bayesvalidrox.bayes_inference.bayes_model_comparison.BayesModelComparison¶

class bayesvalidrox.bayes_inference.bayes_model_comparison.BayesModelComparison(justifiability=True, perturbed_data=None, n_bootstrap=1000, data_noise_level=0.01, use_Bayes_settings=True, emulator=True, out_dir='Outputs_Comparison/')¶

Bases: object

A class to perform Bayesian Analysis.

Attributes¶

justifiabilitybool, optional: Whether to perform the justifiability analysis. The default is True.
perturbed_dataarray of shape (n_bootstrap_itrs, n_obs), optional: User defined perturbed data. The default is None.
n_bootstrapint: Number of bootstrap iteration. The default is 1000.
data_noise_levelfloat: A noise level to perturb the data set. The default is 0.01.

__init__(justifiability=True, perturbed_data=None, n_bootstrap=1000, data_noise_level=0.01, use_Bayes_settings=True, emulator=True, out_dir='Outputs_Comparison/')¶

Methods

`__init__`([justifiability, perturbed_data, ...])
`cal_model_weight`(BME_dict[, justifiability, ...])	Normalize the BME (Asumption: Model Prior weights are equal for models)
`calc_bayes_factors`(model_dict, opts_dict)	Calculate the BayesFactors for each pair of models in the model_dict with respect to given data.
`calc_justifiability_analysis`(model_dict, ...)	Perform justifiability analysis by calculating the confusion matrix
`calc_model_weights`(model_dict, opts_dict)	Calculate the model weights from BME evaluations for Bayes factors.
`generate_dataset`(model_dict[, ...])	Generates the perturbed data set for the Bayes factor calculations and the data set for the justifiability analysis.
`model_comparison_all`(model_dict, opts_dict)	Perform all three types of model comparison:
`plot_bayes_factor`(BME_dict[, plot_name])	Plots the Bayes factor distibutions in a \(N_m \times N_m\) matrix, where \(N_m\) is the number of the models.
`plot_just_analysis`()	Visualizes the confusion matrix and the model wights for the justifiability analysis.
`plot_model_weights`(model_weights, plot_name)	Visualizes the model weights resulting from BMS via the observation data.
`setup`(model_dict)	Initialize parameters that are needed for all types of model comparison

cal_model_weight(BME_dict, justifiability=False, n_bootstrap=1)¶

Normalize the BME (Asumption: Model Prior weights are equal for models)

Parameters¶

BME_dictdict: A dictionary containing the BME values.

Returns¶

model_weightsarray: Model weights.

calc_bayes_factors(model_dict, opts_dict)¶

Calculate the BayesFactors for each pair of models in the model_dict with respect to given data.

Parameters¶

model_dictdict: A dictionary including the metamodels.
opts_dictdict: A dictionary given the BayesInference options.

Returns¶

None.

calc_justifiability_analysis(model_dict, opts_dict)¶

Perform justifiability analysis by calculating the confusion matrix

Parameters¶

model_dictdict: A dictionary including the metamodels.
opts_dictdict: A dictionary given the BayesInference options.

Returns¶

confusion_matrix: dict: The averaged confusion matrix

calc_model_weights(model_dict, opts_dict)¶

Calculate the model weights from BME evaluations for Bayes factors.

Parameters¶

model_dictTYPE: DESCRIPTION.
opts_dictTYPE: DESCRIPTION.

Returns¶

None.

generate_dataset(model_dict, justifiability=False, n_bootstrap=1)¶

Generates the perturbed data set for the Bayes factor calculations and the data set for the justifiability analysis.

Parameters¶

model_dictdict: A dictionary including the metamodels.
bool, optional: Whether to perform the justifiability analysis. The default is False.
n_bootstrapint, optional: Number of bootstrap iterations. The default is 1.

Returns¶

all_just_data: array: Created data set.

model_comparison_all(model_dict, opts_dict)¶

Perform all three types of model comparison:

Bayes Factors
Model weights
Justifiability analysis

Parameters¶

model_dictdict: A dictionary including the metamodels.
opts_dictdict: A dictionary given the BayesInference options.

Returns¶

resultsdict: A dictionary that contains the calculated BME values, model weights and confusion matrix

plot_bayes_factor(BME_dict, plot_name='')¶

Plots the Bayes factor distibutions in a \(N_m \times N_m\) matrix, where \(N_m\) is the number of the models.

Parameters¶

BME_dictdict: A dictionary containing the BME values of the models.
plot_namestr, optional: Plot name. The default is ‘’.

Returns¶

None.

plot_just_analysis()¶

Visualizes the confusion matrix and the model wights for the justifiability analysis.

Parameters¶

model_weights_dictdict: Model weights.

Returns¶

None.

plot_model_weights(model_weights, plot_name)¶

Visualizes the model weights resulting from BMS via the observation data.

Parameters¶

model_weightsarray: Model weights.
plot_namestr: Plot name.

Returns¶

None.

setup(model_dict)¶: Initialize parameters that are needed for all types of model comparison

Returns¶

None.