def predict(self,
data,
batch_size=4,
feature_cols=None,
hard_code_batch_size=False):
if isinstance(data, DataFrame):
assert feature_cols is not None, \
"feature columns is None; it should not be None in prediction"
dataset = to_dataset(data,
batch_size=-1,
batch_per_thread=batch_size,
validation_data=None,
feature_cols=feature_cols,
labels_cols=None,
hard_code_batch_size=hard_code_batch_size,
sequential_order=True,
shuffle=False)
predicted_rdd = self.model.predict(dataset, batch_size)
if isinstance(data, DataFrame):
return convert_predict_to_dataframe(data, predicted_rdd)
else:
return predicted_rdd
def fit(self,
data,
epochs=1,
batch_size=32,
feature_cols=None,
labels_cols=None,
validation_data=None,
hard_code_batch_size=False,
session_config=None):
if isinstance(data, DataFrame):
assert feature_cols is not None, \
"feature columns is None; it should not be None in training"
assert labels_cols is not None, \
"label columns is None; it should not be None in training"
dataset = to_dataset(data,
batch_size=batch_size,
batch_per_thread=-1,
validation_data=validation_data,
feature_cols=feature_cols,
labels_cols=labels_cols,
hard_code_batch_size=hard_code_batch_size,
sequential_order=False,
shuffle=True)
self.model.fit(dataset,
batch_size=batch_size,
epochs=epochs,
session_config=session_config)
return self
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 predict(self,
data,
batch_size=4,
feature_cols=None,
hard_code_batch_size=False):
assert self.outputs is not None, \
"output is None, it should not be None in prediction"
if isinstance(data, DataFrame):
assert feature_cols is not None, \
"feature columns is None; it should not be None in prediction"
dataset = to_dataset(data,
batch_size=-1,
batch_per_thread=batch_size,
validation_data=None,
feature_cols=feature_cols,
labels_cols=None,
hard_code_batch_size=hard_code_batch_size,
sequential_order=True,
shuffle=False)
flat_inputs = nest.flatten(self.inputs)
flat_outputs = nest.flatten(self.outputs)
tfnet = TFNet.from_session(sess=self.sess,
inputs=flat_inputs,
outputs=flat_outputs)
predicted_rdd = tfnet.predict(dataset)
if isinstance(data, DataFrame):
return convert_predict_to_dataframe(data, predicted_rdd)
else:
return predicted_rdd
def fit(self,
data,
epochs=1,
batch_size=32,
feature_cols=None,
labels_cols=None,
validation_data=None,
hard_code_batch_size=False,
session_config=None,
feed_dict=None):
assert self.labels is not None, \
"labels is None; it should not be None in training"
assert self.loss is not None, \
"loss is None; it should not be None in training"
assert self.optimizer is not None, \
"optimizer is None; it should not be None in training"
if isinstance(data, DataFrame):
assert feature_cols is not None, \
"feature columns is None; it should not be None in training"
assert labels_cols is not None, \
"label columns is None; it should not be None in training"
dataset = to_dataset(data,
batch_size=batch_size,
batch_per_thread=-1,
validation_data=validation_data,
feature_cols=feature_cols,
labels_cols=labels_cols,
hard_code_batch_size=hard_code_batch_size,
sequential_order=False,
shuffle=True)
if feed_dict is not None:
tensor_with_value = {
key: (value, value)
for key, value in feed_dict.items()
}
else:
tensor_with_value = None
optimizer = TFOptimizer.from_train_op(
train_op=self.train_op,
loss=self.loss,
inputs=self.inputs,
labels=self.labels,
dataset=dataset,
metrics=self.metrics,
updates=self.updates,
sess=self.sess,
tensor_with_value=tensor_with_value,
session_config=session_config,
model_dir=self.model_dir)
optimizer.optimize(end_trigger=MaxEpoch(epochs))
return self
def evaluate(self, data, batch_size=4,
feature_cols=None,
labels_cols=None,
hard_code_batch_size=False
):
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
)
return self.model.evaluate(dataset, batch_per_thread=batch_size)