Skip to content

Change outlier checks as warnings #1323

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.

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

Merged
merged 4 commits into from
Oct 22, 2021
Merged
Show file tree
Hide file tree
Changes from 3 commits
Commits
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
4 changes: 2 additions & 2 deletions _delphi_utils_python/delphi_utils/validator/dynamic.py
Original file line number Diff line number Diff line change
Expand Up @@ -525,7 +525,7 @@ def outlier_nearby(frame):

if source_outliers.shape[0] > 0:
for time_val in source_outliers["time_value"].unique():
report.add_raised_error(
report.add_raised_warning(
ValidationFailure(
"check_positive_negative_spikes",
time_val,
Expand Down Expand Up @@ -637,7 +637,7 @@ def check_avg_val_vs_reference(self, df_to_test, df_to_reference, checking_date,
thres["mean_abs_z"])).any()

if mean_z_high or mean_abs_z_high:
report.add_raised_error(
report.add_raised_warning(
ValidationFailure(
"check_test_vs_reference_avg_changed",
checking_date,
Expand Down
11 changes: 11 additions & 0 deletions _delphi_utils_python/delphi_utils/validator/report.py
Original file line number Diff line number Diff line change
Expand Up @@ -103,6 +103,17 @@ def log(self, logger=None):
checks_suppressed = self.num_suppressed,
warnings = len(self.raised_warnings),
phase="validation")
excessive_warnings = self.total_checks > 0 and \
(len(self.raised_warnings) > 200 or \
len(self.raised_warnings) / self.total_checks > 0.015)
if excessive_warnings:
logger.info("Excessive number of warnings",
data_source = self.data_source,
checks_run = self.total_checks,
checks_failed = len(self.unsuppressed_errors),
checks_suppressed = self.num_suppressed,
warnings = len(self.raised_warnings),
phase = "validation")
for error in self.unsuppressed_errors:
logger.critical(str(error), phase="validation")
for warning in self.raised_warnings:
Expand Down
30 changes: 15 additions & 15 deletions _delphi_utils_python/tests/validator/test_dynamic.py
Original file line number Diff line number Diff line change
Expand Up @@ -202,8 +202,8 @@ def test_10x_val(self):
test_df, ref_df,
datetime.combine(date.today(), datetime.min.time()), "geo", "signal", report)

assert len(report.raised_errors) == 1
assert report.raised_errors[0].check_name == "check_test_vs_reference_avg_changed"
assert len(report.raised_warnings) == 1
assert report.raised_warnings[0].check_name == "check_test_vs_reference_avg_changed"

def test_100x_val(self):
validator = DynamicValidator(self.params)
Expand All @@ -223,8 +223,8 @@ def test_100x_val(self):
test_df, ref_df,
datetime.combine(date.today(), datetime.min.time()), "geo", "signal", report)

assert len(report.raised_errors) == 1
assert report.raised_errors[0].check_name == "check_test_vs_reference_avg_changed"
assert len(report.raised_warnings) == 1
assert report.raised_warnings[0].check_name == "check_test_vs_reference_avg_changed"

def test_1000x_val(self):
validator = DynamicValidator(self.params)
Expand All @@ -244,8 +244,8 @@ def test_1000x_val(self):
test_df, ref_df,
datetime.combine(date.today(), datetime.min.time()), "geo", "signal", report)

assert len(report.raised_errors) == 1
assert report.raised_errors[0].check_name == "check_test_vs_reference_avg_changed"
assert len(report.raised_warnings) == 1
assert report.raised_warnings[0].check_name == "check_test_vs_reference_avg_changed"


class TestDataOutlier:
Expand Down Expand Up @@ -292,8 +292,8 @@ def test_pos_outlier(self):
validator.check_positive_negative_spikes(
test_df, ref_df, "state", "signal", report)

assert len(report.raised_errors) == 2
assert report.raised_errors[0].check_name == "check_positive_negative_spikes"
assert len(report.raised_warnings) == 2
assert report.raised_warnings[0].check_name == "check_positive_negative_spikes"

def test_neg_outlier(self):
validator = DynamicValidator(self.params)
Expand Down Expand Up @@ -329,8 +329,8 @@ def test_neg_outlier(self):
validator.check_positive_negative_spikes(
test_df, ref_df, "state", "signal", report)

assert len(report.raised_errors) == 2
assert report.raised_errors[0].check_name == "check_positive_negative_spikes"
assert len(report.raised_warnings) == 2
assert report.raised_warnings[0].check_name == "check_positive_negative_spikes"

def test_zero_outlier(self):
validator = DynamicValidator(self.params)
Expand Down Expand Up @@ -365,8 +365,8 @@ def test_zero_outlier(self):
validator.check_positive_negative_spikes(
test_df, ref_df, "state", "signal", report)

assert len(report.raised_errors) == 1
assert report.raised_errors[0].check_name == "check_positive_negative_spikes"
assert len(report.raised_warnings) == 1
assert report.raised_warnings[0].check_name == "check_positive_negative_spikes"

def test_no_outlier(self):
validator = DynamicValidator(self.params)
Expand Down Expand Up @@ -402,7 +402,7 @@ def test_no_outlier(self):
validator.check_positive_negative_spikes(
test_df, ref_df, "state", "signal", report)

assert len(report.raised_errors) == 0
assert len(report.raised_warnings) == 0

def test_source_api_overlap(self):
validator = DynamicValidator(self.params)
Expand Down Expand Up @@ -438,5 +438,5 @@ def test_source_api_overlap(self):
validator.check_positive_negative_spikes(
test_df, ref_df, "state", "signal", report)

assert len(report.raised_errors) == 2
assert report.raised_errors[0].check_name == "check_positive_negative_spikes"
assert len(report.raised_warnings) == 2
assert report.raised_warnings[0].check_name == "check_positive_negative_spikes"