Fix bug with null replication metrics when row is all null (#706)

* Fix bug when row is all null

* Improve test

* Remove unnecessary type

* Improve efficiency

dataprofiler/profilers/profile_builder.py

@@ -2287,7 +2287,11 @@ def _update_null_replication_metrics(self, clean_samples: Dict) -> None:
             # Partition data based on whether target column value is null or not
             # Calculate sum, mean of each partition without including current column
             # in calculation
-            sum_null = data.iloc[null_indices, data.columns != col_id].sum().to_numpy()
+            sum_null = (
+                data.loc[data.index.intersection(null_indices), data.columns != col_id]
+                .sum()
+                .to_numpy()
+            )
 
             # Add old sum_null if exists
             if col_id in self._null_replication_metrics:

dataprofiler/tests/profilers/test_profile_builder.py

@@ -2081,6 +2081,21 @@ def test_null_replication_metrics_calculation(self):
         np.testing.assert_array_almost_equal([[np.nan], [18]], column["class_sum"])
         np.testing.assert_array_almost_equal([[np.nan], [9]], column["class_mean"])
 
+        # Test with all null in a row
+        data_4 = pd.DataFrame(
+            [[10, 20], [9999999, 9999999], [30, 9999999], [9999999, 9999999]]
+        )
+
+        profiler = dp.StructuredProfiler(data_4, options=profile_options)
+        report = profiler.report()
+
+        self.assertTrue("null_replication_metrics" in report["data_stats"][0])
+        column = report["data_stats"][0]["null_replication_metrics"]
+
+        np.testing.assert_array_almost_equal([0.5, 0.5], column["class_prior"])
+        np.testing.assert_array_almost_equal([[20], [0]], column["class_sum"])
+        np.testing.assert_array_almost_equal([[10], [0]], column["class_mean"])
+
     def test_column_level_invalid_values(self):
         data = pd.DataFrame([[1, 1], [9999999, 2], [3, 3]])