pymecht.RandomParameters module

class pymecht.RandomParameters.Parameter(low, high, value, rtype)

Bases: object

Data structure to store a random parameter.

class pymecht.RandomParameters.RandomParameters(params)

Bases: object

A class to generate random parameters from sample parameters

Parameters:

params (ParamDict) – A dictionary of parameters (e.g., obtained from sample.parameters)

sample(N=1, sample_type=None)

Returns a list of N samples of the parameters

Parameters:

• N (int) – Number of samples to be generated

• sample_type (str) –

  Type of sampling to be performed. Options are

  • None (default)

  • ’lhcube’ for Latin-Hypercube sampling

  • ’sobol’ for Sobol sequence sampling

  If None, random sampling is performed.

Returns:

A list of N dictionaries with random values of the parameters

Return type:

list

fix(keys, x=None)

Fix the parameters to the value x

Parameters:

• keys (str or list of str) – The keys of the parameters to be fixed

• x (float or list of float) – The value to which the parameters are fixed

Return type:

None

make_normal(key, x=None)

Make the parameter normal with mean x

Parameters:

• key (str) – The key of the parameter to be made normal

• x (float) – The mean of the normal distribution

Return type:

None

make_lognormal(key, x=None)

Make the parameter lognormal with mean x

Parameters:

• key (str) – The key of the parameter to be made lognormal

• x (float) – The mean of the lognormal distribution

Return type:

None

add(key, value, low, high, rtype)

Add a new parameter

Parameters:

• key (str) – The key of the parameter

• value (float) – The default value of the parameter

• low (float) – The lower bound of the parameter

• high (float) – The upper bound of the parameter

• rtype (str) – The type of the parameter. Options are ‘fixed’, ‘uniform’, ‘normal’, and ‘lognormal’

Return type:

None

prob(param_sample)

Returns the probability of the parameter sample

Parameters:

param_sample (dict) – A dictionary of the parameter sample

Returns:

p – The probability of the parameter sample

Return type:

float