We recently merged a discretizing transformer into the discrete branch (see diff between that branch and master). Before merging it into master, we'd like it to be able to one-hot encode the output by default.
I propose that we have a parameter encode='onehot' by default which produces a one-hot encoded sparse matrix, with other options 'ordinal' (for the current default output) and encode-dense which produces a dense version of 'onehot'.
To dear contributor: Make sure to submit a pull request to the discrete branch.
We recently merged a discretizing transformer into the
discretebranch (see diff between that branch and master). Before merging it into master, we'd like it to be able to one-hot encode the output by default.I propose that we have a parameter
encode='onehot'by default which produces a one-hot encoded sparse matrix, with other options'ordinal'(for the current default output) andencode-densewhich produces a dense version of'onehot'.To dear contributor: Make sure to submit a pull request to the
discretebranch.