search

snap-stanford / pretrain-gnns

Strategies for Pre-training Graph Neural Networks
MIT License
966 stars 162 forks source link

ModuleNotFoundError: No module named 'pandas.core.indexes.numeric' #68

Open hxu105 opened 7 months ago

hxu105 commented 7 months ago

Howdy, thank you for providing this amazing work to the community; however, there are some bugs in the code hindering us from exploring the dataset. Could you help to revise the code? I believe some bugs are due to the package version, but I do face one about

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/scratch/user/hx105/pretrain-gnns/chem/loader.py", line 284, in __init__
    super(MoleculeDataset, self).__init__(root, transform, pre_transform,
  File "/scratch/user/hx105/explainer/lib/python3.8/site-packages/torch_geometric/data/in_memory_dataset.py", line 76, in __init__
    super().__init__(root, transform, pre_transform, pre_filter, log)
  File "/scratch/user/hx105/explainer/lib/python3.8/site-packages/torch_geometric/data/dataset.py", line 102, in __init__
    self._process()
  File "/scratch/user/hx105/explainer/lib/python3.8/site-packages/torch_geometric/data/dataset.py", line 235, in _process
    self.process()
  File "/scratch/user/hx105/pretrain-gnns/chem/loader.py", line 398, in process
    _load_chembl_with_labels_dataset(os.path.join(self.root, 'raw'))
  File "/scratch/user/hx105/pretrain-gnns/chem/loader.py", line 1201, in _load_chembl_with_labels_dataset
    sampleAnnInd=pickle.load(f)
ModuleNotFoundError: No module named 'pandas.core.indexes.numeric'

Many thanks!