def _spark(
cls,
execution_engine: "SparkDFExecutionEngine",
metric_domain_kwargs: Dict,
metric_value_kwargs: Dict,
metrics: Dict[Tuple, Any],
runtime_configuration: Dict,
):
ignore_row_if = metric_value_kwargs["ignore_row_if"]
compute_domain_kwargs = copy.deepcopy(metric_domain_kwargs)
if ignore_row_if == "both_values_are_missing":
compute_domain_kwargs["row_condition"] = (
F.col(metric_domain_kwargs["column_A"]).isNotNull()
& F.col(metric_domain_kwargs["column_B"]).isNotNull())
compute_domain_kwargs["condition_parser"] = "spark"
elif ignore_row_if == "either_value_is_missing":
compute_domain_kwargs["row_condition"] = (
F.col(metric_domain_kwargs["column_A"]).isNotNull()
| F.col(metric_domain_kwargs["column_B"]).isNotNull())
compute_domain_kwargs["condition_parser"] = "spark"
(
df,
compute_domain_kwargs,
accessor_domain_kwargs,
) = execution_engine.get_compute_domain(compute_domain_kwargs,
MetricDomainTypes.COLUMN_PAIR)
return (
df[metric_domain_kwargs["column_A"]] == df[
metric_domain_kwargs["column_B"]],
compute_domain_kwargs,
accessor_domain_kwargs,
)
def _spark(cls, column_list, **kwargs):
column_names = column_list.columns
num_columns = len(column_names)
conditions = []
for idx_src in range(num_columns - 1):
for idx_dest in range(idx_src + 1, num_columns):
conditions.append(
F.col(column_names[idx_src]).eqNullSafe(
F.col(column_names[idx_dest])))
row_wise_cond = ~reduce(lambda a, b: a | b, conditions)
return row_wise_cond
def _spark(
cls,
execution_engine,
metric_domain_kwargs,
metric_value_kwargs,
metrics,
runtime_configuration,
):
column_name = metric_domain_kwargs["column"]
table_columns = metrics["table.column_types"]
column_metadata = [
col for col in table_columns if col["name"] == column_name
][0]
if isinstance(column_metadata["type"], (sparktypes.StringType)):
column = F.col(column_name).cast(sparktypes.IntegerType())
else:
raise TypeError(
"Column must be a string-type capable of being cast to int.")
compute_domain_kwargs = metric_domain_kwargs
(
df,
compute_domain_kwargs,
accessor_domain_kwargs,
) = execution_engine.get_compute_domain(
compute_domain_kwargs, domain_type=MetricDomainTypes.COLUMN)
if any(np.array(df.select(column.isNull()).collect())):
raise TypeError(
"Column must be a string-type capable of being cast to int.")
diff = column - F.lag(column).over(Window.orderBy(F.lit("constant")))
diff = F.when(diff.isNull(), 1).otherwise(diff)
if metric_value_kwargs["strictly"] is True:
diff = F.when(diff <= 0, F.lit(False)).otherwise(F.lit(True))
else:
diff = F.when(diff < 0, F.lit(False)).otherwise(F.lit(True))
return (
np.array(df.select(diff).collect()).reshape(-1)[1:],
compute_domain_kwargs,
accessor_domain_kwargs,
)
def _spark(
cls,
execution_engine: "SparkDFExecutionEngine",
metric_domain_kwargs: Dict,
metric_value_kwargs: Dict,
metrics: Dict[Tuple, Any],
runtime_configuration: Dict,
):
ignore_row_if = metric_value_kwargs["ignore_row_if"]
compute_domain_kwargs = copy.deepcopy(metric_domain_kwargs)
if ignore_row_if == "both_values_are_missing":
compute_domain_kwargs["row_condition"] = (
F.col(metric_domain_kwargs["column_A"]).isNotNull()
& F.col(metric_domain_kwargs["column_B"]).isNotNull())
compute_domain_kwargs["condition_parser"] = "spark"
elif ignore_row_if == "either_value_is_missing":
compute_domain_kwargs["row_condition"] = (
F.col(metric_domain_kwargs["column_A"]).isNotNull()
| F.col(metric_domain_kwargs["column_B"]).isNotNull())
compute_domain_kwargs["condition_parser"] = "spark"
(
df,
compute_domain_kwargs,
accessor_domain_kwargs,
) = execution_engine.get_compute_domain(
compute_domain_kwargs, domain_type=MetricDomainTypes.COLUMN_PAIR)
df = df.withColumn(
"combined",
F.array(
F.col(metric_domain_kwargs["column_A"]),
F.col(metric_domain_kwargs["column_A"]),
),
)
value_set_df = (SQLContext(df._sc).createDataFrame(
metric_value_kwargs["value_pairs_set"], ["col_A", "col_B"]).select(
F.array("col_A", "col_B").alias("set_AB")))
df = df.join(value_set_df, df["combined"] == value_set_df["set_AB"],
"left").withColumn(
"__success",
F.when(F.col("set_AB").isNull(),
F.lit(False)).otherwise(F.lit(True)),
)
return df["__success"], compute_domain_kwargs, accessor_domain_kwargs
def _spark(
cls,
execution_engine: SparkDFExecutionEngine,
metric_domain_kwargs,
metric_value_kwargs,
metrics,
runtime_configuration,
):
(
selectable,
compute_domain_kwargs,
accessor_domain_kwargs,
) = execution_engine.get_compute_domain(metric_domain_kwargs,
MetricDomainTypes.COLUMN)
column_name = accessor_domain_kwargs["column"]
column = F.col(column_name)
query = F.when(column == 3, F.lit(False)).otherwise(F.lit(True))
return (query, compute_domain_kwargs, accessor_domain_kwargs)
def _spark(
cls,
execution_engine: SparkDFExecutionEngine,
metric_domain_kwargs: Dict,
metric_value_kwargs: Dict,
metrics: Dict[Tuple, Any],
runtime_configuration: Dict,
):
sort = metric_value_kwargs.get("sort",
cls.default_kwarg_values["sort"])
collate = metric_value_kwargs.get("collate",
cls.default_kwarg_values["collate"])
if sort not in ["value", "count", "none"]:
raise ValueError("sort must be either 'value', 'count', or 'none'")
if collate is not None:
raise ValueError(
"collate parameter is not supported in SparkDFDataset")
df, _, accessor_domain_kwargs = execution_engine.get_compute_domain(
metric_domain_kwargs, MetricDomainTypes.COLUMN)
column = accessor_domain_kwargs["column"]
value_counts = (df.select(column).where(
F.col(column).isNotNull()).groupBy(column).count())
if sort == "value":
value_counts = value_counts.orderBy(column)
elif sort == "count":
value_counts = value_counts.orderBy(F.desc("count"))
value_counts = value_counts.collect()
series = pd.Series(
[row["count"] for row in value_counts],
index=pd.Index(data=[row[column] for row in value_counts],
name="value"),
name="count",
)
return series
def _spark(
cls,
execution_engine: SparkDFExecutionEngine,
metric_domain_kwargs: Dict,
metric_value_kwargs: Dict,
metrics: Dict[str, Any],
runtime_configuration: Dict,
):
parse_strings_as_datetimes: bool = (
metric_value_kwargs.get("parse_strings_as_datetimes") or False)
if parse_strings_as_datetimes:
warnings.warn(
f"""The parameter "parse_strings_as_datetimes" is no longer supported and will be deprecated in a \
future release. Please update code accordingly. Moreover, in "{cls.__name__}._spark()", types are detected naturally.
""",
DeprecationWarning,
)
# check if column is any type that could have na (numeric types)
column_name = metric_domain_kwargs["column"]
table_columns = metrics["table.column_types"]
column_metadata = [
col for col in table_columns if col["name"] == column_name
][0]
if isinstance(
column_metadata["type"],
(
sparktypes.LongType,
sparktypes.DoubleType,
sparktypes.IntegerType,
),
):
# if column is any type that could have NA values, remove them (not filtered by .isNotNull())
compute_domain_kwargs = execution_engine.add_column_row_condition(
metric_domain_kwargs,
filter_null=cls.filter_column_isnull,
filter_nan=True,
)
else:
compute_domain_kwargs = metric_domain_kwargs
(
df,
compute_domain_kwargs,
accessor_domain_kwargs,
) = execution_engine.get_compute_domain(compute_domain_kwargs,
MetricDomainTypes.COLUMN)
# NOTE: 20201105 - parse_strings_as_datetimes is not supported here;
# instead detect types naturally
column = F.col(column_name)
if isinstance(column_metadata["type"],
(sparktypes.TimestampType, sparktypes.DateType)):
diff = F.datediff(
column,
F.lag(column).over(Window.orderBy(F.lit("constant"))))
else:
diff = column - F.lag(column).over(
Window.orderBy(F.lit("constant")))
diff = F.when(diff.isNull(), -1).otherwise(diff)
# NOTE: because in spark we are implementing the window function directly,
# we have to return the *unexpected* condition
if metric_value_kwargs["strictly"]:
return (
F.when(diff >= 0, F.lit(True)).otherwise(F.lit(False)),
compute_domain_kwargs,
accessor_domain_kwargs,
)
# If we expect values to be flat or decreasing then unexpected values are those
# that are decreasing
else:
return (
F.when(diff > 0, F.lit(True)).otherwise(F.lit(False)),
compute_domain_kwargs,
accessor_domain_kwargs,
)
def _spark(
cls,
execution_engine: SparkDFExecutionEngine,
metric_domain_kwargs: Dict,
metric_value_kwargs: Dict,
metrics: Dict[str, Any],
runtime_configuration: Dict,
):
df, _, accessor_domain_kwargs = execution_engine.get_compute_domain(
domain_kwargs=metric_domain_kwargs,
domain_type=MetricDomainTypes.COLUMN)
bins = metric_value_kwargs["bins"]
column = metric_domain_kwargs["column"]
"""return a list of counts corresponding to bins"""
bins = list(copy.deepcopy(
bins)) # take a copy since we are inserting and popping
if bins[0] == -np.inf or bins[0] == -float("inf"):
added_min = False
bins[0] = -float("inf")
else:
added_min = True
bins.insert(0, -float("inf"))
if bins[-1] == np.inf or bins[-1] == float("inf"):
added_max = False
bins[-1] = float("inf")
else:
added_max = True
bins.append(float("inf"))
temp_column = df.select(column).where(F.col(column).isNotNull())
bucketizer = Bucketizer(splits=bins,
inputCol=column,
outputCol="buckets")
bucketed = bucketizer.setHandleInvalid("skip").transform(temp_column)
# This is painful to do, but: bucketizer cannot handle values outside of a range
# (hence adding -/+ infinity above)
# Further, it *always* follows the numpy convention of lower_bound <= bin < upper_bound
# for all but the last bin
# But, since the last bin in our case will often be +infinity, we need to
# find the number of values exactly equal to the upper bound to add those
# We'll try for an optimization by asking for it at the same time
if added_max:
upper_bound_count = (temp_column.select(column).filter(
F.col(column) == bins[-2]).count())
else:
upper_bound_count = 0
hist_rows = bucketed.groupBy("buckets").count().collect()
# Spark only returns buckets that have nonzero counts.
hist = [0] * (len(bins) - 1)
for row in hist_rows:
hist[int(row["buckets"])] = row["count"]
hist[-2] += upper_bound_count
if added_min:
below_bins = hist.pop(0)
bins.pop(0)
if below_bins > 0:
logger.warning("Discarding histogram values below lowest bin.")
if added_max:
above_bins = hist.pop(-1)
bins.pop(-1)
if above_bins > 0:
logger.warning(
"Discarding histogram values above highest bin.")
return hist
def _spark(
cls,
execution_engine: SparkDFExecutionEngine,
metric_domain_kwargs: Dict,
metric_value_kwargs: Dict,
metrics: Dict[str, Any],
runtime_configuration: Dict,
):
parse_strings_as_datetimes: bool = (
metric_value_kwargs.get("parse_strings_as_datetimes") or False)
if parse_strings_as_datetimes:
# deprecated-v0.13.41
warnings.warn(
"""The parameter "parse_strings_as_datetimes" is deprecated as of v0.13.41 in \
v0.16. As part of the V3 API transition, we've moved away from input transformation. For more information, \
please see: https://greatexpectations.io/blog/why_we_dont_do_transformations_for_expectations/
""",
DeprecationWarning,
)
# check if column is any type that could have na (numeric types)
column_name = metric_domain_kwargs["column"]
table_columns = metrics["table.column_types"]
column_metadata = [
col for col in table_columns if col["name"] == column_name
][0]
if isinstance(
column_metadata["type"],
(
sparktypes.LongType,
sparktypes.DoubleType,
sparktypes.IntegerType,
),
):
# if column is any type that could have NA values, remove them (not filtered by .isNotNull())
compute_domain_kwargs = execution_engine.add_column_row_condition(
metric_domain_kwargs,
filter_null=cls.filter_column_isnull,
filter_nan=True,
)
else:
compute_domain_kwargs = metric_domain_kwargs
(
df,
compute_domain_kwargs,
accessor_domain_kwargs,
) = execution_engine.get_compute_domain(
compute_domain_kwargs, domain_type=MetricDomainTypes.COLUMN)
# NOTE: 20201105 - parse_strings_as_datetimes is not supported here;
# instead detect types naturally
column = F.col(column_name)
if isinstance(column_metadata["type"],
(sparktypes.TimestampType, sparktypes.DateType)):
diff = F.datediff(
column,
F.lag(column).over(Window.orderBy(F.lit("constant"))))
else:
diff = column - F.lag(column).over(
Window.orderBy(F.lit("constant")))
diff = F.when(diff.isNull(), 1).otherwise(diff)
# NOTE: because in spark we are implementing the window function directly,
# we have to return the *unexpected* condition.
# If we expect values to be *strictly* increasing then unexpected values are those
# that are flat or decreasing
if metric_value_kwargs["strictly"] is True:
return (
F.when(diff <= 0, F.lit(True)).otherwise(F.lit(False)),
compute_domain_kwargs,
accessor_domain_kwargs,
)
# If we expect values to be flat or increasing then unexpected values are those
# that are decreasing
else:
return (
F.when(diff < 0, F.lit(True)).otherwise(F.lit(False)),
compute_domain_kwargs,
accessor_domain_kwargs,
)
def _spark(
cls,
execution_engine: SparkDFExecutionEngine,
metric_domain_kwargs: Dict,
metric_value_kwargs: Dict,
metrics: Dict[Tuple, Any],
runtime_configuration: Dict,
):
# check if column is any type that could have na (numeric types)
column_name = metric_domain_kwargs["column"]
table_columns = metrics["table.column_types"]
column_metadata = [
col for col in table_columns if col["name"] == column_name
][0]
if isinstance(
column_metadata["type"],
(
sparktypes.LongType,
sparktypes.DoubleType,
sparktypes.IntegerType,
),
):
# if column is any type that could have NA values, remove them (not filtered by .isNotNull())
compute_domain_kwargs = execution_engine.add_column_row_condition(
metric_domain_kwargs,
filter_null=cls.filter_column_isnull,
filter_nan=True,
)
else:
compute_domain_kwargs = metric_domain_kwargs
(
df,
compute_domain_kwargs,
accessor_domain_kwargs,
) = execution_engine.get_compute_domain(
compute_domain_kwargs, domain_type=MetricDomainTypes.COLUMN)
# NOTE: 20201105 - parse_strings_as_datetimes is not supported here;
# instead detect types naturally
column = F.col(column_name)
if isinstance(column_metadata["type"],
(sparktypes.TimestampType, sparktypes.DateType)):
diff = F.datediff(
column,
F.lag(column).over(Window.orderBy(F.lit("constant"))))
else:
diff = column - F.lag(column).over(
Window.orderBy(F.lit("constant")))
diff = F.when(diff.isNull(), 1).otherwise(diff)
# NOTE: because in spark we are implementing the window function directly,
# we have to return the *unexpected* condition.
# If we expect values to be *strictly* increasing then unexpected values are those
# that are flat or decreasing
if metric_value_kwargs["strictly"] is True:
return (
F.when(diff <= 0, F.lit(True)).otherwise(F.lit(False)),
compute_domain_kwargs,
accessor_domain_kwargs,
)
# If we expect values to be flat or increasing then unexpected values are those
# that are decreasing
else:
return (
F.when(diff < 0, F.lit(True)).otherwise(F.lit(False)),
compute_domain_kwargs,
accessor_domain_kwargs,
)
