Skip to content

Standarize fix #10

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

Closed
werag55 wants to merge 2 commits into from
Closed

Standarize fix #10

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
06033c2
standarize fix
werag55 Mar 31, 2025
c8f5a76
Pandas
werag55 Mar 31, 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
110 changes: 51 additions & 59 deletions notebooks/experiments/synthetic_data/synthetic_data.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

23 changes: 17 additions & 6 deletions src/data/dataset_interface.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,8 +55,6 @@ def preprocess_data(self, missing_values_strategy='mean', ratio=0.5):
f"Added {num_dummy_features} dummy features."
)

self.standardize_data()

return self

def reduce_samples(self, num_samples=1000):
Expand Down Expand Up @@ -158,10 +156,23 @@ def standardize_data(self):
"""
Standardize the dataset (mean=0, variance=1).
"""
scaler = StandardScaler()
self.data.data = pd.DataFrame(
scaler.fit_transform(self.data.data), columns=self.data.data.columns
)

if self.train_data is not None:
scaler = StandardScaler()
scaler.fit(self.train_data.data)
self.train_data.data = scaler.transform(self.train_data.data)
self.data.data = pd.DataFrame(
scaler.transform(self.data.data), columns=self.data.data.columns
)
if self.val_data.data is not None:
self.val_data.data = pd.DataFrame(
scaler.transform(self.val_data.data), columns=self.val_data.data.columns
)
if self.test_data.data is not None:
self.test_data.data = pd.DataFrame(
scaler.transform(self.test_data.data), columns=self.test_data.data.columns
)

return self

def convert2binary(self, strategy='default', in_labels=None, reset_index=True):
Expand Down
14 changes: 8 additions & 6 deletions tests/data/test_dataset_interface.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -165,17 +165,19 @@ def test_standardize_data():
"""Test standardizing the dataset."""
data_interface = DataInterface()
data_interface.data.data = pd.DataFrame({
'feature1': [1, 2, 3, 4],
'feature2': [5, 6, 7, 8]
'feature1': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
'feature2': [5, 6, 7, 8, 9, 10, 11, 12, 13, 14]
})
data_interface.data.labels = pd.Series([0, 1, 0, 1, 0, 1, 0, 1, 0, 1])
data_interface.split_data(test_size=0.2, val_size=0.2)

data_interface.standardize_data()

print(f'Mean of each column:\n{data_interface.data.data.mean()}')
print(f'Standard deviation of each column:\n{data_interface.data.data.std()}')
print(f'Mean of each column:\n{data_interface.train_data.data.mean()}')
print(f'Standard deviation of each column:\n{data_interface.train_data.data.std()}')

assert np.allclose(data_interface.data.data.mean(), 0, atol=1e-7)
assert np.allclose(data_interface.data.data.std(ddof=0), 1, atol=1e-7)
assert np.allclose(data_interface.train_data.data.mean(), 0, atol=1e-7)
assert np.allclose(data_interface.train_data.data.std(ddof=0), 1, atol=1e-7)

def test_split_data():
"""Test splitting data into train, test, and validation sets."""
Expand Down