Skip to content

Allow data_generator.py to run without requiring classical datasets for custom datasets #28

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

Allow data_generator.py to run without requiring classical datasets for custom datasets #28

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
6 changes: 4 additions & 2 deletions adbench/datasets/data_generator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,7 @@ def __init__(self, seed:int=42, dataset:str=None, test_size:float=0.3,
self.n_samples_threshold = n_samples_threshold

# dataset list
self.dataset_list_classical, self.dataset_list_cv, self.dataset_list_nlp = self.generate_dataset_list()
# self.dataset_list_classical, self.dataset_list_cv, self.dataset_list_nlp = self.generate_dataset_list()

# myutils function
self.utils = Utils()
Expand Down Expand Up @@ -232,6 +232,8 @@ def generator(self, X=None, y=None, minmax=True,
assert X is not None and y is not None, "For customized dataset, you should provide the X and y!"
print('Testing on customized dataset...')
else:
self.dataset_list_classical, self.dataset_list_cv, self.dataset_list_nlp = self.generate_dataset_list()

if self.dataset in self.dataset_list_classical:
data = np.load(os.path.join(os.path.dirname(os.path.abspath(__file__)), 'Classical', self.dataset + '.npz'), allow_pickle=True)
elif self.dataset in self.dataset_list_cv:
Expand Down Expand Up @@ -368,4 +370,4 @@ def generator(self, X=None, y=None, minmax=True,
y_train[idx_unlabeled] = 0
y_train[idx_labeled_anomaly] = 1

return {'X_train':X_train, 'y_train':y_train, 'X_test':X_test, 'y_test':y_test}
return {'X_train':X_train, 'y_train':y_train, 'X_test':X_test, 'y_test':y_test}