def __init__(self, n_estimators=100):
self.decorated_estimator = RandomForestClassifier(
n_estimators=n_estimators, random_state=0)
self.trained_estimator_ = None
self.transform_steps = [
NullColumnCleanse(),
StandardScaler(),
LDA(3)
]
def __init__(self, nu=0.1, kernel="rbf", cache_size=800, gamma='auto'):
self.decorated_estimator = svm.OneClassSVM(nu=nu,
kernel=kernel,
gamma=gamma,
cache_size=cache_size)
self.nu = nu
self.kernel = kernel
self.gamma = gamma
self.trained_estimator_ = None
self.transform_steps = [NullColumnCleanse(), StandardScaler(), LDA(3)]
def __init__(self, class_weight='balanced', max_iter=10000):
self.decorated_estimator = LinearSVC(class_weight=class_weight,
max_iter=1)
self.class_weight = class_weight
self.max_iter = max_iter
self.trained_estimator_ = None
self.transform_steps = [
NullColumnCleanse(),
StandardScaler(),
LDA(1)
]
def __init__(self,
C=1,
kernel='rbf',
gamma='auto',
class_weight='balanced',
cache_size=800,
probability=False):
self.decorated_estimator = SVC(C=C,
kernel=kernel,
gamma=gamma,
class_weight=class_weight,
cache_size=cache_size,
max_iter=1,
probability=probability)
self.C = C
self.kernel = kernel
self.class_weight = class_weight
self.gamma = gamma
self.trained_estimator_ = None
self.transform_steps = [NullColumnCleanse(), StandardScaler(), LDA(1)]
def __init__(self,
max_iter=200,
solver='adam',
activation='relu',
alpha=0.0001,
learning_rate_init=0.001,
batch_size='auto'):
self.decorated_estimator = MLPClassifier(
max_iter=max_iter,
activation=activation,
solver=solver,
alpha=alpha,
learning_rate_init=learning_rate_init,
batch_size=batch_size)
self.max_iter = max_iter
self.activation = activation
self.solver = solver
self.alpha = alpha
self.learning_rate_init = learning_rate_init,
self.batch_size = batch_size,
self.trained_estimator_ = None
self.transform_steps = [NullColumnCleanse(), StandardScaler(), LDA(1)]
def __init__(self, n_estimators=100):
self.decorated_estimator = linear_model.SGDClassifier(max_iter=10000,
penalty='l1')
self.trained_estimator_ = None
self.transform_steps = [NullColumnCleanse(), StandardScaler(), LDA(3)]
def __init__(self,
estimator=LocalOutlierFactor(n_neighbors=3, novelty=True)):
self.decorated_estimator = estimator
self.trained_estimator_ = None
self.transform_steps = [NullColumnCleanse(), StandardScaler(), LDA(3)]
def __init__(self, estimator=DecisionTreeClassifier(random_state=0)):
self.decorated_estimator = estimator
self.trained_estimator_ = None
self.transform_steps = [NullColumnCleanse(), StandardScaler(), LDA(3)]