尝试将 pandas 数据框保存到数据块中的工作区目录时出现无效参数错误

Question

我正在尝试将 pandas DataFrame 保存为

csv

到我在 Databricks 工作区中创建的目录。

import pandas as pd
df.to_csv("data.csv", index=False)

OSError                                   Traceback (most recent call last)
File <command-1050805454984878>:2
      1 # Save CSV to Databricks filesystem
----> 2 df.to_csv(str(os.getcwd()) + "data.csv", index=False)

File /databricks/python/lib/python3.9/site-packages/pandas/core/generic.py:3551, in NDFrame.to_csv(self, path_or_buf, sep, na_rep, float_format, columns, header, index, index_label, mode, encoding, compression, quoting, quotechar, line_terminator, chunksize, date_format, doublequote, escapechar, decimal, errors, storage_options)
   3540 df = self if isinstance(self, ABCDataFrame) else self.to_frame()
   3542 formatter = DataFrameFormatter(
   3543     frame=df,
   3544     header=header,
   (...)
   3548     decimal=decimal,
   3549 )
-> 3551 return DataFrameRenderer(formatter).to_csv(
   3552     path_or_buf,
   3553     line_terminator=line_terminator,
   3554     sep=sep,
   3555     encoding=encoding,
   3556     errors=errors,
   3557     compression=compression,
   3558     quoting=quoting,
   3559     columns=columns,
   3560     index_label=index_label,
   3561     mode=mode,
   3562     chunksize=chunksize,
   3563     quotechar=quotechar,
   3564     date_format=date_format,
   3565     doublequote=doublequote,
   3566     escapechar=escapechar,
   3567     storage_options=storage_options,
   3568 )

File /databricks/python/lib/python3.9/site-packages/pandas/io/formats/format.py:1180, in DataFrameRenderer.to_csv(self, path_or_buf, encoding, sep, columns, index_label, mode, compression, quoting, quotechar, line_terminator, chunksize, date_format, doublequote, escapechar, errors, storage_options)
   1159     created_buffer = False
   1161 csv_formatter = CSVFormatter(
   1162     path_or_buf=path_or_buf,
   1163     line_terminator=line_terminator,
   (...)
   1178     formatter=self.fmt,
   1179 )
-> 1180 csv_formatter.save()
   1182 if created_buffer:
   1183     assert isinstance(path_or_buf, StringIO)

File /databricks/python/lib/python3.9/site-packages/pandas/io/formats/csvs.py:261, in CSVFormatter.save(self)
    241 with get_handle(
    242     self.filepath_or_buffer,
    243     self.mode,
   (...)
    249 
    250     # Note: self.encoding is irrelevant here
    251     self.writer = csvlib.writer(
    252         handles.handle,
    253         lineterminator=self.line_terminator,
   (...)
    258         quotechar=self.quotechar,
    259     )
--> 261     self._save()

File /databricks/python/lib/python3.9/site-packages/pandas/io/formats/csvs.py:266, in CSVFormatter._save(self)
    264 if self._need_to_save_header:
    265     self._save_header()
--> 266 self._save_body()

File /databricks/python/lib/python3.9/site-packages/pandas/io/formats/csvs.py:304, in CSVFormatter._save_body(self)
    302 if start_i >= end_i:
    303     break
--> 304 self._save_chunk(start_i, end_i)

File /databricks/python/lib/python3.9/site-packages/pandas/io/formats/csvs.py:315, in CSVFormatter._save_chunk(self, start_i, end_i)
    312 data = [res.iget_values(i) for i in range(len(res.items))]
    314 ix = self.data_index[slicer]._format_native_types(**self._number_format)
--> 315 libwriters.write_csv_rows(
    316     data,
    317     ix,
    318     self.nlevels,
    319     self.cols,
    320     self.writer,
    321 )

File /databricks/python/lib/python3.9/site-packages/pandas/_libs/writers.pyx:72, in pandas._libs.writers.write_csv_rows()

OSError: [Errno 22] Invalid argument

我希望将其保存为

csv

或

.pickle

文件。我还尝试指定目录的完整绝对路径。