Upgrade to ConfigSpace 1.x (#1124)

* Upgrad to ConfigSpace 1.x

* refactor: ConfigSpace API

* fix(jsondump): add numpy encoder

ConfigSpace integer hyperparameters do not return python int type but numpy int64, which is not json serializable

* fix(jsondump): add numpy encoder

* fix(ConfigSpace): parameter API

* Fix example (ConfigSpace API)

* Make format

* Fix pre-commit

* isort

CHANGELOG.md

@@ -4,7 +4,8 @@
 - Add example to specify total budget (fidelity units) instead of n_trials for multi-fidelity/Hyperband (#1121)
 
 ## Dependencies
-- Update numpy NaN (#1122) and restrict numpy and ConfigSpace versions
+- Update numpy NaN (#1122) and restrict numpy version
+- Upgrade to ConfigSpace 1.x.x (#1124)
 
 # 2.1.0
 

benchmark/src/benchmark.py

@@ -17,6 +17,8 @@
 from collections import defaultdict
 from pathlib import Path
 
+from smac.utils.numpyencoder import NumpyEncoder
+
 import pandas as pd
 from src.tasks import TASKS # noqa: E402
 from src.utils.exceptions import NotSupportedError # noqa: E402
@@ -79,7 +81,7 @@ def _save_data(self) -> None:
  """Saves the internal data to the file."""
  print("Saving data...")
  with open(str(RAW_FILENAME), "w") as f:
- json.dump(self._data, f, indent=4)
+ json.dump(self._data, f, indent=4, cls=NumpyEncoder)
 
  def _fill_keys(self) -> None:
  """Fill data with keys based on computer name, tasks, and selected version."""

benchmark/src/models/ac_branin.py

@@ -20,7 +20,7 @@ def configspace(self) -> ConfigurationSpace:
  x2 = Float("x2", (0, 15), default=7.5)
 
  # Add hyperparameters and conditions to our configspace
- cs.add_hyperparameters([x2])
+ cs.add([x2])
 
  return cs
 

benchmark/src/models/branin.py

@@ -20,7 +20,7 @@ def configspace(self) -> ConfigurationSpace:
  x2 = Float("x2", (0, 15), default=0)
 
  # Add hyperparameters and conditions to our configspace
- cs.add_hyperparameters([x1, x2])
+ cs.add([x1, x2])
 
  return cs
 

benchmark/src/models/himmelblau.py

@@ -19,7 +19,7 @@ def configspace(self) -> ConfigurationSpace:
  y = Float("y", (-5, 5))
 
  # Add hyperparameters and conditions to our configspace
- cs.add_hyperparameters([x, y])
+ cs.add([x, y])
 
  return cs
 

benchmark/src/models/mlp.py

@@ -33,7 +33,7 @@ def configspace(self) -> ConfigurationSpace:
  learning_rate_init = Float("learning_rate_init", (0.0001, 1.0), default=0.001, log=True)
 
  # Add all hyperparameters at once:
- cs.add_hyperparameters([n_layer, n_neurons, activation, solver, batch_size, learning_rate, learning_rate_init])
+ cs.add([n_layer, n_neurons, activation, solver, batch_size, learning_rate, learning_rate_init])
 
  # Adding conditions to restrict the hyperparameter space...
  # ... since learning rate is used when solver is 'sgd'.
@@ -44,7 +44,7 @@ def configspace(self) -> ConfigurationSpace:
  use_batch_size = InCondition(child=batch_size, parent=solver, values=["sgd", "adam"])
 
  # We can also add multiple conditions on hyperparameters at once:
- cs.add_conditions([use_lr, use_batch_size, use_lr_init])
+ cs.add([use_lr, use_batch_size, use_lr_init])
 
  return cs
 

benchmark/src/models/svm.py

@@ -34,8 +34,8 @@ def configspace(self) -> ConfigurationSpace:
  use_gamma_value = InCondition(child=gamma_value, parent=gamma, values=["value"])
 
  # Add hyperparameters and conditions to our configspace
- cs.add_hyperparameters([kernel, C, shrinking, degree, coef, gamma, gamma_value])
- cs.add_conditions([use_degree, use_coef, use_gamma, use_gamma_value])
+ cs.add([kernel, C, shrinking, degree, coef, gamma, gamma_value])
+ cs.add([use_degree, use_coef, use_gamma, use_gamma_value])
 
  return cs
 

examples/1_basics/1_quadratic_function.py

@@ -26,7 +26,7 @@ class QuadraticFunction:
  def configspace(self) -> ConfigurationSpace:
  cs = ConfigurationSpace(seed=0)
  x = Float("x", (-5, 5), default=-5)
- cs.add_hyperparameters([x])
+ cs.add([x])
 
  return cs
 

examples/1_basics/2_svm_cv.py

@@ -46,8 +46,8 @@ def configspace(self) -> ConfigurationSpace:
  use_gamma_value = InCondition(child=gamma_value, parent=gamma, values=["value"])
 
  # Add hyperparameters and conditions to our configspace
- cs.add_hyperparameters([kernel, C, shrinking, degree, coef, gamma, gamma_value])
- cs.add_conditions([use_degree, use_coef, use_gamma, use_gamma_value])
+ cs.add([kernel, C, shrinking, degree, coef, gamma, gamma_value])
+ cs.add([use_degree, use_coef, use_gamma, use_gamma_value])
 
  return cs
 

examples/1_basics/3_ask_and_tell.py

@@ -20,7 +20,7 @@ def configspace(self) -> ConfigurationSpace:
  cs = ConfigurationSpace(seed=0)
  x0 = Float("x0", (-5, 10), default=-3)
  x1 = Float("x1", (-5, 10), default=-4)
- cs.add_hyperparameters([x0, x1])
+ cs.add([x0, x1])
 
  return cs
 

examples/1_basics/4_callback.py

@@ -27,7 +27,7 @@ def configspace(self) -> ConfigurationSpace:
  cs = ConfigurationSpace(seed=0)
  x0 = Float("x0", (-5, 10), default=-3)
  x1 = Float("x1", (-5, 10), default=-4)
- cs.add_hyperparameters([x0, x1])
+ cs.add([x0, x1])
 
  return cs
 

examples/1_basics/5_continue.py

@@ -47,7 +47,7 @@ class QuadraticFunction:
  def configspace(self) -> ConfigurationSpace:
  cs = ConfigurationSpace(seed=0)
  x = Float("x", (-5, 5), default=-5)
- cs.add_hyperparameters([x])
+ cs.add([x])
 
  return cs
 

examples/1_basics/6_priors.py

@@ -95,13 +95,13 @@ def configspace(self) -> ConfigurationSpace:
  "learning_rate_init",
  lower=1e-5,
  upper=1.0,
- mu=np.log(1e-3),
- sigma=np.log(10),
+ mu=1e-3, # will be transformed to log space later
+ sigma=10, # will be transformed to log space later
  log=True,
  )
 
  # Add all hyperparameters at once:
- cs.add_hyperparameters([n_layer, n_neurons, activation, optimizer, batch_size, learning_rate_init])
+ cs.add([n_layer, n_neurons, activation, optimizer, batch_size, learning_rate_init])
 
  return cs
 

examples/1_basics/7_parallelization_cluster.py

@@ -44,7 +44,7 @@ def configspace(self) -> ConfigurationSpace:
  cs = ConfigurationSpace(seed=0)
  x0 = Float("x0", (-5, 10), default=-5, log=False)
  x1 = Float("x1", (0, 15), default=2, log=False)
- cs.add_hyperparameters([x0, x1])
+ cs.add([x0, x1])
 
  return cs
 

examples/2_multi_fidelity/1_mlp_epochs.py

@@ -65,7 +65,7 @@ def configspace(self) -> ConfigurationSpace:
  learning_rate_init = Float("learning_rate_init", (0.0001, 1.0), default=0.001, log=True)
 
  # Add all hyperparameters at once:
- cs.add_hyperparameters([n_layer, n_neurons, activation, solver, batch_size, learning_rate, learning_rate_init])
+ cs.add([n_layer, n_neurons, activation, solver, batch_size, learning_rate, learning_rate_init])
 
  # Adding conditions to restrict the hyperparameter space...
  # ... since learning rate is only used when solver is 'sgd'.
@@ -76,7 +76,7 @@ def configspace(self) -> ConfigurationSpace:
  use_batch_size = InCondition(child=batch_size, parent=solver, values=["sgd", "adam"])
 
  # We can also add multiple conditions on hyperparameters at once:
- cs.add_conditions([use_lr, use_batch_size, use_lr_init])
+ cs.add([use_lr, use_batch_size, use_lr_init])
 
  return cs
 

examples/2_multi_fidelity/2_sgd_datasets.py

@@ -76,7 +76,7 @@ def configspace(self) -> ConfigurationSpace:
  learning_rate = Categorical("learning_rate", ["constant", "invscaling", "adaptive"], default="constant")
  eta0 = Float("eta0", (0.00001, 1), default=0.1, log=True)
  # Add the parameters to configuration space
- cs.add_hyperparameters([alpha, l1_ratio, learning_rate, eta0])
+ cs.add([alpha, l1_ratio, learning_rate, eta0])
 
  return cs
 

examples/2_multi_fidelity/3_specify_HB_via_total_budget.py

@@ -31,7 +31,7 @@ class QuadraticFunction:
  def configspace(self) -> ConfigurationSpace:
  cs = ConfigurationSpace(seed=0)
  x = Float("x", (-5, 5), default=-5)
- cs.add_hyperparameters([x])
+ cs.add([x])
 
  return cs
 

examples/3_multi_objective/2_parego.py

@@ -54,14 +54,14 @@ def configspace(self) -> ConfigurationSpace:
  learning_rate = Categorical("learning_rate", ["constant", "invscaling", "adaptive"], default="constant")
  learning_rate_init = Float("learning_rate_init", (0.0001, 1.0), default=0.001, log=True)
 
- cs.add_hyperparameters([n_layer, n_neurons, activation, solver, batch_size, learning_rate, learning_rate_init])
+ cs.add([n_layer, n_neurons, activation, solver, batch_size, learning_rate, learning_rate_init])
 
  use_lr = EqualsCondition(child=learning_rate, parent=solver, value="sgd")
  use_lr_init = InCondition(child=learning_rate_init, parent=solver, values=["sgd", "adam"])
  use_batch_size = InCondition(child=batch_size, parent=solver, values=["sgd", "adam"])
 
  # We can also add multiple conditions on hyperparameters at once:
- cs.add_conditions([use_lr, use_batch_size, use_lr_init])
+ cs.add([use_lr, use_batch_size, use_lr_init])
 
  return cs
 

examples/4_advanced_optimizer/1_turbo_optimizer.py

@@ -28,7 +28,7 @@
 # cs = ConfigurationSpace(seed=0)
 # x0 = Float("x0", (-5, 10), default=-3)
 # x1 = Float("x1", (-5, 10), default=-4)
-# cs.add_hyperparameters([x0, x1])
+# cs.add([x0, x1])
 
 # return cs
 

examples/4_advanced_optimizer/2_boing_optimizer.py

@@ -27,7 +27,7 @@
 # cs = ConfigurationSpace(seed=0)
 # x0 = Float("x0", (-5, 10), default=-3)
 # x1 = Float("x1", (-5, 10), default=-4)
-# cs.add_hyperparameters([x0, x1])
+# cs.add([x0, x1])
 
 # return cs
 

examples/4_advanced_optimizer/3_metadata_callback.py

@@ -36,7 +36,7 @@ def configspace(self) -> ConfigurationSpace:
  cs = ConfigurationSpace(seed=0)
  x0 = Float("x0", (-5, 10), default=-3)
  x1 = Float("x1", (-5, 10), default=-4)
- cs.add_hyperparameters([x0, x1])
+ cs.add([x0, x1])
 
  return cs
 

examples/4_advanced_optimizer/4_intensify_crossvalidation.py

@@ -35,17 +35,17 @@ def configspace(self) -> ConfigurationSpace:
  cs = ConfigurationSpace(seed=0)
 
  # First we create our hyperparameters
- C = Float("C", (2 ** - 5, 2 ** 15), default=1.0, log=True)
- gamma = Float("gamma", (2 ** -15, 2 ** 3), default=1.0, log=True)
+ C = Float("C", (2**-5, 2**15), default=1.0, log=True)
+ gamma = Float("gamma", (2**-15, 2**3), default=1.0, log=True)
 
  # Add hyperparameters to our configspace
- cs.add_hyperparameters([C, gamma])
+ cs.add([C, gamma])
 
  return cs
 
  def train(self, config: Configuration, instance: str, seed: int = 0) -> float:
  """Creates a SVM based on a configuration and evaluate on the given fold of the digits dataset
- 
+
  Parameters
  ----------
  config: Configuration
@@ -81,15 +81,14 @@ def train(self, config: Configuration, instance: str, seed: int = 0) -> float:
  scenario = Scenario(
  classifier.configspace,
  n_trials=50, # We want to run max 50 trials (combination of config and instances in the case of
-  # deterministic=True. In the case of deterministic=False, this would be the
-  # combination of instances, seeds and configs). The number of distinct configurations
-  # evaluated by SMAC will be lower than this number because some of the configurations
-  # will be executed on more than one instance (CV fold).
+ # deterministic=True. In the case of deterministic=False, this would be the
+ # combination of instances, seeds and configs). The number of distinct configurations
+ # evaluated by SMAC will be lower than this number because some of the configurations
+ # will be executed on more than one instance (CV fold).
  instances=[f"{i}" for i in range(N_FOLDS)], # Specify all instances by their name (as a string)
- instance_features={f"{i}": [i] for i in range(N_FOLDS)}, # breaks SMAC
+ instance_features={f"{i}": [i] for i in range(N_FOLDS)},  # breaks SMAC
  deterministic=True # To simplify the problem we make SMAC believe that we have a deterministic
- # optimization problem.
-
+ # optimization problem.
  )
 
  # We want to run the facade's default initial design, but we want to change the number
@@ -102,12 +101,12 @@ def train(self, config: Configuration, instance: str, seed: int = 0) -> float:
  classifier.train,
  initial_design=initial_design,
  overwrite=True, # If the run exists, we overwrite it; alternatively, we can continue from last state
- # The next line defines the intensifier, i.e., the module that governs the selection of 
+ # The next line defines the intensifier, i.e., the module that governs the selection of
  # instance-seed pairs. Since we set deterministic to True above, it only governs the instance in
  # this example. Technically, it is not necessary to create the intensifier as a user, but it is
  # necessary to do so because we change the argument max_config_calls (the number of instance-seed pairs
  # per configuration to try) to the number of cross-validation folds, while the default would be 3.
- intensifier=Intensifier(scenario=scenario, max_config_calls=N_FOLDS, seed=0)
+ intensifier=Intensifier(scenario=scenario, max_config_calls=N_FOLDS, seed=0),
  )
 
  incumbent = smac.optimize()
@@ -124,4 +123,4 @@ def train(self, config: Configuration, instance: str, seed: int = 0) -> float:
  # at more configurations than would have been possible with regular cross-validation, where the number
  # of configurations would be determined by the number of trials divided by the number of folds (50 / 10).
  runhistory = smac.runhistory
- print(f"Number of evaluated configurations: {len(runhistory.config_ids)}")
+ print(f"Number of evaluated configurations: {len(runhistory.config_ids)}")

setup.py

@@ -61,7 +61,7 @@ def read_file(filepath: str) -> str:
  "scipy>=1.9.2",
  "psutil",
  "pynisher>=1.0.0",
- "ConfigSpace>=0.6.1,<1.0.0",
+ "ConfigSpace>=1.0.0",
  "joblib",
  "scikit-learn>=1.1.2",
  "pyrfr>=0.9.0",

smac/acquisition/maximizer/local_and_random_search.py

@@ -145,7 +145,6 @@ def _maximize(
  previous_configs: list[Configuration],
  n_points: int,
  ) -> list[tuple[float, Configuration]]:
-
  if self._uniform_configspace is not None and self._prior_sampling_fraction is not None:
  # Get configurations sorted by acquisition function value
  next_configs_by_prior_random_search_sorted = self._prior_random_search._maximize(

smac/acquisition/maximizer/local_search.py

@@ -389,7 +389,7 @@ def _search(
  if acq_val[acq_index] > acq_val_candidates[i]:
  is_valid = False
  try:
- neighbors[acq_index].is_valid_configuration()
+ neighbors[acq_index].check_valid_configuration()
  is_valid = True
  except (ValueError, ForbiddenValueError) as e:
  logger.debug("Local search %d: %s", i, e)

smac/callback/metadata_callback.py

@@ -7,6 +7,7 @@
 import smac
 from smac.callback.callback import Callback
 from smac.main.smbo import SMBO
+from smac.utils.numpyencoder import NumpyEncoder
 
 __copyright__ = "Copyright 2023, AutoML.org Freiburg-Hannover"
 __license__ = "3-clause BSD"
@@ -31,4 +32,4 @@ def on_start(self, smbo: SMBO) -> None:
  path.mkdir(parents=True, exist_ok=True)
 
  with open(path / "metadata.json", "w") as fp:
- json.dump(meta_dict, fp, indent=2)
+ json.dump(meta_dict, fp, indent=2, cls=NumpyEncoder)

smac/initial_design/abstract_initial_design.py

@@ -176,7 +176,6 @@ def _transform_continuous_designs(
  """
  params = configspace.get_hyperparameters()
  for idx, param in enumerate(params):
-
  if isinstance(param, IntegerHyperparameter):
  design[:, idx] = param._inverse_transform(param._transform(design[:, idx]))
  elif isinstance(param, NumericalHyperparameter):

smac/intensifier/abstract_intensifier.py

@@ -26,6 +26,7 @@
 from smac.scenario import Scenario
 from smac.utils.configspace import get_config_hash, print_config_changes
 from smac.utils.logging import get_logger
+from smac.utils.numpyencoder import NumpyEncoder
 from smac.utils.pareto_front import calculate_pareto_front, sort_by_crowding_distance
 
 __copyright__ = "Copyright 2022, automl.org"
@@ -666,7 +667,7 @@ def save(self, filename: str | Path) -> None:
  }
 
  with open(filename, "w") as fp:
- json.dump(data, fp, indent=2)
+ json.dump(data, fp, indent=2, cls=NumpyEncoder)
 
  def load(self, filename: str | Path) -> None:
  """Loads the latest state of the intensifier including the incumbents and trajectory."""