leaspy.datasets.loader module

class Loader

Bases: object

Contains static methods to load synthetic longitudinal dataset, calibrated Leaspy instances & IndividualParameters.

Notes

A Leaspy instance named <name> have been calibrated on the dataset <name>.
An IndividualParameters name <name> have been computed by personalizing the Leaspy instance named <name> on the dataset <name>.

See the documentation of each method to get their respective available names.

Attributes:

data_pathsdict [str, str]: Contains the datasets’ names and their respective path within leaspy.datasets subpackage.
model_pathsdict [str, str]: Contains the Leaspy instances’ names and their respective path within leaspy.datasets subpackage.
ip_pathsdict [str, str]: Contains the individual parameters’ names and their respective path within leaspy.datasets subpackage.

Methods

`load_dataset`(dataset_name)	Load synthetic longitudinal observations mimicking cohort of subjects with neurodegenerative disorders.
`load_individual_parameters`(ip_name)	Load a Leaspy instance with a model already calibrated on the synthetic dataset corresponding to the name of the instance.
`load_leaspy_instance`(instance_name)	Load a Leaspy instance with a model already calibrated on the synthetic dataset corresponding to the name of the instance.

static load_dataset(dataset_name)

Load synthetic longitudinal observations mimicking cohort of subjects with neurodegenerative disorders.

Parameters:

dataset_name{‘parkinson-multivariate’, ‘alzheimer-multivariate’, ‘parkinson-putamen’, ‘parkinson-putamen-train_and_test’}: Name of the dataset.

Returns:

pandas.DataFrame: DataFrame containing the IDs, timepoints and observations.

Notes

All DataFrames have the same structures.

Index: a pandas.MultiIndex - ['ID', 'TIME'] which contain IDs and timepoints. The DataFrame is sorted by index. So, one line corresponds to one visit for one subject. The DataFrame having ‘train_and_test’ in their name also have 'SPLIT' as the third index level. It differentiate train and test data.
Columns: One column correspond to one feature (or score).

static load_individual_parameters(ip_name)

Load a Leaspy instance with a model already calibrated on the synthetic dataset corresponding to the name of the instance.

Parameters:

ip_name{‘alzheimer-multivariate’, ‘parkinson-multivariate’, ‘parkinson-putamen-train’}: Name of the individual parameters.

Returns:

static load_leaspy_instance(instance_name)

Load a Leaspy instance with a model already calibrated on the synthetic dataset corresponding to the name of the instance.

Parameters:

instance_name{‘alzheimer-multivariate’, ‘parkinson-multivariate’, ‘parkinson-putamen-train’}: Name of the instance.

Returns: