Filtering the dataset
Employees at senior levels such as Vice President, Director, Senior Manager etc. have very different labor market conditions and are few in numbers too, hence, including them in your analysis can disproportionately affect your findings.
In this exercise, you will count the number of employees only at the Analyst and Specialist levels using the filter() function.
The following example filters df such that only the observations for which x is a or b or c are selected:
df %>%
filter(x %in% c("a", "b", "c"))
Latihan ini adalah bagian dari kursus
HR Analytics: Predicting Employee Churn in R
Petunjuk latihan
- First, count the number of employees across levels.
- Subset the data to retain employees only at the
AnalystandSpecialistlevels. - Review the number of employees across all levels, again.
Latihan interaktif praktis
Cobalah latihan ini dengan menyelesaikan kode contoh berikut.
# Count the number of employees across levels
org %>%
___(level)
# Select the employees at Analyst and Specialist level
org2 <- org %>%
___(level ___)
# Validate the results
org2 %>%
count(level)