features.py 文件源码

def _calculate(self, X, y, categorical, metafeatures, helpers):
        import sklearn.tree

        if len(y.shape) == 1 or y.shape[1] == 1:
            kf = cross_validation.StratifiedKFold(y, n_folds=10)
        else:
            kf = cross_validation.KFold(y.shape[0], n_folds=10)
        accuracy = 0.

        for train, test in kf:
            random_state = check_random_state(42)
            node = sklearn.tree.DecisionTreeClassifier(
                    criterion="entropy", max_depth=1, random_state=random_state,
                    min_samples_split=1, min_samples_leaf=1, max_features=1)
            if len(y.shape) == 1 or y.shape[1] == 1:
                node.fit(X[train], y[train])
            else:
                node = OneVsRestClassifier(node)
                node.fit(X[train], y[train])
            predictions = node.predict(X[test])
            accuracy += sklearn.metrics.accuracy_score(predictions, y[test])
        return accuracy / 10