michael-s-molina commented on code in PR #28432:
URL: https://github.com/apache/superset/pull/28432#discussion_r1600457643
##########
superset/common/query_context_processor.py:
##########
@@ -339,19 +339,31 @@ def get_time_grain(query_object: QueryObject) -> Any |
None:
return query_object.extras.get("time_grain_sqla")
- def add_aggregated_join_column(
+ # pylint: disable=too-many-arguments
+ def add_offset_join_column(
self,
df: pd.DataFrame,
+ name: str,
time_grain: str,
+ time_offset: str | None = None,
join_column_producer: Any = None,
) -> None:
+ """
+ Adds an offset join column to the provided DataFrame.
+
+ :param df: pandas DataFrame to which the offset join column will be
added.
+ :param name: The name of the new column to be added.
+ :param time_grain: The time grain used to calculate the new column.
+ :param time_offset: The time offset used to calculate the new column.
+ :param join_column_producer: A function to generate the join column.
+
+ :return: None. The function modifies the DataFrame in-place.
Review Comment:
Done!
##########
superset/common/query_context_processor.py:
##########
@@ -339,19 +339,31 @@ def get_time_grain(query_object: QueryObject) -> Any |
None:
return query_object.extras.get("time_grain_sqla")
- def add_aggregated_join_column(
+ # pylint: disable=too-many-arguments
+ def add_offset_join_column(
self,
df: pd.DataFrame,
+ name: str,
time_grain: str,
+ time_offset: str | None = None,
join_column_producer: Any = None,
) -> None:
+ """
+ Adds an offset join column to the provided DataFrame.
+
Review Comment:
Done!
##########
superset/common/query_context_processor.py:
##########
@@ -519,51 +510,112 @@ def processing_time_offsets( # pylint:
disable=too-many-locals,too-many-stateme
datasource_uid=query_context.datasource.uid,
region=CacheRegion.DATA,
)
- offset_dfs.append(offset_metrics_df)
+ offset_dfs[offset] = offset_metrics_df
if offset_dfs:
- # iterate on offset_dfs, left join each with df
- for offset_df in offset_dfs:
- df = dataframe_utils.left_join_df(
- left_df=df,
- right_df=offset_df,
- join_keys=join_keys,
- rsuffix=R_SUFFIX,
- )
+ df = self.join_offset_dfs(
+ df,
+ offset_dfs,
+ time_grain,
+ join_keys,
+ )
+
+ return CachedTimeOffset(df=df, queries=queries, cache_keys=cache_keys)
+
+ def join_offset_dfs(
+ self,
+ df: pd.DataFrame,
+ offset_dfs: dict[str, pd.DataFrame],
+ time_grain: str,
+ join_keys: list[str],
+ ) -> pd.DataFrame:
+ """
+ Join offset DataFrames with the main DataFrame.
- # removes columns used for join
- df.drop(
- list(df.filter(regex=f"{AGGREGATED_JOIN_COLUMN}|{R_SUFFIX}")),
- axis=1,
- inplace=True,
+ :param df: The main DataFrame.
+ :param offset_dfs: A list of offset DataFrames.
+ :param time_grain: The time grain used to calculate the temporal join
key.
+ :param join_keys: The keys to join on.
+ """
+ join_column_producer = config["TIME_GRAIN_JOIN_COLUMN_PRODUCERS"].get(
+ time_grain
)
- return CachedTimeOffset(df=df, queries=queries, cache_keys=cache_keys)
+ # iterate on offset_dfs, left join each with df
+ for offset, offset_df in offset_dfs.items():
+ # defines a column name for the offset join column
+ column_name = OFFSET_JOIN_COLUMN_SUFFIX + offset
+
+ # add offset join column to df
+ self.add_offset_join_column(
+ df, column_name, time_grain, offset, join_column_producer
+ )
+
+ # add artifoffseticial join column to offset_df
Review Comment:
Done!
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
