Praktikum Datmin

SOAL NO. 2

Import data

data <- read.csv("bank latih.csv", sep = ";")
head(data, 20)

Memeriksa apakah ada missing value

any(is.na(data))

## [1] FALSE

Artinya tidak ada data yang missing

Memeriksa apakah ada baris atau kolom yang duplikat

# baris
anyDuplicated(data)

## [1] 0

# kolom
duplicated_cols <- duplicated(t(data))
sum(duplicated_cols) 

## [1] 0

# memeriksa apakah ada variabel yang beda nama tapi memiliki arti yang sama 
cor_matrix <- cor(data[sapply(data, is.integer)])

library(pheatmap)

## Warning: package 'pheatmap' was built under R version 4.4.3

# Membuat heatmap dengan pheatmap
pheatmap(cor_matrix, 
         color = colorRampPalette(c("blue", "white", "red"))(50),
         main = "Heatmap Korelasi Kolom Integer")

Artinya tidak ada duplikat data baik di baris maupun kolom. Selain itu, berdasarkan hasil matriks korelasi di atas terlihat tidak ada korelasi yang kuat antar variabel sehingga dapat dikatakan bahwa tidak ada variabel yang redundan.

Memeriksa apakah ada kesalahan isian

# Untuk mengetahui tipe data setiap variabel
str(data)

## 'data.frame':    4521 obs. of  17 variables:
##  $ Age      : int  30 33 35 30 59 35 36 39 41 43 ...
##  $ job      : chr  "unemployed" "services" "management" "management" ...
##  $ marital  : chr  "married" "married" "single" "married" ...
##  $ education: chr  "primary" "secondary" "tertiary" "tertier" ...
##  $ default  : chr  "no" "no" "no" "no" ...
##  $ balance  : int  1787 4789 1350 1476 0 747 307 147 221 -88 ...
##  $ housing  : chr  "no" "yes" "yes" "yes" ...
##  $ loan     : chr  "no" "yes" "no" "yes" ...
##  $ contact  : chr  "cellular" "cellular" "cellular" "unknown" ...
##  $ day      : int  19 11 16 3 5 23 14 6 14 17 ...
##  $ month    : chr  "10" "may" "apr" "jun" ...
##  $ duration : int  79 220 185 199 226 141 341 151 57 313 ...
##  $ campaign : int  1 1 1 4 1 2 1 2 2 1 ...
##  $ pdays    : int  -1 339 330 -1 -1 176 330 -1 -1 147 ...
##  $ previous : int  0 4 1 0 0 3 2 0 0 2 ...
##  $ poutcome : chr  "unknown" "failure" "failure" "unknown" ...
##  $ y        : chr  "no" "no" "no" "no" ...

cat("\n")

# Untuk mengetahui ada apa saja macam isian dan untuk melihat apakah ada kata yang typo atau bersinonim
lapply(data[, sapply(data, is.character)], unique)

## $job
##  [1] "unemployed"    "services"      "management"    "blue-collar"  
##  [5] "self-employed" "technician"    "entrepreneur"  "admin."       
##  [9] "student"       "housemaid"     "retired"       "unknown"      
## 
## $marital
## [1] "married"  "single"   "menikah"  "divorced"
## 
## $education
## [1] "primary"   "secondary" "tertiary"  "tertier"   "sekunder"  "unknown"  
## 
## $default
## [1] "no"  "yes"
## 
## $housing
## [1] "no"    "yes"   "tidak"
## 
## $loan
## [1] "no"    "yes"   "tidak"
## 
## $contact
## [1] "cellular"  "unknown"   "seluler"   "telephone"
## 
## $month
##  [1] "10"  "may" "apr" "jun" "feb" "aug" "jan" "7"   "nov" "jul" "oct" "sep"
## [13] "mar" "dec"
## 
## $poutcome
## [1] "unknown" "failure" "other"   "success"
## 
## $y
## [1] "no"  "iya" "yes"

• Ada beberapa isian yang bersinonim sehingga harus disesuaikan contohnya no dan tidak, married dan menikah, tertiary dan tertier, secondary dan sekunder, cellular dan seluler, yes dan iya
• Terdapat data yang tidak sesuai dengan tipe data variabel tersebut contohnya variabel month bertipe char namun ada isian dalam bentuk angka.

Mengganti isian yang salah

library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

# Mengganti "tidak" dengan "no" di variabel housing dan loan
data <- data %>%
  mutate(across(c(housing, loan), ~ gsub("tidak", "no", .)))

# Mengganti "menikah" denagn "married" di variabel marital
data <- data %>%
  mutate(across(marital, ~ gsub("menikah", "married", .)))

# Mengganti "tertier" denagn "tertiary" di variabel education
data <- data %>%
  mutate(education = case_when(
    education == "tertier"  ~ "tertiary",
    education == "sekunder" ~ "secondary",
    TRUE ~ education 
  ))

# Mengganti "seluler" dengan "cellular" di variabel contact
data <- data %>%
  mutate(across(contact, ~ gsub("seluler", "cellular", .)))

# Megganti "iya" dengan "yes" di variabel y
data <- data %>%
  mutate(across(y, ~ gsub("iya", "yes", .)))

nama_bulan <- c("jan", "feb", "mar", "apr", "may", "jun", "jul", "aug", "sep", "oct", "nov", "dec")

data <- data %>% 
  mutate(month = ifelse(month %in% as.character(1:12), 
                        nama_bulan[as.numeric(month)], 
                        month))

## Warning: There was 1 warning in `mutate()`.
## ℹ In argument: `month = ifelse(...)`.
## Caused by warning in `ifelse()`:
## ! NAs introduced by coercion

# dicek lagi 
lapply(data[, sapply(data, is.character)], unique)

## $job
##  [1] "unemployed"    "services"      "management"    "blue-collar"  
##  [5] "self-employed" "technician"    "entrepreneur"  "admin."       
##  [9] "student"       "housemaid"     "retired"       "unknown"      
## 
## $marital
## [1] "married"  "single"   "divorced"
## 
## $education
## [1] "primary"   "secondary" "tertiary"  "unknown"  
## 
## $default
## [1] "no"  "yes"
## 
## $housing
## [1] "no"  "yes"
## 
## $loan
## [1] "no"  "yes"
## 
## $contact
## [1] "cellular"  "unknown"   "telephone"
## 
## $month
##  [1] "oct" "may" "apr" "jun" "feb" "aug" "jan" "jul" "nov" "sep" "mar" "dec"
## 
## $poutcome
## [1] "unknown" "failure" "other"   "success"
## 
## $y
## [1] "no"  "yes"

head(data, 20)

#Graphical Boxplot Test
par(mfrow = c(2, 2))

# Pilih kolom numerik saja
num_cols <- sapply(data, is.numeric)

# Loop hanya untuk kolom numerik
for(i in which(num_cols)) {
  boxplot(data[[i]], main = names(data)[i])
}

library(writexl)

## Warning: package 'writexl' was built under R version 4.4.3

write_xlsx(data, "hasil_prepo_bank.xlsx")