def test_batch_average(self):
expected_error = 0.9 # or 225 / 250
actual_error = average_batch_errors([1, 1, 0.5], 250, 100)
self.assertAlmostEqual(expected_error, actual_error)
expected_error = 0.8 # or 240 / 300
actual_error = average_batch_errors([1, 1, 0.4], 300, 100)
self.assertAlmostEqual(expected_error, actual_error)
def test_batch_average(self):
expected_error = 0.9 # or 225 / 250
actual_error = average_batch_errors([1, 1, 0.5], 250, 100)
self.assertAlmostEqual(expected_error, actual_error)
expected_error = 0.8 # or 270 / 300
actual_error = average_batch_errors([1, 1, 0.4], 300, 100)
self.assertAlmostEqual(expected_error, actual_error)
def prediction_error(self, input_data, target_data=None):
"""
Compute the pseudo-likelihood of input samples.
Parameters
----------
input_data : array-like
Values of the visible layer
Returns
-------
float
Value of the pseudo-likelihood.
"""
is_input_feature1d = (self.n_visible == 1)
input_data = format_data(input_data, is_input_feature1d)
errors = self.apply_batches(
function=self.methods.prediction_error,
input_data=input_data,
description='Validation batches',
show_error_output=True,
)
return average_batch_errors(errors,
n_samples=len(input_data),
batch_size=self.batch_size)
def prediction_error(self, input_data, target_data=None):
"""
Compute the pseudo-likelihood of input samples.
Parameters
----------
input_data : array-like
Values of the visible layer
Returns
-------
float
Value of the pseudo-likelihood.
"""
is_input_feature1d = (self.n_visible == 1)
input_data = format_data(input_data, is_input_feature1d)
errors = self.apply_batches(
function=self.methods.prediction_error,
input_data=input_data,
description='Validation batches',
show_error_output=True,
)
return average_batch_errors(
errors,
n_samples=len(input_data),
batch_size=self.batch_size,
)
def train_epoch(self, input_train, target_train=None):
"""
Train one epoch.
Parameters
----------
input_train : array-like (n_samples, n_features)
Returns
-------
float
"""
errors = self.apply_batches(
function=self.methods.train_epoch,
input_data=input_train,
description='Training batches',
show_error_output=True,
)
n_samples = len(input_train)
return average_batch_errors(errors, n_samples, self.batch_size)
def train_epoch(self, input_train, target_train=None):
"""
Train one epoch.
Parameters
----------
input_train : array-like (n_samples, n_features)
Returns
-------
float
"""
errors = self.apply_batches(
function=self.methods.train_epoch,
input_data=input_train,
description='Training batches',
show_error_output=True,
)
n_samples = len(input_train)
return average_batch_errors(errors, n_samples, self.batch_size)
