Skip to content

feat: add standardization as parameter for dataset #21

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

feat: add standardization as parameter for dataset #21

Show file tree
Hide file tree
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
7 changes: 5 additions & 2 deletions datasets/breheny.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,17 +44,20 @@ class Dataset(BaseDataset):

parameters = {
"dataset": ["Scheetz2006", "Rhee2006", "bcTCGA"],
"standardize" : [True, False]
}

install_cmd = "conda"
requirements = ["rpy2", "numpy", "scipy", "appdirs", "r"]

def __init__(self, dataset="bcTCGA"):
def __init__(self, dataset="bcTCGA", standardize=True):
self.dataset = dataset
self.X, self.y = None, None
self.standardize = standardize

def get_data(self):
X, y = fetch_breheny(self.dataset)
X, y = preprocess_data(X, y)
if self.standardize:
X, y = preprocess_data(X, y)

return dict(X=X, y=y)
7 changes: 5 additions & 2 deletions datasets/libsvm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,17 +12,20 @@ class Dataset(BaseDataset):

parameters = {
"dataset": ["finance", "finance-tf-idf", "YearPredictionMSD"],
"standardize" : [True, False]
}

install_cmd = "conda"
requirements = ["pip:libsvmdata"]

def __init__(self, dataset="bodyfat"):
def __init__(self, dataset="bodyfat", standardize=True):
self.dataset = dataset
self.X, self.y = None, None
self.standardize = standardize

def get_data(self):
X, y = fetch_libsvm(self.dataset)
X, y = preprocess_data(X, y)
if self.standardize:
X, y = preprocess_data(X, y)

return dict(X=X, y=y)
13 changes: 11 additions & 2 deletions datasets/simulated.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,16 +15,24 @@ class Dataset(BaseDataset):
(200, 10_000, 20),
],
"rho": [0, 0.5],
"standardize": [True, False],
}

def __init__(
self, n_samples=10, n_features=50, n_signals=5, rho=0, random_state=27
self,
n_samples=10,
n_features=50,
n_signals=5,
rho=0,
random_state=27,
standardize=True,
):
self.n_samples = n_samples
self.n_features = n_features
self.n_signals = n_signals
self.random_state = random_state
self.rho = rho
self.standardize = standardize

def get_data(self):
X, y, _ = make_correlated_data(
Expand All @@ -35,6 +43,7 @@ def get_data(self):
random_state=self.random_state,
)

X, y = preprocess_data(X, y)
if self.standardize:
X, y = preprocess_data(X, y)

return dict(X=X, y=y)