postprocessor.core.multisignal.mi.miParameters¶
- class postprocessor.core.multisignal.mi.miParameters(**kwargs)¶
Bases:
ParametersABC
Parameters for the ‘mi’ process
Parameters for the ‘mi’ process.
- Attributes
- overtime: boolean (default: True)
If True, calculate the mutual information as a function of the duration of the time series, by finding the mutuation information for all possible sub-time series that start from t= 0.
- n_bootstraps: int, optional (default: 100)
The number of bootstraps used to estimate errors.
- ci: 1x2 array or list, optional (default: [0.25, 0.75])
The lower and upper confidence intervals.
E.g. [0.25, 0.75] for the interquartile range
- Crange: array, optional
An array of potential values for the C parameter of the support vector machine and from which the optimal value of C will be chosen.
If None, np.logspace(-3, 3, 10) is used. This range should be increased if the optimal C is one of the boundary values.
See https://scikit-learn.org/stable/modules/generated/sklearn.svm.SVC.html
- gammarange: array, optional
An array of potential values for the gamma parameter for the radial basis function kernel of the support vector machine and from which the optimal value of gamma will be chosen.
If None, np.logspace(-3, 3, 10) is used. This range should be increased if the optimal gamma is one of the boundary values.
See https://scikit-learn.org/stable/auto_examples/svm/plot_rbf_parameters.html
- train_test_split_seeding: boolean, optional (default: False)
If True, force a random state for the train-test split in each bootstrap. This is useful in case the user requires reproducibility e.g. code testing.
See https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html
Methods
from_yaml
(source)Returns instance from a yaml filename or stdin
to_dict
([iterable])Recursive function to return a nested dictionary of the attributes of the class instance.
to_yaml
([path])Returns a yaml stream of the attributes of the class instance.
update
(name, new_value)Update values recursively if name is a dictionary, inject data where found.
default
from_dict
- __init__(**kwargs)¶
Defines parameters as attributes
Methods
__init__
(**kwargs)Defines parameters as attributes
default
(**kwargs)from_dict
(d)from_yaml
(source)Returns instance from a yaml filename or stdin
to_dict
([iterable])Recursive function to return a nested dictionary of the attributes of the class instance.
to_yaml
([path])Returns a yaml stream of the attributes of the class instance.
update
(name, new_value)Update values recursively if name is a dictionary, inject data where found.
- classmethod from_yaml(source: Union[PosixPath, str])¶
Returns instance from a yaml filename or stdin
- to_dict(iterable='null')¶
Recursive function to return a nested dictionary of the attributes of the class instance.
- to_yaml(path: Optional[Union[PosixPath, str]] = None)¶
Returns a yaml stream of the attributes of the class instance. If path is provided, the yaml stream is saved there.
- Parameters
- pathUnion[PosixPath, str]
Output path.
- update(name: str, new_value)¶
Update values recursively if name is a dictionary, inject data where found. It forbids type changes.