lazypredict导入后无可用方法，导入Supervised模块触发依赖报错

我安装了lazypredict，但调用时发现主库似乎没有可用方法。执行以下代码：

import lazypredict
#from lazypredict.Supervised import LazyClassifier

print(lazypredict.__version__)
dir(lazypredict)

输出结果：

0.2.7
['__author__',
 '__builtins__',
 '__cached__',
 '__doc__',
 '__email__',
 '__file__',
 '__loader__',
 '__name__',
 '__package__',
 '__path__',
 '__spec__',
 '__version__']

我尝试过不同版本的lazypredict（0.2.7、0.2.8、0.2.11），搭配不同版本的sklearn（0.23.1、0.24、1.2.1），运行环境为Python3.8和3.9，但结果始终一致。

如果取消注释from lazypredict.Supervised import LazyClassifier这一行，会触发如下错误：
（补充完整错误追踪信息）

OSError                                   Traceback (most recent call last)
/var/folders/v8/gy4lk66j5jv7krxs16hk5wzh0000gn/T/ipykernel_42613/1479214520.py in <module>
      1 import lazypredict
----> 2 from lazypredict.Supervised import LazyClassifier
      3 
      4 print(lazypredict.__version__)

~/opt/anaconda3/lib/python3.9/site-packages/lazypredict/Supervised.py in <module>
     28 
     29 # import catboost
---> 30 import lightgbm
     31 
     32 warnings.filterwarnings("ignore")

~/opt/anaconda3/lib/python3.9/site-packages/lightgbm/__init__.py in <module>
      6 from pathlib import Path
      7 
----> 8 from .basic import Booster, Dataset, Sequence, register_logger
      9 from .callback import early_stopping, log_evaluation, print_evaluation, record_evaluation, reset_parameter
     10 from .engine import CVBooster, cv, train

~/opt/anaconda3/lib/python3.9/site-packages/lightgbm/basic.py in <module>
    108 
    109 
---> 110 _LIB = _load_lib()
    111 
    112 

~/opt/anaconda3/lib/python3.9/site-packages/lightgbm/basic.py in _load_lib()
     99     if len(lib_path) == 0:
    100         return None
---> 101     lib = ctypes.cdll.LoadLibrary(lib_path[0])
    102     lib.LGBM_GetLastError.restype = ctypes.c_char_p
    103     callback = ctypes.CFUNCTYPE(None, ctypes.c_char_p)

~/opt/anaconda3/lib/python3.9/ctypes/__init__.py in LoadLibrary(self, name)
    458 
    459     def LoadLibrary(self, name):
---> 460         return self._dlltype(name)
    461 
    462     __class_getitem__ = classmethod(_types.GenericAlias)

~/opt/anaconda3/lib/python3.9/ctypes/__init__.py in __init__(self, name, mode, handle, use_errno, use_last_error, winmode)
    380 
    381         if handle is None:
---> 382             self._handle = _dlopen(self._name, mode)
    383         else:
    384             self._handle = handle

OSError: dlopen(/Users/nz/opt/anaconda3/lib/python3.9/site-packages/lightgbm/lib_lightgbm.so, 0x0006): Library not loaded: /usr/local/opt/libomp/lib/libomp.dylib
  Referenced from: <D21A7969-4567-3BC7-94ED-6A9E83AE9D78> /Users/nz/opt/anaconda3/lib/python3.9/site-packages/lightgbm/lib_lightgbm.so
  Reason: tried: '/usr/local/opt/libomp/lib/libomp.dylib' (no such file), '/System/Volumes/Preboot/Cryptexes/OS/usr/local/opt/libomp/lib/libomp.dylib' (no such file), '/usr/local/opt/libomp/lib/libomp.dylib' (no such file), '/usr/local/lib/libomp.dylib' (no such file), '/usr/lib/libomp.dylib' (no such file, not in dyld cache)

1. 问题根源 #

错误本质是lightgbm依赖的libomp.dylib运行库缺失（macOS环境下的OpenMP组件），而lazypredict的Supervised模块依赖lightgbm，因此导入时触发依赖错误。另外，lazypredict的核心功能都封装在子模块中，直接导入主模块看不到可用方法是正常设计。

2. 修复步骤 #

• 安装libomp库：通过Homebrew安装（若未安装Homebrew，先自行安装）：

  brew install libomp
  

• 重装lightgbm：确保lightgbm能正确链接到新安装的库：

  pip uninstall -y lightgbm
  pip install lightgbm --no-cache-dir
  

• 验证功能：重新运行导入代码，此时应该可以正常加载LazyClassifier：

  from lazypredict.Supervised import LazyClassifier
  import lazypredict
  print(lazypredict.__version__)
  

内容的提问来源于stack exchange，提问作者CSe