RuleFit parameter `sample_fract` seems to do nothing

[Feelx234]

Dear maintainers of imodel,

Thank you very much for creating and maintaining this library.
Looking at the source code of RuleFit, I find that the sample_fract parameter/attribute is unused. It is set in the constructor and then never used again. I also searched through the source files and could not find a meaningful use of sample_fract . It is set in other classes such as StableLinear and FPLasso but not used there either. Also i checked against TransformerMixin and ClassifierMixin they also don't seem to use the sample_fract parameter.

It seems there is an sample_frac_ in line 37 in extract.py

imodels/imodels/util/extract.py

Lines 36 to 39 in 6efaa90

	if tree_generator is None:
	sample_fract_ = min(0.5, (100 + 6 * np.sqrt(X.shape[0])) / X.shape[0])
	tree_generator = GradientBoostingRegressor(n_estimators=n_estimators,

But it seems to be unaffected by RuleFit.sample_fract.

Is this intended behavior? Or is it planned, that this parameter is used in the future/ was used in the past?

Thank you very much for clarifying