skfolio.descriptor.BookLeverage#

class skfolio.descriptor.BookLeverage[source]#

Book leverage descriptor.

Computes the proportion of total book capital financed by debt:

\[\text{book\_leverage}(t) = \frac{\text{total\_debt}(t)} {\text{total\_debt}(t) + \text{book\_equity}(t)}\]

Book leverage measures financial risk through the lens of the capital structure: the fraction of a firm’s total invested capital (debt plus common equity) that comes from creditors rather than common shareholders [1].

NaNs are allowed as missing observations and propagate to the output. Non-missing total_debt and book_equity values must be finite.

This form is preferred over the debt-to-equity ratio (\(D / E\)) because the two are monotonically related (\(D / E = \text{book\_leverage} / (1 - \text{book\_leverage})\)) but book leverage is bounded in \([0, 1]\) for healthy firms, producing well-behaved cross-sectional distributions that do not require aggressive winsorization.

book_equity is common shareholders’ equity (excluding preferred stock and minority interest). When it is negative (e.g., firms with accumulated losses exceeding paid-in capital), the denominator total_debt + book_equity may remain positive, become zero or turn negative:

Denominator > 0 and book_equity < 0: the ratio exceeds 1. The firm is extremely leveraged, with debt exceeding total book capital. The value is a valid distress signal and is preserved in the output.
Denominator <= 0: the ratio is undefined or negative, and no longer has its intended interpretation as a measure of book leverage. These observations are masked to NaN.

This differs from ReturnOnEquity, where any negative equity makes the concept meaningless. Here, a ratio above 1 carries real information about financial risk.

Parameters:

None

Attributes:

n_assets_int: Number of assets seen during fitting.
asset_names_ndarray of shape (n_assets,): Asset names seen during fitting.

Methods

`fit_transform`(X[, y])	Compute book leverage ratios.
`get_metadata_routing`()	Get metadata routing of this object.
`get_params`([deep])	Get parameters for this estimator.
`partial_fit_transform`(X[, y])	Stateless class delegation to `fit_transform`.
`set_params`(**params)	Set the parameters of this estimator.

See also

DebtToAssets: Leverage relative to total assets.
MarketLeverage: Leverage as a fraction of total market capital.

References

[1]

“Capital structure decisions: which factors are reliably important?” Financial Management. Frank, M. Z., & Goyal, V. K. (2009).

Examples

>>> from skfolio.datasets import make_synthetic_characteristics
>>> from skfolio.descriptor import BookLeverage
>>>
>>> X = make_synthetic_characteristics()
>>>
>>> descriptor = BookLeverage()
>>> book_leverage = descriptor.fit_transform(X)

fit_transform(X, y=None, **fit_params)[source]#

Compute book leverage ratios.

Parameters:

XAssetPanel: Input panel containing total_debt and book_equity.
yNone: Ignored. Present for compatibility with scikit-learn’s API.
**fit_paramsdict: Additional fit parameters. Ignored.

Returns:

book_leveragendarray of shape (n_observations, n_assets): Book leverage ratio for each observation and asset.

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.

partial_fit_transform(X, y=None, **fit_params)#: Stateless class delegation to fit_transform.

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.