Bayesian

The samplesizelib.linear.bayesian contains classes: - samplesizelib.linear.bayesian.APVCEstimator - samplesizelib.linear.bayesian.ACCEstimator - samplesizelib.linear.bayesian.ALCEstimator - samplesizelib.linear.bayesian.MaxUtilityEstimator - samplesizelib.linear.bayesian.KLEstimator

class samplesizelib.linear.bayesian.ACCEstimator(statmodel, **kwards)[source]

Description of ACC Method

Parameters:
  • statmodel (RegressionModel or LogisticModel) – the machine learning algorithm
  • averaging (float) – to do
  • alpha (float) – to do
  • length (float) – to do
  • begin (int) – to do
  • end (int) – to do
  • num (int) – to do
  • multiprocess (bool) – to do
  • progressbar (bool) – to do
forward(features, target)[source]

Returns sample size prediction for the given dataset.

Parameters:
  • features (array.) – The tensor of shape num_elements \(\times\) num_feature.
  • target (array.) – The tensor of shape num_elements.
Returns:

sample size estimation for the given dataset.
Return type:

dict
class samplesizelib.linear.bayesian.ALCEstimator(statmodel, **kwards)[source]

Description of ALC Method

Parameters:
  • statmodel (RegressionModel or LogisticModel) – the machine learning algorithm
  • averaging (float) – to do
  • alpha (float) – to do
  • length (float) – to do
  • begin (int) – to do
  • end (int) – to do
  • num (int) – to do
  • multiprocess (bool) – to do
  • progressbar (bool) – to do
forward(features, target)[source]

Returns sample size prediction for the given dataset.

Parameters:
  • features (array.) – The tensor of shape num_elements \(\times\) num_feature.
  • target (array.) – The tensor of shape num_elements.
Returns:

sample size estimation for the given dataset.
Return type:

dict
class samplesizelib.linear.bayesian.APVCEstimator(statmodel, **kwards)[source]

Description of APVC Method

Parameters:
  • statmodel (RegressionModel or LogisticModel) – the machine learning algorithm
  • averaging (float) – to do
  • epsilon (float) – to do
  • begin (int) – to do
  • end (int) – to do
  • num (int) – to do
  • multiprocess (bool) – to do
  • progressbar (bool) – to do
forward(features, target)[source]

Returns sample size prediction for the given dataset.

Parameters:
  • features (array.) – The tensor of shape num_elements \(\times\) num_feature.
  • target (array.) – The tensor of shape num_elements.
Returns:

sample size estimation for the given dataset.
Return type:

dict
class samplesizelib.linear.bayesian.KLEstimator(statmodel, **kwards)[source]

Description of KL based Method

Parameters:
  • statmodel (RegressionModel or LogisticModel) – the machine learning algorithm
  • averaging (float) – to do
  • epsilon (float) – to do
  • begin (int) – to do
  • end (int) – to do
  • num (int) – to do
  • multiprocess (bool) – to do
  • progressbar (bool) – to do
forward(features, target)[source]

Returns sample size prediction for the given dataset.

Parameters:
  • features (array.) – The tensor of shape num_elements \(\times\) num_feature.
  • target (array.) – The tensor of shape num_elements.
Returns:

sample size estimation for the given dataset.
Return type:

dict
class samplesizelib.linear.bayesian.MaxUtilityEstimator(statmodel, **kwards)[source]

Description of Utility Maximisation Method

Parameters:
  • statmodel (RegressionModel or LogisticModel) – the machine learning algorithm
  • averaging (float) – to do
  • c (float) – to do
  • begin (int) – to do
  • end (int) – to do
  • num (int) – to do
  • multiprocess (bool) – to do
  • progressbar (bool) – to do
forward(features, target)[source]

Returns sample size prediction for the given dataset.

Parameters:
  • features (array.) – The tensor of shape num_elements \(\times\) num_feature.
  • target (array.) – The tensor of shape num_elements.
Returns:

sample size estimation for the given dataset.
Return type:

dict