Hey Cindy, What versions of cuDF and PyArrow do you have installed? I've typically seen this pop up when there's a mismatched version.
-Keith On Tue, Mar 1, 2022 at 8:28 PM Cindy McMullen <cmcmul...@twitter.com> wrote: > Hi - > > I'm trying to use DGL (Deep Graph Library) DGLDataset API with the RAPIDS > cuda DataFrame API. Am getting this error: > > module 'pyarrow.lib' has no attribute '_CRecordBatchReader' > > > Wonder if you see anything obvious in the stack trace that might help me > debug? > > > > Here's the full stack trace: > > > <ipython-input-5-81f2b1833437> in __init__(self) 10 """ 11 def > __init__(self):---> 12 super(UserSimsSingleFileDataset, > self).__init__(name='UserSimsDataset', verbose=False) 13 14 # > One quirk of DGLDataset is that process() and __len__ (load, save) are called > immediately after super(), > /opt/conda/lib/python3.7/site-packages/dgl/data/dgl_dataset.py in > __init__(self, name, url, raw_dir, save_dir, hash_key, force_reload, verbose) > 91 self._save_dir = save_dir 92 ---> 93 > self._load() 94 95 def download(self): > /opt/conda/lib/python3.7/site-packages/dgl/data/dgl_dataset.py in _load(self) > 176 if not load_flag: 177 self._download()--> 178 > self.process() 179 self.save() 180 if > self.verbose: > <ipython-input-5-81f2b1833437> in process(self) 20 21 import > gcsfs---> 22 import cudf 23 self.rows_per_batch = 10000 24 > gs = gcsfs.GCSFileSystem() > /opt/conda/lib/python3.7/site-packages/cudf/__init__.py in <module> 9 > import rmm 10 ---> 11 from cudf import core, datasets, testing 12 > from cudf._version import get_versions 13 from cudf.api.extensions import > ( > /opt/conda/lib/python3.7/site-packages/cudf/core/__init__.py in <module> > 1 # Copyright (c) 2018-2020, NVIDIA CORPORATION. 2 ----> 3 from > cudf.core import buffer, column, column_accessor, common 4 from > cudf.core.buffer import Buffer 5 from cudf.core.dataframe import > DataFrame, from_pandas, merge > /opt/conda/lib/python3.7/site-packages/cudf/core/column/__init__.py in > <module> 1 # Copyright (c) 2020-2021, NVIDIA CORPORATION. 2 ----> 3 > from cudf.core.column.categorical import CategoricalColumn 4 from > cudf.core.column.column import ( 5 ColumnBase, > /opt/conda/lib/python3.7/site-packages/cudf/core/column/categorical.py in > <module> 20 21 import cudf---> 22 from cudf import _lib as libcudf > 23 from cudf._lib.scalar import as_device_scalar 24 from > cudf._lib.transform import bools_to_mask > /opt/conda/lib/python3.7/site-packages/cudf/_lib/__init__.py in <module> > 2 import numpy as np 3 ----> 4 from . import ( 5 avro, 6 > binaryop, > cudf/_lib/gpuarrow.pyx in init cudf._lib.gpuarrow() > AttributeError: module 'pyarrow.lib' has no attribute '_CRecordBatchReader' > >
