Joining HR data

HR Analytics: Exploring Employee Data in R

Ben Teusch

HR Analytics Consultant

HR data systems

employee data
recruiting/ATS data
benefits data
compensation data
timekeeping data
payroll data
performance data
... plus data from other business groups (Finance, IT, etc.)

Joining HR Data

hr_data

# A tibble: 2 × 2
  employee_id department 
        <dbl> <chr>      
1           1 Engineering
2           2 Sales

bonus_pay_data

# A tibble: 2 × 2
  employee_id bonus_amount
        <dbl>        <dbl>
1           1         3000
2           2        10000

left_join(hr_data, bonus_pay_data, by = "employee_id")

# A tibble: 2 × 3
  employee_id department  bonus_amount
        <dbl> <chr>              <dbl>
1           1 Engineering         3000
2           2 Sales              10000

Using left_join()

hr_data

# A tibble: 4 × 2
  employee_id department 
        <dbl> <chr>      
1           2 Engineering
2           3 Sales      
3           4 Engineering
4           5 Finance

bonus_pay_data

# A tibble: 4 × 2
  employee_id bonus_amount
        <dbl>        <dbl>
1           1         3000
2           2        10000
3           3         2500
4           5         4000

left_join(hr_data, bonus_pay_data, by = "employee_id")

# A tibble: 4 × 3
  employee_id department  bonus_amount
        <dbl> <chr>              <dbl>
1           2 Engineering        10000
2           3 Sales               2500
3           4 Engineering           NA
4           5 Finance             4000

Other joins

To learn more about other joins, refer to Joining Data in R with dplyr

Choosing a key for joining

Use unique identifiers such as employee id when joining data frames
Avoid using names

Let's practice!

HR Analytics: Exploring Employee Data in R