scale_spatial_for_fit()

scale_spatial_for_fit

R Documentation

Scale Spatial Predictors for Model Fitting

Description

Centres and scales all spatial predictor columns, records the scaling attributes for later back-transformation, and returns both the scaled data frame and the attributes as a named list.

Usage

scale_spatial_for_fit(data_spatial = NULL)

Arguments

data_spatial

A data frame with row names in the format ’"<dataset_name>__<age>"’ and numeric columns containing spatial predictor variables (e.g. ‘coord_x_km’, ‘coord_y_km’), as returned by ‘prepare_spatial_predictors_for_fit()’.

Details

All columns are centred (mean subtracted) and divided by their standard deviation using ‘base::scale()’, provided more than one sample is present. When only one row exists, only centring is applied.

Value

A named list with two elements:

‘data_spatial_scaled’: A data frame with the same row names as the input, with all predictor columns centred and scaled. When only one sample is present, columns are centred only (scale = FALSE).
‘spatial_scale_attributes’: A named list of ‘center’ and ‘scale’ attributes for each predictor column, which can be used to back-transform predictions.