dwavesystems / dwave-scikit-learn-plugin Goto Github PK

Readme - Add reference to scikit learn documentation for details on how to prepare data for and use the package

The time_limit keyword is not used in the fit

The variable time_limit is not passed to the solver, instead, an internal variable is passed.

D-wave system functions have a parameter called 'token' to pass it. But I don't know how pass this parameter to run the simple example of this web with SelectFromQuadraticModel(num_features=20).fit_transform(X_tmp.values, y.values)

Regards,

Is this plugin up to date? Can we use it?

It would be nice to have the titanic dataset that we use in our examples (link, link, link), available in code. Something like

from dwave.plugins.sklearn.datasets import load_titanic

to mirror scikit-learn's datasets

Currently, it is possible to construct a dataset where, even with alpha=1, a fixed or random column is chosen because of the penalties in the quadratic term. This contradicts the docstring which claims

            alpha:
                Hyperparameter between 0 and 1 that controls the relative weight of
                the relevance and redundancy terms.
                ``alpha=0`` places no weight on the quality of the features,
                therefore the features will be selected as to minimize the
                redundancy without any consideration to quality.
                ``alpha=1`` places the maximum weight on the quality of the features,
                and therefore will be equivalent to using
                :class:`sklearn.feature_selection.SelectKBest`.

One solution is to multiply the quadratic/redundany terms by 1-alpha to ensure that they are zeroed when alpha=1.

For instance we could replace

            diag = np.array(correlations[:, -1] * (-2 * alpha * num_features), copy=True)

            correlations *= (1-alpha)

            # our objective
            # we multiply by 2 because the matrix is symmetric
            np.fill_diagonal(correlations, diag)