Output

writer

Write run outputs: CSV metadata, numpy arrays, and serialized models.

write_run_config

write_run_config(config: RunConfig, output_dir: Path, source_path: Path) -> Path

Save a copy of the run configuration to the output directory.

Parameters:

Name	Type	Description	Default
config	RunConfig	Parsed configuration object.	required
output_dir	Path	Run output directory.	required
source_path	Path	Original YAML file path (copied verbatim when available).	required

Returns:

Type	Description
Path	Path to the saved configuration file.

write_assignments

write_assignments(assignments: ndarray, output_dir: Path) -> Path

Save per-frame cluster assignments as a numpy array.

Parameters:

Name	Type	Description	Default
assignments	ndarray	Cluster label per frame.	required
output_dir	Path	Run output directory.	required

Returns:

Type	Description
Path	Path to assignments.npy.

write_cluster_model

write_cluster_model(model: Any, output_dir: Path) -> Path

Serialize the fitted clustering model with joblib.

Parameters:

Name	Type	Description	Default
model	object	Fitted clustering model.	required
output_dir	Path	Run output directory.	required

Returns:

Type	Description
Path	Path to cluster_model.pkl.

write_cluster_statistics

write_cluster_statistics(cluster_stats: ClusterStats, output_dir: Path) -> Path

Write cluster population statistics to metadata.csv.

Parameters:

Name	Type	Description	Default
cluster_stats	dict	Per-cluster statistics.	required
output_dir	Path	Run output directory.	required

Returns:

Type	Description
Path	Path to metadata.csv.

write_seeds_csv

write_seeds_csv(seeds: Iterable[SeedResult], output_dir: Path) -> Path

Write selected seeds to seeds.csv.

Parameters:

Name	Type	Description	Default
seeds	iterable of SeedResult	Seed records for one policy.	required
output_dir	Path	Policy-specific output directory.	required

Returns:

Type	Description
Path	Path to seeds.csv.

write_combined_metadata

write_combined_metadata(policy_seeds: Dict[str, List[SeedResult]], output_dir: Path) -> Path

Write a combined seed table across all policies.

Parameters:

Name	Type	Description	Default
policy_seeds	dict	Mapping from policy name to seed lists.	required
output_dir	Path	Top-level results directory.	required

Returns:

Type	Description
Path	Path to combined_metadata.csv.

write_policy_outputs

write_policy_outputs(policy_name: str, seeds: List[SeedResult], cluster_stats: ClusterStats, results_dir: Path, include_cluster_metadata: bool = True) -> Path

Write all outputs for a single policy into its subdirectory.

Parameters:

Name	Type	Description	Default
policy_name	str	Policy identifier used as subdirectory name.	required
seeds	list of SeedResult	Seeds selected by the policy.	required
cluster_stats	dict	Global cluster statistics (same for all policies). Ignored when include_cluster_metadata is False.	required
results_dir	Path	Top-level results directory.	required
include_cluster_metadata	bool	Whether to write per-policy cluster metadata.csv.	True

Returns:

Type	Description
Path	Policy output directory path.

write_fast_scores

write_fast_scores(scores: Dict[int, Dict[str, float]], output_dir: Path) -> Path

Write FAST reward components to scores.csv.

Parameters:

Name	Type	Description	Default
scores	dict	Mapping from cluster ID to score components.	required
output_dir	Path	Policy-specific output directory.	required

Returns:

Type	Description
Path	Path to scores.csv.

write_ma_reap_outputs

write_ma_reap_outputs(scores: Dict[int, Dict[str, float]], weights: Dict[str, List[float]], stakes: Dict[int, Dict[str, float]], executors: Dict[int, str], agent_names: List[str], seeds: List[SeedResult], output_dir: Path) -> None

Write MA-REAP sidecar CSV files under the policy output directory.

write_maxent_vampnet_scores

write_maxent_vampnet_scores(scores: Dict[int, Dict[str, Any]], output_dir: Path) -> Path

Write MaxEnt VAMPNet per-frame entropy scores to scores.csv.

write_ts_dar_scores

write_ts_dar_scores(scores: Dict[int, Dict[str, Any]], output_dir: Path) -> Path

Write TS-DAR per-frame OOD scores to scores.csv.

pdb_writer

PDB export for selected seed frames using mdtraj.

write_seed_pdbs

write_seed_pdbs(seeds: List[SeedResult], topology: Path, trajectory_map: Dict[int, Path], output_dir: Path) -> List[Path]

Extract coordinate frames and save each seed as a PDB file.

Parameters:

Name	Type	Description	Default
seeds	list of SeedResult	Selected seed frames.	required
topology	Path	Topology file for mdtraj loading.	required
trajectory_map	dict	Mapping from traj_id to trajectory file path.	required
output_dir	Path	Directory where PDB files are written (typically pdbs/).	required

Returns:

Type	Description
list of Path	Paths to written PDB files.