def test_name_flattening(self):
num_tests = 1000
for i in range(num_tests):
random_config = self.cache_param_space.random()
flat_dimensions = []
for dimension_name, value in random_config:
original_dimension = self.cache_param_space[dimension_name]
flat_dimension = original_dimension.copy()
flat_dimension.name = Dimension.flatten_dimension_name(
dimension_name)
flat_dimensions.append(flat_dimension)
# Let's create a flat hypergrid that contains that random_config
flat_cache_param_space = SimpleHypergrid(
name=f"Flat{self.cache_param_space.name}",
dimensions=flat_dimensions)
flat_random_config = random_config.flat_copy()
self.assertTrue(flat_random_config in flat_cache_param_space)
# let's try another random config
another_random_config = self.cache_param_space.random()
flattened_config = another_random_config.flat_copy()
try:
if flattened_config in flat_cache_param_space:
...
self.assertTrue(True)
except:
self.assertTrue(False)
def __init__(self, adaptee: Hypergrid):
HypergridAdapter.__init__(self,
name=adaptee.name,
random_state=adaptee.random_state)
self._adaptee: Hypergrid = adaptee
self._target: SimpleHypergrid = None
self._forward_name_mapping = dict()
self._backward_name_mapping = dict()
if HypergridAdapter.is_like_simple_hypergrid(self._adaptee):
# Need to flatten all the names
target_dimensions = []
for adaptee_dimension in self._adaptee.dimensions:
target_dimension_name = Dimension.flatten_dimension_name(
adaptee_dimension.name)
self._forward_name_mapping[
adaptee_dimension.name] = target_dimension_name
self._backward_name_mapping[
target_dimension_name] = adaptee_dimension.name
target_dimension = adaptee_dimension.copy()
target_dimension.name = target_dimension_name
target_dimensions.append(target_dimension)
self._target = SimpleHypergrid(name=self._adaptee.name,
dimensions=target_dimensions)
else:
raise TypeError(
f"Cannot build CompositeToSImpleHypergridAdapter for object of type {type(self._adaptee)}."
)
def _create_random_flat_subspace(original_space, subspace_name, max_num_dimensions):
""" Creates a random simple hypergrid from the hypergrid with up to max_num_dimensions dimensions.
TODO: move this to the *Hypergrid classes.
:param original_space:
:return:
"""
random_point = original_space.random()
dimensions_for_point = original_space.get_dimensions_for_point(random_point, return_join_dimensions=False)
selected_dimensions = random.sample(dimensions_for_point, min(len(dimensions_for_point), max_num_dimensions))
flat_dimensions = []
for dimension in selected_dimensions:
flat_dimension = dimension.copy()
flat_dimension.name = Dimension.flatten_dimension_name(flat_dimension.name)
flat_dimensions.append(flat_dimension)
flat_hypergrid = SimpleHypergrid(
name=subspace_name,
dimensions=flat_dimensions
)
return flat_hypergrid
def __init__(
self,
model_config: RegressionEnhancedRandomForestRegressionModelConfig,
input_space: Hypergrid,
output_space: Hypergrid,
logger=None
):
if logger is None:
logger = create_logger("RegressionEnhancedRandomForestRegressionModel")
self.logger = logger
assert RegressionEnhancedRandomForestRegressionModelConfig.contains(model_config)
RegressionModel.__init__(
self,
model_type=type(self),
model_config=model_config,
input_space=input_space,
output_space=output_space
)
self.input_dimension_names = [dimension.name for dimension in self.input_space.dimensions]
self.output_dimension_names = [dimension.name for dimension in self.output_space.dimensions]
self._input_space_dimension_name_mappings = {
dimension.name: Dimension.flatten_dimension_name(dimension.name)
for dimension in self.input_space.dimensions
}
self._output_space_dimension_name_mappings = {
dimension.name: Dimension.flatten_dimension_name(dimension.name)
for dimension in self.output_space.dimensions
}
self.base_regressor_ = None
self.base_regressor_config = dict()
self.base_regressor_config = self.model_config.boosting_root_model_config
if self.model_config.boosting_root_model_name == SklearnLassoRegressionModelConfig.__name__:
self.base_regressor_ = linear_model.Lasso(
alpha=self.base_regressor_config.alpha,
fit_intercept=self.base_regressor_config.fit_intercept,
normalize=self.base_regressor_config.normalize,
precompute=self.base_regressor_config.precompute,
copy_X=self.base_regressor_config.copy_x,
max_iter=self.base_regressor_config.max_iter,
tol=self.base_regressor_config.tol,
warm_start=self.base_regressor_config.warm_start,
positive=self.base_regressor_config.positive,
random_state=self.base_regressor_config.random_state,
selection=self.base_regressor_config.selection
)
elif self.model_config.boosting_root_model_name == SklearnRidgeRegressionModelConfig.__name__:
self.base_regressor_ = linear_model.Ridge(
alpha=self.base_regressor_config.alpha,
fit_intercept=self.base_regressor_config.fit_intercept,
normalize=self.base_regressor_config.normalize,
copy_X=self.base_regressor_config.copy_x,
max_iter=self.base_regressor_config.max_iter,
tol=self.base_regressor_config.tol,
random_state=self.base_regressor_config.random_state,
solver=self.base_regressor_config.solver
)
else:
self.logger('Boosting base model name "{0}" not supported currently.' \
.format(self.model_config.boosting_root_model_name))
rf_config = self.model_config.random_forest_model_config
self.random_forest_regressor_ = RandomForestRegressor(
n_estimators=rf_config.n_estimators,
criterion=rf_config.criterion,
max_depth=rf_config.max_depth_value,
min_samples_split=rf_config.min_samples_split,
min_samples_leaf=rf_config.min_samples_leaf,
min_weight_fraction_leaf=rf_config.min_weight_fraction_leaf,
max_features=rf_config.max_features,
max_leaf_nodes=rf_config.max_leaf_nodes_value,
min_impurity_decrease=rf_config.min_impurity_decrease,
bootstrap=rf_config.bootstrap,
oob_score=rf_config.oob_score,
n_jobs=rf_config.n_jobs,
warm_start=rf_config.warm_start,
ccp_alpha=rf_config.ccp_alpha,
max_samples=rf_config.max_sample_value
)
# set up basis feature transform
self.polynomial_features_transform_ = None
if self.model_config.max_basis_function_degree > 1:
self.polynomial_features_transform_ = \
PolynomialFeatures(degree=self.model_config.max_basis_function_degree)
self.random_forest_kwargs = None
self.root_model_kwargs = None
self.detected_feature_indices_ = None
self.screening_root_model_coef_ = None
self.fit_X_ = None
self.partial_hat_matrix_ = None
self.base_regressor_standard_error_ = None
self.dof_ = None
self.variance_estimate_ = None
self.root_model_gradient_coef_ = None