jiayuasu commented on code in PR #2209:
URL: https://github.com/apache/sedona/pull/2209#discussion_r2249637599
##########
python/sedona/geopandas/tools/sjoin.py:
##########
@@ -195,36 +203,35 @@ def _frame_join(
final_columns.append(f"{col_name} as {base_name}")
# Select final columns
- result_df = spatial_join_df.selectExpr(*final_columns)
-
- # Return appropriate type based on input
- if isinstance(left_df, GeoSeries) and isinstance(right_df, GeoSeries):
- # Return GeoSeries for GeoSeries inputs
- internal = InternalFrame(
- spark_frame=result_df,
- index_spark_columns=None,
- column_labels=[left_df._col_label],
- data_spark_columns=[scol_for(result_df, "geometry")],
- data_fields=[left_df._internal.data_fields[0]],
- column_label_names=left_df._internal.column_label_names,
- )
- return _to_geo_series(first_series(ps.DataFrame(internal)))
- else:
- # Return GeoDataFrame for GeoDataFrame inputs
- return GeoDataFrame(result_df)
+ result_df = spatial_join_df.selectExpr(*final_columns).orderBy(
+ SPARK_DEFAULT_INDEX_NAME
+ )
Review Comment:
This is a good comment. We also noticed that in the demo this week, although
you were using 144 cores, the distributed mode was only 10X faster than
GeoPandas. Is it because we pay extra cost on maintaining the sorted order?
##########
python/sedona/geopandas/tools/sjoin.py:
##########
@@ -195,36 +203,35 @@ def _frame_join(
final_columns.append(f"{col_name} as {base_name}")
# Select final columns
- result_df = spatial_join_df.selectExpr(*final_columns)
-
- # Return appropriate type based on input
- if isinstance(left_df, GeoSeries) and isinstance(right_df, GeoSeries):
- # Return GeoSeries for GeoSeries inputs
- internal = InternalFrame(
- spark_frame=result_df,
- index_spark_columns=None,
- column_labels=[left_df._col_label],
- data_spark_columns=[scol_for(result_df, "geometry")],
- data_fields=[left_df._internal.data_fields[0]],
- column_label_names=left_df._internal.column_label_names,
- )
- return _to_geo_series(first_series(ps.DataFrame(internal)))
- else:
- # Return GeoDataFrame for GeoDataFrame inputs
- return GeoDataFrame(result_df)
+ result_df = spatial_join_df.selectExpr(*final_columns).orderBy(
+ SPARK_DEFAULT_INDEX_NAME
+ )
Review Comment:
@petern48
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
