis yang kompleks, atau gabungan dari berbagai kondisi.

Fungsi case_when() digunakan dalam fungsi mutate() dan setiap kondisi dalam case_when() harus menggunakan formula dua sisi (dengan kondisi di sebelah kiri dan hasil di sebelah kanan).

library(dplyr)
data_TAMAT <- data_ssn %>%
  mutate(TAMAT = case_when(
    is.na(R614) ~ 1,                    # Jika nilai R614 adalah missing (SYSMIS), maka TAMAT = 1
    R614 == 25 ~ 1,                     # Jika R614 = 25, maka TAMAT = 1
    R614 >= 1 & R614 <= 5 ~ 2,          # Jika R614 antara 1 sampai 5, maka TAMAT = 2
    R614 >= 6 & R614 <= 10 ~ 3,         # Jika R614 antara 6 sampai 10, maka TAMAT = 3
    R614 >= 11 & R614 <= 17 ~ 4,        # Jika R614 antara 11 sampai 17, maka TAMAT = 4
    R614 >= 18 & R614 <= 24 ~ 5         # Jika R614 antara 18 sampai 24, maka TAMAT = 5
  ))
head(data_ssn[,c("URUT","TAMAT")],5)

8 Rename Columns


base
names(df_ori)[names(df_ori == "VarA"] <- "VarA_baru"

dplyr
library(dplyr)
data_ssn1 <- rename(df_ori, VarA_baru = VarA)

library(dplyr)
data_ssn2 <- data_ssn %>% 
                rename(VarA_baru = VarA)

library(dplyr)
data_ssn3 <- data_ssn %>% 
             rename(VarA_baru = VarA, VarB_baru = VarB)

8.1 Rename Columns: Single

1. Menggunakan names() atau colnames()

##   [1] "URUT"     "R101"     "R102"     "R105"     "R401"     "R403"    
##   [7] "R404"     "R405"     "R407"     "R408"     "R409"     "R406A"   
##  [13] "R406B"    "R406C"    "R410"     "R601"     "R602"     "R603"    
##  [19] "R604"     "R605"     "R606"     "R607"     "R608"     "R609"    
##  [25] "R610"     "R611"     "R612"     "R613"     "R614"     "R615"    
##  [31] "R616"     "R617"     "R618"     "R619"     "R620"     "R621"    
##  [37] "R1101_A"  "R1101_B"  "R1101_C"  "R1101_D"  "R1101_E"  "R1101_X" 
##  [43] "R1102"    "R1103"    "R1104"    "R1105"    "R1106"    "R1107_A" 
##  [49] "R1107_B"  "R1107_C"  "R1107_D"  "R1107_E"  "R1107_F"  "R1107_G" 
##  [55] "R1107_H"  "R1108"    "R1109_A"  "R1109_B"  "R1109_C"  "R1109_D" 
##  [61] "R1109_E"  "R1109_X"  "R1110_A"  "R1110_B"  "R1110_C"  "R1110_D" 
##  [67] "R1110_E"  "R1110_F"  "R1110_G"  "R1110_H"  "R1110_I"  "R1201"   
##  [73] "R1202_A"  "R1202_B"  "R1202_C"  "R1202_D"  "R1202_E"  "R1202_F" 
##  [79] "R1202_G"  "R1203"    "R1204_A"  "R1204_B"  "R1204_C"  "R1204_D" 
##  [85] "R1204_E"  "R1204_X"  "R1205_A"  "R1205_B"  "R1205_C"  "R1205_D" 
##  [91] "R1205_E"  "R1205_F"  "R1205_G"  "R1205_H"  "R1205_I"  "R1206"   
##  [97] "R1207"    "R1208"    "R1209"    "FWT"      "R301"     "R302"    
## [103] "R303"     "R304"     "R305"     "EXPEND"   "KAPITA"   "WERT"    
## [109] "WEIND"    "NKS"      "NURT"     "GK"       "MISKIN"   "MISKINWB"
## [115] "KABU"     "Z101"     "Z102"     "zkabu"
# Mengganti nama kolom
names(data_ssn)[names(data_ssn) == "R101"] <- "PROV"
names(data_ssn)
##   [1] "URUT"     "PROV"     "R102"     "R105"     "R401"     "R403"    
##   [7] "R404"     "R405"     "R407"     "R408"     "R409"     "R406A"   
##  [13] "R406B"    "R406C"    "R410"     "R601"     "R602"     "R603"    
##  [19] "R604"     "R605"     "R606"     "R607"     "R608"     "R609"    
##  [25] "R610"     "R611"     "R612"     "R613"     "R614"     "R615"    
##  [31] "R616"     "R617"     "R618"     "R619"     "R620"     "R621"    
##  [37] "R1101_A"  "R1101_B"  "R1101_C"  "R1101_D"  "R1101_E"  "R1101_X" 
##  [43] "R1102"    "R1103"    "R1104"    "R1105"    "R1106"    "R1107_A" 
##  [49] "R1107_B"  "R1107_C"  "R1107_D"  "R1107_E"  "R1107_F"  "R1107_G" 
##  [55] "R1107_H"  "R1108"    "R1109_A"  "R1109_B"  "R1109_C"  "R1109_D" 
##  [61] "R1109_E"  "R1109_X"  "R1110_A"  "R1110_B"  "R1110_C"  "R1110_D" 
##  [67] "R1110_E"  "R1110_F"  "R1110_G"  "R1110_H"  "R1110_I"  "R1201"   
##  [73] "R1202_A"  "R1202_B"  "R1202_C"  "R1202_D"  "R1202_E"  "R1202_F" 
##  [79] "R1202_G"  "R1203"    "R1204_A"  "R1204_B"  "R1204_C"  "R1204_D" 
##  [85] "R1204_E"  "R1204_X"  "R1205_A"  "R1205_B"  "R1205_C"  "R1205_D" 
##  [91] "R1205_E"  "R1205_F"  "R1205_G"  "R1205_H"  "R1205_I"  "R1206"   
##  [97] "R1207"    "R1208"    "R1209"    "FWT"      "R301"     "R302"    
## [103] "R303"     "R304"     "R305"     "EXPEND"   "KAPITA"   "WERT"    
## [109] "WEIND"    "NKS"      "NURT"     "GK"       "MISKIN"   "MISKINWB"
## [115] "KABU"     "Z101"     "Z102"     "zkabu"
#Hasil names() = Hasil colnames()
colnames(data_ssn)
##   [1] "URUT"     "PROV"     "R102"     "R105"     "R401"     "R403"    
##   [7] "R404"     "R405"     "R407"     "R408"     "R409"     "R406A"   
##  [13] "R406B"    "R406C"    "R410"     "R601"     "R602"     "R603"    
##  [19] "R604"     "R605"     "R606"     "R607"     "R608"     "R609"    
##  [25] "R610"     "R611"     "R612"     "R613"     "R614"     "R615"    
##  [31] "R616"     "R617"     "R618"     "R619"     "R620"     "R621"    
##  [37] "R1101_A"  "R1101_B"  "R1101_C"  "R1101_D"  "R1101_E"  "R1101_X" 
##  [43] "R1102"    "R1103"    "R1104"    "R1105"    "R1106"    "R1107_A" 
##  [49] "R1107_B"  "R1107_C"  "R1107_D"  "R1107_E"  "R1107_F"  "R1107_G" 
##  [55] "R1107_H"  "R1108"    "R1109_A"  "R1109_B"  "R1109_C"  "R1109_D" 
##  [61] "R1109_E"  "R1109_X"  "R1110_A"  "R1110_B"  "R1110_C"  "R1110_D" 
##  [67] "R1110_E"  "R1110_F"  "R1110_G"  "R1110_H"  "R1110_I"  "R1201"   
##  [73] "R1202_A"  "R1202_B"  "R1202_C"  "R1202_D"  "R1202_E"  "R1202_F" 
##  [79] "R1202_G"  "R1203"    "R1204_A"  "R1204_B"  "R1204_C"  "R1204_D" 
##  [85] "R1204_E"  "R1204_X"  "R1205_A"  "R1205_B"  "R1205_C"  "R1205_D" 
##  [91] "R1205_E"  "R1205_F"  "R1205_G"  "R1205_H"  "R1205_I"  "R1206"   
##  [97] "R1207"    "R1208"    "R1209"    "FWT"      "R301"     "R302"    
## [103] "R303"     "R304"     "R305"     "EXPEND"   "KAPITA"   "WERT"    
## [109] "WEIND"    "NKS"      "NURT"     "GK"       "MISKIN"   "MISKINWB"
## [115] "KABU"     "Z101"     "Z102"     "zkabu"
# Mengganti nama kolom dengan colnames
#colnames(data_ssn)[colnames(data_ssn) == "R102"] <- "KAB_KOTA"
#colnames(data_ssn)

2. Menggunakan rename()

library(dplyr)
data_ssnA <- rename(data_ssn, HUB = R403)
names(data_ssnA)
##   [1] "URUT"     "PROV"     "R102"     "R105"     "R401"     "HUB"     
##   [7] "R404"     "R405"     "R407"     "R408"     "R409"     "R406A"   
##  [13] "R406B"    "R406C"    "R410"     "R601"     "R602"     "R603"    
##  [19] "R604"     "R605"     "R606"     "R607"     "R608"     "R609"    
##  [25] "R610"     "R611"     "R612"     "R613"     "R614"     "R615"    
##  [31] "R616"     "R617"     "R618"     "R619"     "R620"     "R621"    
##  [37] "R1101_A"  "R1101_B"  "R1101_C"  "R1101_D"  "R1101_E"  "R1101_X" 
##  [43] "R1102"    "R1103"    "R1104"    "R1105"    "R1106"    "R1107_A" 
##  [49] "R1107_B"  "R1107_C"  "R1107_D"  "R1107_E"  "R1107_F"  "R1107_G" 
##  [55] "R1107_H"  "R1108"    "R1109_A"  "R1109_B"  "R1109_C"  "R1109_D" 
##  [61] "R1109_E"  "R1109_X"  "R1110_A"  "R1110_B"  "R1110_C"  "R1110_D" 
##  [67] "R1110_E"  "R1110_F"  "R1110_G"  "R1110_H"  "R1110_I"  "R1201"   
##  [73] "R1202_A"  "R1202_B"  "R1202_C"  "R1202_D"  "R1202_E"  "R1202_F" 
##  [79] "R1202_G"  "R1203"    "R1204_A"  "R1204_B"  "R1204_C"  "R1204_D" 
##  [85] "R1204_E"  "R1204_X"  "R1205_A"  "R1205_B"  "R1205_C"  "R1205_D" 
##  [91] "R1205_E"  "R1205_F"  "R1205_G"  "R1205_H"  "R1205_I"  "R1206"   
##  [97] "R1207"    "R1208"    "R1209"    "FWT"      "R301"     "R302"    
## [103] "R303"     "R304"     "R305"     "EXPEND"   "KAPITA"   "WERT"    
## [109] "WEIND"    "NKS"      "NURT"     "GK"       "MISKIN"   "MISKINWB"
## [115] "KABU"     "Z101"     "Z102"     "zkabu"
library(dplyr)
data_ssn1 <- data_ssn %>% 
                rename(Sex = R405)
names(data_ssn1)
##   [1] "URUT"     "PROV"     "R102"     "R105"     "R401"     "R403"    
##   [7] "R404"     "Sex"      "R407"     "R408"     "R409"     "R406A"   
##  [13] "R406B"    "R406C"    "R410"     "R601"     "R602"     "R603"    
##  [19] "R604"     "R605"     "R606"     "R607"     "R608"     "R609"    
##  [25] "R610"     "R611"     "R612"     "R613"     "R614"     "R615"    
##  [31] "R616"     "R617"     "R618"     "R619"     "R620"     "R621"    
##  [37] "R1101_A"  "R1101_B"  "R1101_C"  "R1101_D"  "R1101_E"  "R1101_X" 
##  [43] "R1102"    "R1103"    "R1104"    "R1105"    "R1106"    "R1107_A" 
##  [49] "R1107_B"  "R1107_C"  "R1107_D"  "R1107_E"  "R1107_F"  "R1107_G" 
##  [55] "R1107_H"  "R1108"    "R1109_A"  "R1109_B"  "R1109_C"  "R1109_D" 
##  [61] "R1109_E"  "R1109_X"  "R1110_A"  "R1110_B"  "R1110_C"  "R1110_D" 
##  [67] "R1110_E"  "R1110_F"  "R1110_G"  "R1110_H"  "R1110_I"  "R1201"   
##  [73] "R1202_A"  "R1202_B"  "R1202_C"  "R1202_D"  "R1202_E"  "R1202_F" 
##  [79] "R1202_G"  "R1203"    "R1204_A"  "R1204_B"  "R1204_C"  "R1204_D" 
##  [85] "R1204_E"  "R1204_X"  "R1205_A"  "R1205_B"  "R1205_C"  "R1205_D" 
##  [91] "R1205_E"  "R1205_F"  "R1205_G"  "R1205_H"  "R1205_I"  "R1206"   
##  [97] "R1207"    "R1208"    "R1209"    "FWT"      "R301"     "R302"    
## [103] "R303"     "R304"     "R305"     "EXPEND"   "KAPITA"   "WERT"    
## [109] "WEIND"    "NKS"      "NURT"     "GK"       "MISKIN"   "MISKINWB"
## [115] "KABU"     "Z101"     "Z102"     "zkabu"

8.2 Rename Columns: Multiple

1. Mengganti Nama Banyak Kolom Sekaligus

names(data_ssn)[names(data_ssn) %in% c("R403", "R404")] <- c("HB_KRT", "STATUS_KWN")

2. Menggunakan rename()

library(dplyr)
data_ssn3 <- data_ssn %>% 
             rename(SEKO = R610, JENJANG = R611)
names(data_ssn3)
##   [1] "URUT"       "PROV"       "R102"       "R105"       "R401"      
##   [6] "HB_KRT"     "STATUS_KWN" "R405"       "R407"       "R408"      
##  [11] "R409"       "R406A"      "R406B"      "R406C"      "R410"      
##  [16] "R601"       "R602"       "R603"       "R604"       "R605"      
##  [21] "R606"       "R607"       "R608"       "R609"       "SEKO"      
##  [26] "JENJANG"    "R612"       "R613"       "R614"       "R615"      
##  [31] "R616"       "R617"       "R618"       "R619"       "R620"      
##  [36] "R621"       "R1101_A"    "R1101_B"    "R1101_C"    "R1101_D"   
##  [41] "R1101_E"    "R1101_X"    "R1102"      "R1103"      "R1104"     
##  [46] "R1105"      "R1106"      "R1107_A"    "R1107_B"    "R1107_C"   
##  [51] "R1107_D"    "R1107_E"    "R1107_F"    "R1107_G"    "R1107_H"   
##  [56] "R1108"      "R1109_A"    "R1109_B"    "R1109_C"    "R1109_D"   
##  [61] "R1109_E"    "R1109_X"    "R1110_A"    "R1110_B"    "R1110_C"   
##  [66] "R1110_D"    "R1110_E"    "R1110_F"    "R1110_G"    "R1110_H"   
##  [71] "R1110_I"    "R1201"      "R1202_A"    "R1202_B"    "R1202_C"   
##  [76] "R1202_D"    "R1202_E"    "R1202_F"    "R1202_G"    "R1203"     
##  [81] "R1204_A"    "R1204_B"    "R1204_C"    "R1204_D"    "R1204_E"   
##  [86] "R1204_X"    "R1205_A"    "R1205_B"    "R1205_C"    "R1205_D"   
##  [91] "R1205_E"    "R1205_F"    "R1205_G"    "R1205_H"    "R1205_I"   
##  [96] "R1206"      "R1207"      "R1208"      "R1209"      "FWT"       
## [101] "R301"       "R302"       "R303"       "R304"       "R305"      
## [106] "EXPEND"     "KAPITA"     "WERT"       "WEIND"      "NKS"       
## [111] "NURT"       "GK"         "MISKIN"     "MISKINWB"   "KABU"      
## [116] "Z101"       "Z102"       "zkabu"

9 Aggregating

Untuk melakukan agregasi, digunakan fungsi summarize() dan group_by ()

Ingin melihat hasil agregasi menurut provinsi:

aggr1 <- data_ssn %>%
    group_by(R101) %>%
    summarize(mean_theta = mean(KAPITA, na.rm = TRUE))
print(aggr1)
## # A tibble: 34 × 2
##    R101                           mean_theta
##    <dbl+lbl>                           <dbl>
##  1 11 [Aceh]                        1298305.
##  2 12 [Sumatera Utara]              1260795.
##  3 13 [Sumatera Barat]              1425005.
##  4 14 [Riau]                        1536939.
##  5 15 [Jambi]                       1470432.
##  6 16 [Sumatera Selatan]            1196369.
##  7 17 [Bengkulu]                    1324300.
##  8 18 [Lampung]                     1170050.
##  9 19 [Kepulauan Bangka Belitung]   1822676.
## 10 21 [Kepulauan Riau]              1799927.
## # ℹ 24 more rows

Ingin melihat hasil agregasi menurut provinsi dan tipe daerah:

aggr2 <- data_ssn %>%
    group_by(R101, R105) %>%
    summarize(mean_theta = mean(KAPITA, na.rm = TRUE))
print(aggr2)
## # A tibble: 67 × 3
## # Groups:   R101 [34]
##    R101                R105          mean_theta
##    <dbl+lbl>           <dbl+lbl>          <dbl>
##  1 11 [Aceh]           1 [Perkotaan]   1607555.
##  2 11 [Aceh]           2 [Perdesaan]   1161717.
##  3 12 [Sumatera Utara] 1 [Perkotaan]   1482937.
##  4 12 [Sumatera Utara] 2 [Perdesaan]   1088072.
##  5 13 [Sumatera Barat] 1 [Perkotaan]   1683709.
##  6 13 [Sumatera Barat] 2 [Perdesaan]   1225497.
##  7 14 [Riau]           1 [Perkotaan]   1811815.
##  8 14 [Riau]           2 [Perdesaan]   1386664.
##  9 15 [Jambi]          1 [Perkotaan]   1797469.
## 10 15 [Jambi]          2 [Perdesaan]   1341387.
## # ℹ 57 more rows

10 Tabulation

tab <- xtabs(~ R101 + R105 + R405, data = data_ssn)
print(tab)
## , , R405 = 1
## 
##     R105
## R101    1    2
##   11  295  685
##   12  670  885
##   13  395  519
##   14  200  425
##   15  140  350
##   16  266  551
##   17  129  286
##   18  203  563
##   19  138  139
##   21  225   88
##   31  357    0
##   32 1162  564
##   33 1026  891
##   34  156   65
##   35 1099  950
##   36  370  173
##   51  285  203
##   52  188  266
##   53  181  877
##   61  166  436
##   62  172  396
##   63  220  305
##   64  277  174
##   65  111  103
##   71  240  377
##   72  105  422
##   73  377  726
##   74  152  505
##   75   70  181
##   76   55  204
##   81  168  381
##   82   85  320
##   91  110  425
##   94  210  939
## 
## , , R405 = 2
## 
##     R105
## R101    1    2
##   11  307  678
##   12  721  904
##   13  397  508
##   14  239  378
##   15  137  352
##   16  256  551
##   17  114  216
##   18  215  490
##   19  137  136
##   21  212   71
##   31  371    0
##   32 1144  545
##   33 1111  905
##   34  178   84
##   35 1081  959
##   36  345  186
##   51  315  198
##   52  192  278
##   53  178  823
##   61  170  447
##   62  182  346
##   63  237  291
##   64  253  158
##   65  118   94
##   71  223  355
##   72  138  426
##   73  406  772
##   74  146  595
##   75   71  174
##   76   51  217
##   81  160  369
##   82  104  319
##   91  121  460
##   94  204  901
# Menghitung frekuensi untuk kombinasi variabel
tab1 <- data_ssn %>%
  count(R101, R105, R405)
print(tab1)
## # A tibble: 134 × 4
##    R101                R105          R405              n
##    <dbl+lbl>           <dbl+lbl>     <dbl+lbl>     <int>
##  1 11 [Aceh]           1 [Perkotaan] 1 [Laki-laki]   295
##  2 11 [Aceh]           1 [Perkotaan] 2 [Perempuan]   307
##  3 11 [Aceh]           2 [Perdesaan] 1 [Laki-laki]   685
##  4 11 [Aceh]           2 [Perdesaan] 2 [Perempuan]   678
##  5 12 [Sumatera Utara] 1 [Perkotaan] 1 [Laki-laki]   670
##  6 12 [Sumatera Utara] 1 [Perkotaan] 2 [Perempuan]   721
##  7 12 [Sumatera Utara] 2 [Perdesaan] 1 [Laki-laki]   885
##  8 12 [Sumatera Utara] 2 [Perdesaan] 2 [Perempuan]   904
##  9 13 [Sumatera Barat] 1 [Perkotaan] 1 [Laki-laki]   395
## 10 13 [Sumatera Barat] 1 [Perkotaan] 2 [Perempuan]   397
## # ℹ 124 more rows

10.1 Tabulasi 2 Arah

library(dplyr)
library(tidyr)
library(gt)
# Buat tabel agregat
tabel <- data_ssn %>%
  group_by(R101, R405) %>% #Perhatikan urutan. Mempengaruhi posisi pada tabel
  summarise(Mean_theta = mean(KAPITA, na.rm = TRUE), .groups = "drop")

# Pivot tabel agar sesuai dengan format tabel kustom (opsional, jika diperlukan format lebar)
tabel_wide <- tabel %>%
  pivot_wider(names_from = R405, values_from = Mean_theta)

# 3. Tambahkan kolom total baris
tabel_wide <- tabel_wide %>%
  mutate(Total_Baris = rowSums(select(., where(is.numeric)), na.rm = TRUE))

# Membuat tabel dengan gt
tabel_gt <- tabel_wide %>%
  gt() %>%
  tab_header(
    title = "Tabel 1. Rata-rata Kapita menurut Provinsi dan Jenis Kelamin, 2023",
    subtitle = "Sumber: Data 2023"
  ) %>%
  cols_label(
    R101 = "Provinsi",
    Total_Baris = "Total"
  )

# Menyimpan tabel ke file HTML
gtsave(tabel_gt, "tabel 2 arah.html")

library(writexl)
write_xlsx(tabel_wide, "tabel_2_arah.xlsx")

10.2 Tabulasi 3 Arah

library(dplyr)
library(tidyr)
library(gt)
# Buat tabel agregat
tabel <- data_ssn %>%
  group_by(R101, KABU, R405) %>% #Perhatikan urutan. Mempengaruhi posisi pada tabel
  summarise(Mean_theta = mean(KAPITA, na.rm = TRUE), .groups = "drop")

# Pivot tabel agar sesuai dengan format tabel kustom (opsional, jika diperlukan format lebar)
tabel_wide <- tabel %>%
  pivot_wider(names_from = R405, values_from = Mean_theta)

# 3. Tambahkan kolom total baris
tabel_wide <- tabel_wide %>%
  mutate(Total_Baris = rowSums(select(., where(is.numeric)), na.rm = TRUE))

# Membuat tabel dengan gt
tabel_gt <- tabel_wide %>%
  gt() %>%
  tab_header(
    title = "Tabel 1. Rata-rata Kapita menurut Provinsi, Kabupaten/kota dan Jenis Kelamin, 2023",
    subtitle = "Sumber: Data 2023"
  ) %>%
  cols_label(
    KABU = "Kabupaten/Kota",
    R101 = "Provinsi",
    Total_Baris = "Total"
  )

# Menyimpan tabel ke file HTML
gtsave(tabel_gt, "tabel 3 arah.html")

library(writexl)
write_xlsx(tabel_wide, "tabel_3_arah.xlsx")

https://rpubs.com/kaz_yos/rboot02

Direktorat Statistik Kesejahteraan Rakyat, BPS,