infer.py 文件源码

def predict_with_gbm(X, y, model):
    """

    Args:
        X:
        y:
        model:

    Returns:

    """
    assert model['model_name'] == 'GBM',\
        'Wrong model name in model info: {}. Need GBM.'.format(model['model_name'])
    testData = xgb.DMatrix(data=X, label=y.nMut.values, feature_names=model['feature_names'])
    testData.set_base_margin(np.array(np.log(y.length+1/y.N) + np.log(y.N)))
    kfold = model['kfold']
    pred = np.zeros(y.shape[0])
    for k in range(1, kfold+1):
        model['model'][k].set_param(model['params'])  # Bypass a bug of dumping without max_delta_step
        pred += model['model'][k].predict(testData)
    pred = pred / kfold
    return pred