noether.data.schemas

Classes

FieldDimSpec	A specification for a group of named data fields and their dimensions.
DomainDataSpec	Data specification for a single domain (e.g., surface, volume, wake).
ModelDataSpecs	Base data specification for models that operate on arbitrary named domains.
FileMap	File mapping schema for aerodynamic datasets.
AeroStatsSchema	Unified statistics dataclass for aerodynamics datasets such as AhmedML, and DrivAerML, DrivAerNet++,

Module Contents

class noether.data.schemas.FieldDimSpec

Bases: pydantic.RootModel[collections.OrderedDict[str, int]]

A specification for a group of named data fields and their dimensions.

property field_slices: dict[str, slice]

Calculates slice indices for each field in concatenation order.

Return type:

dict[str, slice]

property total_dim: int

Calculates the total dimension of all fields combined.

Return type:

int

keys()

values()

items()

class noether.data.schemas.DomainDataSpec(/, **data)

Bases: pydantic.BaseModel

Data specification for a single domain (e.g., surface, volume, wake).

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)

output_dims: FieldDimSpec

1, “velocity”: 3}.

Type:

Output fields and their dimensions for this domain, e.g. {“pressure”

feature_dim: FieldDimSpec | None = None

Input feature fields and their dimensions for this domain.

class noether.data.schemas.ModelDataSpecs(/, **data)

Bases: pydantic.BaseModel

Base data specification for models that operate on arbitrary named domains.

This is the minimal interface that model configs need from data specifications: position dimensions, available conditioning, and per-domain data descriptions.

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)

position_dim: int = None

Dimension of the input position vectors.

conditioning_dims: FieldDimSpec | None = None

Available conditioning features and their dimensions.

domains: dict[str, DomainDataSpec] = None

Per-domain data specifications keyed by domain name.

use_physics_features: bool = True

Whether physics features are used as input.

property total_output_dim: int

Calculates the total output dimension across all domains.

Return type:

int

property all_targets: set[str]

Returns all target field names across all domains, prefixed by domain name.

Return type:

set[str]

property all_features: set[str]

Returns all feature field names across all domains.

Return type:

set[str]

remove_feature_fields()

class noether.data.schemas.FileMap(/, **data)

Bases: pydantic.BaseModel

File mapping schema for aerodynamic datasets.

Maps field names to their corresponding file names in the dataset directory. This allows different datasets to use different file naming conventions while maintaining a unified interface.

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)

surface_position: str | None = None

surface_pressure: str | None = None

surface_friction: str | None = None

surface_normals: str | None = None

surface_area: str | None = None

volume_position: str | None = None

volume_pressure: str | None = None

volume_velocity: str | None = None

volume_vorticity: str | None = None

volume_normals: str | None = None

surface_position_stl: str | None = None

surface_position_stl_resampled: str | None = None

volume_friction: str | None = None

volume_distance_to_surface: str | None = None

design_parameters: str | None = None

class noether.data.schemas.AeroStatsSchema(/, **data)

Bases: pydantic.BaseModel

Unified statistics dataclass for aerodynamics datasets such as AhmedML, and DrivAerML, DrivAerNet++, ShapeNet-Car, and Wing.

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)

surface_domain_min: tuple[float, float, float] | None = None

surface_domain_max: tuple[float, float, float] | None = None

surface_pos_mean: tuple[float, float, float] | None = None

surface_pos_std: tuple[float, float, float] | None = None

surface_pressure_mean: tuple[float] | None = None

surface_pressure_std: tuple[float] | None = None

surface_friction_mean: tuple[float, float, float] | None = None

surface_friction_std: tuple[float, float, float] | None = None

volume_pos_mean: tuple[float, float, float] | None = None

volume_pos_std: tuple[float, float, float] | None = None

volume_pressure_mean: tuple[float] | None = None

volume_pressure_std: tuple[float] | None = None

volume_velocity_mean: tuple[float, float, float] | None = None

volume_velocity_std: tuple[float, float, float] | None = None

volume_vorticity_mean: tuple[float, float, float] | None = None

volume_vorticity_std: tuple[float, float, float] | None = None

volume_vorticity_logscale_mean: tuple[float, float, float] | None = None

volume_vorticity_logscale_std: tuple[float, float, float] | None = None

volume_vorticity_magnitude_mean: float | None = None

volume_vorticity_magnitude_std: float | None = None

volume_domain_min: tuple[float, float, float] | None = None

volume_domain_max: tuple[float, float, float] | None = None

volume_sdf_mean: tuple[float] | None = None

volume_sdf_std: tuple[float] | None = None

inflow_design_parameters_min: collections.abc.Sequence[float] | None = None

inflow_design_parameters_max: collections.abc.Sequence[float] | None = None

inflow_design_parameters_mean: collections.abc.Sequence[float] | None = None

inflow_design_parameters_std: collections.abc.Sequence[float] | None = None

geometry_design_parameters_min: collections.abc.Sequence[float] | None = None

geometry_design_parameters_max: collections.abc.Sequence[float] | None = None

geometry_design_parameters_mean: collections.abc.Sequence[float] | None = None

geometry_design_parameters_std: collections.abc.Sequence[float] | None = None

raw_pos_min: tuple[float] | None = None

raw_pos_max: tuple[float] | None = None