def evaluate(self,
data,
batch_size=32,
feature_cols=None,
label_cols=None):
from zoo.orca.data.utils import xshard_to_sample
assert data is not None, "validation data shouldn't be None"
assert self.metrics is not None, "metrics shouldn't be None, please specify the metrics" \
" argument when creating this estimator."
if isinstance(data, SparkXShards):
val_feature_set = FeatureSet.sample_rdd(
data.rdd.flatMap(xshard_to_sample))
result = self.estimator.evaluate(val_feature_set, self.metrics,
batch_size)
elif isinstance(data, DataFrame):
schema = data.schema
val_feature_set = FeatureSet.sample_rdd(
data.rdd.map(lambda row: row_to_sample(
row, schema, feature_cols, label_cols)))
result = self.estimator.evaluate(val_feature_set, self.metrics,
batch_size)
elif isinstance(data, DataLoader) or callable(data):
val_feature_set = FeatureSet.pytorch_dataloader(data)
result = self.estimator.evaluate_minibatch(val_feature_set,
self.metrics)
else:
raise ValueError(
"Data should be a SparkXShards, a DataLoader or a callable "
"data_creator, but get " + data.__class__.__name__)
return bigdl_metric_results_to_dict(result)
def evaluate(self,
data,
batch_size=32,
feature_cols=None,
label_cols=None):
"""
Evaluate model.
:param data: validation data. It can be XShards, each partition is a dictionary of
{'x': feature, 'y': label}, where feature(label) is a numpy array or a list of numpy arrays.
:param batch_size: Batch size used for validation. Default: 32.
:param feature_cols: (Not supported yet) Feature column name(s) of data. Only used when
data is a Spark DataFrame. Default: None.
:param label_cols: (Not supported yet) Label column name(s) of data. Only used when data
is a Spark DataFrame. Default: None.
:return:
"""
assert data is not None, "validation data shouldn't be None"
assert self.metrics is not None, "metrics shouldn't be None, please specify the metrics" \
" argument when creating this estimator."
if isinstance(data, DataFrame):
raise NotImplementedError
elif isinstance(data, SparkXShards):
from zoo.orca.data.utils import xshard_to_sample
val_feature_set = FeatureSet.sample_rdd(
data.rdd.flatMap(xshard_to_sample))
result = self.estimator.evaluate(val_feature_set, self.metrics,
batch_size)
else:
raise ValueError(
"Data should be XShards or Spark DataFrame, but get " +
data.__class__.__name__)
return bigdl_metric_results_to_dict(result)
def evaluate(self,
data,
batch_size=32,
feature_cols="features",
label_cols="label"):
"""
Evaluate model.
:param data: validation data. It can be XShardsor or Spark DataFrame, each partition is
a dictionary of {'x': feature, 'y': label}, where feature(label) is a numpy array
or a list of numpy arrays.
:param batch_size: Batch size used for validation. Default: 32.
:param feature_cols: (Not supported yet) Feature column name(s) of data. Only used when
data is a Spark DataFrame. Default: None.
:param label_cols: (Not supported yet) Label column name(s) of data. Only used when data
is a Spark DataFrame. Default: None.
:return:
"""
assert data is not None, "validation data shouldn't be None"
assert self.metrics is not None, "metrics shouldn't be None, please specify the metrics" \
" argument when creating this estimator."
if isinstance(data, DataFrame):
if isinstance(feature_cols, list):
data, _, feature_cols = \
BigDLEstimator._combine_cols(data, [feature_cols], col_name="features")
if isinstance(label_cols, list):
data, _, label_cols = \
BigDLEstimator._combine_cols(data, label_cols, col_name="label")
self.nn_estimator._setNNBatchSize(batch_size)._setNNFeaturesCol(feature_cols) \
._setNNLabelCol(label_cols)
self.nn_estimator.setValidation(None, None, self.metrics,
batch_size)
if self.log_dir is not None and self.app_name is not None:
from bigdl.optim.optimizer import TrainSummary
from bigdl.optim.optimizer import ValidationSummary
val_summary = ValidationSummary(log_dir=self.log_dir,
app_name=self.app_name)
self.nn_estimator.setValidationSummary(val_summary)
result = self.nn_estimator._eval(data)
elif isinstance(data, SparkXShards):
from zoo.orca.data.utils import xshard_to_sample
val_feature_set = FeatureSet.sample_rdd(
data.rdd.flatMap(xshard_to_sample))
result = self.estimator.evaluate(val_feature_set, self.metrics,
batch_size)
else:
raise ValueError(
"Data should be XShards or Spark DataFrame, but get " +
data.__class__.__name__)
return bigdl_metric_results_to_dict(result)
def evaluate(self,
data,
batch_size=32,
feature_cols=None,
label_cols=None,
validation_metrics=None):
"""
Evaluate model.
:param data: data: evaluation data. It can be an XShards, Spark Dataframe,
PyTorch DataLoader and PyTorch DataLoader creator function.
If data is an XShards, each partition can be a Pandas DataFrame or a dictionary of
{'x': feature, 'y': label}, where feature(label) is a numpy array or a list of
numpy arrays.
:param batch_size: Batch size used for evaluation. Only used when data is a SparkXShard.
:param feature_cols: Feature column name(s) of data. Only used when data
is a Spark DataFrame or an XShards of Pandas DataFrame. Default: None.
:param label_cols: Label column name(s) of data. Only used when data is
a Spark DataFrame or an XShards of Pandas DataFrame. Default: None.
:param validation_metrics: Orca validation metrics to be computed on validation_data.
:return: validation results.
"""
from zoo.orca.data.utils import xshard_to_sample
assert data is not None, "validation data shouldn't be None"
assert self.metrics is not None, "metrics shouldn't be None, please specify the metrics" \
" argument when creating this estimator."
if isinstance(data, SparkXShards):
if data._get_class_name() == 'pandas.core.frame.DataFrame':
data = process_xshards_of_pandas_dataframe(
data, feature_cols, label_cols)
val_feature_set = FeatureSet.sample_rdd(
data.rdd.flatMap(xshard_to_sample))
result = self.estimator.evaluate(val_feature_set, self.metrics,
batch_size)
elif isinstance(data, DataFrame):
schema = data.schema
val_feature_set = FeatureSet.sample_rdd(
data.rdd.map(lambda row: row_to_sample(
row, schema, feature_cols, label_cols)))
result = self.estimator.evaluate(val_feature_set, self.metrics,
batch_size)
elif isinstance(data, DataLoader) or callable(data):
val_feature_set = FeatureSet.pytorch_dataloader(data)
result = self.estimator.evaluate_minibatch(val_feature_set,
self.metrics)
else:
raise ValueError(
"Data should be a SparkXShards, a DataLoader or a callable "
"data_creator, but get " + data.__class__.__name__)
return bigdl_metric_results_to_dict(result)
def evaluate(self, data, batch_size=32, feature_cols=None, label_cols=None):
assert data is not None, "validation data shouldn't be None"
assert self.metrics is not None, "metrics shouldn't be None, please specify the metrics" \
" argument when creating this estimator."
if isinstance(data, DataFrame):
raise NotImplementedError
elif isinstance(data, SparkXShards):
from zoo.orca.data.utils import xshard_to_sample
from zoo.orca.learn.metrics import Metrics
val_feature_set = FeatureSet.sample_rdd(data.rdd.flatMap(xshard_to_sample))
result = self.estimator.evaluate(val_feature_set, self.metrics, batch_size)
else:
raise ValueError("Data should be XShards or Spark DataFrame, but get " +
data.__class__.__name__)
return bigdl_metric_results_to_dict(result)
