Employee Data Management

#the dataset
emp_id <- c(101, 102, 103, 104, 105, 106)
emp_name <- c("john", "anna", "mary", "ryan", "peter", "ruth")
salary <- c(65000, 80000, 54000, 75000, 95000, 56000)
start_date <- as.Date(c("2022-01-01", "2023-09-23", "2024-11-22", "2022-05-11", "2019-03-27", "2020-03-02"))
gender <- c("male", "female", "female", "male", "male", "female")

emp.data <- data.frame(emp_id, emp_name, salary, start_date, gender)

#Displaying the dataset
print(emp.data)

##   emp_id emp_name salary start_date gender
## 1    101     john  65000 2022-01-01   male
## 2    102     anna  80000 2023-09-23 female
## 3    103     mary  54000 2024-11-22 female
## 4    104     ryan  75000 2022-05-11   male
## 5    105    peter  95000 2019-03-27   male
## 6    106     ruth  56000 2020-03-02 female

#Summary 
print(summary(emp.data))

##      emp_id        emp_name             salary        start_date        
##  Min.   :101.0   Length:6           Min.   :54000   Min.   :2019-03-27  
##  1st Qu.:102.2   Class :character   1st Qu.:58250   1st Qu.:2020-08-16  
##  Median :103.5   Mode  :character   Median :70000   Median :2022-03-07  
##  Mean   :103.5                      Mean   :70833   Mean   :2022-01-23  
##  3rd Qu.:104.8                      3rd Qu.:78750   3rd Qu.:2023-05-21  
##  Max.   :106.0                      Max.   :95000   Max.   :2024-11-22  
##     gender         
##  Length:6          
##  Class :character  
##  Mode  :character  
##                    
##                    
## 

#Structure of the data frame
str(emp.data)

## 'data.frame':    6 obs. of  5 variables:
##  $ emp_id    : num  101 102 103 104 105 106
##  $ emp_name  : chr  "john" "anna" "mary" "ryan" ...
##  $ salary    : num  65000 80000 54000 75000 95000 56000
##  $ start_date: Date, format: "2022-01-01" "2023-09-23" ...
##  $ gender    : chr  "male" "female" "female" "male" ...

#High earners
high_earners <- emp.data[emp.data$salary >= 75000, ]
print(high_earners)

##   emp_id emp_name salary start_date gender
## 2    102     anna  80000 2023-09-23 female
## 4    104     ryan  75000 2022-05-11   male
## 5    105    peter  95000 2019-03-27   male

#Ordering the records in descending order
emp.data_sorted_desc <- emp.data[order(-emp.data$salary), ]
print(emp.data_sorted_desc)

##   emp_id emp_name salary start_date gender
## 5    105    peter  95000 2019-03-27   male
## 2    102     anna  80000 2023-09-23 female
## 4    104     ryan  75000 2022-05-11   male
## 1    101     john  65000 2022-01-01   male
## 6    106     ruth  56000 2020-03-02 female
## 3    103     mary  54000 2024-11-22 female

# Bar chart of employee salaries
library(ggplot2)
ggplot(emp.data, aes(x = emp_name, y = salary)) +
  geom_bar(stat = "identity", fill = "steelblue") +
  theme_minimal() +
  labs(title = "Employee Salaries", x = "Employee Name", y = "Salary")