def setUp(self):
"""
Generate X, y datasets and fit a RF
"""
#Generate datasets
self.X, self.y = get_classification_data(10,
5,
2,
1000,
random_state=0,
sigma=0)
# Fit a RF
self.clf_base = RandomForestClassifier(
n_estimators=1,
criterion='entropy',
bootstrap=False,
class_weight='balanced_subsample')
self.bag_clf = BaggingClassifier(base_estimator=self.clf_base,
max_features=1.0,
n_estimators=100,
oob_score=True,
random_state=1)
self.fit_clf = self.bag_clf.fit(self.X, self.y)
self.cv_gen = KFold(n_splits=3, random_state=0)
def setUp(self):
"""
Set the file path for the sample dollar bars data.
"""
state = np.random.RandomState(42)
self.x = state.normal(size=1000)
self.y_1 = self.x ** 2 + state.normal(size=1000) / 5
self.y_2 = abs(self.x) + state.normal(size=1000) / 5
self.X_matrix, _ = get_classification_data(6, 2, 2, 100, sigma=0)
def setUp(self):
"""
Set the file path for the sample dollar bars data.
"""
state = np.random.RandomState(42)
self.x = state.normal(size=1000)
self.y_1 = self.x**2 + state.normal(size=1000) / 5
self.y_2 = abs(self.x) + state.normal(size=1000) / 5
self.y_3 = self.x + state.normal(size=1000) / 5
self.X_matrix, _ = get_classification_data(6, 2, 2, 100, sigma=0)
# Setting sample correlation matrices
self.corr_A = np.array(
[[1, 0.70573243, 0.03085437, 0.6019651, 0.81214341],
[0.70573243, 1, 0.03126594, 0.56559443, 0.88961155],
[0.03085437, 0.03126594, 1, 0.01760481, 0.02842086],
[0.60196510, 0.56559443, 0.01760481, 1, 0.73827921],
[0.81214341, 0.88961155, 0.02842086, 0.73827921, 1]])
self.corr_B = np.array(
[[1, 0.49805826, 0.00095199, 0.36236198, 0.65957691],
[0.49805826, 1, 0.00097755, 0.31989705, 0.79140871],
[0.00095199, 0.00097755, 1, 0.00030992, 0.00080774],
[0.36236198, 0.31989705, 0.00030992, 1, 0.54505619],
[0.65957691, 0.79140871, 0.00080774, 0.54505619, 1]])
def setUp(self):
"""
Create X, y datasets
"""
self.X, self.y = get_classification_data(40, 5, 30, 1000, sigma=2)