sync w/ internal repo; update models #1083
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -330,7 +330,9 @@ def infer_app_meta(eventlogs: List[str]) -> Mapping[str, Mapping]: | |
| ) | ||
| toc_list.append(tmp) | ||
|
|
||
| if not toc_list: | ||
| raise ValueError(f'No CSV files found for: {ds_name}') | ||
| else: | ||
| toc = pd.concat(toc_list) | ||
| raw_features = extract_raw_features(toc, node_level_supp, qualtool_filter) | ||
| if raw_features.empty: | ||
|
|
@@ -415,7 +417,7 @@ def combine_tables(table_name: str) -> pd.DataFrame: | |
|
|
||
| # normalize WholeStageCodegen labels | ||
| ops_tbl.loc[ | ||
| ops_tbl['nodeName'].str.startswith('WholeStageCodegen'), 'nodeName' | ||
| ] = 'WholeStageCodegen' | ||
|
|
||
| # format WholeStageCodegen for merging | ||
|
|
@@ -449,7 +451,7 @@ def combine_tables(table_name: str) -> pd.DataFrame: | |
| ] | ||
| for op in dynamic_op_labels: | ||
| sql_ops_counter.loc[ | ||
| sql_ops_counter['nodeName'].str.startswith(op), 'nodeName' | ||
| ] = op | ||
|
|
||
| # count occurrences | ||
|
|
@@ -533,7 +535,7 @@ def combine_tables(table_name: str) -> pd.DataFrame: | |
|
|
||
| # filter rows w/ sqlID | ||
| sql_job_agg_tbl['hasSqlID'] = sql_job_agg_tbl['sqlID'] >= 0 | ||
| full_tbl = sql_job_agg_tbl[sql_job_agg_tbl['hasSqlID']] | ||
|
|
||
| # add runType features from toc | ||
| app_runtype = toc[['appId', 'runType']].drop_duplicates() | ||
|
|
@@ -929,21 +931,22 @@ def scan_tbl( | |
| sql_to_stage, left_on='ID', right_on='stageId' | ||
| ) | ||
| total_stage_time = ( | ||
| stage_agg_tbl[['sqlID', 'Duration']] | ||
| .groupby('sqlID') | ||
| .agg('sum') | ||
| .reset_index() | ||
| ) | ||
| failed_stage_time = ( | ||
| stage_agg_tbl[['sqlID', 'ID', 'Duration']] | ||
| .merge(failed_stages, left_on='ID', right_on='stageId', how='inner')[ | ||
| ['sqlID', 'Duration'] | ||
| ] | ||
| .groupby('sqlID') | ||
| .agg('sum') | ||
| .reset_index() | ||
| ) | ||
| stage_times = total_stage_time.merge( | ||
| failed_stage_time, on='sqlID', how='inner' | ||
| ) | ||
| stage_times.info() | ||
| sqls_to_drop = set( | ||
|
|
@@ -1074,10 +1077,14 @@ def load_qtool_execs(qtool_execs: List[str]) -> Optional[pd.DataFrame]: | |
| if qtool_execs: | ||
| exec_info = pd.concat([pd.read_csv(f) for f in qtool_execs]) | ||
| node_level_supp = exec_info.copy() | ||
| node_level_supp['Exec Is Supported'] = ( | ||
| node_level_supp['Exec Is Supported'] | ||
| | node_level_supp['Exec Name'].apply( | ||
| lambda x: any([x.startswith(nm) for nm in unsupported_overrides]) | ||
| ) | ||
| | node_level_supp['Exec Name'].apply( | ||
| lambda x: x.startswith('WholeStageCodegen') | ||
| ) | ||
|
Comment on lines
+1080
to
+1087
There was a problem hiding this comment. I thought that change was rolled back..Just double checking. There was a problem hiding this comment. Per @eordentlich's commit to internal repo, this is a workaround for #860. |
||
| ) | ||
| node_level_supp = ( | ||
| node_level_supp[['App ID', 'SQL ID', 'SQL Node Id', 'Exec Is Supported']] | ||
|
|
||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Lets set the standard:
For the case when it is "not toc_list", do we want to raise an error? or return 1.0 after logging that files were missing?
CC: @eordentlich and @parthosa
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@amahussein this should be a very rare case. Basically, the user has requested to load CSV files for a dataset, and we have found none at all for the entire dataset. Previously, we would just skip this dataset (failing silently), so added this code to raise it to the user's attention. Presumably, the legacy Speedup would also fail in this case too (or would it just return 1.0?).