def iterative_fit(self, X, y, n_iter=2, refit=False, sample_weight=None):
from sklearn.linear_model.passive_aggressive import \
PassiveAggressiveRegressor
# Need to fit at least two iterations, otherwise early stopping will not
# work because we cannot determine whether the algorithm actually
# converged. The only way of finding this out is if the sgd spends less
# iterations than max_iter. If max_iter == 1, it has to spend at least
# one iteration and will always spend at least one iteration, so we
# cannot know about convergence.
if refit:
self.estimator = None
if self.estimator is None:
self.fully_fit_ = False
self.average = check_for_bool(self.average)
self.fit_intercept = check_for_bool(self.fit_intercept)
self.tol = float(self.tol)
self.C = float(self.C)
call_fit = True
self.estimator = PassiveAggressiveRegressor(
C=self.C,
fit_intercept=self.fit_intercept,
max_iter=n_iter,
tol=self.tol,
loss=self.loss,
shuffle=True,
random_state=self.random_state,
warm_start=True,
average=self.average,
)
else:
call_fit = False
if call_fit:
self.estimator.fit(X, y)
else:
self.estimator.max_iter += n_iter
self.estimator.max_iter = min(self.estimator.max_iter,
1000)
self.estimator._validate_params()
lr = "pa1" if self.estimator.loss == "epsilon_insensitive" else "pa2"
self.estimator._partial_fit(
X, y,
alpha=1.0,
C=self.estimator.C,
loss="epsilon_insensitive",
learning_rate=lr,
max_iter=n_iter,
sample_weight=sample_weight,
coef_init=None,
intercept_init=None
)
if self.estimator.max_iter >= 1000 or n_iter > self.estimator.n_iter_:
self.fully_fit_ = True
return self
class PassiveAggressiveRegressorImpl():
def __init__(self, C=1.0, fit_intercept=True, max_iter=None, tol=None, early_stopping=False, validation_fraction=0.1, n_iter_no_change=5, shuffle=True, verbose=0, loss='epsilon_insensitive', epsilon=0.1, random_state=None, warm_start=False, average=False, n_iter=None):
self._hyperparams = {
'C': C,
'fit_intercept': fit_intercept,
'max_iter': max_iter,
'tol': tol,
'early_stopping': early_stopping,
'validation_fraction': validation_fraction,
'n_iter_no_change': n_iter_no_change,
'shuffle': shuffle,
'verbose': verbose,
'loss': loss,
'epsilon': epsilon,
'random_state': random_state,
'warm_start': warm_start,
'average': average,
'n_iter': n_iter}
def fit(self, X, y=None):
self._sklearn_model = SKLModel(**self._hyperparams)
if (y is not None):
self._sklearn_model.fit(X, y)
else:
self._sklearn_model.fit(X)
return self
def predict(self, X):
return self._sklearn_model.predict(X)
def __init__(self,
C=1.0,
fit_intercept=True,
max_iter=None,
tol=None,
early_stopping=False,
validation_fraction=0.1,
n_iter_no_change=5,
shuffle=True,
verbose=0,
loss='epsilon_insensitive',
epsilon=0.1,
random_state=None,
warm_start=False,
average=False,
n_iter=None):
self._hyperparams = {
'C': C,
'fit_intercept': fit_intercept,
'max_iter': max_iter,
'tol': tol,
'early_stopping': early_stopping,
'validation_fraction': validation_fraction,
'n_iter_no_change': n_iter_no_change,
'shuffle': shuffle,
'verbose': verbose,
'loss': loss,
'epsilon': epsilon,
'random_state': random_state,
'warm_start': warm_start,
'average': average,
'n_iter': n_iter
}
self._wrapped_model = Op(**self._hyperparams)
def fit(self, X, y=None):
self._sklearn_model = SKLModel(**self._hyperparams)
if (y is not None):
self._sklearn_model.fit(X, y)
else:
self._sklearn_model.fit(X)
return self
"Extra Tree",
"SVR"
]
classifiers = [
RandomForestRegressor(n_estimators=200, n_jobs=5,
random_state=randomstate),
ExtraTreesRegressor(n_estimators=200, n_jobs=5, random_state=randomstate),
# GradientBoostingRegressor(random_state=randomstate), # learning_rate is a hyper-parameter in the range (0.0, 1.0]
# HistGradientBoostingClassifier(random_state=randomstate), # learning_rate is a hyper-parameter in the range (0.0, 1.0]
AdaBoostRegressor(n_estimators=200, random_state=randomstate),
GaussianProcessRegressor(normalize_y=True),
ARDRegression(),
# HuberRegressor(), # epsilon: greater than 1.0, default 1.35
LinearRegression(n_jobs=5),
PassiveAggressiveRegressor(
random_state=randomstate), # C: 0.25, 0.5, 1, 5, 10
SGDRegressor(random_state=randomstate),
TheilSenRegressor(n_jobs=5, random_state=randomstate),
RANSACRegressor(random_state=randomstate),
KNeighborsRegressor(
weights='distance'), # n_neighbors: 3, 6, 9, 12, 15, 20
RadiusNeighborsRegressor(weights='distance'), # radius: 1, 2, 5, 10, 15
MLPRegressor(max_iter=10000000, random_state=randomstate),
DecisionTreeRegressor(
random_state=randomstate), # max_depth = 2, 3, 4, 6, 8
ExtraTreeRegressor(random_state=randomstate), # max_depth = 2, 3, 4, 6, 8
SVR() # C: 0.25, 0.5, 1, 5, 10
]
selectors = [
reliefF.reliefF,
'NearestCentroid':NearestCentroid(), 'NearestNeighbors':NearestNeighbors(), 'Normalizer':Normalizer(), 'NuSVC':NuSVC(), 'NuSVR':NuSVR(), 'Nystroem':Nystroem(), 'OAS':OAS(), 'OneClassSVM':OneClassSVM(), 'OrthogonalMatchingPursuit':OrthogonalMatchingPursuit(), 'OrthogonalMatchingPursuitCV':OrthogonalMatchingPursuitCV(), 'PCA':PCA(), 'PLSCanonical':PLSCanonical(), 'PLSRegression':PLSRegression(), 'PLSSVD':PLSSVD(), 'PassiveAggressiveClassifier':PassiveAggressiveClassifier(), 'PassiveAggressiveRegressor':PassiveAggressiveRegressor(), 'Perceptron':Perceptron(), 'ProjectedGradientNMF':ProjectedGradientNMF(), 'QuadraticDiscriminantAnalysis':QuadraticDiscriminantAnalysis(), 'RANSACRegressor':RANSACRegressor(), 'RBFSampler':RBFSampler(), 'RadiusNeighborsClassifier':RadiusNeighborsClassifier(), 'RadiusNeighborsRegressor':RadiusNeighborsRegressor(), 'RandomForestClassifier':RandomForestClassifier(), 'RandomForestRegressor':RandomForestRegressor(), 'RandomizedLasso':RandomizedLasso(), 'RandomizedLogisticRegression':RandomizedLogisticRegression(), 'RandomizedPCA':RandomizedPCA(), 'Ridge':Ridge(), 'RidgeCV':RidgeCV(), 'RidgeClassifier':RidgeClassifier(),
class PassiveAggressive(
IterativeComponentWithSampleWeight,
BaseRegressionModel,
):
def __init__(self, C, fit_intercept, tol, loss, average, random_state=None):
self.C = C
self.fit_intercept = fit_intercept
self.average = average
self.tol = tol
self.loss = loss
self.random_state = random_state
self.estimator = None
self.start_time = time.time()
self.time_limit = None
def iterative_fit(self, X, y, n_iter=2, refit=False, sample_weight=None):
from sklearn.linear_model.passive_aggressive import \
PassiveAggressiveRegressor
# Need to fit at least two iterations, otherwise early stopping will not
# work because we cannot determine whether the algorithm actually
# converged. The only way of finding this out is if the sgd spends less
# iterations than max_iter. If max_iter == 1, it has to spend at least
# one iteration and will always spend at least one iteration, so we
# cannot know about convergence.
if refit:
self.estimator = None
if self.estimator is None:
self.fully_fit_ = False
self.average = check_for_bool(self.average)
self.fit_intercept = check_for_bool(self.fit_intercept)
self.tol = float(self.tol)
self.C = float(self.C)
call_fit = True
self.estimator = PassiveAggressiveRegressor(
C=self.C,
fit_intercept=self.fit_intercept,
max_iter=n_iter,
tol=self.tol,
loss=self.loss,
shuffle=True,
random_state=self.random_state,
warm_start=True,
average=self.average,
)
else:
call_fit = False
if call_fit:
self.estimator.fit(X, y)
else:
self.estimator.max_iter += n_iter
self.estimator.max_iter = min(self.estimator.max_iter,
1000)
self.estimator._validate_params()
lr = "pa1" if self.estimator.loss == "epsilon_insensitive" else "pa2"
self.estimator._partial_fit(
X, y,
alpha=1.0,
C=self.estimator.C,
loss="epsilon_insensitive",
learning_rate=lr,
max_iter=n_iter,
sample_weight=sample_weight,
coef_init=None,
intercept_init=None
)
if self.estimator.max_iter >= 1000 or n_iter > self.estimator.n_iter_:
self.fully_fit_ = True
return self
def configuration_fully_fitted(self):
if self.estimator is None:
return False
elif not hasattr(self, 'fully_fit_'):
return False
else:
return self.fully_fit_
def predict(self, X):
if self.estimator is None:
raise NotImplementedError()
return self.estimator.predict(X)
@staticmethod
def get_properties(dataset_properties=None):
return {'shortname': 'PassiveAggressive Regressor',
'name': 'Passive Aggressive Regressor',
'handles_regression': True,
'handles_classification': False,
'handles_multiclass': False,
'handles_multilabel': False,
'is_deterministic': True,
'input': (DENSE, SPARSE, UNSIGNED_DATA),
'output': (PREDICTIONS,)}
@staticmethod
def get_hyperparameter_search_space(dataset_properties=None):
C = UniformFloatHyperparameter("C", 1e-5, 10, 1.0, log=True)
fit_intercept = UnParametrizedHyperparameter("fit_intercept", "True")
loss = CategoricalHyperparameter(
"loss", ["epsilon_insensitive", "squared_epsilon_insensitive"], default_value="epsilon_insensitive"
)
tol = UniformFloatHyperparameter("tol", 1e-5, 1e-1, default_value=1e-4,
log=True)
# Note: Average could also be an Integer if > 1
average = CategoricalHyperparameter('average', ['False', 'True'],
default_value='False')
cs = ConfigurationSpace()
cs.add_hyperparameters([loss, fit_intercept, tol, C, average])
return cs