cache.py 文件源码

def cached_run(steps, X, y):
    step_identifier = ''

    # split data
    n = len(y)
    kf = KFold(n, _n_fold, random_state=_random_state)
    folded_data = [(X[train_index], y[train_index], X[test_index], y[test_index]) for train_index, test_index in kf]

    # last step is estimator, handle separately
    for step in steps[:-1]:
        step_identifier += "/%s" % _step_identifier(step)
        logger.info("Processing %s", step_identifier)
        folded_data = run_step_on_demand(step_identifier, step, folded_data)

    scores = []
    estimator = steps[-1]
    step_identifier += "/%s" % _step_identifier(estimator)
    for (X_train, y_train, X_test, y_test) in folded_data:
        estimator.fit(X_train, y_train)
        scores.append(estimator.score(X_test, y_test))

    score = np.mean(scores)
    logger.info("score of %s is %r", step_identifier, score)
    return score