def test_maui_updates_neural_weight_product_when_training():
maui_model = Maui(n_hidden=[10], n_latent=2, epochs=1)
z_before = maui_model.fit_transform({"d1": df1, "d2": df2})
nwp_before_fine_tuning = maui_model.get_neural_weight_product()
maui_model.fine_tune({"d1": df1, "d2": df2})
z_after = maui_model.transform({"d1": df1, "d2": df2})
nwp_after_fine_tuning = maui_model.get_neural_weight_product()
assert not np.allclose(z_before, z_after)
assert not np.allclose(nwp_before_fine_tuning, nwp_after_fine_tuning)
def test_maui_saves_neural_weight_product():
maui_model = Maui(n_hidden=[10], n_latent=2, epochs=1)
z = maui_model.fit_transform({"d1": df1, "d2": df2})
nwp = maui_model.get_neural_weight_product()
assert nwp is not None
assert hasattr(maui_model, "nwp_")
print(maui_model.encoder.summary())
w1 = maui_model.encoder.layers[2].get_weights()[0]
w2 = maui_model.encoder.layers[3].get_weights()[0]
nwp_11 = np.dot(w1[0, :], w2[:, 0])
assert np.allclose(nwp_11, nwp.iloc[0, 0])
