biomedical_data_generator.DatasetConfig

class biomedical_data_generator.DatasetConfig(*, n_samples=100, n_features=None, n_informative=2, n_pseudo=0, n_noise=0, noise_distribution=NoiseDistribution.normal, noise_scale=1.0, noise_params=None, n_classes=2, weights=None, class_counts=None, class_sep=1.5, feature_naming='prefixed', prefix_informative='i', prefix_pseudo='p', prefix_noise='n', prefix_corr='corr', corr_clusters=<factory>, corr_between=0.0, anchor_mode='equalized', effect_size='medium', batch=None, random_state=None)

Bases: BaseModel

Configuration for synthetic dataset generation.

The strict mode=”before” normalizer fills/validates n_features without Pydantic warnings.

Note: - The ‘before’ validator normalizes raw inputs:

• fills n_features if omitted,

• enforces n_features >= minimal requirement (strict).

• Use DatasetConfig.relaxed(…) if you want silent auto-fix instead of a validation error.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• n_samples (int)

• n_features (int | None)

• n_informative (int)

• n_pseudo (int)

• n_noise (int)

• noise_distribution (NoiseDistribution)

• noise_scale (float)

• noise_params (Mapping[str, Any] | None)

• n_classes (int)

• weights (list[float] | None)

• class_counts (dict[int, int] | None)

• class_sep (float)

• feature_naming (Literal['prefixed', 'simple'])

• prefix_informative (str)

• prefix_pseudo (str)

• prefix_noise (str)

• prefix_corr (str)

• corr_clusters (list[CorrCluster])

• corr_between (float)

• anchor_mode (Literal['equalized', 'strong'])

• effect_size (Literal['small', 'medium', 'large'])

• batch (BatchConfig | None)

• random_state (int | None)

__init__(**data)

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

data (Any)

Return type:

None

Methods

__init__(**data)	Create a new model by parsing and validating input data from keyword arguments.
breakdown()	Return a structured breakdown of feature counts, incl.
construct([_fields_set])
copy(*[, include, exclude, update, deep])	Returns a copy of the model.
count_informative_anchors()	Count clusters whose anchor contributes as 'informative'.
dict(*[, include, exclude, by_alias, ...])
from_orm(obj)
from_yaml(path)	Load from YAML and validate via the same 'before' pipeline.
json(*[, include, exclude, by_alias, ...])
model_construct([_fields_set])	Creates a new instance of the Model class with validated data.
model_copy(*[, update, deep])	!!! abstract "Usage Documentation"
model_dump(*[, mode, include, exclude, ...])	!!! abstract "Usage Documentation"
model_dump_json(*[, indent, ensure_ascii, ...])	!!! abstract "Usage Documentation"
model_json_schema([by_alias, ref_template, ...])	Generates a JSON schema for a model class.
model_parametrized_name(params)	Compute the class name for parametrizations of generic classes.
model_post_init(context, /)	Override this method to perform additional initialization after __init__ and model_construct.
model_rebuild(*[, force, raise_errors, ...])	Try to rebuild the pydantic-core schema for the model.
model_validate(obj, *[, strict, extra, ...])	Validate a pydantic model instance.
model_validate_json(json_data, *[, strict, ...])	!!! abstract "Usage Documentation"
model_validate_strings(obj, *[, strict, ...])	Validate the given object with string data against the Pydantic model.
parse_file(path, *[, content_type, ...])
parse_obj(obj)
parse_raw(b, *[, content_type, encoding, ...])
relaxed(**kwargs)	Create a configuration, silently autofixing n_features to the required minimum.
schema([by_alias, ref_template])
schema_json(*[, by_alias, ref_template])
summary(*[, per_cluster, as_markdown])	Return a human-readable summary of the configuration.
update_forward_refs(**localns)
validate(value)

Attributes

model_computed_fields
model_config	Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
model_extra	Get extra fields set during validation.
model_fields
model_fields_set	Returns the set of fields that have been explicitly set on this model instance.
n_samples
n_features
n_informative
n_pseudo
n_noise
noise_distribution
noise_scale
noise_params
n_classes
weights
class_counts
class_sep
feature_naming
prefix_informative
prefix_pseudo
prefix_noise
prefix_corr
corr_clusters
corr_between
anchor_mode
effect_size
batch
random_state

breakdown()

Return a structured breakdown of feature counts, incl. cluster proxies.

Returns:

A dict with keys: - n_informative_total - n_informative_anchors - n_informative_free - n_pseudo_free - n_noise - proxies_from_clusters - n_features_expected - n_features_configured

Raises:

ValueError: If self.n_features is inconsistent (should not happen if validated).

This is a safeguard against manual tampering with the instance attributes. This should not happen if the instance was created via the normal validators. If you encounter this, please report a bug.

Note

n_features_expected = n_informative + n_pseudo + n_noise + proxies_from_clusters n_features_configured = self.n_features (may be larger than expected)

Return type:

dict[str, int]

count_informative_anchors()

Count clusters whose anchor contributes as ‘informative’.

Note: This is a subset of n_informative, not a separate count.

Returns:

The number of clusters with anchor_role == “informative”.

Note

If you want the number of additional features contributed by clusters, use self._proxies_from_clusters(self.corr_clusters).

Return type:

int

classmethod from_yaml(path)

Load from YAML and validate via the same ‘before’ pipeline.

Parameters:

• cls – The DatasetConfig class.

• path (str) – Path to a YAML file.

Return type:

DatasetConfig

Returns:

A validated DatasetConfig instance.

Raises:

FileNotFoundError: If the file does not exist. yaml.YAMLError: If the file cannot be parsed as YAML. pydantic.ValidationError: If the loaded config is invalid.

Note

This requires PyYAML to be installed.

model_config: ClassVar[ConfigDict] = {'extra': 'forbid', 'use_enum_values': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

classmethod relaxed(**kwargs)

Create a configuration, silently autofixing n_features to the required minimum.

Convenience factory that silently ‘autofixes’ n_features to the required minimum. Prefer this in teaching notebooks to avoid interruptions.

Parameters:

**kwargs (Any) – Any valid DatasetConfig field.

Return type:

DatasetConfig

Returns:

A validated DatasetConfig instance with n_features >= required minimum.

Note

This does NOT modify the original kwargs dict.

summary(*, per_cluster=False, as_markdown=False)

Return a human-readable summary of the configuration.

Parameters:

• per_cluster (bool) – Include one line per cluster (size/role/rho/etc.).

• as_markdown (bool) – Render as a Markdown table-like text.

Return type:

str

Returns:

A formatted string summarizing the feature layout and counts.