Skip to content

Fix for recursive calls for load_processed_data method #90

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

Merged
sfluegel05 merged 2 commits into from
May 14, 2025
Merged

Fix for recursive calls for load_processed_data method #90

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
fdf6f5e
no need to catch exceptions
aditya0by0 May 10, 2025
8c5dce4
fix: use `torch.load` instead of `load_processed_data`
aditya0by0 May 10, 2025
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
31 changes: 14 additions & 17 deletions chebai/preprocessing/datasets/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1103,7 +1103,9 @@ def _retrieve_splits_from_csv(self) -> None:
splits_df = pd.read_csv(self.splits_file_path)

filename = self.processed_file_names_dict["data"]
data = self.load_processed_data(filename=filename)
data = torch.load(
os.path.join(self.processed_dir, filename), weights_only=False
)
df_data = pd.DataFrame(data)

train_ids = splits_df[splits_df["split"] == "train"]["id"]
Expand All @@ -1114,6 +1116,7 @@ def _retrieve_splits_from_csv(self) -> None:
self._dynamic_df_val = df_data[df_data["ident"].isin(validation_ids)]
self._dynamic_df_test = df_data[df_data["ident"].isin(test_ids)]

# ------------------------------ Phase: DataLoaders -----------------------------------
def load_processed_data(
self, kind: Optional[str] = None, filename: Optional[str] = None
) -> List[Dict[str, Any]]:
Expand Down Expand Up @@ -1149,24 +1152,18 @@ def load_processed_data(

# If both kind and filename are given, use filename
if kind is not None and filename is None:
try:
if self.use_inner_cross_validation and kind != "test":
filename = self.processed_file_names_dict[
f"fold_{self.fold_index}_{kind}"
]
else:
data_df = self.dynamic_split_dfs[kind]
return data_df.to_dict(orient="records")
except KeyError:
kind = f"{kind}"
if self.use_inner_cross_validation and kind != "test":
filename = self.processed_file_names_dict[
f"fold_{self.fold_index}_{kind}"
]
else:
data_df = self.dynamic_split_dfs[kind]
return data_df.to_dict(orient="records")

# If filename is provided
try:
return torch.load(
os.path.join(self.processed_dir, filename), weights_only=False
)
except FileNotFoundError:
raise FileNotFoundError(f"File {filename} doesn't exist")
return torch.load(
os.path.join(self.processed_dir, filename), weights_only=False
)

# ------------------------------ Phase: Raw Properties -----------------------------------
@property
Expand Down