def make_fixture(binary=False, balanced=False, split=False):
"""
Make a dataset for testing ClassBalance based on the specified params.
"""
kwargs = {
"n_samples": 100,
"n_features": 20,
"n_informative": 8,
"n_redundant": 2,
"n_clusters_per_class": 1,
"random_state": 89092,
}
if binary:
kwargs["n_classes"] = 2
kwargs["weights"] = None if balanced else [0.3, 0.7]
else:
kwargs["n_classes"] = 5
kwargs["weights"] = None if balanced else [0.1, 0.2, 0.4, 0.2, 0.01]
X, y = make_classification(**kwargs)
if split:
X_train, X_test, y_train, y_test = tts(X, y, test_size=0.2, random_state=101)
return Dataset(Split(X_train, X_test), Split(y_train, y_test))
return Dataset(X, y)
def digits(request):
"""
Creates a fixture of train and test splits for the sklearn digits dataset
For ease of use returns a Dataset named tuple composed of two Split tuples.
"""
data = load_digits()
X_train, X_test, y_train, y_test = tts(
data.data, data.target, test_size=0.2, random_state=11
)
# Set a class attribute for digits
request.cls.digits = Dataset(Split(X_train, X_test), Split(y_train, y_test))
def continuous(request):
"""
Creates a random continuous regression dataset fixture
"""
X, y = make_regression(
n_samples=500,
n_features=22,
n_informative=8,
random_state=42,
noise=0.2,
bias=0.2,
)
X_train, X_test, y_train, y_test = tts(X, y, test_size=0.2, random_state=11)
# Set a class attribute for regression
request.cls.continuous = Dataset(Split(X_train, X_test), Split(y_train, y_test))
def multiclass(request):
"""
Creates a random multiclass classification dataset fixture
"""
X, y = make_classification(
n_samples=500,
n_features=20,
n_informative=8,
n_redundant=2,
n_classes=6,
n_clusters_per_class=3,
random_state=87,
)
X_train, X_test, y_train, y_test = tts(X, y, test_size=0.2, random_state=93)
dataset = Dataset(Split(X_train, X_test), Split(y_train, y_test))
request.cls.multiclass = dataset
def data(request):
"""
Creates a fixture of train and test splits for the sklearn digits dataset
For ease of use returns a Dataset named tuple composed of two Split tuples.
"""
X, y = make_regression(
n_samples=500,
n_features=22,
n_informative=8,
random_state=42,
noise=0.2,
bias=0.2,
)
X_train, X_test, y_train, y_test = tts(X,
y,
test_size=0.2,
random_state=11)
# Set a class attribute for digits
request.cls.data = Dataset(Split(X_train, X_test), Split(y_train, y_test))