ValueError: Cannot setitem on a Categorical with a new category, set the categories first

[NicolasMICAUX]

When using Categorical columns, imputer.fit(train_df=df_train) raises error ValueError: Cannot setitem on a Categorical with a new category, set the categories first _validate_setitem_value, categorical.py:2044

stack is :

***pandas files ***
__init__, iterators.py:223 : data_frame = data_frame.fillna(value={x: "" for x in string_columns})
__build_iterators, imputer.py:592 : iter_train = ImputerIterDf(
fit, imputer.py:263 : iter_train, iter_test = self.__build_iterators(train_df, test_df, test_split)
fit, simple_imputer.py:386 : self.imputer = self.imputer.fit(train_df, test_df, ctx, learning_rate, num_epochs, patience,