Loading Molecule dataset

[faizan1234567]

Hi, I am using the following code to load the molecule dataset for classification, however, it gives me an error. I am using this dataset from this repository.

import pandas as pd
import torch
import torch_geometric
from torch_geometric.data import Dataset
import numpy as np 
import os
from tqdm import tqdm
import deepchem as dc

print(f"Torch version: {torch.__version__}")
print(f"Cuda available: {torch.cuda.is_available()}")
print(f"Torch geometric version: {torch_geometric.__version__}")

class MoleculeDataset(Dataset):
    def __init__(self, root, filename, test=False, transform=None, pre_transform=None):
        """
        root = Where the dataset should be stored. This folder is split
        into raw_dir (downloaded dataset) and processed_dir (processed data). 
        """
        self.test = test
        self.filename = filename
        super(MoleculeDataset, self).__init__(root, transform, pre_transform)
        
    @property
    def raw_file_names(self):
        """ If this file exists in raw_dir, the download is not triggered.
            (The download func. is not implemented here)  
        """
        return self.filename

    @property
    def processed_file_names(self):
        """ If these files are found in raw_dir, processing is skipped"""
        self.data = pd.read_csv(self.raw_paths[0]).reset_index()

        if self.test:
            return [f'data_test_{i}.pt' for i in list(self.data.index)]
        else:
            return [f'data_{i}.pt' for i in list(self.data.index)]
        

    def download(self):
        pass

    def process(self):
        self.data = pd.read_csv(self.raw_paths[0]).reset_index()
        featurizer = dc.feat.MolGraphConvFeaturizer(use_edges=True)
        for index, mol in tqdm(self.data.iterrows(), total=self.data.shape[0]):
            # Featurize molecule
            f = featurizer.featurize(mol["smiles"])
            data = f[0].to_pyg_graph()
            data.y = self._get_label(mol["HIV_active"])
            data.smiles = mol["smiles"]
            if self.test:
                torch.save(data, 
                    os.path.join(self.processed_dir, 
                                 f'data_test_{index}.pt'))
            else:
                torch.save(data, 
                    os.path.join(self.processed_dir, 
                                 f'data_{index}.pt'))
            

    def _get_label(self, label):
        label = np.asarray([label])
        return torch.tensor(label, dtype=torch.int64)

    def len(self):
        return self.data.shape[0]

    def get(self, idx):
        """ - Equivalent to __getitem__ in pytorch
            - Is not needed for PyG's InMemoryDataset
        """
        if self.test:
            data = torch.load(os.path.join(self.processed_dir, 
                                 f'data_test_{idx}.pt'))
        else:
            data = torch.load(os.path.join(self.processed_dir, 
                                 f'data_{idx}.pt'))        
        return data
import argparse
def read_args():
    parser = argparse.ArgumentParser()
    parser.add_argument("--test_data", type = str, help= "test data path")
    parser.add_argument("--data", type = str, help= "data path")

    opt = parser.parse_args()
    return opt
    


def main():
    # args = read_args()
    test_dataset = MoleculeDataset(root="/data", filename="HIV_test.csv", test=True)
    print(type(test_dataset))
    print('processing dataset...')
    print(test_dataset.len())
if __name__ == "__main__":
    main()

it gives me the directory error.
FileNotFoundError: [Errno 2] No such file or directory: '\data\raw\HIV_test.csv'
I have downloaded the file from the repo, and put under data dir, but it it not working still.

[rusty1s]

If you specify a raw_file_name, then PyG expects that this is placed in {root_dir}/raw/HIV_test.csv. Where is your CSV file located?