read_parquet failed with Internal Error

[anmyachev]

Modin version: 45ad9de

Reproducer:

from time import time
import modin.pandas as pd
from modin.utils import execute
import numpy as np


df = pd.DataFrame(np.random.rand(10**5, 10**2))


df.to_parquet("test_parquet_usual.parquet")
df = pd.read_parquet("test_parquet_usual.parquet")

Traceback:

Traceback (most recent call last):
  File "C:\projects\modin\test_parquet_glob.py", line 11, in <module>
    df = pd.read_parquet("test_parquet_usual.parquet")
  File "C:\projects\modin\modin\utils.py", line 484, in wrapped
    return func(*params.args, **params.kwargs)
  File "C:\projects\modin\modin\logging\logger_decorator.py", line 129, in run_and_log
    return obj(*args, **kwargs)
  File "C:\projects\modin\modin\pandas\io.py", line 325, in read_parquet
    query_compiler=FactoryDispatcher.read_parquet(
  File "C:\projects\modin\modin\core\execution\dispatching\factories\dispatcher.py", line 187, in read_parquet
    return cls.get_factory()._read_parquet(**kwargs)
  File "C:\projects\modin\modin\core\execution\dispatching\factories\factories.py", line 212, in _read_parquet
    return cls.io_cls.read_parquet(**kwargs)
  File "C:\projects\modin\modin\logging\logger_decorator.py", line 129, in run_and_log
    return obj(*args, **kwargs)
  File "C:\projects\modin\modin\core\io\file_dispatcher.py", line 164, in read
    if not AsyncReadMode.get() and hasattr(query_compiler, "dtypes"):
  File "C:\projects\modin\modin\core\storage_formats\pandas\query_compiler.py", line 321, in dtypes
    return self._modin_frame.dtypes
  File "C:\projects\modin\modin\core\dataframe\pandas\dataframe\dataframe.py", line 383, in dtypes
    dtypes = self._dtypes.get()
  File "C:\projects\modin\modin\core\dataframe\pandas\metadata\dtypes.py", line 830, in get
    self._value = self._value.to_series()
  File "C:\projects\modin\modin\core\dataframe\pandas\metadata\dtypes.py", line 436, in to_series
    self.materialize()
  File "C:\projects\modin\modin\core\dataframe\pandas\metadata\dtypes.py", line 402, in materialize
    self._materialize_cols_with_unknown_dtypes()
  File "C:\projects\modin\modin\core\dataframe\pandas\metadata\dtypes.py", line 388, in _materialize_cols_with_unknown_dtypes
    self._known_dtypes.update(self._parent_df._compute_dtypes(subset))
  File "C:\projects\modin\modin\logging\logger_decorator.py", line 129, in run_and_log
    return obj(*args, **kwargs)
  File "C:\projects\modin\modin\core\dataframe\pandas\dataframe\dataframe.py", line 436, in _compute_dtypes
    obj.tree_reduce(0, lambda df: df.dtypes, dtype_builder)
  File "C:\projects\modin\modin\logging\logger_decorator.py", line 129, in run_and_log
    return obj(*args, **kwargs)
  File "C:\projects\modin\modin\core\dataframe\pandas\dataframe\utils.py", line 501, in run_f_on_minimally_updated_metadata
    result = f(self, *args, **kwargs)
  File "C:\projects\modin\modin\core\dataframe\pandas\dataframe\dataframe.py", line 4062, in to_pandas
    ErrorMessage.catch_bugs_and_request_email(
  File "C:\projects\modin\modin\error_message.py", line 81, in catch_bugs_and_request_email
    raise Exception(
Exception: Internal Error. Please visit https://github.com/modin-project/modin/issues to file an issue with the traceback and the command that caused this error. If you can't file a GitHub issue, please email bug_reports@modin.org.
Internal and external indices on axis 1 do not match.