esda.LOSH¶

class esda.LOSH(connectivity=None, inference=None)[source]¶

Local spatial heteroscedasticity (LOSH)

__init__(connectivity=None, inference=None)[source]¶

Initialize a losh estimator

Parameters:

connectivityW | Graph: spatial weights instance as W or Graph aligned with y
inferencestr: describes type of inference to be used. options are “chi-square” or “permutation” methods.

Attributes:

Hinumpy array: Array of LOSH values for each spatial unit.
ylagnumpy array: Spatially lagged y values.
yresidnumpy array: Spatially lagged residual values.
VarHinumpy array: Variance of Hi.
pvalnumpy array: P-values for inference based on either “chi-square” or “permutation” methods.

Methods

`__init__`([connectivity, inference])	Initialize a losh estimator
`fit`(y[, a])
`get_metadata_routing`()	Get metadata routing of this object.
`get_params`([deep])	Get parameters for this estimator.
`set_fit_request`(*[, a])	Request metadata passed to the `fit` method.
`set_params`(**params)	Set the parameters of this estimator.

fit(y, a=2)[source]¶

Parameters:

ynumpy.ndarray: array containing continuous data
aint: residual multiplier. Default is 2 in order to generate a variance measure. Users may use 1 for absolute deviations.

Returns:

the fitted estimator.

Notes

Technical details and derivations can be found in [].

Examples

>>> import libpysal
>>> w = libpysal.io.open(libpysal.examples.get_path("stl.gal")).read()
>>> f = libpysal.io.open(libpysal.examples.get_path("stl_hom.txt"))
>>> y = np.array(f.by_col['HR8893'])
>>> from esda import losh
>>> ls = losh(connectivity=w, inference="chi-square").fit(y)
>>> np.round(ls.Hi[0], 3)
>>> np.round(ls.pval[0], 3)

Boston housing data replicating R spdep::LOSH() >>> import libpysal >>> import geopandas as gpd >>> boston = libpysal.examples.load_example(‘Bostonhsg’) >>> boston_ds = gpd.read_file(boston.get_path(‘boston.shp’)) >>> w = libpysal.weights.Queen.from_dataframe(boston_ds) >>> ls = losh(connectivity=w, inference=”chi-square”).fit(boston[‘NOX’]) >>> np.round(ls.Hi[0], 3) >>> np.round(ls.VarHi[0], 3)

set_fit_request(*, a: bool | None | str = '$UNCHANGED$') → LOSH¶

Request metadata passed to the fit method.

Note that this method is only relevant if enable_metadata_routing=True (see sklearn.set_config()). Please see User Guide on how the routing mechanism works.

The options for each parameter are:

True: metadata is requested, and passed to fit 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 fit.
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.

Note

This method is only relevant if this estimator is used as a sub-estimator of a meta-estimator, e.g. used inside a Pipeline. Otherwise it has no effect.

Parameters:

astr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED: Metadata routing for a parameter in fit.

Returns:

selfobject: The updated object.