def svc_rbf(name,
C=None,
gamma=None,
shrinking=None,
tol=None,
max_iter=None,
verbose=False,
random_state=None,
cache_size=_svc_default_cache_size):
"""
Return a pyll graph with hyperparamters that will construct
a sklearn.svm.SVC model with an RBF kernel.
"""
def _name(msg):
return '%s.%s_%s' % (name, 'rbf', msg)
rval = scope.sklearn_SVC(
kernel='rbf',
C=_svc_C(name + '.rbf') if C is None else C,
gamma=_svc_gamma(name) if gamma is None else gamma,
shrinking=hp_bool(
_name('shrinking')) if shrinking is None else shrinking,
tol=_svc_tol(name + '.rbf') if tol is None else tol,
max_iter=(_svc_max_iter(name + '.rbf')
if max_iter is None else max_iter),
verbose=verbose,
cache_size=cache_size,
random_state=_random_state(_name('rstate'), random_state),
)
return rval
def svc_rbf(name,
C=None,
gamma=None,
shrinking=None,
tol=None,
max_iter=None,
verbose=False,
random_state=None,
cache_size=_svc_default_cache_size):
"""
Return a pyll graph with hyperparamters that will construct
a sklearn.svm.SVC model with an RBF kernel.
"""
def _name(msg):
return '%s.%s_%s' % (name, 'rbf', msg)
rval = scope.sklearn_SVC(
kernel='rbf',
C=_svc_C(name + '.rbf') if C is None else C,
gamma=_svc_gamma(name) if gamma is None else gamma,
shrinking=hp_bool(_name('shrinking'))
if shrinking is None else shrinking,
tol=_svc_tol(name + '.rbf') if tol is None else tol,
max_iter=(_svc_max_iter(name +
'.rbf') if max_iter is None else max_iter),
verbose=verbose,
cache_size=cache_size,
random_state=_random_state(_name('rstate'), random_state),
)
return rval
def svc_kernel(name, kernel, random_state=None, **kwargs):
"""
Return a pyll graph with hyperparamters that will construct
a sklearn.svm.SVC model with a user specified kernel.
See help(hpsklearn.components._svm_hp_space) for info on additional SVM
arguments.
"""
def _name(msg):
return '%s.%s_%s' % (name, kernel, msg)
hp_space = _svm_hp_space(_name, kernel=kernel, **kwargs)
hp_space.update(_svc_hp_space(_name, random_state))
return scope.sklearn_SVC(**hp_space)
def svc_kernel(name, kernel, random_state=None, **kwargs):
"""
Return a pyll graph with hyperparamters that will construct
a sklearn.svm.SVC model with a user specified kernel.
See help(hpsklearn.components._svm_hp_space) for info on additional SVM
arguments.
"""
def _name(msg):
return '%s.%s_%s' % (name, kernel, msg)
hp_space = _svm_hp_space(_name, kernel=kernel, **kwargs)
hp_space.update(_svc_hp_space(_name, random_state))
return scope.sklearn_SVC(**hp_space)
def svc_poly(name,
C=None,
gamma=None,
coef0=None,
degree=None,
shrinking=None,
tol=None,
max_iter=None,
verbose=False,
random_state=None,
cache_size=_svc_default_cache_size):
"""
Return a pyll graph with hyperparamters that will construct
a sklearn.svm.SVC model with an RBF kernel.
"""
def _name(msg):
return '%s.%s_%s' % (name, 'poly', msg)
# -- (K(x, y) + coef0)^d
coef0nz = hp.choice(_name('coef0nz'), [0, 1])
coef0 = hp.uniform(_name('coef0'), 0.0, 1.0)
poly_coef0 = coef0nz * coef0
rval = scope.sklearn_SVC(
kernel='poly',
C=_svc_C(name + '.poly') if C is None else C,
gamma=_svc_gamma(name + '.poly') if gamma is None else gamma,
coef0=poly_coef0 if coef0 is None else coef0,
degree=hp.quniform(
_name('degree'),
low=1.5,
high=8.5,
q=1) if degree is None else degree,
shrinking=hp_bool(
_name('shrinking')) if shrinking is None else shrinking,
tol=_svc_tol(name + '.poly') if tol is None else tol,
max_iter=(_svc_max_iter(name + '.poly')
if max_iter is None else max_iter),
verbose=verbose,
random_state=_random_state(_name('.rstate'), random_state),
cache_size=cache_size,
)
return rval
def svc_poly(name,
C=None,
gamma=None,
coef0=None,
degree=None,
shrinking=None,
tol=None,
max_iter=None,
verbose=False,
random_state=None,
cache_size=_svc_default_cache_size):
"""
Return a pyll graph with hyperparamters that will construct
a sklearn.svm.SVC model with an RBF kernel.
"""
def _name(msg):
return '%s.%s_%s' % (name, 'poly', msg)
# -- (K(x, y) + coef0)^d
coef0nz = hp.choice(_name('coef0nz'), [0, 1])
coef0 = hp.uniform(_name('coef0'), 0.0, 1.0)
poly_coef0 = coef0nz * coef0
rval = scope.sklearn_SVC(
kernel='poly',
C=_svc_C(name + '.poly') if C is None else C,
gamma=_svc_gamma(name + '.poly') if gamma is None else gamma,
coef0=poly_coef0 if coef0 is None else coef0,
degree=hp.quniform(_name('degree'), low=1.5, high=8.5, q=1)
if degree is None else degree,
shrinking=hp_bool(_name('shrinking'))
if shrinking is None else shrinking,
tol=_svc_tol(name + '.poly') if tol is None else tol,
max_iter=(_svc_max_iter(name +
'.poly') if max_iter is None else max_iter),
verbose=verbose,
random_state=_random_state(_name('.rstate'), random_state),
cache_size=cache_size,
)
return rval
def svc_sigmoid(name,
C=None,
gamma=None,
coef0=None,
shrinking=None,
tol=None,
max_iter=None,
verbose=False,
random_state=None,
cache_size=_svc_default_cache_size):
"""
Return a pyll graph with hyperparamters that will construct
a sklearn.svm.SVC model with an RBF kernel.
"""
def _name(msg):
return '%s.%s_%s' % (name, 'sigmoid', msg)
# -- tanh(K(x, y) + coef0)
coef0nz = hp.choice(_name('coef0nz'), [0, 1])
coef0 = hp.normal(_name('coef0'), 0.0, 1.0)
sigm_coef0 = coef0nz * coef0
rval = scope.sklearn_SVC(
kernel='sigmoid',
C=_svc_C(name + '.sigmoid') if C is None else C,
gamma=_svc_gamma(name + '.sigmoid') if gamma is None else gamma,
coef0=sigm_coef0 if coef0 is None else coef0,
shrinking=hp_bool(
_name('shrinking')) if shrinking is None else shrinking,
tol=_svc_tol(name + '.sigmoid') if tol is None else tol,
max_iter=(_svc_max_iter(name + '.sigmoid')
if max_iter is None else max_iter),
verbose=verbose,
random_state=_random_state(_name('rstate'), random_state),
cache_size=cache_size)
return rval
def svc_sigmoid(name,
C=None,
gamma=None,
coef0=None,
shrinking=None,
tol=None,
max_iter=None,
verbose=False,
random_state=None,
cache_size=_svc_default_cache_size):
"""
Return a pyll graph with hyperparamters that will construct
a sklearn.svm.SVC model with an RBF kernel.
"""
def _name(msg):
return '%s.%s_%s' % (name, 'sigmoid', msg)
# -- tanh(K(x, y) + coef0)
coef0nz = hp.choice(_name('coef0nz'), [0, 1])
coef0 = hp.normal(_name('coef0'), 0.0, 1.0)
sigm_coef0 = coef0nz * coef0
rval = scope.sklearn_SVC(
kernel='sigmoid',
C=_svc_C(name + '.sigmoid') if C is None else C,
gamma=_svc_gamma(name + '.sigmoid') if gamma is None else gamma,
coef0=sigm_coef0 if coef0 is None else coef0,
shrinking=hp_bool(_name('shrinking'))
if shrinking is None else shrinking,
tol=_svc_tol(name + '.sigmoid') if tol is None else tol,
max_iter=(_svc_max_iter(name +
'.sigmoid') if max_iter is None else max_iter),
verbose=verbose,
random_state=_random_state(_name('rstate'), random_state),
cache_size=cache_size)
return rval
