def _get_dataset_column_histogram(self,
column_profile: DatasetFieldProfileClass,
column: str) -> None:
if self.config.include_field_histogram:
self.dataset.set_config_value("interactive_evaluation", True)
res = self.dataset.expect_column_kl_divergence_to_be_less_than(
column,
partition_object=None,
threshold=None,
result_format="COMPLETE",
).result
if "details" in res and "observed_partition" in res["details"]:
partition = res["details"]["observed_partition"]
column_profile.histogram = HistogramClass(
[str(v) for v in partition["bins"]],
[
partition["tail_weights"][0],
*partition["weights"],
partition["tail_weights"][1],
],
)
def _handle_convert_column_evrs( # noqa: C901 (complexity)
self,
profile: DatasetProfileClass,
column: str,
col_evrs: Iterable[ExpectationValidationResult],
pretty_name: str,
send_sample_values: bool,
) -> None:
# TRICKY: This method mutates the profile directly.
column_profile = DatasetFieldProfileClass(fieldPath=column)
profile.fieldProfiles = profile.fieldProfiles or []
profile.fieldProfiles.append(column_profile)
for evr in col_evrs:
exp: str = evr.expectation_config.expectation_type
res: dict = evr.result
if not res:
self.report.report_warning(f"profile of {pretty_name}",
f"{exp} did not yield any results")
continue
if exp == "expect_column_unique_value_count_to_be_between":
column_profile.uniqueCount = res["observed_value"]
elif exp == "expect_column_proportion_of_unique_values_to_be_between":
column_profile.uniqueProportion = res["observed_value"]
elif exp == "expect_column_values_to_not_be_null":
column_profile.nullCount = res["unexpected_count"]
if ("unexpected_percent" in res
and res["unexpected_percent"] is not None):
column_profile.nullProportion = res[
"unexpected_percent"] / 100
elif exp == "expect_column_values_to_not_match_regex":
# ignore; generally used for whitespace checks using regex r"^\s+|\s+$"
pass
elif exp == "expect_column_mean_to_be_between":
column_profile.mean = str(res["observed_value"])
elif exp == "expect_column_min_to_be_between":
column_profile.min = str(res["observed_value"])
elif exp == "expect_column_max_to_be_between":
column_profile.max = str(res["observed_value"])
elif exp == "expect_column_median_to_be_between":
column_profile.median = str(res["observed_value"])
elif exp == "expect_column_stdev_to_be_between":
column_profile.stdev = str(res["observed_value"])
elif exp == "expect_column_quantile_values_to_be_between":
if "observed_value" in res:
column_profile.quantiles = [
QuantileClass(quantile=str(quantile), value=str(value))
for quantile, value in zip(
res["observed_value"]["quantiles"],
res["observed_value"]["values"],
)
]
elif exp == "expect_column_values_to_be_in_set":
column_profile.sampleValues = [
str(v) for v in res["partial_unexpected_list"]
]
if not send_sample_values:
column_profile.sampleValues = []
elif exp == "expect_column_kl_divergence_to_be_less_than":
if "details" in res and "observed_partition" in res["details"]:
partition = res["details"]["observed_partition"]
column_profile.histogram = HistogramClass(
[str(v) for v in partition["bins"]],
[
partition["tail_weights"][0],
*partition["weights"],
partition["tail_weights"][1],
],
)
elif exp == "expect_column_distinct_values_to_be_in_set":
if "details" in res and "value_counts" in res["details"]:
# This can be used to produce a bar chart since it includes values and frequencies.
# As such, it is handled differently from expect_column_values_to_be_in_set, which
# is nonexhaustive.
column_profile.distinctValueFrequencies = [
ValueFrequencyClass(value=str(value), frequency=count)
for value, count in res["details"]
["value_counts"].items()
]
if not send_sample_values:
column_profile.distinctValueFrequencies = []
elif exp == "expect_column_values_to_be_in_type_list":
# ignore; we already know the types for each column via ingestion
pass
elif exp == "expect_column_values_to_be_unique":
# ignore; this is generally covered by the unique value count test
pass
else:
self.report.report_warning(
f"profile of {pretty_name}",
f"warning: unknown column mapper {exp} in col {column}",
)