Proyek Data Mining Bagian Abelia
Abelia Permatasari
2025-05-23
R Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
summary(cars)## speed dist
## Min. : 4.0 Min. : 2.00
## 1st Qu.:12.0 1st Qu.: 26.00
## Median :15.0 Median : 36.00
## Mean :15.4 Mean : 42.98
## 3rd Qu.:19.0 3rd Qu.: 56.00
## Max. :25.0 Max. :120.00Including Plots
You can also embed plots, for example:
Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.
#Memuat Data
library(mlbench)## Warning: package 'mlbench' was built under R version 4.4.3library(dplyr)## Warning: package 'dplyr' was built under R version 4.4.3##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(readr)## Warning: package 'readr' was built under R version 4.4.3WA_Fn_UseC_HR_Employee_Attrition_csv <- read_csv("C:/Users/LENOVO/Downloads/WA_Fn-UseC_-HR-Employee-Attrition.csv.csv")## Rows: 1470 Columns: 35## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (9): Attrition, BusinessTravel, Department, EducationField, Gender, Job...
## dbl (26): Age, DailyRate, DistanceFromHome, Education, EmployeeCount, Employ...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.View(WA_Fn_UseC_HR_Employee_Attrition_csv)#Mengeksplor Dataset
str(WA_Fn_UseC_HR_Employee_Attrition_csv)## spc_tbl_ [1,470 × 35] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
## $ Age : num [1:1470] 41 49 37 33 27 32 59 30 38 36 ...
## $ Attrition : chr [1:1470] "Yes" "No" "Yes" "No" ...
## $ BusinessTravel : chr [1:1470] "Travel_Rarely" "Travel_Frequently" "Travel_Rarely" "Travel_Frequently" ...
## $ DailyRate : num [1:1470] 1102 279 1373 1392 591 ...
## $ Department : chr [1:1470] "Sales" "Research & Development" "Research & Development" "Research & Development" ...
## $ DistanceFromHome : num [1:1470] 1 8 2 3 2 2 3 24 23 27 ...
## $ Education : num [1:1470] 2 1 2 4 1 2 3 1 3 3 ...
## $ EducationField : chr [1:1470] "Life Sciences" "Life Sciences" "Other" "Life Sciences" ...
## $ EmployeeCount : num [1:1470] 1 1 1 1 1 1 1 1 1 1 ...
## $ EmployeeNumber : num [1:1470] 1 2 4 5 7 8 10 11 12 13 ...
## $ EnvironmentSatisfaction : num [1:1470] 2 3 4 4 1 4 3 4 4 3 ...
## $ Gender : chr [1:1470] "Female" "Male" "Male" "Female" ...
## $ HourlyRate : num [1:1470] 94 61 92 56 40 79 81 67 44 94 ...
## $ JobInvolvement : num [1:1470] 3 2 2 3 3 3 4 3 2 3 ...
## $ JobLevel : num [1:1470] 2 2 1 1 1 1 1 1 3 2 ...
## $ JobRole : chr [1:1470] "Sales Executive" "Research Scientist" "Laboratory Technician" "Research Scientist" ...
## $ JobSatisfaction : num [1:1470] 4 2 3 3 2 4 1 3 3 3 ...
## $ MaritalStatus : chr [1:1470] "Single" "Married" "Single" "Married" ...
## $ MonthlyIncome : num [1:1470] 5993 5130 2090 2909 3468 ...
## $ MonthlyRate : num [1:1470] 19479 24907 2396 23159 16632 ...
## $ NumCompaniesWorked : num [1:1470] 8 1 6 1 9 0 4 1 0 6 ...
## $ Over18 : chr [1:1470] "Y" "Y" "Y" "Y" ...
## $ OverTime : chr [1:1470] "Yes" "No" "Yes" "Yes" ...
## $ PercentSalaryHike : num [1:1470] 11 23 15 11 12 13 20 22 21 13 ...
## $ PerformanceRating : num [1:1470] 3 4 3 3 3 3 4 4 4 3 ...
## $ RelationshipSatisfaction: num [1:1470] 1 4 2 3 4 3 1 2 2 2 ...
## $ StandardHours : num [1:1470] 80 80 80 80 80 80 80 80 80 80 ...
## $ StockOptionLevel : num [1:1470] 0 1 0 0 1 0 3 1 0 2 ...
## $ TotalWorkingYears : num [1:1470] 8 10 7 8 6 8 12 1 10 17 ...
## $ TrainingTimesLastYear : num [1:1470] 0 3 3 3 3 2 3 2 2 3 ...
## $ WorkLifeBalance : num [1:1470] 1 3 3 3 3 2 2 3 3 2 ...
## $ YearsAtCompany : num [1:1470] 6 10 0 8 2 7 1 1 9 7 ...
## $ YearsInCurrentRole : num [1:1470] 4 7 0 7 2 7 0 0 7 7 ...
## $ YearsSinceLastPromotion : num [1:1470] 0 1 0 3 2 3 0 0 1 7 ...
## $ YearsWithCurrManager : num [1:1470] 5 7 0 0 2 6 0 0 8 7 ...
## - attr(*, "spec")=
## .. cols(
## .. Age = col_double(),
## .. Attrition = col_character(),
## .. BusinessTravel = col_character(),
## .. DailyRate = col_double(),
## .. Department = col_character(),
## .. DistanceFromHome = col_double(),
## .. Education = col_double(),
## .. EducationField = col_character(),
## .. EmployeeCount = col_double(),
## .. EmployeeNumber = col_double(),
## .. EnvironmentSatisfaction = col_double(),
## .. Gender = col_character(),
## .. HourlyRate = col_double(),
## .. JobInvolvement = col_double(),
## .. JobLevel = col_double(),
## .. JobRole = col_character(),
## .. JobSatisfaction = col_double(),
## .. MaritalStatus = col_character(),
## .. MonthlyIncome = col_double(),
## .. MonthlyRate = col_double(),
## .. NumCompaniesWorked = col_double(),
## .. Over18 = col_character(),
## .. OverTime = col_character(),
## .. PercentSalaryHike = col_double(),
## .. PerformanceRating = col_double(),
## .. RelationshipSatisfaction = col_double(),
## .. StandardHours = col_double(),
## .. StockOptionLevel = col_double(),
## .. TotalWorkingYears = col_double(),
## .. TrainingTimesLastYear = col_double(),
## .. WorkLifeBalance = col_double(),
## .. YearsAtCompany = col_double(),
## .. YearsInCurrentRole = col_double(),
## .. YearsSinceLastPromotion = col_double(),
## .. YearsWithCurrManager = col_double()
## .. )
## - attr(*, "problems")=<externalptr>levels(as.factor(WA_Fn_UseC_HR_Employee_Attrition_csv$Attrition))## [1] "No" "Yes"sapply(WA_Fn_UseC_HR_Employee_Attrition_csv, function(x) if(is.factor(x)) levels(x))## $Age
## NULL
##
## $Attrition
## NULL
##
## $BusinessTravel
## NULL
##
## $DailyRate
## NULL
##
## $Department
## NULL
##
## $DistanceFromHome
## NULL
##
## $Education
## NULL
##
## $EducationField
## NULL
##
## $EmployeeCount
## NULL
##
## $EmployeeNumber
## NULL
##
## $EnvironmentSatisfaction
## NULL
##
## $Gender
## NULL
##
## $HourlyRate
## NULL
##
## $JobInvolvement
## NULL
##
## $JobLevel
## NULL
##
## $JobRole
## NULL
##
## $JobSatisfaction
## NULL
##
## $MaritalStatus
## NULL
##
## $MonthlyIncome
## NULL
##
## $MonthlyRate
## NULL
##
## $NumCompaniesWorked
## NULL
##
## $Over18
## NULL
##
## $OverTime
## NULL
##
## $PercentSalaryHike
## NULL
##
## $PerformanceRating
## NULL
##
## $RelationshipSatisfaction
## NULL
##
## $StandardHours
## NULL
##
## $StockOptionLevel
## NULL
##
## $TotalWorkingYears
## NULL
##
## $TrainingTimesLastYear
## NULL
##
## $WorkLifeBalance
## NULL
##
## $YearsAtCompany
## NULL
##
## $YearsInCurrentRole
## NULL
##
## $YearsSinceLastPromotion
## NULL
##
## $YearsWithCurrManager
## NULLsummary(WA_Fn_UseC_HR_Employee_Attrition_csv)## Age Attrition BusinessTravel DailyRate
## Min. :18.00 Length:1470 Length:1470 Min. : 102.0
## 1st Qu.:30.00 Class :character Class :character 1st Qu.: 465.0
## Median :36.00 Mode :character Mode :character Median : 802.0
## Mean :36.92 Mean : 802.5
## 3rd Qu.:43.00 3rd Qu.:1157.0
## Max. :60.00 Max. :1499.0
## Department DistanceFromHome Education EducationField
## Length:1470 Min. : 1.000 Min. :1.000 Length:1470
## Class :character 1st Qu.: 2.000 1st Qu.:2.000 Class :character
## Mode :character Median : 7.000 Median :3.000 Mode :character
## Mean : 9.193 Mean :2.913
## 3rd Qu.:14.000 3rd Qu.:4.000
## Max. :29.000 Max. :5.000
## EmployeeCount EmployeeNumber EnvironmentSatisfaction Gender
## Min. :1 Min. : 1.0 Min. :1.000 Length:1470
## 1st Qu.:1 1st Qu.: 491.2 1st Qu.:2.000 Class :character
## Median :1 Median :1020.5 Median :3.000 Mode :character
## Mean :1 Mean :1024.9 Mean :2.722
## 3rd Qu.:1 3rd Qu.:1555.8 3rd Qu.:4.000
## Max. :1 Max. :2068.0 Max. :4.000
## HourlyRate JobInvolvement JobLevel JobRole
## Min. : 30.00 Min. :1.00 Min. :1.000 Length:1470
## 1st Qu.: 48.00 1st Qu.:2.00 1st Qu.:1.000 Class :character
## Median : 66.00 Median :3.00 Median :2.000 Mode :character
## Mean : 65.89 Mean :2.73 Mean :2.064
## 3rd Qu.: 83.75 3rd Qu.:3.00 3rd Qu.:3.000
## Max. :100.00 Max. :4.00 Max. :5.000
## JobSatisfaction MaritalStatus MonthlyIncome MonthlyRate
## Min. :1.000 Length:1470 Min. : 1009 Min. : 2094
## 1st Qu.:2.000 Class :character 1st Qu.: 2911 1st Qu.: 8047
## Median :3.000 Mode :character Median : 4919 Median :14236
## Mean :2.729 Mean : 6503 Mean :14313
## 3rd Qu.:4.000 3rd Qu.: 8379 3rd Qu.:20462
## Max. :4.000 Max. :19999 Max. :26999
## NumCompaniesWorked Over18 OverTime PercentSalaryHike
## Min. :0.000 Length:1470 Length:1470 Min. :11.00
## 1st Qu.:1.000 Class :character Class :character 1st Qu.:12.00
## Median :2.000 Mode :character Mode :character Median :14.00
## Mean :2.693 Mean :15.21
## 3rd Qu.:4.000 3rd Qu.:18.00
## Max. :9.000 Max. :25.00
## PerformanceRating RelationshipSatisfaction StandardHours StockOptionLevel
## Min. :3.000 Min. :1.000 Min. :80 Min. :0.0000
## 1st Qu.:3.000 1st Qu.:2.000 1st Qu.:80 1st Qu.:0.0000
## Median :3.000 Median :3.000 Median :80 Median :1.0000
## Mean :3.154 Mean :2.712 Mean :80 Mean :0.7939
## 3rd Qu.:3.000 3rd Qu.:4.000 3rd Qu.:80 3rd Qu.:1.0000
## Max. :4.000 Max. :4.000 Max. :80 Max. :3.0000
## TotalWorkingYears TrainingTimesLastYear WorkLifeBalance YearsAtCompany
## Min. : 0.00 Min. :0.000 Min. :1.000 Min. : 0.000
## 1st Qu.: 6.00 1st Qu.:2.000 1st Qu.:2.000 1st Qu.: 3.000
## Median :10.00 Median :3.000 Median :3.000 Median : 5.000
## Mean :11.28 Mean :2.799 Mean :2.761 Mean : 7.008
## 3rd Qu.:15.00 3rd Qu.:3.000 3rd Qu.:3.000 3rd Qu.: 9.000
## Max. :40.00 Max. :6.000 Max. :4.000 Max. :40.000
## YearsInCurrentRole YearsSinceLastPromotion YearsWithCurrManager
## Min. : 0.000 Min. : 0.000 Min. : 0.000
## 1st Qu.: 2.000 1st Qu.: 0.000 1st Qu.: 2.000
## Median : 3.000 Median : 1.000 Median : 3.000
## Mean : 4.229 Mean : 2.188 Mean : 4.123
## 3rd Qu.: 7.000 3rd Qu.: 3.000 3rd Qu.: 7.000
## Max. :18.000 Max. :15.000 Max. :17.000#Pembersihan Data
anyNA(WA_Fn_UseC_HR_Employee_Attrition_csv) #cek apakah ada NA## [1] FALSEcolSums(is.na(WA_Fn_UseC_HR_Employee_Attrition_csv)) #melihat jumlah nilai NA per kolom## Age Attrition BusinessTravel
## 0 0 0
## DailyRate Department DistanceFromHome
## 0 0 0
## Education EducationField EmployeeCount
## 0 0 0
## EmployeeNumber EnvironmentSatisfaction Gender
## 0 0 0
## HourlyRate JobInvolvement JobLevel
## 0 0 0
## JobRole JobSatisfaction MaritalStatus
## 0 0 0
## MonthlyIncome MonthlyRate NumCompaniesWorked
## 0 0 0
## Over18 OverTime PercentSalaryHike
## 0 0 0
## PerformanceRating RelationshipSatisfaction StandardHours
## 0 0 0
## StockOptionLevel TotalWorkingYears TrainingTimesLastYear
## 0 0 0
## WorkLifeBalance YearsAtCompany YearsInCurrentRole
## 0 0 0
## YearsSinceLastPromotion YearsWithCurrManager
## 0 0summary(WA_Fn_UseC_HR_Employee_Attrition_csv)## Age Attrition BusinessTravel DailyRate
## Min. :18.00 Length:1470 Length:1470 Min. : 102.0
## 1st Qu.:30.00 Class :character Class :character 1st Qu.: 465.0
## Median :36.00 Mode :character Mode :character Median : 802.0
## Mean :36.92 Mean : 802.5
## 3rd Qu.:43.00 3rd Qu.:1157.0
## Max. :60.00 Max. :1499.0
## Department DistanceFromHome Education EducationField
## Length:1470 Min. : 1.000 Min. :1.000 Length:1470
## Class :character 1st Qu.: 2.000 1st Qu.:2.000 Class :character
## Mode :character Median : 7.000 Median :3.000 Mode :character
## Mean : 9.193 Mean :2.913
## 3rd Qu.:14.000 3rd Qu.:4.000
## Max. :29.000 Max. :5.000
## EmployeeCount EmployeeNumber EnvironmentSatisfaction Gender
## Min. :1 Min. : 1.0 Min. :1.000 Length:1470
## 1st Qu.:1 1st Qu.: 491.2 1st Qu.:2.000 Class :character
## Median :1 Median :1020.5 Median :3.000 Mode :character
## Mean :1 Mean :1024.9 Mean :2.722
## 3rd Qu.:1 3rd Qu.:1555.8 3rd Qu.:4.000
## Max. :1 Max. :2068.0 Max. :4.000
## HourlyRate JobInvolvement JobLevel JobRole
## Min. : 30.00 Min. :1.00 Min. :1.000 Length:1470
## 1st Qu.: 48.00 1st Qu.:2.00 1st Qu.:1.000 Class :character
## Median : 66.00 Median :3.00 Median :2.000 Mode :character
## Mean : 65.89 Mean :2.73 Mean :2.064
## 3rd Qu.: 83.75 3rd Qu.:3.00 3rd Qu.:3.000
## Max. :100.00 Max. :4.00 Max. :5.000
## JobSatisfaction MaritalStatus MonthlyIncome MonthlyRate
## Min. :1.000 Length:1470 Min. : 1009 Min. : 2094
## 1st Qu.:2.000 Class :character 1st Qu.: 2911 1st Qu.: 8047
## Median :3.000 Mode :character Median : 4919 Median :14236
## Mean :2.729 Mean : 6503 Mean :14313
## 3rd Qu.:4.000 3rd Qu.: 8379 3rd Qu.:20462
## Max. :4.000 Max. :19999 Max. :26999
## NumCompaniesWorked Over18 OverTime PercentSalaryHike
## Min. :0.000 Length:1470 Length:1470 Min. :11.00
## 1st Qu.:1.000 Class :character Class :character 1st Qu.:12.00
## Median :2.000 Mode :character Mode :character Median :14.00
## Mean :2.693 Mean :15.21
## 3rd Qu.:4.000 3rd Qu.:18.00
## Max. :9.000 Max. :25.00
## PerformanceRating RelationshipSatisfaction StandardHours StockOptionLevel
## Min. :3.000 Min. :1.000 Min. :80 Min. :0.0000
## 1st Qu.:3.000 1st Qu.:2.000 1st Qu.:80 1st Qu.:0.0000
## Median :3.000 Median :3.000 Median :80 Median :1.0000
## Mean :3.154 Mean :2.712 Mean :80 Mean :0.7939
## 3rd Qu.:3.000 3rd Qu.:4.000 3rd Qu.:80 3rd Qu.:1.0000
## Max. :4.000 Max. :4.000 Max. :80 Max. :3.0000
## TotalWorkingYears TrainingTimesLastYear WorkLifeBalance YearsAtCompany
## Min. : 0.00 Min. :0.000 Min. :1.000 Min. : 0.000
## 1st Qu.: 6.00 1st Qu.:2.000 1st Qu.:2.000 1st Qu.: 3.000
## Median :10.00 Median :3.000 Median :3.000 Median : 5.000
## Mean :11.28 Mean :2.799 Mean :2.761 Mean : 7.008
## 3rd Qu.:15.00 3rd Qu.:3.000 3rd Qu.:3.000 3rd Qu.: 9.000
## Max. :40.00 Max. :6.000 Max. :4.000 Max. :40.000
## YearsInCurrentRole YearsSinceLastPromotion YearsWithCurrManager
## Min. : 0.000 Min. : 0.000 Min. : 0.000
## 1st Qu.: 2.000 1st Qu.: 0.000 1st Qu.: 2.000
## Median : 3.000 Median : 1.000 Median : 3.000
## Mean : 4.229 Mean : 2.188 Mean : 4.123
## 3rd Qu.: 7.000 3rd Qu.: 3.000 3rd Qu.: 7.000
## Max. :18.000 Max. :15.000 Max. :17.000#Membagi Dataset kedalam bentuk data training, data testing, dan data untuk prediksi
library(caTools) #library untuk pembagian dataset## Warning: package 'caTools' was built under R version 4.4.3set.seed(123)
# Hitung jumlah baris untuk training set
n <- nrow(WA_Fn_UseC_HR_Employee_Attrition_csv)
train_size <- floor(0.7 * n)
# Buat indeks acak
train_indices <- sample(seq_len(n), size = train_size)
# Split data
training_set <- WA_Fn_UseC_HR_Employee_Attrition_csv[train_indices, ]
test_set <- WA_Fn_UseC_HR_Employee_Attrition_csv[-train_indices, ]
dim(training_set) #Dimensi data training## [1] 1029 35dim(test_set) #Untuk melihat dimensi dari Data Testing yang sudah dibuat## [1] 441 35library(dplyr)
topredict_set <- test_set %>% select(-Attrition) #menghapus target Attrition
dim(topredict_set)## [1] 441 34#Naive Bayes Classifier
library(e1071)## Warning: package 'e1071' was built under R version 4.4.3library(caret)## Warning: package 'caret' was built under R version 4.4.3## Loading required package: ggplot2## Warning: package 'ggplot2' was built under R version 4.4.3## Loading required package: latticemodel_naive <- naiveBayes(Attrition ~ .,data = training_set) #Implementasi Naive Bayes
preds_naive <- predict(model_naive, newdata = topredict_set) #Memprediksi Target Class untuk validasi
(conf_matrix_naive <- table(preds_naive, test_set$Attrition))##
## preds_naive No Yes
## No 278 26
## Yes 88 49confusionMatrix(conf_matrix_naive) # script untuk mengetahui akurasi dari Metode Klasifikasi Naive Bayes## Confusion Matrix and Statistics
##
##
## preds_naive No Yes
## No 278 26
## Yes 88 49
##
## Accuracy : 0.7415
## 95% CI : (0.698, 0.7818)
## No Information Rate : 0.8299
## P-Value [Acc > NIR] : 1
##
## Kappa : 0.3108
##
## Mcnemar's Test P-Value : 1.109e-08
##
## Sensitivity : 0.7596
## Specificity : 0.6533
## Pos Pred Value : 0.9145
## Neg Pred Value : 0.3577
## Prevalence : 0.8299
## Detection Rate : 0.6304
## Detection Prevalence : 0.6893
## Balanced Accuracy : 0.7064
##
## 'Positive' Class : No
##