Improve error message in ColumnTransformer parser (#792)

* Improves error message in ColumnTransformer parser * fix attribute error
onnx · Nov 25, 2021 · da34917 · da34917
1 parent 9330cde
commit da34917
Show file tree

Hide file tree

Showing 5 changed files with 151 additions and 97 deletions.
diff --git a/skl2onnx/_parse.py b/skl2onnx/_parse.py
@@ -223,9 +223,20 @@ def _parse_sklearn_simple_model(scope, model, inputs, custom_parsers=None,
         variable = scope.declare_local_variable('variable', otype)
         this_operator.outputs.append(variable)
     else:
-        # We assume that all scikit-learn operator produce a single output.
+        if hasattr(model, 'get_feature_names_out'):
+            try:
+                out_names = model.get_feature_names_out()
+            except AttributeError:
+                # Catch a bug in scikit-learn.
+                out_names = None
+            this_operator.feature_names_out_ = out_names
+            if out_names is not None and len(out_names) == 0:
+                raise RuntimeError(
+                    "get_feature_names_out() cannot return an empty value, "
+                    "model is %r." % type(model))
+        input_type = guess_tensor_type(inputs[0].type)
         variable = scope.declare_local_variable(
-            'variable', guess_tensor_type(inputs[0].type))
+            'variable', input_type)
         this_operator.outputs.append(variable)
 
     options = scope.get_options(model, dict(decision_path=False), fail=False)

diff --git a/skl2onnx/_supported_operators.py b/skl2onnx/_supported_operators.py
@@ -2,6 +2,7 @@
 
 
 import warnings
+import logging
 
 # Calibrated classifier CV
 from sklearn.calibration import CalibratedClassifierCV
@@ -241,6 +242,8 @@
 
 from .common._registration import register_converter, register_shape_calculator
 
+logger = logging.getLogger('skl2onnx')
+
 # In most cases, scikit-learn operator produces only one output.
 # However, each classifier has basically two outputs; one is the
 # predicted label and the other one is the probabilities of all
@@ -505,9 +508,12 @@ def _get_sklearn_operator_name(model_type):
              our conversion framework
     """
     if model_type not in sklearn_operator_name_map:
-        # "No proper operator name found, it means a local operator.
-        return None
-    return sklearn_operator_name_map[model_type]
+        # No proper operator name found, it means a local operator.
+        alias = None
+    else:
+        alias = sklearn_operator_name_map[model_type]
+    logger.debug('[parsing] found alias=%r for type=%r.', alias, model_type)
+    return alias
 
 
 def get_model_alias(model_type):

diff --git a/skl2onnx/common/utils.py b/skl2onnx/common/utils.py
@@ -112,7 +112,10 @@ def get_column_index(i, inputs):
             "Unable to find column name %r among names %r. "
             "Make sure the input names specified with parameter "
             "initial_types fits the column names specified in the "
-            "pipeline to convert." % (i, [n.onnx_name for n in inputs]))
+            "pipeline to convert. This may happen because a "
+            "ColumnTransformer follows a transformer without "
+            "any mapped converter in a pipeline." % (
+                i, [n.onnx_name for n in inputs]))
 
 
 def get_column_indices(indices, inputs, multiple):

diff --git a/tests/test_sklearn_k_bins_discretiser_converter.py b/tests/test_sklearn_k_bins_discretiser_converter.py
@@ -35,14 +35,8 @@ def test_model_k_bins_discretiser_ordinal_uniform(self):
         )
         self.assertTrue(model_onnx is not None)
         dump_data_and_model(
-            X.astype(np.float32),
-            model,
-            model_onnx,
-            basename="SklearnKBinsDiscretiserOrdinalUniform",
-            allow_failure="StrictVersion("
-            "onnxruntime.__version__)"
-            "<= StrictVersion('0.2.1')",
-        )
+            X.astype(np.float32), model, model_onnx,
+            basename="SklearnKBinsDiscretiserOrdinalUniform")
 
     @unittest.skipIf(
         KBinsDiscretizer is None,
@@ -67,14 +61,8 @@ def test_model_k_bins_discretiser_ordinal_quantile(self):
         )
         self.assertTrue(model_onnx is not None)
         dump_data_and_model(
-            X.astype(np.float32),
-            model,
-            model_onnx,
-            basename="SklearnKBinsDiscretiserOrdinalQuantile",
-            allow_failure="StrictVersion("
-            "onnxruntime.__version__)"
-            "<= StrictVersion('0.2.1')",
-        )
+            X.astype(np.float32), model, model_onnx,
+            basename="SklearnKBinsDiscretiserOrdinalQuantile")
 
     @unittest.skipIf(
         KBinsDiscretizer is None,
@@ -98,14 +86,8 @@ def test_model_k_bins_discretiser_ordinal_kmeans(self):
         )
         self.assertTrue(model_onnx is not None)
         dump_data_and_model(
-            X.astype(np.float32),
-            model,
-            model_onnx,
-            basename="SklearnKBinsDiscretiserOrdinalKMeans",
-            allow_failure="StrictVersion("
-            "onnxruntime.__version__)"
-            "<= StrictVersion('0.2.1')",
-        )
+            X.astype(np.float32), model, model_onnx,
+            basename="SklearnKBinsDiscretiserOrdinalKMeans")
 
     @unittest.skipIf(
         KBinsDiscretizer is None,
@@ -125,13 +107,8 @@ def test_model_k_bins_discretiser_onehot_dense_uniform(self):
         )
         self.assertTrue(model_onnx is not None)
         dump_data_and_model(
-            X.astype(np.float32),
-            model,
-            model_onnx,
-            basename="SklearnKBinsDiscretiserOneHotDenseUniform",
-            allow_failure="StrictVersion(onnxruntime.__version__)"
-            "<= StrictVersion('0.2.1')",
-        )
+            X.astype(np.float32), model, model_onnx,
+            basename="SklearnKBinsDiscretiserOneHotDenseUniform")
 
     @unittest.skipIf(
         KBinsDiscretizer is None,
@@ -156,13 +133,8 @@ def test_model_k_bins_discretiser_onehot_dense_quantile(self):
         )
         self.assertTrue(model_onnx is not None)
         dump_data_and_model(
-            X.astype(np.float32),
-            model,
-            model_onnx,
-            basename="SklearnKBinsDiscretiserOneHotDenseQuantile",
-            allow_failure="StrictVersion(onnxruntime.__version__)"
-            "<= StrictVersion('0.2.1')",
-        )
+            X.astype(np.float32), model, model_onnx,
+            basename="SklearnKBinsDiscretiserOneHotDenseQuantile")
 
     @unittest.skipIf(
         KBinsDiscretizer is None,
@@ -187,13 +159,8 @@ def test_model_k_bins_discretiser_onehot_dense_kmeans(self):
         )
         self.assertTrue(model_onnx is not None)
         dump_data_and_model(
-            X.astype(np.float32),
-            model,
-            model_onnx,
-            basename="SklearnKBinsDiscretiserOneHotDenseKMeans",
-            allow_failure="StrictVersion(onnxruntime.__version__)"
-            "<= StrictVersion('0.2.1')",
-        )
+            X.astype(np.float32), model, model_onnx,
+            basename="SklearnKBinsDiscretiserOneHotDenseKMeans")
 
     @unittest.skipIf(
         KBinsDiscretizer is None,
@@ -212,13 +179,8 @@ def test_model_k_bins_discretiser_ordinal_uniform_int(self):
         )
         self.assertTrue(model_onnx is not None)
         dump_data_and_model(
-            X.astype(np.int64),
-            model,
-            model_onnx,
-            basename="SklearnKBinsDiscretiserOrdinalUniformInt",
-            allow_failure="StrictVersion(onnxruntime.__version__)"
-            "<= StrictVersion('0.2.1')",
-        )
+            X.astype(np.int64), model, model_onnx,
+            basename="SklearnKBinsDiscretiserOrdinalUniformInt")
 
     @unittest.skipIf(
         KBinsDiscretizer is None,
@@ -241,13 +203,8 @@ def test_model_k_bins_discretiser_ordinal_quantile_int(self):
         )
         self.assertTrue(model_onnx is not None)
         dump_data_and_model(
-            X.astype(np.int64),
-            model,
-            model_onnx,
-            basename="SklearnKBinsDiscretiserOrdinalQuantileInt",
-            allow_failure="StrictVersion(onnxruntime.__version__)"
-            "<= StrictVersion('0.2.1')",
-        )
+            X.astype(np.int64), model, model_onnx,
+            basename="SklearnKBinsDiscretiserOrdinalQuantileInt")
 
     @unittest.skipIf(
         KBinsDiscretizer is None,
@@ -268,13 +225,8 @@ def test_model_k_bins_discretiser_ordinal_kmeans_int(self):
         )
         self.assertTrue(model_onnx is not None)
         dump_data_and_model(
-            X.astype(np.int64),
-            model,
-            model_onnx,
-            basename="SklearnKBinsDiscretiserOrdinalKMeansInt",
-            allow_failure="StrictVersion(onnxruntime.__version__)"
-            "<= StrictVersion('0.2.1')",
-        )
+            X.astype(np.int64), model, model_onnx,
+            basename="SklearnKBinsDiscretiserOrdinalKMeansInt")
 
     @unittest.skipIf(
         KBinsDiscretizer is None,
@@ -293,13 +245,8 @@ def test_model_k_bins_discretiser_onehot_dense_uniform_int(self):
         )
         self.assertTrue(model_onnx is not None)
         dump_data_and_model(
-            X.astype(np.int64),
-            model,
-            model_onnx,
-            basename="SklearnKBinsDiscretiserOneHotDenseUniformInt",
-            allow_failure="StrictVersion(onnxruntime.__version__)"
-            "<= StrictVersion('0.2.1')",
-        )
+            X.astype(np.int64), model, model_onnx,
+            basename="SklearnKBinsDiscretiserOneHotDenseUniformInt")
 
     @unittest.skipIf(
         KBinsDiscretizer is None,
@@ -318,13 +265,8 @@ def test_model_k_bins_discretiser_onehot_dense_quantile_int(self):
         )
         self.assertTrue(model_onnx is not None)
         dump_data_and_model(
-            X.astype(np.int64),
-            model,
-            model_onnx,
-            basename="SklearnKBinsDiscretiserOneHotDenseQuantileInt",
-            allow_failure="StrictVersion(onnxruntime.__version__)"
-            "<= StrictVersion('0.2.1')",
-        )
+            X.astype(np.int64), model, model_onnx,
+            basename="SklearnKBinsDiscretiserOneHotDenseQuantileInt")
 
     @unittest.skipIf(
         KBinsDiscretizer is None,
@@ -347,13 +289,8 @@ def test_model_k_bins_discretiser_onehot_dense_kmeans_int(self):
         )
         self.assertTrue(model_onnx is not None)
         dump_data_and_model(
-            X.astype(np.int64),
-            model,
-            model_onnx,
-            basename="SklearnKBinsDiscretiserOneHotDenseKMeansInt",
-            allow_failure="StrictVersion(onnxruntime.__version__)"
-            "<= StrictVersion('0.2.1')",
-        )
+            X.astype(np.int64), model, model_onnx,
+            basename="SklearnKBinsDiscretiserOneHotDenseKMeansInt")
 
 
 if __name__ == "__main__":