library(tidyr)
library(ggplot2)
library(dplyr)
library(tidyverse) #


#import the data
employee <- read.csv(file="c:\\Users\\Asus\\OneDrive\\Desktop\\employee_attrition.csv",header=TRUE,sep=",")
employee
View(employee)


#Data exploration
head(employee,10)  #for first 10 lines
tail(employee,10)  #for last 10 lines
str(employee)      #displaying the internal structure of a datassets
class(employee)    #To check the class of the datasets
dim(employee)      #To check the dataset number of row and column
names(employee)    #To check the dataset column title
summary(employee)  #See the summary of the dataset
View(summary(employee)) #To see the summary of the dataset using table format


#Data Cleaning
employee$gender_full <-NULL
employee$birthdate_key <- NULL
#Change the entire dataset from Not Applicable to NA
Employee_Dataset<- employee[employee == "Not Applicable"] <- NA
View(Employee_Dataset)
#Remove the duplicate data by EmployeeID
Employee_Dataset<-employee[!rev(duplicated(rev(employee$`EmployeeID`))),]
#Remove the NA Value in the dataset
Employee_Attrition<-na.omit(Employee_Dataset)
rownames(Employee_Attrition) <- 1:nrow(Employee_Attrition)
View(Employee_Attrition)
#Data Processing
names(Employee_Attrition)=c("Employee_ID(PK)","Record_Date","Hire_Date","Termination_Date","Age",
                            "Length_of_Service","City","Department","Job_Title","Store_Number","Gender",
                            "Term_desc","Type_term","Status_Year","Status","Business_unit")
names(Employee_Attrition)



View(Employee_Dataset)
#how data stores




statusCount<-as.data.frame.matrix(Employee_Attrition %>%
                                    group_by(Status_Year) %>%
                                    select(Status) %>%
                                    table())
View(statusCount)


statusCount$Terminated<-statusCount$TERMINATED/1485*100


statusCount
View(statusCount)

mean(statusCount$TERMINATED)
#Analysis part


TerminateData<- Employee_Attrition %>% filter(Status=="TERMINATED")
#Status Year and Termination Description
ggplot(TerminateData)+geom_bar(aes(x=Status_Year, fill=Term_desc))+  labs(title="Status of termination", x="Status of year", y="Number of employee")

ggplot(TerminateData)+geom_bar(aes(x=Length_of_Service, fill=Status))
#Analysis 1-1
TerminateData_Department <-Employee_Attrition %>%
  filter(Status_Year >=2014 &Term_desc=="Layoff")
#Department and Termination Description
ggplot(TerminateData_Department)+geom_bar(aes(x=as.factor(Department),
                                                fill=as.factor(Term_desc)))+labs(title="Department Statistic", x="Department", y="Number of employee")+
  theme(axis.text.x = element_text(angle=90, hjust=1,vjust=0.5))

Layoff = TerminateData_Department[(TerminateData_Department$Term_desc=="Layoff")

  &(TerminateData_Department$Status_Year>=2014),]
#To show the number of layoff during 2014-2015
nrow(Layoff)

#Analysis 1-2
#Age and Length_of_Services
#TerminateData_Services <- Employee_Attrition %>%
 # filter(Status_Year>=2014 &Term_desc=="Layoff")

ggplot(aes(x=Age,y=Length_of_Service),data=TerminateData_Services)+
  geom_point()+
  xlim(20,67)+
  ylim(1,28)

#To check average of age and length of services during 2014-2015
TerminateData_Services<-select(Employee_Attrition,Age,Length_of_Service) %>%
  filter(Employee_Attrition$Status_Year>=2014, Employee_Attrition$Term_desc=="Layoff")

mean(TerminateData_Services$Length_of_Service) #11.94
mean(TerminateData_Services$Age) #40.80
 View(Employee_Attrition)
#Analysis 1-3
 TerminateData_Gender<-select(Employee_Attrition,Gender,Length_of_Service) %>%
  filter(Employee_Attrition$Status_Year>=2014,
                                         Employee_Attrition$Term_desc=="Layoff")

 ggplot(TerminateData_Gender,aes(y=Length_of_Service,x=Gender))+geom_boxplot()

###Analysis 1.3 (Last part)
#To show how many female being terminated
Female<-TerminateData_Gender[(TerminateData_Gender$Gender=="F"),]
rownames(Female) <- 1:nrow(Female)
nrow(Female)
max(Female$Length_of_Service)#25
min(Female$Length_of_Service)#1
mean(Female$Length_of_Service)#11.522

#To calculate all the female contribute how many length of services
Total_Female<-sum(TerminateData_Gender[which(TerminateData_Gender$Gender=="F"),2])
Female_Dataset<- subset(TerminateData_Gender,TerminateData_Gender$Gender=="F")
rownames(Female_Dataset) <- 1:nrow(Female_Dataset)
Female_Length_of_Service<-head(Female_Dataset,1)
Female_Length_of_Service$Length_of_Service <- NULL
Total_Female_Leng_Of_Service<-mutate(Female_Length_of_Service,Total_Length_of_Service=Total_Female)
View(Total_Female_Leng_Of_Service)


Male=TerminateData_Gender[(TerminateData_Gender$Gender=="M"),]
rownames(Male) <- 1:nrow(Male)
nrow(Male)
max(Male$Length_of_Service)#25
min(Male$Length_of_Service)#2
mean(Male$Length_of_Service)#12.42

Total_Male<-sum(TerminateData_Gender[which(TerminateData_Gender$Gender=="M"),2])


Male_Dataset<- subset(TerminateData_Gender,TerminateData_Gender$Gender=="M")
rownames(Male_Dataset) <- 1:nrow(Male_Dataset)
Male_Length_of_Service<-head(Male_Dataset,1)
Male_Length_of_Service$Length_of_Service <- NULL
Total_Male_Leng_Of_Service<-mutate(Male_Length_of_Service,Total_Length_of_Service=Total_Male)
View(Total_Male_Leng_Of_Service)


ggplot(TerminateData)+geom_bar(aes(x=as.factor(Department), fill=as.factor(Term_desc)))+
  theme(axis.text.x = element_text(angle=90, hjust=1,vjust=0.5))




AgeData<- Employee_Attrition %>% filter(Age <40 & Status=="TERMINATED")
#Age and Termination Description

ggplot(AgeData)+geom_bar(aes(x=Age, fill=Term_desc))
#Age and Length of service
ggplot(data=Employee_Attrition,aes(x=Age,y=Length_of_Service)) + geom_line()
#Scatter plot

#To show older will work how long for the services
#Age and Length of service

ggplot(Employee_Attrition, aes(x=Age,y=Length_of_Service, color=Age)) + geom_point() + xlim(10,60)+ ylim(0,25)

Employee_Dataset %>% filter(Age>20) %>% ggplot(aes(x=Length_of_Service)) + geom_density(fill="#69b3a2", color="#e9ecef", alpha=0.8)

Female_Terminated <- Employee_Attrition %>% filter(Status=="TERMINATED")

#Why many man gender to being termination
#Gender and length of services
p <- ggplot(Female_Terminated, aes(x= Length_of_Service, y = Gender))
p <- p +   geom_boxplot()

p <- p + theme_classic()
p <- p + coord_flip()
p <- p + labs(title = "Female Active Statistic")

p



bp
nrow(Employee_Attrition)
nrow(Employee_Attrition,Gender="F")