blend_ensemble.py 文件源码

def online2(X_org, y_org, test_x, test_uid):
    n_folds = 5
    verbose = True
    shuffle = False

    X = X_org
    y = y_org
    X_submission = test_x

    if shuffle:
        idx = np.random.permutation(y.size)
        X = X[idx]
        y = y[idx]

    skf = list(StratifiedKFold(y, n_folds))

    clfs = [
        RandomForestClassifier().set_params(**INITIAL_PARAMS.get("RFC:one", {})),
        ExtraTreesClassifier().set_params(**INITIAL_PARAMS.get("ETC:one", {})),
        GradientBoostingClassifier().set_params(**INITIAL_PARAMS.get("GBC:one", {})),
        LogisticRegression().set_params(**INITIAL_PARAMS.get("LR:one", {})),
        # xgb.XGBClassifier().set_params(**INITIAL_PARAMS.get("XGBC:two", {})),
        # xgb.XGBClassifier().set_params(**INITIAL_PARAMS.get("XGBC:one", {})),
        ]

    print "Creating train and test sets for blending."

    dataset_blend_train = np.zeros((X.shape[0], len(clfs)))
    dataset_blend_test = np.zeros((X_submission.shape[0], len(clfs)))

    for j, clf in enumerate(clfs):
        print j, clf
        dataset_blend_test_j = np.zeros((X_submission.shape[0], len(skf)))
        for i, (train, test) in enumerate(skf):
            print "Fold", i
            X_train = X[train]
            y_train = y[train]
            clf.fit(X_train, y_train)
            dataset_blend_test_j[:, i] = clf.predict_proba(X_submission)[:, 1]
        dataset_blend_test[:,j] = dataset_blend_test_j.mean(1)
        save_submission(os.path.join(consts.SUBMISSION_PATH,
                                         clf.__class__.__name__ + '_' + strftime("%m_%d_%H_%M_%S", localtime()) + '.csv'),
                            test_uid, dataset_blend_test[:, j])