@@ -254,11 +254,56 @@ def test_mutable_train_data_fit_transform(self, mocker: MockerFixture):
254254 }
255255 ),
256256 ),
257+ # example 4 categorical
258+ (
259+ pd .DataFrame (
260+ {
261+ "a" : [1 , 8 , np .nan ],
262+ "b" : [np .nan , np .nan , np .nan ],
263+ "d" : [np .nan , np .nan , 5 ],
264+ "e" : [1 , 960 , np .nan ],
265+ "category_1" : ["A" , "A" , "B" ],
266+ "category_2" : [np .nan , "A" , "B" ],
267+ "category_3" : [np .nan , np .nan , np .nan ],
268+ },
269+ ).astype (
270+ {
271+ "a" : np .float64 (),
272+ "b" : np .float64 (),
273+ "d" : np .float64 (),
274+ "e" : np .float64 (),
275+ "category_1" : pd .CategoricalDtype (),
276+ "category_2" : pd .CategoricalDtype (),
277+ "category_3" : pd .CategoricalDtype (),
278+ }
279+ ),
280+ pd .DataFrame (
281+ {
282+ "a" : [1 , 8 , np .nan ],
283+ "d" : [np .nan , np .nan , 5 ],
284+ "e" : [1 , 960 , np .nan ],
285+ "category_1" : ["A" , "A" , "B" ],
286+ "category_2" : [np .nan , "A" , "B" ],
287+ }
288+ ).astype (
289+ {
290+ "a" : np .float64 (),
291+ "d" : np .float64 (),
292+ "e" : np .float64 (),
293+ "category_1" : pd .CategoricalDtype (),
294+ "category_2" : pd .CategoricalDtype (),
295+ }
296+ ),
297+ ),
257298 ],
258299 )
259300 def test_drops_columns_containing_only_nan (self , input , expected ):
260301
302+ print (input )
261303 output = PreProcessor ._check_nan_columns_and_drop_columns_containing_only_nan (
262304 input
263305 )
306+
307+ print (output )
308+ print (expected )
264309 assert output .equals (expected )
0 commit comments