mephistopheies.py 文件源码

def compute_sgd(data):
    logging.info('Computing SGD')

    n_splits = 10
    folder = StratifiedKFold(n_splits=n_splits, shuffle=True)
    for ix_first, ix_second in tqdm_notebook(folder.split(np.zeros(data['y_train'].shape[0]), data['y_train']),
                                             total=n_splits):
        # {'en__l1_ratio': 0.0001, 'en__alpha': 1e-05}
        model = SGDClassifier(
            loss='log',
            penalty='elasticnet',
            fit_intercept=True,
            n_iter=100,
            shuffle=True,
            n_jobs=-1,
            l1_ratio=0.0001,
            alpha=1e-05,
            class_weight=None)
        model = model.fit(data['X_train'][ix_first, :], data['y_train'][ix_first])
        data['y_train_pred'][ix_second] = logit(model.predict_proba(data['X_train'][ix_second, :])[:, 1])
        data['y_test_pred'].append(logit(model.predict_proba(data['X_test'])[:, 1]))

    data['y_test_pred'] = np.array(data['y_test_pred']).T.mean(axis=1)

    return data