def empty_feature_detection(data_instances):
is_empty_feature = data_overview.is_empty_feature(data_instances)
if is_empty_feature:
table_name = data_instances.get_name()
namespace = data_instances.get_namespace()
raise ValueError(
"Number of features of DTable is 0., table_name: {}, namespace: {}"
.format(table_name, namespace))
def fit(self, data):
LOGGER.debug(f"fit receives data is {data}")
if not isinstance(data, dict):
raise ValueError(
"Union module must receive more than one table as input.")
empty_count = 0
combined_table = None
combined_schema = None
metrics = []
for (key, local_table) in data.items():
LOGGER.debug("table to combine name: {}".format(key))
num_data = local_table.count()
LOGGER.debug("table count: {}".format(num_data))
metrics.append(Metric(key, num_data))
self.add_summary(key, num_data)
if num_data == 0:
LOGGER.warning("Table {} is empty.".format(key))
if combined_table is None:
combined_table = local_table
combined_schema = local_table.schema
empty_count += 1
continue
local_is_data_instance = self.check_is_data_instance(local_table)
if combined_table is None:
self.is_data_instance = local_is_data_instance
LOGGER.debug(f"self.is_data_instance is {self.is_data_instance}, "
f"local_is_data_instance is {local_is_data_instance}")
if self.is_data_instance != local_is_data_instance:
raise ValueError(
f"Cannot combine DataInstance and non-DataInstance object. Union aborted."
)
if self.is_data_instance:
self.is_empty_feature = data_overview.is_empty_feature(
local_table)
if self.is_empty_feature:
LOGGER.warning("Table {} has empty feature.".format(key))
else:
self.check_schema_content(local_table.schema)
if combined_table is None:
# first table to combine
combined_table = local_table
combined_schema = local_table.schema
else:
self.check_id(local_table, combined_table)
self.check_label_name(local_table, combined_table)
self.check_header(local_table, combined_table)
if self.keep_duplicate:
repeated_ids = combined_table.join(local_table,
lambda v1, v2: 1)
self.repeated_ids = [v[0] for v in repeated_ids.collect()]
self.key = key
local_table = local_table.flatMap(self._renew_id)
combined_table = combined_table.union(local_table,
self._keep_first)
combined_table.schema = combined_schema
# only check feature length if not empty
if self.is_data_instance and not self.is_empty_feature:
self.feature_count = len(combined_schema.get("header"))
LOGGER.debug("feature count: {}".format(self.feature_count))
combined_table.mapValues(self.check_feature_length)
if combined_table is None:
num_data = 0
LOGGER.warning(
"All tables provided are empty or have empty features.")
else:
num_data = combined_table.count()
metrics.append(Metric("Total", num_data))
self.add_summary("Total", num_data)
self.callback_metric(metric_name=self.metric_name,
metric_namespace=self.metric_namespace,
metric_data=metrics)
self.tracker.set_metric_meta(metric_namespace=self.metric_namespace,
metric_name=self.metric_name,
metric_meta=MetricMeta(
name=self.metric_name,
metric_type=self.metric_type))
LOGGER.info(
"Union operation finished. Total {} empty tables encountered.".
format(empty_count))
return combined_table
def empty_feature_detection(data_instances):
is_empty_feature = data_overview.is_empty_feature(data_instances)
if is_empty_feature:
raise ValueError(f"Number of features of Table is 0: {data_instances}")
def fit(self, data):
if not isinstance(data, dict):
raise ValueError(
"Union module must receive more than one table as input.")
empty_count = 0
combined_table = None
combined_schema = None
metrics = []
for (key, local_table) in data.items():
LOGGER.debug("table to combine name: {}".format(key))
num_data = local_table.count()
LOGGER.debug("table count: {}".format(num_data))
local_schema = local_table.schema
metrics.append(Metric(key, num_data))
if num_data == 0:
LOGGER.warning("Table {} is empty.".format(key))
empty_count += 1
continue
if combined_table is None:
self.check_is_data_instance(local_table)
if self.is_data_instance:
self.is_empty_feature = data_overview.is_empty_feature(
local_table)
if self.is_empty_feature:
LOGGER.warning("Table {} has empty feature.".format(key))
if combined_table is None:
# first table to combine
combined_table = local_table
if self.is_data_instance:
combined_schema = local_table.schema
combined_table.schema = combined_schema
else:
self.check_schema_id(local_schema, combined_schema)
self.check_schema_label_name(local_schema, combined_schema)
self.check_schema_header(local_schema, combined_schema)
combined_table = combined_table.union(local_table,
self._keep_first)
# only check feature length if not empty
if self.is_data_instance and not self.is_empty_feature:
self.feature_count = len(combined_schema.get("header"))
LOGGER.debug("feature count: {}".format(self.feature_count))
combined_table.mapValues(self.check_feature_length)
if combined_table is None:
num_data = 0
LOGGER.warning(
"All tables provided are empty or have empty features.")
else:
num_data = combined_table.count()
metrics.append(Metric("Total", num_data))
self.callback_metric(metric_name=self.metric_name,
metric_namespace=self.metric_namespace,
metric_data=metrics)
self.tracker.set_metric_meta(metric_namespace=self.metric_namespace,
metric_name=self.metric_name,
metric_meta=MetricMeta(
name=self.metric_name,
metric_type=self.metric_type))
LOGGER.info(
"Union operation finished. Total {} empty tables encountered.".
format(empty_count))
return combined_table
