问题：

在使用pyss3文档中给出的网格搜索调参示例过程中

scikit-learn==0.23.2
pyss3==0.6.4

from pyss3.util import Evaluation

clf = SS3()
best_s, best_l, best_p, _ = Evaluation.grid_search(
    clf, x_train, y_train,
    s=[0.2, 0.32, 0.44, 0.56, 0.68, 0.8],
    l=[0.1, 0.48, 0.86, 1.24, 1.62, 2],
    p=[0.5, 0.8, 1.1, 1.4, 1.7, 2],
    k_fold=10
)

报错：

  File "x.py", line 85, in <module>
    batch()
  File "x.py", line 54, in batch
    best_s, best_l, best_p, _ = Evaluation.grid_search(
  File "x\lib\site-packages\pyss3\util.py", line 1638, in grid_search
    Evaluation.__grid_search_loop__(
  File "x\lib\site-packages\pyss3\util.py", line 809, in __grid_search_loop__
    Evaluation.__evaluation_result__(
  File "x\lib\site-packages\pyss3\util.py", line 661, in __evaluation_result__
    classification_report(
  File "x\lib\site-packages\sklearn\utils\validation.py", line 72, in inner_f
    return f(**kwargs)
  File "x\lib\site-packages\sklearn\metrics\_classification.py", line 1979, in classification_report
    name_width = max(len(cn) for cn in target_names)
ValueError: max() arg is an empty sequence
                                                                
Process finished with exit code 1

问题原因和解决方案：

调用了sklearn的classification_report方法，需要传入标签，但是SS3类中的__categories__属性为[]，引发了报错。 __categories__只有在执行SS3.fit方法时才会添加，因此在进行网格搜索之前，需要先执行一遍训练过程，即添加

clf.fit(x_train, y_train)

或着直接指定标签，即添加

clf.__categories__ = ['xxx', 'yyy']

后记

网格搜索会自动缓存一份各参数的表现，第二遍运行会直接读取结果。