esda.MoranLocalConditional

class esda.MoranLocalConditional(permutations=999, unit_scale=True, transformer=None, alternative='two-sided')

Fit a local moran statistic for y after regressing out the effects of confounding X on y. A “stronger” version of the MoranLocalPartial statistic, as defined by [Wol24]

Methods

by_col(df, cols[, w, inplace, pvalue, outvals])	Function to compute a Moran_Local statistic on a dataframe.
explore(gdf[, crit_value])	Create interactive map of LISA indicators
fit(X, y, W)	Parameters :2: (WARNING/2) Title underline too short. Parameters --------- y (N,1) array array of data that is the targeted "outcome" covariate to compute the multivariable Moran's I X (N,3) array array of data that is used as "confounding factors" to account for their covariance with Y. W (N,N) weights object spatial weights instance as W or Graph aligned with y. Immediately row-standardized.
get_cluster_labels([crit_value])	Return LISA cluster labels for each observation.
plot(gdf[, crit_value])	Create static map of LISA indicators
plot_combination(gdf, attribute[, ...])	Produce three-plot visualisation of Moran Scatteprlot, LISA cluster and Choropleth maps, with Local Moran region and quadrant masking
plot_scatter([crit_value, ax, scatter_kwds, ...])	Plot a Moran scatterplot with optional coloring for significant points.

fit(X, y, W)

Parameters

y(N,1) array

array of data that is the targeted “outcome” covariate to compute the multivariable Moran’s I

X(N,3) array

array of data that is used as “confounding factors” to account for their covariance with Y.

W(N,N) weights object

spatial weights instance as W or Graph aligned with y. Immediately row-standardized.

Returns:

A fitted MoranLocalConditional() estimator