Skip to content

Move jsonargparse to main dependencies, lazy-load sklearn/scipy in PubChem #153

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
Copilot wants to merge 2 commits into
base: dev
Choose a base branch
from
Draft

Move jsonargparse to main dependencies, lazy-load sklearn/scipy in PubChem #153

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cec2eb8
Initial plan
Copilot Feb 17, 2026
ccd7da6
Move jsonargparse to main dependencies and implement lazy imports for…
Copilot Feb 17, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 10 additions & 3 deletions chebai/preprocessing/datasets/pubchem.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,9 +23,6 @@
import tqdm
from rdkit import Chem, DataStructs
from rdkit.Chem import AllChem
from scipy import spatial
from sklearn.cluster import KMeans
from sklearn.model_selection import train_test_split

from chebai.preprocessing import reader as dr
from chebai.preprocessing.datasets.base import DataLoader, XYBaseDataModule
Expand Down Expand Up @@ -150,6 +147,8 @@ def setup_processed(self):
"""
Prepares processed data and saves them as Torch tensors.
"""
from sklearn.model_selection import train_test_split

filename = os.path.join(self.raw_dir, self.raw_file_names[0])
print("Load data from file", filename)
data = self._load_data_from_file(filename)
Expand Down Expand Up @@ -294,6 +293,8 @@ def setup_processed(self):
"""
Prepares processed data and saves them as Torch tensors.
"""
from sklearn.model_selection import train_test_split

filename = os.path.join(self.raw_dir, self.raw_file_names[0])
print("Load data from file", filename)
data_not_tokenized = [entry for entry in self._load_dict(filename)]
Expand Down Expand Up @@ -557,6 +558,8 @@ def _build_clusters(self) -> tuple[pd.DataFrame, pd.DataFrame]:
Returns:
tuple: Tuple containing cluster centers DataFrame and clustered fingerprints DataFrame.
"""
from sklearn.cluster import KMeans

fingerprints_clustered_path = os.path.join(
self.raw_dir, "fingerprints_clustered.pkl"
)
Expand Down Expand Up @@ -603,6 +606,8 @@ def _exclude_clusters(self, cluster_centers: pd.DataFrame) -> pd.DataFrame:
Returns:
pd.DataFrame: DataFrame of filtered cluster centers.
"""
from scipy import spatial

exclusion_data_path = os.path.join(self.raw_dir, "exclusion_data_clustered.pkl")
cluster_centers_np = np.array(
[
Expand Down Expand Up @@ -701,6 +706,8 @@ def cluster_centers_superclustered(self) -> pd.DataFrame:
Returns:
pd.DataFrame: DataFrame of superclustered cluster centers.
"""
from sklearn.cluster import KMeans

cluster_centers_path = os.path.join(
self.raw_dir, "cluster_centers_superclustered.pkl"
)
Expand Down
2 changes: 1 addition & 1 deletion pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@ dependencies = [
"pysmiles==1.1.2",
"rdkit==2024.3.6",
"lightning==2.5.1",
"jsonargparse[signatures]>=4.17",
]

[project.optional-dependencies]
Expand All @@ -36,7 +37,6 @@ dev = [
"scipy",
"fastobo",
"selfies",
"jsonargparse[signatures]>=4.17",
"omegaconf",
"deepsmiles",
"iterative-stratification",
Expand Down