[SILENT BUG] Fitted values not requested when needed

[AzulGarza]

Some methods and functionality (bootstrapped prediction intervals) need the fitted values of the models. But the following iteration omits to request them.

hierarchicalforecast/hierarchicalforecast/core.py

Lines 128 to 146 in 0c5cc36

	if model_name in Y_df:
	y_hat_insample = Y_df.pivot(columns='ds', values=model_name).loc[uids].values
	y_hat_insample = y_hat_insample.astype(np.float32)
	if has_fitted:
	common_vals['y_hat_insample'] = y_hat_insample
	if bootstrap and has_level:
	common_vals['bootstrap_samples'] = _bootstrap_samples(
	y_insample=common_vals['y_insample'],
	y_hat_insample=y_hat_insample,
	y_hat=y_hat_model,
	n_samples=1_000
	)
	common_vals['bootstrap'] = bootstrap
	common_vals['level'] = level
	else:
	# some methods have the residuals argument
	# but they don't need them
	# ej MinTrace(method='ols')
	common_vals['y_hat_insample'] = None

The above leads to unintelligible bugs.

[elephaint]

I think this has already been addressed here