What does RandomForestClassifier () do if we select bootstrap = False?
As defined in this link
http://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html#sklearn.ensemble.RandomForestClassifier
bootstrap: boolean, optional (default = True) Whether bootstrapping patterns are used when building trees.
Having asked this because I want to use an arbitrary forest approach to the time series, so train with a sliding window of size (tn) and a predicted date (t + k) and would like to know if this will happen if we select True or False:
1) If Bootstrap = True, then when training samples can be of any day and any number of functions. So, for example, it can have samples from day (t-15), day (t-19) and day (t-35), each with randomly selected functions, and then predict the date output (t + 1).
2) If Bootstrap = False, he will use all the samples and all functions from the date (tn) to t to learn, so he will actually follow the order of the dates (that is, he will use t-35, t-34, t-33 ... and etc. Up to t-1). And then it will predict the date output (t + 1).
, Bootstrap , Boostrap = False, ( ) t-39 t-19 t-15, t + 1. .
... Bootstrap?