def evaluate(self,
data,
batch_size=32,
feature_cols=None,
labels_cols=None,
hard_code_batch_size=False):
assert self.metrics is not None, \
"metrics is None, it should not be None in evaluate"
if isinstance(data, DataFrame):
assert feature_cols is not None, \
"feature columns is None; it should not be None in evaluation"
assert labels_cols is not None, \
"label columns is None; it should not be None in evaluation"
dataset = to_dataset(data,
batch_size=-1,
batch_per_thread=batch_size,
validation_data=None,
feature_cols=feature_cols,
labels_cols=labels_cols,
hard_code_batch_size=hard_code_batch_size,
sequential_order=True,
shuffle=False)
flat_inputs = nest.flatten(self.inputs)
flat_labels = nest.flatten(self.labels)
return evaluate_metrics(flat_inputs + flat_labels,
sess=self.sess,
dataset=dataset,
metrics=self.metrics)
def evaluate(
self,
data,
batch_size=32,
feature_cols=None,
labels_cols=None,
hard_code_batch_size=False,
auto_shard_files=True,
):
"""
Evaluate model.
:param data: evaluation data. It can be XShards, Spark DataFrame, tf.data.Dataset.
If data is XShards, each element needs to be {'x': a feature numpy array
or a tuple of feature numpy arrays, 'y': a label numpy array or a tuple of
label numpy arrays}
If data is tf.data.Dataset, each element is a tuple of input tensors.
:param batch_size: batch size per thread.
:param feature_cols: feature_cols: feature column names if train data is Spark DataFrame.
:param labels_cols: label column names if train data is Spark DataFrame.
:param hard_code_batch_size: whether to hard code batch size for evaluation.
:return: evaluation result as a dictionary of {'metric name': metric value}
"""
assert self.metrics is not None, \
"metrics is None, it should not be None in evaluate"
if isinstance(data, DataFrame):
assert feature_cols is not None, \
"feature columns is None; it should not be None in evaluation"
assert labels_cols is not None, \
"label columns is None; it should not be None in evaluation"
dataset = to_dataset(
data,
batch_size=-1,
batch_per_thread=batch_size,
validation_data=None,
feature_cols=feature_cols,
labels_cols=labels_cols,
hard_code_batch_size=hard_code_batch_size,
sequential_order=True,
shuffle=False,
auto_shard_files=auto_shard_files,
)
flat_inputs = nest.flatten(self.inputs)
flat_labels = nest.flatten(self.labels)
return evaluate_metrics(flat_inputs + flat_labels,
sess=self.sess,
dataset=dataset,
metrics=self.metrics)
def evaluate(
self,
data,
batch_size=32,
feature_cols=None,
label_cols=None,
auto_shard_files=False,
):
"""
Evaluate model.
:param data: evaluation data. It can be XShards, Spark DataFrame, tf.data.Dataset.
If data is XShards, each partition is a dictionary of {'x': feature, 'y': label}, where
feature(label) is a numpy array or a tuple of numpy arrays.
If data is tf.data.Dataset, each element is a tuple of input tensors.
:param batch_size: batch size per thread.
:param feature_cols: feature_cols: feature column names if train data is Spark DataFrame.
:param label_cols: label column names if train data is Spark DataFrame.
:param auto_shard_files: whether to automatically detect if the dataset is file-based and
and apply sharding on files, otherwise sharding on records. Default is False.
:return: evaluation result as a dictionary of {'metric name': metric value}
"""
assert self.metrics is not None, \
"metrics is None, it should not be None in evaluate"
if isinstance(data, DataFrame):
assert feature_cols is not None, \
"feature columns is None; it should not be None in evaluation"
assert label_cols is not None, \
"label columns is None; it should not be None in evaluation"
dataset = to_dataset(
data,
batch_size=-1,
batch_per_thread=batch_size,
validation_data=None,
feature_cols=feature_cols,
label_cols=label_cols,
hard_code_batch_size=False,
sequential_order=True,
shuffle=False,
auto_shard_files=auto_shard_files,
)
flat_inputs = nest.flatten(self.inputs)
flat_labels = nest.flatten(self.labels)
return evaluate_metrics(flat_inputs + flat_labels,
sess=self.sess,
dataset=dataset,
metrics=self.metrics)
def evaluate(self, data, batch_size=32):
assert self.metrics is not None, \
"metrics is None, it should not be None in evaluate"
dataset = _to_dataset(data, batch_size=-1, batch_per_thread=batch_size)
flat_inputs = nest.flatten(self.inputs)
flat_labels = nest.flatten(self.labels)
return evaluate_metrics(flat_inputs + flat_labels,
sess=self.sess,
dataset=dataset,
metrics=self.metrics)