model.py 文件源码

def run_lasso(X, y, max_iter=3000, cv=5, n_threads=1):
    """ Implement LassoCV in sklearn

    Args:
        X (np.array): scaled X.
        y (pd.df): four columns response table. 
        max_iter (int): max iteration. 
        cv (int): CV fold.
        n_threads (int): Number of threads to use for parallel computing.

    Returns:
        float: trained alpha value.

    """
    logger.info('Implementing LassoCV with {} iter. and {}-fold CV'.format(max_iter, cv))
    # generate logit response
    y_logit = logit((y.nMut + 0.5) / (y.length * y.N))
    # sub-sampling X and y (300,000)
    use_ix = np.random.choice(y_logit.shape[0], 300000, replace=False)
    Xsub = X[use_ix, :]
    ysub = y_logit[use_ix]
    reg = LassoCV(max_iter=max_iter, cv=cv, copy_X=False, n_jobs=n_threads)
    lassocv = reg.fit(Xsub, ysub)
    logger.info('LassoCV alpha = {}'.format(lassocv.alpha_))
    return lassocv.alpha_