Exercise

Preparing employee data for safe release

When you deal with real data, you need to make sure that there's no way our customer's or other people's personal information can be traced or exposed. In this exercise, you'll use a simplified version of the IBM HR Analytics Employee dataset to practice suppression and generalization techniques.

To avoid leaking information about the dataset, you will replace the column names with numbers.

The DataFrame is loaded as hr, use the console to explore it. numpy is imported as np.

Instructions 1/3

undefined XP

1

2

3

Drop the unique values from hr.
Obtain df_cleaned by dropping the NaN values from df_dropped.