def test_gp_regressor():
rng = np.random.RandomState(0)
X = np.asarray([["ham", "spam", "ted"], ["ham", "ted", "ted"],
["ham", "spam", "spam"]])
y = rng.randn(3)
hm = HammingKernel(length_scale=[1.0, 1.0, 1.0])
gpr = GaussianProcessRegressor(hm)
gpr.fit(X, y)
assert_array_almost_equal(gpr.predict(X), y)
assert_array_almost_equal(gpr.predict(X[:2]), y[:2])
def __init__(self, dimensions_file: str, min_num_results_to_fit: int=8, lease_timout='2 days'):
self.__all_experiments = pd.DataFrame()
self.__all_experiments['status'] = [self.WAITING] * len(self.__all_experiments)
self.__all_experiments['last_update'] = pd.Series(pd.Timestamp(float('NaN')))
self.__all_experiments['client'] = [""] * len(self.__all_experiments)
self.__lease_duration = pd.to_timedelta(lease_timout)
self.__leased_experiments = []
dims = self.__load_dimensions(dimensions_file)
self.__dimension_names = list(dims.keys())
self.__dimensions = list(dims.values())
self.__min_num_results_to_fit = min_num_results_to_fit
# Initialize
dim_types = [check_dimension(d) for d in self.__dimensions]
is_cat = all([isinstance(check_dimension(d), Categorical) for d in dim_types])
if is_cat:
transformed_dims = [check_dimension(d, transform="identity") for d in self.__dimensions]
else:
transformed_dims = []
for dim_type, dim in zip(dim_types, self.__dimensions):
if isinstance(dim_type, Categorical):
transformed_dims.append(check_dimension(dim, transform="onehot"))
# To make sure that GP operates in the [0, 1] space
else:
transformed_dims.append(check_dimension(dim, transform="normalize"))
space = Space(transformed_dims)
# Default GP
cov_amplitude = ConstantKernel(1.0, (0.01, 1000.0))
if is_cat:
other_kernel = HammingKernel(length_scale=np.ones(space.transformed_n_dims))
acq_optimizer = "lbfgs"
else:
other_kernel = Matern(
length_scale=np.ones(space.transformed_n_dims),
length_scale_bounds=[(0.01, 100)] * space.transformed_n_dims,
nu=2.5)
base_estimator = GaussianProcessRegressor(
kernel=cov_amplitude * other_kernel,
normalize_y=True, random_state=None, alpha=0.0, noise='gaussian',
n_restarts_optimizer=2)
self.__opt = Optimizer(self.__dimensions, base_estimator, acq_optimizer="lbfgs",
n_random_starts=100, acq_optimizer_kwargs=dict(n_points=10000))
def cook_estimator(base_estimator, space=None, **kwargs):
if isinstance(base_estimator, str):
base_estimator = base_estimator.upper()
allowed_estimators = ['GP', 'ET', 'RF', 'GBRT', 'DUMMY']
if base_estimator not in allowed_estimators:
raise ValueError(
'invalid estimator, should be in {}, got {}'.format(
allowed_estimators, base_estimator))
elif not is_regressor(base_estimator):
raise ValueError('base estimator should be a regressor, got {}'.format(
base_estimator))
if base_estimator == 'GP':
if space is not None:
# space = Space(space)
space = Space(normalize_param_space(space))
n_params = space.transformed_n_params
is_cat = space.is_categorical
else:
raise ValueError('expected a space instance, got None')
cov_amplitude = ConstantKernel(1.0, (0.01, 1000.0))
if is_cat:
other_kernel = HammingKernel(length_scale=np.ones(n_params))
else:
other_kernel = Matern(length_scale=np.ones(n_params),
length_scale_bounds=[(0.01, 100)] * n_params,
nu=2.5)
base_estimator = GaussianProcessRegressor(kernel=cov_amplitude *
other_kernel,
normalize_y=True,
noise='gaussian',
n_restarts_optimizer=2)
elif base_estimator == 'RF':
base_estimator = RandomForestRegressor(n_estimators=100,
min_samples_leaf=3)
elif base_estimator == 'ET':
base_estimator = ExtraTreesRegressor(n_estimators=100,
min_samples_leaf=3)
elif base_estimator == 'GRBT':
grbt = GradientBoostingRegressor(n_estimators=30, loss='quantile')
base_estimator = GradientBoostingQuantileRegressor(base_estimator=grbt)
elif base_estimator == 'DUMMY':
return None
base_estimator.set_params(**kwargs)
return base_estimator
def test_distance_string():
# Inspired by test_hamming_string_array in scipy.tests.test_distance
a = np.array([
'eggs', 'spam', 'spam', 'eggs', 'spam', 'spam', 'spam', 'spam', 'spam',
'spam', 'spam', 'eggs', 'eggs', 'spam', 'eggs', 'eggs', 'eggs', 'eggs',
'eggs', 'spam'
],
dtype='|S4')
b = np.array([
'eggs', 'spam', 'spam', 'eggs', 'eggs', 'spam', 'spam', 'spam', 'spam',
'eggs', 'spam', 'eggs', 'spam', 'eggs', 'spam', 'spam', 'eggs', 'spam',
'spam', 'eggs'
],
dtype='|S4')
true_values = np.array([[0, 0.45], [0.45, 0]])
X = np.vstack((a, b))
hm = HammingKernel()
assert_array_almost_equal(-np.log(hm(X)) / 20.0, true_values)
def test_gp_regressor():
rng = np.random.RandomState(0)
X = np.asarray([["ham", "spam", "ted"], ["ham", "ted", "ted"],
["ham", "spam", "spam"]])
y = rng.randn(3)
hm = HammingKernel(length_scale=[1.0, 1.0, 1.0])
if UseOrdinalEncoder:
enc = OrdinalEncoder()
enc.fit(X)
gpr = GaussianProcessRegressor(hm)
if UseOrdinalEncoder:
gpr.fit(enc.transform(X), y)
assert_array_almost_equal(gpr.predict(enc.transform(X)), y)
assert_array_almost_equal(gpr.predict(enc.transform(X[:2])), y[:2])
else:
gpr.fit(X, y)
assert_array_almost_equal(gpr.predict(X), y)
assert_array_almost_equal(gpr.predict(X[:2]), y[:2])
def cook_estimator(base_estimator, space=None, **kwargs):
"""Cook a default estimator
For the special `base_estimator` called "DUMMY", the return value is None. This corresponds to
sampling points at random, hence there is no need for an estimator
Parameters
----------
base_estimator: {SKLearn Regressor, "GP", "RF", "ET", "GBRT", "DUMMY"}, default="GP"
If not string, should inherit from `sklearn.base.RegressorMixin`. In addition, the `predict`
method should have an optional `return_std` argument, which returns `std(Y | x)`,
along with `E[Y | x]`.
If `base_estimator` is a string in {"GP", "RF", "ET", "GBRT", "DUMMY"}, a surrogate model
corresponding to the relevant `X_minimize` function is created
space: `hyperparameter_hunter.space.space_core.Space`
Required only if the `base_estimator` is a Gaussian Process. Ignored otherwise
**kwargs: Dict
Extra parameters provided to the `base_estimator` at initialization time
Returns
-------
SKLearn Regressor
Regressor instance cooked up according to `base_estimator` and `kwargs`"""
#################### Validate `base_estimator` ####################
str_estimators = ["GP", "ET", "RF", "GBRT", "DUMMY"]
if isinstance(base_estimator, str):
if base_estimator.upper() not in str_estimators:
raise ValueError(
f"Expected `base_estimator` in {str_estimators}. Got {base_estimator}"
)
# Convert to upper after error check, so above error shows actual given `base_estimator`
base_estimator = base_estimator.upper()
elif not is_regressor(base_estimator):
raise ValueError("`base_estimator` must be a regressor")
#################### Get Cooking ####################
if base_estimator == "GP":
if space is not None:
space = Space(space)
# NOTE: Below `normalize_dimensions` is NOT an unnecessary duplicate of the call in
# `Optimizer` - `Optimizer` calls `cook_estimator` before its `dimensions` have been
# normalized, so `normalize_dimensions` must also be called here
space = Space(normalize_dimensions(space.dimensions))
n_dims = space.transformed_n_dims
is_cat = space.is_categorical
else:
raise ValueError("Expected a `Space` instance, not None")
cov_amplitude = ConstantKernel(1.0, (0.01, 1000.0))
# Only special if *all* dimensions are `Categorical`
if is_cat:
other_kernel = HammingKernel(length_scale=np.ones(n_dims))
else:
other_kernel = Matern(length_scale=np.ones(n_dims),
length_scale_bounds=[(0.01, 100)] * n_dims,
nu=2.5)
base_estimator = GaussianProcessRegressor(
kernel=cov_amplitude * other_kernel,
normalize_y=True,
noise="gaussian",
n_restarts_optimizer=2,
)
elif base_estimator == "RF":
base_estimator = RandomForestRegressor(n_estimators=100,
min_samples_leaf=3)
elif base_estimator == "ET":
base_estimator = ExtraTreesRegressor(n_estimators=100,
min_samples_leaf=3)
elif base_estimator == "GBRT":
gbrt = GradientBoostingRegressor(n_estimators=30, loss="quantile")
base_estimator = GradientBoostingQuantileRegressor(base_estimator=gbrt)
elif base_estimator == "DUMMY":
return None
base_estimator.set_params(**kwargs)
return base_estimator
def __init__(self,
hyper_param_conf,
command,
expdir,
exp_recipe_dir,
recipe,
computing,
exp_proposal_watch_dir=None):
base_estimator = 'GP'
self.hyper_param_conf = hyper_param_conf
self.command = command
self.expdir = expdir
self.exp_recipe_dir = exp_recipe_dir
self.recipe = recipe
self.computing = computing
# read the hyper parameter file
hyper_param_cfg = configparser.ConfigParser()
hyper_param_cfg.read(hyper_param_conf)
hyper_info = dict(hyper_param_cfg.items('info'))
self.hyper_param_names = hyper_info['hyper_params'].split(' ')
self.num_iters = int(hyper_info['num_iters'])
self.n_initial_points = int(hyper_info['n_initial_points'])
self.n_initial_points_to_start = int(
hyper_info['n_initial_points_to_start'])
self.max_parallel_jobs = int(hyper_info['max_parallel_jobs'])
self.selected_segment_length = hyper_info['segment_length']
self.selected_task = hyper_info['task']
if 'adapt_hyper_param' in hyper_info:
self.adapt_param = {
'param_name': hyper_info['adapt_hyper_param'],
'param_thr': int(hyper_info['param_thr']),
'par_cnt_scheme': hyper_info['par_cnt_scheme']
}
else:
self.adapt_param = None
hyper_param_dict = dict()
skopt_dims = []
for par_name in self.hyper_param_names:
par_dict = dict(hyper_param_cfg.items(par_name))
par_type = par_dict['type']
if par_type == 'Integer':
skopt_dim = skopt_space.Integer(low=int(par_dict['min']),
high=int(par_dict['max']),
name=par_name)
elif par_type == 'Real':
skopt_dim = skopt_space.Real(low=float(par_dict['min']),
high=float(par_dict['max']),
name=par_name)
elif par_type == 'Categorical':
skopt_dim = skopt_space.Categorical(
categories=par_dict['categories'].split(' '),
name=par_name)
else:
raise ValueError('Type %s is not a valid parameter type' %
par_type)
hyper_param_dict[par_name] = par_dict
skopt_dims.append(skopt_dim)
self.hyper_param_dict = hyper_param_dict
self.skopt_dims = skopt_dims
self.last_result = None
# self.all_results = []
self.start_new_run_flag = True
self.iter_ind = 0
self.watch_list = dict()
self.all_dim_values = []
self.all_losses = dict()
self.n_job_running = 0
self.n_initial_points_started = 0
self.n_unsuitable_points_for_estimator = 0
self.max_n_unsuitable_points_for_estimator = 10000
self.unsuitable_runs = []
self.lost_runs = []
self.exp_proposal_watch_dir = exp_proposal_watch_dir
self.use_proposal_run = False
self.proposed_loss_runs = []
# only 0.25% of the point sample in the hyper space are wanted (since they lead to rougly the wanted amount of
# trainable parameters)
self.acq_optimizer_kwargs = {'n_points': 4000000}
if 'debug' in expdir:
self.acq_optimizer_kwargs = {'n_points': 40000}
if base_estimator == 'boundedGP':
# Make own estimator based on Gaussian Process Regressor.
if skopt_dims is not None:
space = Space(skopt_dims)
space = Space(normalize_dimensions(space.dimensions))
n_dims = space.transformed_n_dims
is_cat = space.is_categorical
else:
raise ValueError("Expected a Space instance, not None.")
cov_amplitude = ConstantKernel(1.0, (0.01, 1000.0))
# only special if *all* dimensions are categorical
if is_cat:
other_kernel = HammingKernel(length_scale=np.ones(n_dims))
else:
other_kernel = Matern(length_scale=np.ones(n_dims),
length_scale_bounds=[(0.01, 100)] *
n_dims,
nu=2.5)
base_estimator = BoundedGaussianProcessRegressor(
space,
self.hyper_param_names,
self.adapt_param,
kernel=cov_amplitude * other_kernel,
normalize_y=True,
noise="gaussian",
n_restarts_optimizer=2)
super(HyperParamOptimizer,
self).__init__(skopt_dims,
base_estimator=base_estimator,
n_initial_points=self.n_initial_points,
acq_optimizer_kwargs=self.acq_optimizer_kwargs)
def cook_estimator(base_estimator, space=None, **kwargs):
"""
Cook a default estimator.
For the special base_estimator called "DUMMY" the return value is None.
This corresponds to sampling points at random, hence there is no need
for an estimator.
Parameters
----------
* `base_estimator` ["GP", "RF", "ET", "GBRT", "DUMMY"
or sklearn regressor, default="GP"]:
Should inherit from `sklearn.base.RegressorMixin`.
In addition the `predict` method should have an optional `return_std`
argument, which returns `std(Y | x)`` along with `E[Y | x]`.
If base_estimator is one of ["GP", "RF", "ET", "GBRT", "DUMMY"], a
surrogate model corresponding to the relevant `X_minimize` function
is created.
* `space` [Space instance]:
Has to be provided if the base_estimator is a gaussian process.
Ignored otherwise.
* `kwargs` [dict]:
Extra parameters provided to the base_estimator at init time.
"""
if isinstance(base_estimator, str):
base_estimator = base_estimator.upper()
if base_estimator not in ["GP", "ET", "RF", "GBRT", "DUMMY", "GPM32", "GPM1", "RBF", "RQ"]:
raise ValueError("Valid strings for the base_estimator parameter "
" are: 'RF', 'ET', 'GP', 'GBRT' or 'DUMMY' not "
"%s." % base_estimator)
elif not is_regressor(base_estimator):
raise ValueError("base_estimator has to be a regressor.")
if base_estimator == "GP":
if space is not None:
space = Space(space)
space = Space(normalize_dimensions(space.dimensions))
n_dims = space.transformed_n_dims
is_cat = space.is_categorical
else:
raise ValueError("Expected a Space instance, not None.")
cov_amplitude = ConstantKernel(1.0, (0.01, 1000.0))
# only special if *all* dimensions are categorical
if is_cat:
other_kernel = HammingKernel(length_scale=np.ones(n_dims))
else:
other_kernel = Matern(
length_scale=np.ones(n_dims),
length_scale_bounds=[(0.01, 100)] * n_dims, nu=2.5)
base_estimator = GaussianProcessRegressor(
kernel=cov_amplitude * other_kernel,
normalize_y=True, noise="gaussian",
n_restarts_optimizer=2)
elif base_estimator == "GPM32":
if space is not None:
space = Space(space)
space = Space(normalize_dimensions(space.dimensions))
n_dims = space.transformed_n_dims
is_cat = space.is_categorical
else:
raise ValueError("Expected a Space instance, not None.")
cov_amplitude = ConstantKernel(1.0, (0.01, 1000.0))
# only special if *all* dimensions are categorical
if is_cat:
other_kernel = HammingKernel(length_scale=np.ones(n_dims))
else:
other_kernel = Matern(
length_scale=np.ones(n_dims),
length_scale_bounds=[(0.01, 100)] * n_dims, nu=1.5)
base_estimator = GaussianProcessRegressor(
kernel=cov_amplitude * other_kernel,
normalize_y=True, noise="gaussian",
n_restarts_optimizer=2)
elif base_estimator == "GPM1":
if space is not None:
space = Space(space)
space = Space(normalize_dimensions(space.dimensions))
n_dims = space.transformed_n_dims
is_cat = space.is_categorical
else:
raise ValueError("Expected a Space instance, not None.")
cov_amplitude = ConstantKernel(1.0, (0.01, 1000.0))
# only special if *all* dimensions are categorical
if is_cat:
other_kernel = HammingKernel(length_scale=np.ones(n_dims))
else:
other_kernel = Matern(
length_scale=np.ones(n_dims),
length_scale_bounds=[(0.01, 100)] * n_dims, nu=1.5)
base_estimator = GaussianProcessRegressor(
kernel=cov_amplitude * other_kernel,
normalize_y=True, noise="gaussian",
n_restarts_optimizer=2)
elif base_estimator == "RBF":
if space is not None:
space = Space(space)
space = Space(normalize_dimensions(space.dimensions))
n_dims = space.transformed_n_dims
cov_amplitude = ConstantKernel(1.0, (0.01, 1000.0))
other_kernel = RBF(length_scale=np.ones(n_dims))
base_estimator = GaussianProcessRegressor(
kernel=cov_amplitude * other_kernel,
normalize_y=True, noise="gaussian",
n_restarts_optimizer=2)
elif base_estimator == "RQ":
if space is not None:
space = Space(space)
space = Space(normalize_dimensions(space.dimensions))
n_dims = space.transformed_n_dims
cov_amplitude = ConstantKernel(1.0, (0.01, 1000.0))
other_kernel = RationalQuadratic(length_scale=np.ones(n_dims), alpha=0.1)
base_estimator = GaussianProcessRegressor(
kernel=cov_amplitude * other_kernel,
normalize_y=True, noise="gaussian",
n_restarts_optimizer=2)
elif base_estimator == "RF":
base_estimator = RandomForestRegressor(n_estimators=100,
min_samples_leaf=3)
elif base_estimator == "ET":
base_estimator = ExtraTreesRegressor(n_estimators=100,
min_samples_leaf=3)
elif base_estimator == "GBRT":
gbrt = GradientBoostingRegressor(n_estimators=30, loss="quantile")
base_estimator = GradientBoostingQuantileRegressor(base_estimator=gbrt)
elif base_estimator == "DUMMY":
return None
base_estimator.set_params(**kwargs)
return base_estimator