fix: Optimize bytes processed when retrieving entity df schema to 0 (#3680)

sudohainguyen · web-flow · commit 1c010357affd · 2023-07-12T23:07:41.000-07:00
feat: Optimize bytes processed when retrieving entity df schema to 0

Signed-off-by: Hai Nguyen &lt;quanghai.ng1512@gmail.com&gt;
diff --git a/sdk/python/feast/infra/offline_stores/bigquery.py b/sdk/python/feast/infra/offline_stores/bigquery.py
@@ -693,7 +693,7 @@ def _get_entity_schema(
 ) -> Dict[str, np.dtype]:
     if isinstance(entity_df, str):
         entity_df_sample = (
-            client.query(f"SELECT * FROM ({entity_df}) LIMIT 1").result().to_dataframe()
+            client.query(f"SELECT * FROM ({entity_df}) LIMIT 0").result().to_dataframe()
         )
 
         entity_schema = dict(zip(entity_df_sample.columns, entity_df_sample.dtypes))

Original file line number	Diff line number	Diff line change
`@@ -693,7 +693,7 @@ def _get_entity_schema(`
`693`	`693`	`) -> Dict[str, np.dtype]:`
`694`	`694`	`if isinstance(entity_df, str):`
`695`	`695`	`entity_df_sample = (`
`696`		`- client.query(f"SELECT * FROM ({entity_df}) LIMIT 1").result().to_dataframe()`
	`696`	`+ client.query(f"SELECT * FROM ({entity_df}) LIMIT 0").result().to_dataframe()`
`697`	`697`	`)`
`698`	`698`
`699`	`699`	`entity_schema = dict(zip(entity_df_sample.columns, entity_df_sample.dtypes))`