Corroborate the splits
In the previous exercise, you split the dataset into train_set and test_set. It's important to make sure that the data you are training your model is representative of the test set. So let's make sure both train_set and test_set have the same proportion of active and inactive employees.
本练习是课程的一部分
HR Analytics: Predicting Employee Churn in R
练习说明
Calculate the proportion of Active and Inactive employees in train_set and test_set.
交互式实操练习
通过完成这段示例代码来试试这个练习。
# Calculate turnover proportion in train_set
train_set %>%
___(status) %>%
___(prop = n / sum(n))
# Calculate turnover proportion in test_set
test_set %>%
___(status) %>%
___(prop = n / sum(n))