GVAR.variable_of_column

property GVAR.variable_of_column: tuple[int, ...]

Variable identity for each global column, as integer codes.

Codes are assigned in order of first appearance of each label, so the first unit’s variables are 0, 1, ... and a later unit’s column that repeats a label reuses its code.

Example

>>> import numpy as np
>>> from cultivars.multivariate.reduced_form.vector_autoregression import VARX
>>> y = np.random.default_rng(0).standard_normal((200, 3))
>>> wide = VARX(y[:, :2], y[:, 2:], order=1).fit()
>>> narrow = VARX(y[:, 2:], y[:, :1], order=1).fit()
>>> swap = np.array([[0.0, 1.0], [1.0, 0.0]])
>>> GVAR([wide, narrow], swap, variable_labels=["gdp", "inf", "gdp"]).variable_of_column
(0, 1, 0)