GrowingTubeModel#

class ktch.coiling.GrowingTubeModel(r0: float = 1.0, method: str = 'ode', estimator: str = 'nls_3d', n_jobs: int | None = None, verbose: int = 0)[source]#

Growing tube model.

The growing tube model [Okamoto_1988]. inverse_transform is the generative map Phi: (e_g, c_g, t_g, delta_g, gamma_g) -> form. transform estimates the parameters from measured shells ("nls_3d") or, symmetrically, from a structured surface ("surface").

Parameters:

r0float, default = 1.0: Initial tube radius (scale) used for generation.
method{“ode”, “closed”}, default = “ode”: Forward solver passed to growing_tube().
estimator{“nls_3d”, “surface”}, default = “nls_3d”: Estimation method used by transform. "nls_3d" fits the centerline and radius from a per-point (x, y, z, r) panel. "surface" fits the generative map directly to a structured surface panel (the coordinate output of inverse_transform), recovering the aperture orientation (delta_g, gamma_g) as well; it is consistent with inverse_transform (transform(inverse_transform(params)) ~= params).
n_jobsint, optional: Number of jobs for the per-specimen estimation in transform.
verboseint, default = 0: Verbosity level.

References

[Okamoto_1988]

Okamoto, T., 1988. Analysis of heteromorph ammonoids by differential geometry. Palaeontology 31, 35–52.

fit(X, y=None)[source]#: No-op (stateless). Returns self.

fit_transform(X, y=None, domain_coords=None, aperture=None)[source]#

Fit and transform in one step.

Overridden to support metadata routing of domain_coords, aperture.

get_feature_names_out(input_features=None) → ndarray[source]#: Parameter names (e_g, c_g, t_g, delta_g, gamma_g).

get_metadata_routing()#

Get metadata routing of this object.

Please check User Guide on how the routing mechanism works.

Returns:

routingMetadataRequest: A MetadataRequest encapsulating routing information.

get_params(deep=True)#

Get parameters for this estimator.

Parameters:

deepbool, default=True: If True, will return the parameters for this estimator and contained subobjects that are estimators.

Returns:

paramsdict: Parameter names mapped to their values.

inverse_transform(X_transformed, s_range=None, phi_range=None, aperture=None, as_frame=False)[source]#

Generate shell surfaces from growing tube parameters.

Parameters:

X_transformedarray-like of shape (n_samples, 5) or (5,): Rows of (e_g, c_g, t_g, delta_g, gamma_g). A 3-column input (e_g, c_g, t_g) is also accepted, with orientation defaulted to 0. e_g is the logarithm of the original $E$ described in [Okamoto_1988] ([Noshita_2014]).
s_range, phi_rangearray-like, optional: Sampling grids. See growing_tube().
apertureNone: Aperture shape; only the circular default is supported.
as_framebool, default = False: If True, return a long-format pandas.DataFrame.

Returns:

Xndarray of shape (n_samples, n_s, n_phi, 3) or pd.DataFrame

References

[Okamoto_1988]

Okamoto, T., 1988. Analysis of heteromorph ammonoids by differential geometry. Palaeontology 31, 35–52.

[Noshita_2014]

Noshita, K., 2014. Quantification and geometric analysis of coiling patterns in gastropod shells based on 3D and 2D image data. Journal of Theoretical Biology 363, 93–104.

Configure whether metadata should be requested to be passed to the inverse_transform method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

True: metadata is requested, and passed to inverse_transform if provided. The request is ignored if metadata is not provided.
False: metadata is not requested and the meta-estimator will not pass it to inverse_transform.
None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.
str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

X_transformedstr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED: Metadata routing for X_transformed parameter in inverse_transform.
aperturestr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED: Metadata routing for aperture parameter in inverse_transform.
as_framestr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED: Metadata routing for as_frame parameter in inverse_transform.
phi_rangestr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED: Metadata routing for phi_range parameter in inverse_transform.
s_rangestr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED: Metadata routing for s_range parameter in inverse_transform.

Returns:

selfobject: The updated object.

set_output(*, transform=None)#

Set output container.

Refer to the user guide for more details and Introducing the set_output API for an example on how to use the API.

Parameters:

transform{“default”, “pandas”, “polars”}, default=None

Configure output of transform and fit_transform.

“default”: Default output format of a transformer
“pandas”: DataFrame output
“polars”: Polars output
None: Transform configuration is unchanged

Added in version 1.4: “polars” option was added.

Returns:

selfestimator instance: Estimator instance.

set_params(**params)#

Set the parameters of this estimator.

The method works on simple estimators as well as on nested objects (such as Pipeline). The latter have parameters of the form <component>__<parameter> so that it’s possible to update each component of a nested object.

Parameters:

**paramsdict: Estimator parameters.

Returns:

selfestimator instance: Estimator instance.

set_transform_request(*, aperture: bool | None | str = '$UNCHANGED$', domain_coords: bool | None | str = '$UNCHANGED$') → GrowingTubeModel#

Configure whether metadata should be requested to be passed to the transform method.

The options for each parameter are:

True: metadata is requested, and passed to transform if provided. The request is ignored if metadata is not provided.
False: metadata is not requested and the meta-estimator will not pass it to transform.
None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.
str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

aperturestr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED: Metadata routing for aperture parameter in transform.
domain_coordsstr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED: Metadata routing for domain_coords parameter in transform.

Returns:

selfobject: The updated object.

transform(X, domain_coords=None, aperture=None)[source]#

Estimate growing tube parameters from measured shells.

Parameters:

Xlist of array-like, ndarray, or DataFrame: The input panel; its encoding depends on estimator. For "nls_3d", a per-specimen panel of (n_points_i, 4) centroid-and-thickness sequences (x, y, z, r) (see ktch.coiling._panel._check_panel()). For "surface", a panel of (n_s, n_phi, 3) structured surfaces (see ktch.coiling._panel._check_surface_panel()).
domain_coordslist of array-like, optional: Per-point arc length l (for example from an external arc-length refinement), used by "nls_3d" only. When omitted, a tentative cumulative chord length is used.
apertureNone: Aperture shape; only the circular default is supported.

Returns:

X_transformedndarray of shape (n_samples, 5): Estimated (e_g, c_g, t_g, delta_g, gamma_g). The "nls_3d" estimator returns zeros for the orientation columns; the "surface" estimator recovers them.