Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

fix(ingest): handle exceptions in min, max, mean profiling #9129

Merged
merged 3 commits into from
Nov 1, 2023
Merged

fix(ingest): handle exceptions in min, max, mean profiling #9129

Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
47fb297
fix(ingest): handle exceptions in min, max, mean profiling
mayurinehate Oct 27, 2023
193fdc9
Merge branch 'master' into snowflake_time_not_profiled
mayurinehate Oct 27, 2023
bcdbf95
Merge branch 'master' into snowflake_time_not_profiled
anshbansal Nov 1, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
36 changes: 33 additions & 3 deletions metadata-ingestion/src/datahub/ingestion/source/ge_data_profiler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -406,22 +406,52 @@ def _get_dataset_rows(self, dataset_profile: DatasetProfileClass) -> None:
def _get_dataset_column_min(
self, column_profile: DatasetFieldProfileClass, column: str
) -> None:
if self.config.include_field_min_value:
if not self.config.include_field_min_value:
return
try:
column_profile.min = str(self.dataset.get_column_min(column))
except Exception as e:
logger.debug(
f"Caught exception while attempting to get column min for column {column}. {e}"
)
self.report.report_warning(
"Profiling - Unable to get column min",
f"{self.dataset_name}.{column}",
)

@_run_with_query_combiner
def _get_dataset_column_max(
self, column_profile: DatasetFieldProfileClass, column: str
) -> None:
if self.config.include_field_max_value:
if not self.config.include_field_max_value:
return
try:
column_profile.max = str(self.dataset.get_column_max(column))
except Exception as e:
logger.debug(
f"Caught exception while attempting to get column max for column {column}. {e}"
)
self.report.report_warning(
"Profiling - Unable to get column max",
f"{self.dataset_name}.{column}",
)

@_run_with_query_combiner
def _get_dataset_column_mean(
self, column_profile: DatasetFieldProfileClass, column: str
) -> None:
if self.config.include_field_mean_value:
if not self.config.include_field_mean_value:
return
try:
column_profile.mean = str(self.dataset.get_column_mean(column))
except Exception as e:
logger.debug(
f"Caught exception while attempting to get column mean for column {column}. {e}"
)
self.report.report_warning(
"Profiling - Unable to get column mean",
f"{self.dataset_name}.{column}",
)

@_run_with_query_combiner
def _get_dataset_column_median(
Expand Down
Loading