Tabular - FillMissing for categorical

Just curious how the Tabular FillMissing proc handles categorical?

df = pd.read_csv(path/'adult.csv')
df.loc[0:1000, 'workclass'] = np.nan

Would it just treat the nans as a class or use some other place holder e.g. unknown

It uses a third (if it’s T/F) category of unknown

1 Like

Thanks @muellerzr

Hi, Zachary,
Can I say fillmissing only add a new boolean column for a column with missing values when the column is numeric? Thanks.