[MRG] Ignore and pass-through NaN values in MaxAbsScaler and maxabs_scale

doc/whats_new/v0.20.rst

@@ -230,6 +230,11 @@ Preprocessing
   :issue:`10404` and :issue:`11243` by :user:`Lucija Gregov <LucijaGregov>` and
   :user:`Guillaume Lemaitre <glemaitre>`.
 
+- :class:`preprocessing.MaxAbsScaler` and :func:`preprocessing.maxabs_scale`
+  handles and ignores NaN values.
+  :issue:`11011` by `Lucija Gregov <LucihaGregov>` and
+  :user:`Guillaume Lemaitre <glemaitre>`
+
 Model evaluation and meta-estimators
 
 - A scorer based on :func:`metrics.brier_score_loss` is also available.

sklearn/preprocessing/data.py

@@ -800,6 +800,9 @@ class MaxAbsScaler(BaseEstimator, TransformerMixin):
 
     Notes
     -----
+    NaNs are treated as missing values: disregarded in fit, and maintained in
+    transform.
+
     For a comparison of the different scalers, transformers, and normalizers,
     see :ref:`examples/preprocessing/plot_all_scaling.py
     <sphx_glr_auto_examples_preprocessing_plot_all_scaling.py>`.
@@ -851,13 +854,14 @@ def partial_fit(self, X, y=None):
             Ignored
         """
         X = check_array(X, accept_sparse=('csr', 'csc'), copy=self.copy,
-                        estimator=self, dtype=FLOAT_DTYPES)
+                        estimator=self, dtype=FLOAT_DTYPES,
+                        force_all_finite='allow-nan')
 
         if sparse.issparse(X):
-            mins, maxs = min_max_axis(X, axis=0)
+            mins, maxs = min_max_axis(X, axis=0, ignore_nan=True)
             max_abs = np.maximum(np.abs(mins), np.abs(maxs))
         else:
-            max_abs = np.abs(X).max(axis=0)
+            max_abs = np.nanmax(np.abs(X), axis=0)
 
         # First pass
         if not hasattr(self, 'n_samples_seen_'):
@@ -881,7 +885,8 @@ def transform(self, X):
         """
         check_is_fitted(self, 'scale_')
         X = check_array(X, accept_sparse=('csr', 'csc'), copy=self.copy,
-                        estimator=self, dtype=FLOAT_DTYPES)
+                        estimator=self, dtype=FLOAT_DTYPES,
+                        force_all_finite='allow-nan')
 
         if sparse.issparse(X):
             inplace_column_scale(X, 1.0 / self.scale_)
@@ -899,7 +904,8 @@ def inverse_transform(self, X):
         """
         check_is_fitted(self, 'scale_')
         X = check_array(X, accept_sparse=('csr', 'csc'), copy=self.copy,
-                        estimator=self, dtype=FLOAT_DTYPES)
+                        estimator=self, dtype=FLOAT_DTYPES,
+                        force_all_finite='allow-nan')
 
         if sparse.issparse(X):
             inplace_column_scale(X, self.scale_)
@@ -937,6 +943,9 @@ def maxabs_scale(X, axis=0, copy=True):
 
     Notes
     -----
+    NaNs are treated as missing values: disregarded to compute the statistics,
+    and maintained during the data transformation.
+
     For a comparison of the different scalers, transformers, and normalizers,
     see :ref:`examples/preprocessing/plot_all_scaling.py
     <sphx_glr_auto_examples_preprocessing_plot_all_scaling.py>`.
@@ -945,7 +954,8 @@ def maxabs_scale(X, axis=0, copy=True):
 
     # If copy is required, it will be done inside the scaler object.
     X = check_array(X, accept_sparse=('csr', 'csc'), copy=False,
-                    ensure_2d=False, dtype=FLOAT_DTYPES)
+                    ensure_2d=False, dtype=FLOAT_DTYPES,
+                    force_all_finite='allow-nan')
     original_ndim = X.ndim
 
     if original_ndim == 1:

sklearn/preprocessing/tests/test_common.py

@@ -8,9 +8,11 @@
 
 from sklearn.base import clone
 
+from sklearn.preprocessing import maxabs_scale
 from sklearn.preprocessing import minmax_scale
 from sklearn.preprocessing import quantile_transform
 
+from sklearn.preprocessing import MaxAbsScaler
 from sklearn.preprocessing import MinMaxScaler
 from sklearn.preprocessing import QuantileTransformer
 
@@ -27,7 +29,8 @@ def _get_valid_samples_by_column(X, col):
 
 @pytest.mark.parametrize(
     "est, func, support_sparse",
-    [(MinMaxScaler(), minmax_scale, False),
+    [(MaxAbsScaler(), maxabs_scale, True),
+     (MinMaxScaler(), minmax_scale, False),
      (QuantileTransformer(n_quantiles=10), quantile_transform, True)]
 )
 def test_missing_value_handling(est, func, support_sparse):

sklearn/utils/estimator_checks.py

@@ -77,7 +77,7 @@
                 'RandomForestRegressor', 'Ridge', 'RidgeCV']
 
 ALLOW_NAN = ['Imputer', 'SimpleImputer', 'MICEImputer',
-             'MinMaxScaler', 'QuantileTransformer']
+             'MinMaxScaler', 'MaxAbsScaler', 'QuantileTransformer']
 
 
 def _yield_non_meta_checks(name, estimator):