Shuffled around the order of the DropColumns transformer in the tests…

… to accomodate the new check for Unknown in get_pp_components. Made Email get treated properly in testing as WW should infer it properly now. Made infer_feature_types replace all pd.NA with np.nan for series as well as dataframes.

evalml/tests/pipeline_tests/test_pipeline_utils.py

@@ -64,8 +64,8 @@ def _get_test_data_from_configuration(
                     "[email protected]",
                     "[email protected]",
                     "[email protected]",
-                    "$titanic_data%&@hotmail.com",
-                    "foo*EMAIL@email.org",
+                    "[email protected]",
+                    "fooEMAIL@email.org",
                     "[email protected]",
                     "[email protected]",
                 ],
@@ -197,11 +197,7 @@ def test_make_pipeline(
                 if "text" in column_names and input_type == "ww"
                 else []
             )
-            email_featurizer = (
-                [EmailFeaturizer]
-                if "email" in column_names and input_type == "ww"
-                else []
-            )
+            email_featurizer = [EmailFeaturizer] if "email" in column_names else []
             url_featurizer = (
                 [URLFeaturizer] if "url" in column_names and input_type == "ww" else []
             )
@@ -213,7 +209,7 @@ def test_make_pipeline(
             )
             drop_col = (
                 [DropColumns]
-                if any(ltype in column_names for ltype in ["url", "email", "text"])
+                if any(ltype in column_names for ltype in ["url", "text"])
                 and input_type == "pd"
                 else []
             )
@@ -223,8 +219,8 @@ def test_make_pipeline(
                 + url_featurizer
                 + drop_null
                 + text_featurizer
-                + imputer
                 + drop_col
+                + imputer
                 + datetime
                 + delayed_features
                 + ohe

evalml/utils/woodwork_utils.py

@@ -82,6 +82,9 @@ def infer_feature_types(data, feature_types=None):
         return data
 
     if isinstance(data, pd.Series):
+        if all([isinstance(x, type(pd.NA)) for x in data]):
+            data = data.replace(pd.NA, np.nan)
+            feature_types = "Double"
         return ww.init_series(data, logical_type=feature_types)
     else:
         ww_data = data.copy()