Tugas Data Analitical 1
Albert
July 23, 2018
Summary of the lesson
- R is Case-Sensitive,
- activity <-“Program”
- activity ==“program”
- You will need to use install.packages() to install any packages that are not already downloaded onto your machine. You then load the package into your workspace using the library() function:
- library(skimr)
- library(dplyr)
R Programming Basic
- Vectors, Speaking of objects, R objects can take on one of five classes:
- character <- c(“andi”, “albert”, “alb3r7”)
- numeric <- c(-1, 1, 2, 3/4, 0.5)
- integer <- c(1L, 2L)
- complex <- c(1+3i, (1+3i)*2)
- logical <- c(TRUE, TRUE, FALSE)
- E.g:
#contoh membuat vector dan memberikan label nama
vector1 <- c("andi", "albert", "alb3r7")
names(vector1) <- c("Nama1","Nama2","Nama3")
#cara print/ melihat vector
print (vector1)## Nama1 Nama2 Nama3
## "andi" "albert" "alb3r7"#melihat class vector dan panjang/jumlah
class (vector1)## [1] "character"length(vector1)## [1] 3#mengubah kelas vector "as.xxxx", as.logical, as.character, dll- Matriks
When we create a vector and give it a dimension attribute, we end up with a matrix:
#contoh buat matriks, munculn dan melihat dimensi nya
matrix1 <- matrix(11:16, nrow=3, ncol=2)
matrix1## [,1] [,2]
## [1,] 11 14
## [2,] 12 15
## [3,] 13 16dim(matrix1)## [1] 3 2# matrix [1,] = row semuanya pada kolom 1
matrix1 [1,]## [1] 11 14# matrix [,1] = kolom semuanya pada row 1
matrix1 [,1]## [1] 11 12 13accounts <- c("alfa", "indo", "asia")
sales <- c(400,320,380)
returns <- c(0,0,480)
netsales <- sales - returns
# cbind = bind as columns
# rbind = bind as rows
# rbind(accounts, sales, returns)
sales_records <- cbind(accounts, sales, netsales)
sales_records## accounts sales netsales
## [1,] "alfa" "400" "400"
## [2,] "indo" "320" "320"
## [3,] "asia" "380" "-100"sales_records <- rbind(accounts, sales, netsales)
sales_records## [,1] [,2] [,3]
## accounts "alfa" "indo" "asia"
## sales "400" "320" "380"
## netsales "400" "320" "-100"- List
#bisa memuat vector dengan class yang berbeda beda
our.list <- list(TRUE, "TRUE", c(1,6,12), 1+5i)
our.list## [[1]]
## [1] TRUE
##
## [[2]]
## [1] "TRUE"
##
## [[3]]
## [1] 1 6 12
##
## [[4]]
## [1] 1+5iFactor suatu kelas data yang memiliki pengaruh atau menentukan keputusan dalam suatu rangkaian data, contoh kredit (kolek, jenis usaha, lama usaha, dll).
Data frame Data frames can be thought of as a special case of lists where every element of the list has to have the same length. Each element of the list can be thought of as a column in the data frame.
categories_df <- data.frame(categories=c("OfficeSupplies", "Computers", "Packaging", "Machinery", "Building"), category_id=111:115)
categories_df## categories category_id
## 1 OfficeSupplies 111
## 2 Computers 112
## 3 Packaging 113
## 4 Machinery 114
## 5 Building 115categories_df$category_id + 1## [1] 112 113 114 115 116Programing with DATA Set (Dive DEEPER)
- analisa data awal
- First make sure the data you’ll like to work with is also in your current directory, and use the read.csv() to read our csv file into your global environment, For Example:
library(readxl)
debitur <- read_xlsx("C:/Users/User/Desktop/Albert Analitical/data tugas 1.xlsx")
# data tersebut adalah contoh data2 debitur bca yang telah disamarkan nama, cis, jmlh plafond, dll
names (debitur) #untuk melihat judul data## [1] "INT_RATE_FINAL" "OS_AMOUNT_IDR" "PLAFOND_AMOUNT_IDR"
## [4] "FAC_DSC" "CIS" "BCA_COM_SECTOR_CD"
## [7] "CORE_BUSINESS" "MARITAL_STATUS_CD" "KAT"
## [10] "BIZ_CITY_DESC" "BIZ_ZIP" "BCA_DEBTOR_SINCE"
## [13] "BCA_CUST_SINCE" "TGL_MEMO" "BRANCH_CD"
## [16] "TGL_KEPUTUSAN" "IS_OWNER_GUARANTEE" "APP_TYPE_CD"
## [19] "JENIS_MEMO"str(debitur) #untuk melihat struktur data## Classes 'tbl_df', 'tbl' and 'data.frame': 999 obs. of 19 variables:
## $ INT_RATE_FINAL : num 12.5 13 11 12.2 12 ...
## $ OS_AMOUNT_IDR : num 6.96e+08 5.65e+08 9.30e+08 0.00 1.80e+09 ...
## $ PLAFOND_AMOUNT_IDR: num 7.0e+08 8.0e+08 9.5e+08 1.0e+09 4.5e+09 ...
## $ FAC_DSC : chr "Kredit Lokal" "Kredit Lokal" "Kredit Modal Kerja" "Kredit Modal Kerja" ...
## $ CIS : num 2.13e+10 2.13e+10 2.13e+10 2.14e+10 2.14e+10 ...
## $ BCA_COM_SECTOR_CD : chr "33" "33" "32" "17" ...
## $ CORE_BUSINESS : chr "Perdagangan Keramik" "Perdagangan Keramik" "Jasa konstruksi" "Industri Sparepart Mobil (Produk PVC)" ...
## $ MARITAL_STATUS_CD : chr "001" "001" "X" "X" ...
## $ KAT : chr "S" "S" "S" "M" ...
## $ BIZ_CITY_DESC : chr "KAB. SUKOHARJO" "KAB. SUKOHARJO" "KAB. JEMBER" "KAB. TANGERANG" ...
## $ BIZ_ZIP : chr "57552" "57552" "68135" "15560" ...
## $ BCA_DEBTOR_SINCE : chr "0" "0" "0" "0" ...
## $ BCA_CUST_SINCE : chr "08/02/2012" "08/02/2012" "15/12/2016" "13/09/1991" ...
## $ TGL_MEMO : POSIXct, format: "2017-09-06" "2017-09-06" ...
## $ BRANCH_CD : chr "7850" "7850" "0024" "0971" ...
## $ TGL_KEPUTUSAN : POSIXct, format: "2017-10-25" "2017-10-25" ...
## $ IS_OWNER_GUARANTEE: chr "N" "N" "N" "N" ...
## $ APP_TYPE_CD : chr "SME" "SME" "SME" "KOMERSIAL" ...
## $ JENIS_MEMO : chr "Baru" "Baru" "Baru" "Baru" ...nrow(debitur) #untuk melihat jumlah row## [1] 999ncol(debitur) #untuk melihat jumlah coloum## [1] 19head (debitur) #untuk melihat 6 data teratas## # A tibble: 6 x 19
## INT_RATE_FINAL OS_AMOUNT_IDR PLAFOND_AMOUNT_~ FAC_DSC CIS
## <dbl> <dbl> <dbl> <chr> <dbl>
## 1 12.5 695980423 700000000 Kredit~ 2.13e10
## 2 13 564533594 800000000 Kredit~ 2.13e10
## 3 11 930399221 950000000 Kredit~ 2.13e10
## 4 12.2 0 1000000000 Kredit~ 2.14e10
## 5 12 1802685958 4500000000 Kredit~ 2.14e10
## 6 12 2550000000 2550000000 Kredit~ 2.14e10
## # ... with 14 more variables: BCA_COM_SECTOR_CD <chr>,
## # CORE_BUSINESS <chr>, MARITAL_STATUS_CD <chr>, KAT <chr>,
## # BIZ_CITY_DESC <chr>, BIZ_ZIP <chr>, BCA_DEBTOR_SINCE <chr>,
## # BCA_CUST_SINCE <chr>, TGL_MEMO <dttm>, BRANCH_CD <chr>,
## # TGL_KEPUTUSAN <dttm>, IS_OWNER_GUARANTEE <chr>, APP_TYPE_CD <chr>,
## # JENIS_MEMO <chr>tail (debitur) #untuk melihat 6 data terbawah## # A tibble: 6 x 19
## INT_RATE_FINAL OS_AMOUNT_IDR PLAFOND_AMOUNT_~ FAC_DSC CIS
## <dbl> <dbl> <dbl> <chr> <dbl>
## 1 13.8 882999999 890000000 Kredit~ 2.13e10
## 2 13.5 1374558701 2000000000 Kredit~ 2.14e10
## 3 9 13888269 13888269 KUR - ~ 2.13e10
## 4 12 2304716610 3000000000 Kredit~ 2.14e10
## 5 12.8 1561858776 1561858776 Instal~ 2.14e10
## 6 13 926044238. 930000000 Kredit~ 2.14e10
## # ... with 14 more variables: BCA_COM_SECTOR_CD <chr>,
## # CORE_BUSINESS <chr>, MARITAL_STATUS_CD <chr>, KAT <chr>,
## # BIZ_CITY_DESC <chr>, BIZ_ZIP <chr>, BCA_DEBTOR_SINCE <chr>,
## # BCA_CUST_SINCE <chr>, TGL_MEMO <dttm>, BRANCH_CD <chr>,
## # TGL_KEPUTUSAN <dttm>, IS_OWNER_GUARANTEE <chr>, APP_TYPE_CD <chr>,
## # JENIS_MEMO <chr>head (debitur,10)#untuk melihat data teratas, (x) sesuai jumlah yang kita inginkan## # A tibble: 10 x 19
## INT_RATE_FINAL OS_AMOUNT_IDR PLAFOND_AMOUNT_~ FAC_DSC CIS
## <dbl> <dbl> <dbl> <chr> <dbl>
## 1 12.5 695980423 700000000 Kredit~ 2.13e10
## 2 13 564533594 800000000 Kredit~ 2.13e10
## 3 11 930399221 950000000 Kredit~ 2.13e10
## 4 12.2 0 1000000000 Kredit~ 2.14e10
## 5 12 1802685958 4500000000 Kredit~ 2.14e10
## 6 12 2550000000 2550000000 Kredit~ 2.14e10
## 7 12 3765177768 3765177768 Kredit~ 2.14e10
## 8 12 1275000000 1275000000 Kredit~ 2.14e10
## 9 13.5 2972665707 3000000000 Kredit~ 2.13e10
## 10 13 1248946207 1248946207 Kredit~ 2.13e10
## # ... with 14 more variables: BCA_COM_SECTOR_CD <chr>,
## # CORE_BUSINESS <chr>, MARITAL_STATUS_CD <chr>, KAT <chr>,
## # BIZ_CITY_DESC <chr>, BIZ_ZIP <chr>, BCA_DEBTOR_SINCE <chr>,
## # BCA_CUST_SINCE <chr>, TGL_MEMO <dttm>, BRANCH_CD <chr>,
## # TGL_KEPUTUSAN <dttm>, IS_OWNER_GUARANTEE <chr>, APP_TYPE_CD <chr>,
## # JENIS_MEMO <chr>- Pengolahan data lanjutan untuk mengubah kelas dari sebuah data serta jika dia berupa tanggal, harus disesuaikan format tanggalnya,
- Konversi kolom as.Date() # %d (date) # %m month (number ) # %b month (abbreviated) # %B month (full name) # %y year ( 2 digit) # %Y year (4 digit)
contoh:
debitur$TGL_MEMO.baru <- as.Date(debitur$TGL_MEMO, "%m/%d/%Y")## Warning in as.POSIXlt.POSIXct(x, tz = tz): unknown timezone '%m/%d/%Y'#untuk mengambil bulan saja, to get months on date type.
debitur$TGL_MEMO.bulan<-months(debitur$TGL_MEMO)
head (debitur)## # A tibble: 6 x 21
## INT_RATE_FINAL OS_AMOUNT_IDR PLAFOND_AMOUNT_~ FAC_DSC CIS
## <dbl> <dbl> <dbl> <chr> <dbl>
## 1 12.5 695980423 700000000 Kredit~ 2.13e10
## 2 13 564533594 800000000 Kredit~ 2.13e10
## 3 11 930399221 950000000 Kredit~ 2.13e10
## 4 12.2 0 1000000000 Kredit~ 2.14e10
## 5 12 1802685958 4500000000 Kredit~ 2.14e10
## 6 12 2550000000 2550000000 Kredit~ 2.14e10
## # ... with 16 more variables: BCA_COM_SECTOR_CD <chr>,
## # CORE_BUSINESS <chr>, MARITAL_STATUS_CD <chr>, KAT <chr>,
## # BIZ_CITY_DESC <chr>, BIZ_ZIP <chr>, BCA_DEBTOR_SINCE <chr>,
## # BCA_CUST_SINCE <chr>, TGL_MEMO <dttm>, BRANCH_CD <chr>,
## # TGL_KEPUTUSAN <dttm>, IS_OWNER_GUARANTEE <chr>, APP_TYPE_CD <chr>,
## # JENIS_MEMO <chr>, TGL_MEMO.baru <date>, TGL_MEMO.bulan <chr>Programing with DATA Set (using table, xtabs, aggregate)
#table digunakan untuk membuat conditional subsetting, tapi hanya 2 kriteria, contoh menampilkan seluruh jumlah pengolahan (jenis memo) kategori K :
debitur.K <- debitur [debitur$KAT == "K",]
table (debitur.K$KAT, debitur.K$JENIS_MEMO)##
## Baru Penambahan Pengurangan Penukaran Perpanjangan
## K 82 2 1 2 1# menampilkan persentase debitur Baru pada kategori K
prop.table (table(debitur.K$KAT, debitur.K$JENIS_MEMO))*100##
## Baru Penambahan Pengurangan Penukaran Perpanjangan
## K 93.181818 2.272727 1.136364 2.272727 1.136364#xtabs digunakan untuk membuat conditional subsetting lebih dari 2), contoh menampilkan amount KAtegori debitur berdasarkan jenis memo
xtabs(OS_AMOUNT_IDR ~ KAT + JENIS_MEMO,debitur)## JENIS_MEMO
## KAT Baru Lain-lain Penambahan Pengurangan Penukaran
## K 3.131867e+10 0.000000e+00 7.182619e+08 1.687500e+08 1.106548e+09
## M 2.883192e+11 0.000000e+00 1.011126e+11 0.000000e+00 0.000000e+00
## S 1.242954e+12 1.012833e+09 1.543201e+11 4.995590e+08 3.500000e+08
## JENIS_MEMO
## KAT Perpanjangan Perpanjangan - BS
## K 2.500000e+08 0.000000e+00
## M 1.434326e+09 0.000000e+00
## S 2.222660e+10 1.221180e+09xtabs(OS_AMOUNT_IDR ~ KAT + MARITAL_STATUS_CD,debitur [debitur$JENIS_MEMO=="Baru",])## MARITAL_STATUS_CD
## KAT 001 002 003 005 X
## K 22285235361 852107087 887410344 0 7293921096
## M 65593125146 33601167874 0 6558922602 182565987740
## S 412823089215 22949583045 19940032915 29075041306 758166002255#aggregate digunakan untuk membuat conditional subsetting lebih dari 2 dan bisa diberi function ato kriteria lain.
aggregate(OS_AMOUNT_IDR ~ KAT + JENIS_MEMO,debitur,sum)## KAT JENIS_MEMO OS_AMOUNT_IDR
## 1 K Baru 3.131867e+10
## 2 M Baru 2.883192e+11
## 3 S Baru 1.242954e+12
## 4 S Lain-lain 1.012833e+09
## 5 K Penambahan 7.182619e+08
## 6 M Penambahan 1.011126e+11
## 7 S Penambahan 1.543201e+11
## 8 K Pengurangan 1.687500e+08
## 9 S Pengurangan 4.995590e+08
## 10 K Penukaran 1.106548e+09
## 11 S Penukaran 3.500000e+08
## 12 K Perpanjangan 2.500000e+08
## 13 M Perpanjangan 1.434326e+09
## 14 S Perpanjangan 2.222660e+10
## 15 S Perpanjangan - BS 1.221180e+09#untuk membuat cross-tabulation
plot(xtabs(OS_AMOUNT_IDR ~ KAT + JENIS_MEMO,debitur))
#untuk membuat cross-tabulation heat maps, Colv untuk diagram kolom, Rowv untuk diagram Row, cexCol untuk ukurantulisan kolom
heatmap (xtabs(OS_AMOUNT_IDR ~ KAT + JENIS_MEMO,debitur),Colv = NA, Rowv = NA, cexCol = 1,cexRow=1,scale = "column")