Fix/1616 pd na in by label count

src/evidently/core/metric_types.py

@@ -486,6 +486,12 @@ class Config:
     count_display_name_template: str = "Missing label {label} count"
     share_display_name_template: str = "Missing label {label} share"
 
+    @validator("counts", "shares", pre=True)
+    def _convert_label_keys(cls, value):
+        if not isinstance(value, dict):
+            return value
+        return {convert_types(k): v for k, v in value.items()}
+
     def labels(self) -> List[Label]:
         return list(self.counts.keys())
 
@@ -551,6 +557,8 @@ def convert_labels(cls, value):
 
 
 def convert_types(val):
+    if val is pd.NA:
+        return None
     if isinstance(
         val,
         (

src/evidently/metrics/column_statistics.py

@@ -869,9 +869,9 @@ def share_label_display_name(self, label: Label) -> str:
         return f"Unique Value Share: {self.metric.column} for label {label}"
 
     def _all_unique_values(self, current: Dataset, reference: Optional[Dataset]) -> set:
-        values = set(current.as_dataframe()[self.metric.column].unique())
+        values = set(current.as_dataframe()[self.metric.column].dropna().unique())
         if reference is not None:
-            values.update(reference.as_dataframe()[self.metric.column].unique())
+            values.update(reference.as_dataframe()[self.metric.column].dropna().unique())
         return values
 
     def _calculate_value(self, dataset: Dataset, values: set):

tests/future/metrics/test_unique_value_count.py

@@ -1,5 +1,7 @@
+import numpy as np
 import pandas as pd
 
+from evidently import DataDefinition
 from evidently import Dataset
 from evidently import Report
 from evidently.core.metric_types import ByLabelCountValue
@@ -40,3 +42,37 @@ def test_unique_value_count_metric():
         assert label_count.display_name == result[label]["count_display_name"]
         assert label_share.value == result[label]["share"]
         assert label_share.display_name == result[label]["share_display_name"]
+
+
+def test_unique_value_count_with_pd_na_in_string_dtype():
+    """Issue #1616: pd.NA in a nullable-string column must not become a label key."""
+    metric = UniqueValueCount(column="col1")
+    data = pd.DataFrame({"col1": pd.Series(["a", "a", "b", pd.NA], dtype="string")})
+    dataset = Dataset.from_pandas(data, DataDefinition(categorical_columns=["col1"]))
+    res = Report([metric]).run(dataset, None)._context.get_metric_result(metric)
+    assert isinstance(res, ByLabelCountValue)
+    assert set(res.labels()) == {"a", "b"}
+    a_count, _ = res.get_label_result("a")
+    b_count, _ = res.get_label_result("b")
+    assert a_count.value == 2
+    assert b_count.value == 1
+
+
+def test_unique_value_count_with_nan_in_object_dtype():
+    """np.nan / None in an object column also must not surface as a label."""
+    metric = UniqueValueCount(column="col1")
+    data = pd.DataFrame({"col1": pd.Series(["a", "b", None, np.nan], dtype="object")})
+    dataset = Dataset.from_pandas(data, DataDefinition(categorical_columns=["col1"]))
+    res = Report([metric]).run(dataset, None)._context.get_metric_result(metric)
+    assert isinstance(res, ByLabelCountValue)
+    assert set(res.labels()) == {"a", "b"}
+
+
+def test_unique_value_count_with_pd_na_in_int64_dtype():
+    """pd.NA in a nullable Int64 column."""
+    metric = UniqueValueCount(column="col1")
+    data = pd.DataFrame({"col1": pd.array([1, 2, 2, pd.NA], dtype="Int64")})
+    dataset = Dataset.from_pandas(data, DataDefinition(categorical_columns=["col1"]))
+    res = Report([metric]).run(dataset, None)._context.get_metric_result(metric)
+    assert isinstance(res, ByLabelCountValue)
+    assert set(res.labels()) == {1, 2}

tests/future/presets/test_dataset_stats_na.py

@@ -0,0 +1,22 @@
+import pandas as pd
+
+from evidently import DataDefinition
+from evidently import Dataset
+from evidently import Report
+from evidently.presets import DataDriftPreset
+from evidently.presets import DataSummaryPreset
+
+
+def _make_dataset() -> Dataset:
+    df = pd.DataFrame({"a": pd.Series(["x", "y", "z", pd.NA], dtype="string")})
+    return Dataset.from_pandas(df, DataDefinition(categorical_columns=["a"]))
+
+
+def test_data_summary_preset_handles_pd_na():
+    """Issue #1616: DataSummaryPreset must not fail on pd.NA in a categorical column."""
+    Report([DataSummaryPreset()]).run(current_data=_make_dataset())
+
+
+def test_data_drift_preset_handles_pd_na():
+    """Issue #1616: DataDriftPreset must not fail on pd.NA in a categorical column."""
+    Report([DataDriftPreset()]).run(current_data=_make_dataset(), reference_data=_make_dataset())

tests/future/test_metric_types.py

@@ -1,4 +1,5 @@
 import numpy as np
+import pandas as pd
 import pytest
 
 from evidently.core.metric_types import ByLabelCountValue
@@ -9,6 +10,8 @@
     "input,output",
     [
         ({np.nan: (1.0, 1.0)}, ({"nan": 1.0}, {"nan": 1.0})),
+        ({pd.NA: (1.0, 1.0)}, ({None: 1.0}, {None: 1.0})),
+        ({np.int64(7): (3.0, 0.5)}, ({7: 3.0}, {7: 0.5})),
     ],
 )
 def test_by_label_count_value(input: dict, output: tuple):