qbiocode.data_generation package#

Data Generation Module for QBioCode.

This module provides functions to generate synthetic datasets for testing machine learning algorithms. Each function creates multiple dataset configurations with varying parameters, useful for benchmarking and evaluation.

Available dataset generators: - generate_blobs_datasets: Isotropic Gaussian blobs (clusters) - generate_circles_datasets: 2D concentric circles - generate_moons_datasets: 2D interleaving half-circles - generate_classification_datasets: High-dimensional multi-class data - generate_s_curve_datasets: 3D S-shaped manifold - generate_spheres_datasets: N-dimensional concentric spheres - generate_spirals_datasets: N-dimensional intertwined spirals - generate_swiss_roll_datasets: 3D Swiss roll manifold

Submodules:

Summary#

__all__ Functions:

generate_blobs_datasets

Generate multiple blob (Gaussian cluster) datasets with varying parameters.

generate_circles_datasets

Generate multiple concentric circles datasets with varying parameters.

generate_classification_datasets

Generate multiple high-dimensional classification datasets with varying parameters.

generate_default_blobs_datasets

Generate blob datasets with default parameter configurations.

generate_moons_datasets

Generate multiple two-moons datasets with varying parameters.

generate_s_curve_datasets

Generate multiple 3D S-curve datasets with varying parameters.

generate_spheres_datasets

Generate multiple concentric n-dimensional spheres datasets with varying parameters.

generate_spirals_datasets

Generate multiple n-dimensional spiral datasets with varying parameters.

generate_swiss_roll_datasets

Generate multiple 3D Swiss roll datasets with varying parameters.