environment_lib_class

class soda_analyzer.environment_lib_class(h5_lib, env_load=False, structure_load=False)

Inspect APE descriptor environments, cluster membership, and model provenance.

Parameters:

• h5_lib (h5py.File) – Open SODA HDF5 file. Keep it open while using views derived from it.

• env_load (bool, optional) – Populate the environment object list during loading. Default: False.

• structure_load (bool, optional) – Construct ASE structure objects during loading rather than on a later request. Default: False.

registry_table

Descriptor registry records.

Type:

numpy.ndarray

full_descriptors

Full descriptor matrix.

Type:

numpy.ndarray

meta

Embedding and clustering metadata.

Type:

dict

env_list

Environment views populated when requested.

Type:

list of environment_class

Notes

Available under the public name ApeEnvironmentLibrary; environment_lib_class remains a compatible name.

This record borrows its HDF5 handle. Keep the owning library open while accessing related records or lazily loaded data.

Methods

build_decaf_model	Reconstruct the DECAF model using this library metadata.
export_cluster_members	Write source structures containing members of one cluster.
get_atom	Read the central atom associated with a registry row.
get_atoms	Read the full source structure associated with a registry row.
get_atoms_by_trace	Read a source structure or one atom using its registry trace.
get_cluster_birth_cycle	Read the earliest known descriptor update cycle for a cluster.
get_cluster_birth_cycles	Read the earliest known update cycle for each cluster.
get_cluster_ids	Read cluster IDs present in the selected source structures.
get_cluster_member_count	Count matching registry or full-descriptor rows for one cluster.
get_cluster_member_traces	Trace cluster members back to their source atoms and structures.
get_cluster_members	Select registry indices assigned to one cluster.
get_cluster_model_member_rows	Return model-member registry indices assigned to one cluster.
get_clustering_member_rows	Read registry indices used for the clustering model.
get_clusters_for_structure	Read cluster IDs appearing in a state or process structure.
get_embedded_descriptor	Read one embedded descriptor vector.
get_embedded_descriptors	Read embedded descriptor vectors for selected registry indices.
get_embedded_descriptors_by_cluster	Read embedded descriptor vectors for members of one cluster.
get_embedded_descriptors_by_registry_rows	Read embedded descriptor vectors for selected registry indices.
get_embedding_member_rows	Read full-descriptor indices used for the embedding model.
get_full_descriptor	Read the full descriptor referenced by one registry row.
get_full_descriptor_id	Map one registry index to its full-descriptor row ID.
get_full_descriptor_ids_by_registry_rows	Map registry indices to valid full-descriptor row IDs.
get_full_descriptors_by_cluster	Read full descriptor vectors for members of one cluster.
get_full_descriptors_by_registry_rows	Read full descriptor vectors referenced by registry indices.
get_model_member_registry_rows	Return valid registry indices used by the clustering model.
get_model_meta	Copy the descriptor model metadata.
get_model_payload	Read descriptor data needed to reconstruct the DECAF model.
get_registry_members	Select descriptor registry indices using structure and cluster filters.
get_registry_row	Read one descriptor registry row.
get_representative_environment	Select a representative environment from one cluster.
get_trace	Read source-structure identifiers and provenance for a registry row.
group_cluster_members_by_structure	Group cluster-member traces by their source structure.
read_env	Read one descriptor-environment view by registry index.
read_envlist	Load and cache all descriptor-environment views.
read_meta	Reload descriptor tables and model metadata.
summarize_clusters	Summarize cluster membership, source structures, and provenance.