Configuration

schema

Configuration schema and validation for AdaptivePy runs.

RunConfig dataclass

RunConfig(features_dir: Path, output_dir: Path, trajectories_dir: Optional[Path] = None, topology: Optional[Path] = None, clustering: ClusteringConfig = ClusteringConfig(), policies: List[str] = (lambda: ['least_counts'])(), n_seeds: int = DEFAULT_N_SEEDS, seed_selection: SeedSelectionConfig = SeedSelectionConfig(), random_seed: int = DEFAULT_RANDOM_SEED, write_pdbs: bool = True, policy_params: Dict[str, Dict[str, Any]] = dict(), metapolicy: MetapolicyConfig = MetapolicyConfig())

Full configuration for an adaptive sampling run.

Attributes:

Name	Type	Description
features_dir	Path	Directory containing *.npy or *.pkl feature files.
output_dir	Path	Directory where results are written.
trajectories_dir	Path or None	Optional directory containing coordinate trajectories.
topology	Path or None	Topology file required when trajectories are provided.
clustering	ClusteringConfig	Clustering settings.
policies	list of str	Policy names to evaluate in parallel.
n_seeds	int	Number of seed frames to select per policy.
seed_selection	SeedSelectionConfig	Frame selection method within chosen clusters.
random_seed	int	Global random seed for reproducibility.
write_pdbs	bool	Whether to write PDB files when trajectories are available.

ClusteringConfig dataclass

ClusteringConfig(method: str = DEFAULT_CLUSTERING_METHOD, n_clusters: int = 10, params: Dict[str, Any] = dict())

Clustering backend configuration.

Attributes:

Name	Type	Description
method	str	Clustering method name: kmeans, minibatch_kmeans, or regular_space.
n_clusters	int	Number of clusters to fit.
params	dict	Additional keyword arguments passed to the clusterer.

SeedSelectionConfig dataclass

SeedSelectionConfig(method: str = DEFAULT_SEED_SELECTION)

Frame-level seed selection configuration.

Attributes:

Name	Type	Description
method	str	Selection method: nearest_center or random_frame.

load_config

load_config(path: str | Path) -> RunConfig

Load and parse a YAML run configuration file.

Parameters:

Name	Type	Description	Default
path	str or Path	Path to the YAML configuration file.	required

Returns:

Type	Description
RunConfig	Parsed and validated configuration object.

Raises:

Type	Description
FileNotFoundError	If the configuration file does not exist.
ValueError	If required fields are missing or invalid.

config_to_dict

config_to_dict(config: RunConfig) -> Dict[str, Any]

Convert a :class:RunConfig to a plain dictionary for serialization.

Parameters:

Name	Type	Description	Default
config	RunConfig	Configuration object to serialize.	required

Returns:

Type	Description
dict	YAML-serializable configuration dictionary.

build_policy_kwargs

build_policy_kwargs(policy_name: str, config: RunConfig, n_features: Optional[int] = None, traj_names: Optional[Sequence[str]] = None, n_clusters: Optional[int] = None, n_seeds: Optional[int] = None, traj_index_map: Optional[Dict[int, tuple[int, int]]] = None) -> Dict[str, Any]

Build constructor keyword arguments for a configured policy.

Parameters:

Name	Type	Description	Default
policy_name	str	Registered policy name.	required
config	RunConfig	Parsed run configuration.	required
n_features	int or None	Feature dimensionality for policies that require it.	None

Returns:

Type	Description
dict	Keyword arguments forwarded to :func:get_policy.

validate_fast_policy_params

validate_fast_policy_params(params: Dict[str, Any], n_features: int) -> Dict[str, Any]

Validate and normalize FAST policy parameters.

Parameters:

Name	Type	Description	Default
params	dict	Raw FAST policy settings from configuration.	required
n_features	int	Number of feature dimensions in the loaded dataset.	required

Returns:

Type	Description
dict	Normalized keyword arguments for :class:FastPolicy.

Raises:

Type	Description
ValueError	If required FAST settings are missing or invalid.

validate_ma_reap_policy_params

validate_ma_reap_policy_params(params: Dict[str, Any], traj_names: Sequence[str], n_features: int, n_seeds: int = DEFAULT_N_SEEDS, n_clusters: Optional[int] = None) -> Dict[str, Any]

Validate and normalize MA-REAP policy parameters.

Parameters:

Name	Type	Description	Default
params	dict	Raw MA-REAP settings from configuration.	required
traj_names	sequence of str	Feature file stems in the loaded dataset.	required
n_features	int	Number of feature dimensions.	required
n_seeds	int	Seeds to select per policy run.	DEFAULT_N_SEEDS
n_clusters	int or None	Number of populated clusters after clustering.	None

Returns:

Type	Description
dict	Normalized keyword arguments for :class:MaReapPolicy.

validate_knn_as_policy_params

validate_knn_as_policy_params(params: Dict[str, Any]) -> Dict[str, Any]

Validate and normalize kNN-AS policy parameters.

Parameters:

Name	Type	Description	Default
params	dict	Raw kNN-AS policy settings from configuration.	required

Returns:

Type	Description
dict	Normalized keyword arguments for :class:KnnAsPolicy.

validate_maxent_vampnet_policy_params

validate_maxent_vampnet_policy_params(params: Dict[str, Any], n_features: int, traj_index_map: Optional[Dict[int, tuple[int, int]]] = None) -> Dict[str, Any]

Validate and normalize MaxEnt VAMPNet policy parameters.

Parameters:

Name	Type	Description	Default
params	dict	Raw MaxEnt VAMPNet settings from configuration.	required
n_features	int	Number of feature dimensions in the loaded dataset.	required
traj_index_map	dict or None	Mapping from trajectory ID to (start, end) indices in the concatenated feature matrix.	None

Returns:

Type	Description
dict	Normalized keyword arguments for :class:MaxEntVampNetPolicy.

validate_ts_dar_policy_params

validate_ts_dar_policy_params(params: Dict[str, Any], n_features: int, traj_index_map: Optional[Dict[int, tuple[int, int]]] = None) -> Dict[str, Any]

Validate and normalize TS-DAR policy parameters.