fix(ingest/snowflake): fix regression in approx count distinct (datah…

…ub-project#7146)
ericyomi · Feb 8, 2023 · bb1eb41 · bb1eb41
1 parent 2b4ff94
commit bb1eb41
Showing 1 changed file with 8 additions and 1 deletion.
diff --git a/metadata-ingestion/src/datahub/ingestion/source/ge_data_profiler.py b/metadata-ingestion/src/datahub/ingestion/source/ge_data_profiler.py
@@ -119,7 +119,7 @@ def get_column_unique_count_patch(self: SqlAlchemyDataset, column: str) -> int:
             ).select_from(self._table)
         )
         return convert_to_json_serializable(element_values.fetchone()[0])
-    elif self.engine.dialect.name.lower() in {"bigquery", "snowflake"}:
+    elif self.engine.dialect.name.lower() == "bigquery":
         element_values = self.engine.execute(
             sa.select(
                 [
@@ -130,6 +130,13 @@ def get_column_unique_count_patch(self: SqlAlchemyDataset, column: str) -> int:
             ).select_from(self._table)
         )
         return convert_to_json_serializable(element_values.fetchone()[0])
+    elif self.engine.dialect.name.lower() == "snowflake":
+        element_values = self.engine.execute(
+            sa.select(
+                sa.func.APPROX_COUNT_DISTINCT(sa.column(column))
+            ).select_from(self._table)
+        )
+        return convert_to_json_serializable(element_values.fetchone()[0])
     return convert_to_json_serializable(
         self.engine.execute(
             sa.select([sa.func.count(sa.func.distinct(sa.column(column)))]).select_from(