Нет модуля с именем «pyspark.sql.metrics» при работе с Pickle или JobLib в Databrick. ⇐ Python

[Anonymous]

Я читаю данные из Databricks

Код: Выделить всё

import pandas as pd
import joblib
query = 'select * from table a"
df = spark.sql(query)
df = df.toPandas()

df.to_pickle('df.pickle')
joblib.dump(df, 'df.joblib')

Затем я пытаюсь прочитать то, что сохранил на своем локальном компьютере (с помощью Pickle или JobLib).

Код: Выделить всё

import joblib
import pandas as pd
df = joblib.load('df.joblib')

и в итоге получаем следующую ошибку:

Код: Выделить всё

ModuleNotFoundError: No module named 'pyspark.sql.metrics'
Cell In[8], line 1
----> 1 df = joblib.load('Data/df.joblib')
Hide Traceback
File ~\myenv\Lib\site-packages\joblib\numpy_pickle.py:658, in load(filename, mmap_mode)
652             if isinstance(fobj, str):
653                 # if the returned file object is a string, this means we
654                 # try to load a pickle file generated with an version of
655                 # Joblib so we load it with joblib compatibility function.
656                 return load_compatibility(fobj)
--> 658             obj = _unpickle(fobj, filename, mmap_mode)
659 return obj

File ~\myenv\Lib\site-packages\joblib\numpy_pickle.py:577, in _unpickle(fobj, filename, mmap_mode)
575 obj = None
576 try:
--> 577     obj = unpickler.load()
578     if unpickler.compat_mode:
579         warnings.warn("The file '%s' has been generated with a "
580                       "joblib version less than 0.10. "
581                       "Please regenerate this pickle file."
582                       % filename,
583                       DeprecationWarning, stacklevel=3)

File ~\AppData\Local\Programs\Python\Python311\Lib\pickle.py:1213, in _Unpickler.load(self)
1211             raise EOFError
1212         assert isinstance(key, bytes_types)
-> 1213         dispatch[key[0]](self)
1214 except _Stop as stopinst:
1215     return stopinst.value

File ~\AppData\Local\Programs\Python\Python311\Lib\pickle.py:1538, in _Unpickler.load_stack_global(self)
1536 if type(name) is not str or type(module) is not str:
1537     raise UnpicklingError("STACK_GLOBAL requires str")
-> 1538 self.append(self.find_class(module, name))

File ~\AppData\Local\Programs\Python\Python311\Lib\pickle.py:1580, in _Unpickler.find_class(self, module, name)
1578     elif module in _compat_pickle.IMPORT_MAPPING:
1579         module = _compat_pickle.IMPORT_MAPPING[module]
-> 1580 __import__(module, level=0)
1581 if self.proto >= 4:
1582     return _getattribute(sys.modules[module], name)[0]

Можно ли это исправить?

Подробнее здесь: https://stackoverflow.com/questions/798 ... ib-on-data