Data check Update

docs/source/release_notes.rst

@@ -15,6 +15,7 @@ Release Notes
         * Updated estimator and pipelines' ``predict``, ``predict_proba``, ``transform``, ``inverse_transform`` methods to preserve input indices :pr:`2979`
         * Updated demo dataset link for daily min temperatures :pr:`3023`
     * Changes
+        * Updated ``OutliersDataCheck`` and ``UniquenessDataCheck`` and allow for the suspension of the Nullable types error :pr:`3018`
     * Documentation Changes
         * Fixed cost benefit matrix demo formatting :pr:`2990`
         * Update ReadMe.md with new badge links and updated installation instructions for conda :pr:`2998`

evalml/data_checks/highly_null_data_check.py

@@ -105,7 +105,7 @@ def validate(self, X, y=None):
         """
         results = {"warnings": [], "errors": [], "actions": []}
 
-        X = infer_feature_types(X)
+        X = infer_feature_types(X, ignore_nullable_types=True)
 
         percent_null_rows = X.isnull().mean(axis=1)
         highly_null_rows = percent_null_rows[

evalml/data_checks/no_variance_data_check.py

@@ -108,8 +108,8 @@ def validate(self, X, y):
 
         """
         results = {"warnings": [], "errors": [], "actions": []}
-        X = infer_feature_types(X)
-        y = infer_feature_types(y)
+        X = infer_feature_types(X, ignore_nullable_types=True)
+        y = infer_feature_types(y, ignore_nullable_types=True)
 
         unique_counts = X.nunique(dropna=self._dropnan).to_dict()
         any_nulls = (X.isnull().any()).to_dict()

evalml/data_checks/outliers_data_check.py

@@ -128,8 +128,7 @@ def get_boxplot_data(data_):
         Returns:
             dict: A payload of box plot statistics.
         """
-        if not data_.ww._schema:
-            data_.ww.init()
+        data_ = infer_feature_types(data_, ignore_nullable_types=True)
         num_records = data_.count()
         box_plot_dict = data_.ww.box_plot_dict()
         quantiles = box_plot_dict["quantiles"]

evalml/data_checks/uniqueness_data_check.py

@@ -143,18 +143,21 @@ def validate(self, X, y=None):
         return results
 
     @staticmethod
-    def uniqueness_score(col):
+    def uniqueness_score(col, drop_na=True):
         """Calculate a uniqueness score for the provided field.  NaN values are not considered as unique values in the calculation.
 
         Based on the Herfindahl–Hirschman Index.
 
         Args:
             col (pd.Series): Feature values.
+            drop_na (bool): Whether to drop null values when computing the uniqueness score. Defaults to True.
 
         Returns:
             (float): Uniqueness score.
         """
-        norm_counts = col.value_counts() / col.value_counts().sum()
+        norm_counts = (
+            col.value_counts(dropna=drop_na) / col.value_counts(dropna=drop_na).sum()
+        )
         square_counts = norm_counts ** 2
         score = 1 - square_counts.sum()
         return score

evalml/utils/woodwork_utils.py

@@ -45,14 +45,15 @@ def _raise_value_error_if_nullable_types_detected(data):
         )
 
 
-def infer_feature_types(data, feature_types=None):
+def infer_feature_types(data, feature_types=None, ignore_nullable_types=False):
     """Create a Woodwork structure from the given list, pandas, or numpy input, with specified types for columns. If a column's type is not specified, it will be inferred by Woodwork.
 
     Args:
         data (pd.DataFrame, pd.Series): Input data to convert to a Woodwork data structure.
         feature_types (string, ww.logical_type obj, dict, optional): If data is a 2D structure, feature_types must be a dictionary
             mapping column names to the type of data represented in the column. If data is a 1D structure, then feature_types must be
             a Woodwork logical type or a string representing a Woodwork logical type ("Double", "Integer", "Boolean", "Categorical", "Datetime", "NaturalLanguage")
+        ignore_nullable_types (bool): Whether to ignore raising an error upon detection of Nullable types. Defaults to False.
 
     Returns:
         A Woodwork data structure where the data type of each column was either specified or inferred.
@@ -65,7 +66,8 @@ def infer_feature_types(data, feature_types=None):
     elif isinstance(data, np.ndarray):
         data = _numpy_to_pandas(data)
 
-    _raise_value_error_if_nullable_types_detected(data)
+    if not ignore_nullable_types:
+        _raise_value_error_if_nullable_types_detected(data)
 
     def convert_all_nan_unknown_to_double(data):
         def is_column_pd_na(data, col):