debug

requirements.txt

@@ -6,4 +6,5 @@ numpy
 scikit-learn==1.7.1
 joblib
 tabulate
-datasets
+datasets
+torch==2.8.0

src/data.py

@@ -6,22 +6,15 @@ As an input it takes a list of SMILES and it outputs a nested dictionary with
 SMILES and target names as keys.
 """
 
-import os
 from typing import Iterable, Literal
 
 import numpy as np
 import torch
 
-from sklearn.preprocessing import StandardScaler
-from statsmodels.distributions.empirical_distribution import ECDF
-
-from rdkit import Chem, DataStructs
-from rdkit.Chem import Descriptors, rdFingerprintGenerator
-from rdkit.Chem.rdchem import Mol
-
-from .utils import USED_200_DESCR, Standardizer, load_pickle, write_pickle, KNOWN_DESCR
 from .preprocess import normalize_features
 
+KNOWN_DESCR = ["ecfps", "rdkit_descr_quantiles", "maccs", "tox"]
+
 
 def get_descriptor_dataset(
     data_path: str,