Skip to content

fix:Improve scaler handling in predict and train methods #64

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix:Improve scaler handling in predict and train methods #64

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
10 changes: 6 additions & 4 deletions ncpi/Inference.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -446,6 +446,8 @@ def process_batch(batch):
# Transform the features
if scaler is not None:
feat = scaler.transform(feat.reshape(1, -1))
# else:
# feat = feat.reshape(-1, 1)

# Check that feat has no NaN or Inf values
if np.all(np.isfinite(feat)):
Expand Down Expand Up @@ -482,7 +484,7 @@ def process_batch(batch):
return batch_index, predictions

model_path = os.path.join(result_dir, 'model.pkl')
# scaler_path = os.path.join(result_dir, 'scaler.pkl')
scaler_path = os.path.join(result_dir, 'scaler.pkl')
density_estimator_path = os.path.join(result_dir, 'density_estimator.pkl')

if not os.path.exists(model_path):
Expand All @@ -493,9 +495,9 @@ def process_batch(batch):
model = pickle.load(file)

# # Load or assign the scaler
# if scaler is not None:
# with open(scaler_path, 'rb') as file:
# scaler = pickle.load(file)
if scaler is None and os.path.exists(scaler_path):
with open(scaler_path, 'rb') as file:
scaler = pickle.load(file)

# Load density_estimator and build posterior if SBI
if self.model[1] == 'sbi':
Expand Down