Skip to content

Fix/resolve conflicts #46

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
aditya0by0 merged 2 commits into from
Aug 6, 2026
Merged

Fix/resolve conflicts #46

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d16270c
compression changes
aditya0by0 Aug 6, 2026
99571a6
cast ids to string
aditya0by0 Aug 6, 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
16 changes: 15 additions & 1 deletion chebai_graph/preprocessing/datasets/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -143,7 +143,12 @@ def enc_if_not_none(encode, value):
assert len(encoded_values) == len(idents) == len(features)
torch.save(
[
{property.name: torch.cat(feat), "ident": id}
{
property.name: property.encoder.compress(
torch.cat(feat)
),
"ident": id,
}
for feat, id in zip(encoded_values, idents)
if feat is not None
],
Expand Down Expand Up @@ -352,11 +357,15 @@ def load_processed_data(
"""
base_data = super().load_processed_data(kind, filename)
base_df = pd.DataFrame(base_data)
base_df["ident"] = base_df["ident"].astype(str)

for property in self.properties:
property_data = torch.load(
self.get_property_path(property), weights_only=False
)

for entry in property_data:
entry[property.name] = property.encoder.decompress(entry[property.name])
if len(property_data[0][property.name].shape) > 1:
property.encoder.set_encoding_length(
property_data[0][property.name].shape[1]
Expand All @@ -366,6 +375,7 @@ def load_processed_data(
property_df.rename(
columns={property.name: f"{property.name}"}, inplace=True
)
property_df["ident"] = property_df["ident"].astype(str)
base_df = base_df.merge(property_df, on="ident", how="left")

base_df["features"] = base_df.apply(
Expand Down Expand Up @@ -451,6 +461,7 @@ def load_processed_data(
"""
base_data = super().load_processed_data(kind, filename)
base_df = pd.DataFrame(base_data)
base_df["ident"] = base_df["ident"].astype(str)
props_categories = {
"AllNodeTypeProperties": [],
"FGNodeTypeProperties": [],
Expand Down Expand Up @@ -505,12 +516,15 @@ def load_processed_data(
property_data = torch.load(
self.get_property_path(property), weights_only=False
)
for entry in property_data:
entry[property.name] = property.encoder.decompress(entry[property.name])
if len(property_data[0][property.name].shape) > 1:
property.encoder.set_encoding_length(
property_data[0][property.name].shape[1]
)

property_df = pd.DataFrame(property_data)
property_df["ident"] = property_df["ident"].astype(str)
property_df.rename(
columns={property.name: f"{property.name}"}, inplace=True
)
Expand Down
Loading