Running BOA Optimization Directly in Python#
This notebook demonstrates how to:
Write a basic Wrapper in Python and launch a optimization from Python. If you wanted to launch it from command line, you would do a similar thing of defining the Wrapper, and then put in your configuration file the information about where the wrapper is, and use BOA’s CLI tools. See Running an Experiment from Command Line (Python Wrapper) for more information.
1import pathlib
2import shutil
3
4from IPython.display import Code
5from wrapper import Wrapper
6
7import boa
[WARNING 08-09 19:01:32] ax.service.utils.with_db_settings_base: Ax currently requires a sqlalchemy version below 2.0. This will be addressed in a future release. Disabling SQL storage in Ax for now, if you would like to use SQL storage please install Ax with mysql extras via `pip install ax-platform[mysql]`.
Show code cell content
1# Remove old runs to have a clean slate for this example
2old_runs = pathlib.Path().resolve().glob("boa_runs*")
3for path in old_runs:
4 shutil.rmtree(path)
Loading the Config File#
1config_path = pathlib.Path().resolve() / "single_config.yaml"
Here we can see what the configuration file looks like
1Code(config_path)
# Single objective optimization config
optimization_options:
objective_options:
objectives:
- name: Cosine8
trials: 50
append_timestamp: False
parameters:
x0:
type: range
bounds: [0.0, 1.0]
x1:
type: range
bounds: [0.0, 1.0]
x2:
type: range
bounds: [0.0, 1.0]
x3:
type: range
bounds: [0.0, 1.0]
x4:
type: range
bounds: [0.0, 1.0]
x5:
type: range
bounds: [0.0, 1.0]
x6:
type: range
bounds: [0.0, 1.0]
x7:
type: range
bounds: [0.0, 1.0]
# These are all defaults, so we don't need to specify them in this case
#script_options:
# wrapper_path: ./wrapper.py
# wrapper_name: Wrapper
# working_dir: .
# experiment_dir: ... # this is where boa will write logs to by default
# if not specified it will be working_dir/experiment_name
# append_timestamp: True
# This last option appends a timestamp to our output experiment directory.
# This is also the default (True)
we need the config normalized, which modifies the parameter section into a less user friendly form, but what the downstream libraries need
1config = boa.load_jsonlike(config_path)
Define Our Wrapper#
We define our wrapper in wrapper.py and use a synthetic function that stands in for any black box model call
1Code(Wrapper.path())
import numpy as np
from ax.utils.measurement.synthetic_functions import from_botorch
from botorch.test_functions.synthetic import Cosine8
import boa
cosine8 = from_botorch(Cosine8())
def black_box_model(X) -> float:
result = -cosine8(X)
return result
class Wrapper(boa.BaseWrapper):
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.data = {}
def run_model(self, trial) -> None:
X = np.array([parameter for parameter in trial.arm.parameters.values()])
# This is a silly toy function, in reality,
# you could instead import your model main() function and use that, and then collect the results.
# You could also call an external script to start a model run from Bash or elsewhere.
self.data[trial.index] = black_box_model(X)
def set_trial_status(self, trial) -> None:
data_exists = self.data.get(trial.index)
if data_exists:
trial.mark_completed()
def fetch_trial_data(self, trial, *args, **kwargs):
return self.data[trial.index]
Initialize our Setup#
1controller = boa.Controller(config_path=config_path, wrapper=Wrapper)
2
3controller.initialize_scheduler()
[INFO 08-09 19:01:34] ax.service.utils.instantiation: Inferred value type of ParameterType.FLOAT for parameter x0. If that is not the expected value type, you can explicity specify 'value_type' ('int', 'float', 'bool' or 'str') in parameter dict.
[INFO 08-09 19:01:34] ax.service.utils.instantiation: Inferred value type of ParameterType.FLOAT for parameter x1. If that is not the expected value type, you can explicity specify 'value_type' ('int', 'float', 'bool' or 'str') in parameter dict.
[INFO 08-09 19:01:34] ax.service.utils.instantiation: Inferred value type of ParameterType.FLOAT for parameter x2. If that is not the expected value type, you can explicity specify 'value_type' ('int', 'float', 'bool' or 'str') in parameter dict.
[INFO 08-09 19:01:34] ax.service.utils.instantiation: Inferred value type of ParameterType.FLOAT for parameter x3. If that is not the expected value type, you can explicity specify 'value_type' ('int', 'float', 'bool' or 'str') in parameter dict.
[INFO 08-09 19:01:34] ax.service.utils.instantiation: Inferred value type of ParameterType.FLOAT for parameter x4. If that is not the expected value type, you can explicity specify 'value_type' ('int', 'float', 'bool' or 'str') in parameter dict.
[INFO 08-09 19:01:34] ax.service.utils.instantiation: Inferred value type of ParameterType.FLOAT for parameter x5. If that is not the expected value type, you can explicity specify 'value_type' ('int', 'float', 'bool' or 'str') in parameter dict.
[INFO 08-09 19:01:34] ax.service.utils.instantiation: Inferred value type of ParameterType.FLOAT for parameter x6. If that is not the expected value type, you can explicity specify 'value_type' ('int', 'float', 'bool' or 'str') in parameter dict.
[INFO 08-09 19:01:34] ax.service.utils.instantiation: Inferred value type of ParameterType.FLOAT for parameter x7. If that is not the expected value type, you can explicity specify 'value_type' ('int', 'float', 'bool' or 'str') in parameter dict.
[INFO 08-09 19:01:34] ax.service.utils.instantiation: Created search space: SearchSpace(parameters=[RangeParameter(name='x0', parameter_type=FLOAT, range=[0.0, 1.0]), RangeParameter(name='x1', parameter_type=FLOAT, range=[0.0, 1.0]), RangeParameter(name='x2', parameter_type=FLOAT, range=[0.0, 1.0]), RangeParameter(name='x3', parameter_type=FLOAT, range=[0.0, 1.0]), RangeParameter(name='x4', parameter_type=FLOAT, range=[0.0, 1.0]), RangeParameter(name='x5', parameter_type=FLOAT, range=[0.0, 1.0]), RangeParameter(name='x6', parameter_type=FLOAT, range=[0.0, 1.0]), RangeParameter(name='x7', parameter_type=FLOAT, range=[0.0, 1.0])], parameter_constraints=[]).
[INFO 08-09 19:01:34] ax.modelbridge.dispatch_utils: Using Models.GPEI since there are more ordered parameters than there are categories for the unordered categorical parameters.
[INFO 08-09 19:01:34] ax.modelbridge.dispatch_utils: Calculating the number of remaining initialization trials based on num_initialization_trials=None max_initialization_trials=None num_tunable_parameters=8 num_trials=None use_batch_trials=False
[INFO 08-09 19:01:34] ax.modelbridge.dispatch_utils: calculated num_initialization_trials=16
[INFO 08-09 19:01:34] ax.modelbridge.dispatch_utils: num_completed_initialization_trials=0 num_remaining_initialization_trials=16
[INFO 08-09 19:01:34] ax.modelbridge.dispatch_utils: Using Bayesian Optimization generation strategy: GenerationStrategy(name='Sobol+GPEI', steps=[Sobol for 16 trials, GPEI for subsequent trials]). Iterations after 16 will take longer to generate due to model-fitting.
[INFO 08-09 19:01:34] Scheduler: `Scheduler` requires experiment to have immutable search space and optimization config. Setting property immutable_search_space_and_opt_config to `True` on experiment.
(Scheduler(experiment=Experiment(boa_runs), generation_strategy=GenerationStrategy(name='Sobol+GPEI', steps=[Sobol for 16 trials, GPEI for subsequent trials]), options=SchedulerOptions(max_pending_trials=10, trial_type=<TrialType.TRIAL: 0>, batch_size=None, total_trials=None, tolerated_trial_failure_rate=0.5, min_failed_trials_for_failure_rate_check=5, log_filepath=None, logging_level=20, ttl_seconds_for_trials=None, init_seconds_between_polls=1, min_seconds_before_poll=1.0, seconds_between_polls_backoff_factor=1.5, timeout_hours=None, run_trials_in_batches=False, debug_log_run_metadata=False, early_stopping_strategy=None, global_stopping_strategy=None, suppress_storage_errors_after_retries=False)),
<wrapper.Wrapper at 0x7f31a0f50fa0>)
Run our Experiment#
The Controller will save our scheduler to JSON after it completes the run so we can reload it at a later time for analysis or to resume our experiment
1scheduler = controller.run()
[INFO 2023-08-09 19:01:34,078 MainProcess] boa:
##############################################
BOA Experiment Run
Output Experiment Dir: /home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134
Start Time: 20230809T190134
Version: 0.8.8.dev0+gd6e453f.d20230809
##############################################
[INFO 08-09 19:01:34] Scheduler: Running trials [0]...
[INFO 08-09 19:01:35] Scheduler: Running trials [1]...
[INFO 08-09 19:01:36] Scheduler: Running trials [2]...
[INFO 08-09 19:01:37] Scheduler: Running trials [3]...
[INFO 08-09 19:01:38] Scheduler: Running trials [4]...
[INFO 08-09 19:01:39] Scheduler: Running trials [5]...
[INFO 08-09 19:01:40] Scheduler: Running trials [6]...
[INFO 08-09 19:01:41] Scheduler: Running trials [7]...
[INFO 08-09 19:01:42] Scheduler: Running trials [8]...
[INFO 08-09 19:01:43] Scheduler: Running trials [9]...
[INFO 08-09 19:01:43] Scheduler: Retrieved COMPLETED trials: 0 - 9.
[INFO 08-09 19:01:43] Scheduler: Fetching data for trials: 0 - 9.
[ERROR 2023-08-09 19:01:43,306 MainProcess] boa: Object <wrapper.Wrapper object at 0x7f31a0f50fa0> passed to `object_to_json` (of type <class 'wrapper.Wrapper'>, module: wrapper) is not registered with a corresponding encoder in ENCODER_REGISTRY.
[INFO 2023-08-09 19:01:43,326 MainProcess] boa: Saved JSON-serialized state of optimization to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/scheduler.json`.
Boa version: 0.8.8.dev0+gd6e453f.d20230809
[INFO 2023-08-09 19:01:43,346 MainProcess] boa: Saved optimization parametrization and objective to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/optimization.csv`.
[INFO 2023-08-09 19:01:43,362 MainProcess] boa: Trials so far: 10
Running trials:
Will Produce next trials from generation step: Sobol
Best trial so far: {3: {'Cosine8': 1.135110414396801}}
[INFO 08-09 19:01:43] Scheduler: Running trials [10]...
[INFO 08-09 19:01:44] Scheduler: Running trials [11]...
[INFO 08-09 19:01:45] Scheduler: Running trials [12]...
[INFO 08-09 19:01:46] Scheduler: Running trials [13]...
[INFO 08-09 19:01:47] Scheduler: Running trials [14]...
[INFO 08-09 19:01:48] Scheduler: Running trials [15]...
[INFO 08-09 19:01:50] Scheduler: Running trials [16]...
[INFO 08-09 19:01:51] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:01:52] Scheduler: Running trials [17]...
[INFO 08-09 19:01:53] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:01:54] Scheduler: Running trials [18]...
[INFO 08-09 19:01:55] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:01:55] Scheduler: Generated all trials that can be generated currently. Max parallelism currently reached.
[INFO 08-09 19:01:55] Scheduler: Retrieved COMPLETED trials: 10 - 18.
[INFO 08-09 19:01:55] Scheduler: Fetching data for trials: 10 - 18.
[ERROR 2023-08-09 19:01:55,514 MainProcess] boa: Object <wrapper.Wrapper object at 0x7f31a0f50fa0> passed to `object_to_json` (of type <class 'wrapper.Wrapper'>, module: wrapper) is not registered with a corresponding encoder in ENCODER_REGISTRY.
[INFO 2023-08-09 19:01:55,540 MainProcess] boa: Saved JSON-serialized state of optimization to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/scheduler.json`.
Boa version: 0.8.8.dev0+gd6e453f.d20230809
[INFO 2023-08-09 19:01:55,560 MainProcess] boa: Saved optimization parametrization and objective to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/optimization.csv`.
[INFO 2023-08-09 19:01:55,579 MainProcess] boa: Trials so far: 19
Running trials:
Will Produce next trials from generation step: GPEI
Best trial so far: {16: {'Cosine8': 0.8315617016335042}}
[INFO 08-09 19:01:56] Scheduler: Running trials [19]...
[INFO 08-09 19:01:56] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:01:58] Scheduler: Running trials [20]...
[INFO 08-09 19:01:59] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:02:01] Scheduler: Running trials [21]...
[INFO 08-09 19:02:02] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:02:02] Scheduler: Generated all trials that can be generated currently. Max parallelism currently reached.
[INFO 08-09 19:02:02] Scheduler: Retrieved COMPLETED trials: 19 - 21.
[INFO 08-09 19:02:02] Scheduler: Fetching data for trials: 19 - 21.
[ERROR 2023-08-09 19:02:02,658 MainProcess] boa: Object <wrapper.Wrapper object at 0x7f31a0f50fa0> passed to `object_to_json` (of type <class 'wrapper.Wrapper'>, module: wrapper) is not registered with a corresponding encoder in ENCODER_REGISTRY.
[INFO 2023-08-09 19:02:02,685 MainProcess] boa: Saved JSON-serialized state of optimization to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/scheduler.json`.
Boa version: 0.8.8.dev0+gd6e453f.d20230809
[INFO 2023-08-09 19:02:02,707 MainProcess] boa: Saved optimization parametrization and objective to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/optimization.csv`.
[INFO 2023-08-09 19:02:02,728 MainProcess] boa: Trials so far: 22
Running trials:
Will Produce next trials from generation step: GPEI
Best trial so far: {20: {'Cosine8': 0.38319413242440825}}
[INFO 08-09 19:02:04] Scheduler: Running trials [22]...
[INFO 08-09 19:02:05] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:02:07] Scheduler: Running trials [23]...
[INFO 08-09 19:02:08] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:02:10] Scheduler: Running trials [24]...
[INFO 08-09 19:02:11] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:02:11] Scheduler: Generated all trials that can be generated currently. Max parallelism currently reached.
[INFO 08-09 19:02:11] Scheduler: Retrieved COMPLETED trials: 22 - 24.
[INFO 08-09 19:02:11] Scheduler: Fetching data for trials: 22 - 24.
[ERROR 2023-08-09 19:02:11,552 MainProcess] boa: Object <wrapper.Wrapper object at 0x7f31a0f50fa0> passed to `object_to_json` (of type <class 'wrapper.Wrapper'>, module: wrapper) is not registered with a corresponding encoder in ENCODER_REGISTRY.
[INFO 2023-08-09 19:02:11,582 MainProcess] boa: Saved JSON-serialized state of optimization to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/scheduler.json`.
Boa version: 0.8.8.dev0+gd6e453f.d20230809
[INFO 2023-08-09 19:02:11,603 MainProcess] boa: Saved optimization parametrization and objective to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/optimization.csv`.
[INFO 2023-08-09 19:02:11,623 MainProcess] boa: Trials so far: 25
Running trials:
Will Produce next trials from generation step: GPEI
Best trial so far: {24: {'Cosine8': 0.22449902572218428}}
[INFO 08-09 19:02:13] Scheduler: Running trials [25]...
[INFO 08-09 19:02:14] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:02:14] Scheduler: Running trials [26]...
[INFO 08-09 19:02:15] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:02:17] Scheduler: Running trials [27]...
[INFO 08-09 19:02:18] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:02:18] Scheduler: Generated all trials that can be generated currently. Max parallelism currently reached.
[INFO 08-09 19:02:18] Scheduler: Retrieved COMPLETED trials: 25 - 27.
[INFO 08-09 19:02:18] Scheduler: Fetching data for trials: 25 - 27.
[ERROR 2023-08-09 19:02:18,363 MainProcess] boa: Object <wrapper.Wrapper object at 0x7f31a0f50fa0> passed to `object_to_json` (of type <class 'wrapper.Wrapper'>, module: wrapper) is not registered with a corresponding encoder in ENCODER_REGISTRY.
[INFO 2023-08-09 19:02:18,396 MainProcess] boa: Saved JSON-serialized state of optimization to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/scheduler.json`.
Boa version: 0.8.8.dev0+gd6e453f.d20230809
[INFO 2023-08-09 19:02:18,419 MainProcess] boa: Saved optimization parametrization and objective to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/optimization.csv`.
[INFO 2023-08-09 19:02:18,440 MainProcess] boa: Trials so far: 28
Running trials:
Will Produce next trials from generation step: GPEI
Best trial so far: {24: {'Cosine8': 0.22449902572218428}}
[INFO 08-09 19:02:19] Scheduler: Running trials [28]...
[INFO 08-09 19:02:20] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:02:23] Scheduler: Running trials [29]...
[INFO 08-09 19:02:24] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:02:27] Scheduler: Running trials [30]...
[INFO 08-09 19:02:28] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:02:28] Scheduler: Generated all trials that can be generated currently. Max parallelism currently reached.
[INFO 08-09 19:02:28] Scheduler: Retrieved COMPLETED trials: 28 - 30.
[INFO 08-09 19:02:28] Scheduler: Fetching data for trials: 28 - 30.
[ERROR 2023-08-09 19:02:28,100 MainProcess] boa: Object <wrapper.Wrapper object at 0x7f31a0f50fa0> passed to `object_to_json` (of type <class 'wrapper.Wrapper'>, module: wrapper) is not registered with a corresponding encoder in ENCODER_REGISTRY.
[INFO 2023-08-09 19:02:28,135 MainProcess] boa: Saved JSON-serialized state of optimization to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/scheduler.json`.
Boa version: 0.8.8.dev0+gd6e453f.d20230809
[INFO 2023-08-09 19:02:28,158 MainProcess] boa: Saved optimization parametrization and objective to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/optimization.csv`.
[INFO 2023-08-09 19:02:28,179 MainProcess] boa: Trials so far: 31
Running trials:
Will Produce next trials from generation step: GPEI
Best trial so far: {24: {'Cosine8': 0.22449902572218428}}
[INFO 08-09 19:02:30] Scheduler: Running trials [31]...
[INFO 08-09 19:02:31] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:02:32] Scheduler: Running trials [32]...
[INFO 08-09 19:02:33] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:02:35] Scheduler: Running trials [33]...
[INFO 08-09 19:02:36] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:02:36] Scheduler: Generated all trials that can be generated currently. Max parallelism currently reached.
[INFO 08-09 19:02:36] Scheduler: Retrieved COMPLETED trials: 31 - 33.
[INFO 08-09 19:02:36] Scheduler: Fetching data for trials: 31 - 33.
[ERROR 2023-08-09 19:02:36,174 MainProcess] boa: Object <wrapper.Wrapper object at 0x7f31a0f50fa0> passed to `object_to_json` (of type <class 'wrapper.Wrapper'>, module: wrapper) is not registered with a corresponding encoder in ENCODER_REGISTRY.
[INFO 2023-08-09 19:02:36,212 MainProcess] boa: Saved JSON-serialized state of optimization to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/scheduler.json`.
Boa version: 0.8.8.dev0+gd6e453f.d20230809
[INFO 2023-08-09 19:02:36,235 MainProcess] boa: Saved optimization parametrization and objective to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/optimization.csv`.
[INFO 2023-08-09 19:02:36,258 MainProcess] boa: Trials so far: 34
Running trials:
Will Produce next trials from generation step: GPEI
Best trial so far: {33: {'Cosine8': 0.13391821113769733}}
[INFO 08-09 19:02:37] Scheduler: Running trials [34]...
[INFO 08-09 19:02:38] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:02:40] Scheduler: Running trials [35]...
[INFO 08-09 19:02:40] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:02:42] Scheduler: Running trials [36]...
[INFO 08-09 19:02:44] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:02:44] Scheduler: Generated all trials that can be generated currently. Max parallelism currently reached.
[INFO 08-09 19:02:44] Scheduler: Retrieved COMPLETED trials: 34 - 36.
[INFO 08-09 19:02:44] Scheduler: Fetching data for trials: 34 - 36.
[ERROR 2023-08-09 19:02:44,059 MainProcess] boa: Object <wrapper.Wrapper object at 0x7f31a0f50fa0> passed to `object_to_json` (of type <class 'wrapper.Wrapper'>, module: wrapper) is not registered with a corresponding encoder in ENCODER_REGISTRY.
[INFO 2023-08-09 19:02:44,099 MainProcess] boa: Saved JSON-serialized state of optimization to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/scheduler.json`.
Boa version: 0.8.8.dev0+gd6e453f.d20230809
[INFO 2023-08-09 19:02:44,123 MainProcess] boa: Saved optimization parametrization and objective to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/optimization.csv`.
[INFO 2023-08-09 19:02:44,147 MainProcess] boa: Trials so far: 37
Running trials:
Will Produce next trials from generation step: GPEI
Best trial so far: {33: {'Cosine8': 0.13391821113769733}}
[INFO 08-09 19:02:46] Scheduler: Running trials [37]...
[INFO 08-09 19:02:47] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:02:48] Scheduler: Running trials [38]...
[INFO 08-09 19:02:49] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:02:51] Scheduler: Running trials [39]...
[INFO 08-09 19:02:52] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:02:52] Scheduler: Generated all trials that can be generated currently. Max parallelism currently reached.
[INFO 08-09 19:02:52] Scheduler: Retrieved COMPLETED trials: 37 - 39.
[INFO 08-09 19:02:52] Scheduler: Fetching data for trials: 37 - 39.
[ERROR 2023-08-09 19:02:52,939 MainProcess] boa: Object <wrapper.Wrapper object at 0x7f31a0f50fa0> passed to `object_to_json` (of type <class 'wrapper.Wrapper'>, module: wrapper) is not registered with a corresponding encoder in ENCODER_REGISTRY.
[INFO 2023-08-09 19:02:52,982 MainProcess] boa: Saved JSON-serialized state of optimization to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/scheduler.json`.
Boa version: 0.8.8.dev0+gd6e453f.d20230809
[INFO 2023-08-09 19:02:53,006 MainProcess] boa: Saved optimization parametrization and objective to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/optimization.csv`.
[INFO 2023-08-09 19:02:53,031 MainProcess] boa: Trials so far: 40
Running trials:
Will Produce next trials from generation step: GPEI
Best trial so far: {39: {'Cosine8': -0.023691096830892044}}
[INFO 08-09 19:02:56] Scheduler: Running trials [40]...
[INFO 08-09 19:02:58] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:02:58] Scheduler: Running trials [41]...
[INFO 08-09 19:02:59] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:02:59] Scheduler: Running trials [42]...
[INFO 08-09 19:03:00] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:03:00] Scheduler: Generated all trials that can be generated currently. Max parallelism currently reached.
[INFO 08-09 19:03:00] Scheduler: Retrieved COMPLETED trials: 40 - 42.
[INFO 08-09 19:03:00] Scheduler: Fetching data for trials: 40 - 42.
[ERROR 2023-08-09 19:03:00,997 MainProcess] boa: Object <wrapper.Wrapper object at 0x7f31a0f50fa0> passed to `object_to_json` (of type <class 'wrapper.Wrapper'>, module: wrapper) is not registered with a corresponding encoder in ENCODER_REGISTRY.
[INFO 2023-08-09 19:03:01,044 MainProcess] boa: Saved JSON-serialized state of optimization to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/scheduler.json`.
Boa version: 0.8.8.dev0+gd6e453f.d20230809
[INFO 2023-08-09 19:03:01,068 MainProcess] boa: Saved optimization parametrization and objective to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/optimization.csv`.
[INFO 2023-08-09 19:03:01,095 MainProcess] boa: Trials so far: 43
Running trials:
Will Produce next trials from generation step: GPEI
Best trial so far: {40: {'Cosine8': -0.0403786875753729}}
[INFO 08-09 19:03:01] Scheduler: Running trials [43]...
[INFO 08-09 19:03:02] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:03:06] Scheduler: Running trials [44]...
[INFO 08-09 19:03:07] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:03:10] Scheduler: Running trials [45]...
[INFO 08-09 19:03:10] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:03:10] Scheduler: Generated all trials that can be generated currently. Max parallelism currently reached.
[INFO 08-09 19:03:10] Scheduler: Retrieved COMPLETED trials: 43 - 45.
[INFO 08-09 19:03:10] Scheduler: Fetching data for trials: 43 - 45.
[ERROR 2023-08-09 19:03:10,933 MainProcess] boa: Object <wrapper.Wrapper object at 0x7f31a0f50fa0> passed to `object_to_json` (of type <class 'wrapper.Wrapper'>, module: wrapper) is not registered with a corresponding encoder in ENCODER_REGISTRY.
[INFO 2023-08-09 19:03:10,982 MainProcess] boa: Saved JSON-serialized state of optimization to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/scheduler.json`.
Boa version: 0.8.8.dev0+gd6e453f.d20230809
[INFO 2023-08-09 19:03:11,009 MainProcess] boa: Saved optimization parametrization and objective to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/optimization.csv`.
[INFO 2023-08-09 19:03:11,036 MainProcess] boa: Trials so far: 46
Running trials:
Will Produce next trials from generation step: GPEI
Best trial so far: {44: {'Cosine8': -0.059944627346360344}}
[INFO 08-09 19:03:14] Scheduler: Running trials [46]...
[INFO 08-09 19:03:15] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:03:16] Scheduler: Running trials [47]...
[INFO 08-09 19:03:17] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:03:17] Scheduler: Running trials [48]...
[INFO 08-09 19:03:18] ax.modelbridge.torch: The observations are identical to the last set of observations used to fit the model. Skipping model fitting.
[INFO 08-09 19:03:18] Scheduler: Generated all trials that can be generated currently. Max parallelism currently reached.
[INFO 08-09 19:03:18] Scheduler: Retrieved COMPLETED trials: 46 - 48.
[INFO 08-09 19:03:18] Scheduler: Fetching data for trials: 46 - 48.
[ERROR 2023-08-09 19:03:18,324 MainProcess] boa: Object <wrapper.Wrapper object at 0x7f31a0f50fa0> passed to `object_to_json` (of type <class 'wrapper.Wrapper'>, module: wrapper) is not registered with a corresponding encoder in ENCODER_REGISTRY.
[INFO 2023-08-09 19:03:18,378 MainProcess] boa: Saved JSON-serialized state of optimization to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/scheduler.json`.
Boa version: 0.8.8.dev0+gd6e453f.d20230809
[INFO 2023-08-09 19:03:18,404 MainProcess] boa: Saved optimization parametrization and objective to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/optimization.csv`.
[INFO 2023-08-09 19:03:18,432 MainProcess] boa: Trials so far: 49
Running trials:
Will Produce next trials from generation step: GPEI
Best trial so far: {44: {'Cosine8': -0.059944627346360344}}
[INFO 08-09 19:03:19] Scheduler: Running trials [49]...
[INFO 08-09 19:03:20] Scheduler: Retrieved COMPLETED trials: [49].
[INFO 08-09 19:03:20] Scheduler: Fetching data for trials: [49].
[ERROR 2023-08-09 19:03:20,443 MainProcess] boa: Object <wrapper.Wrapper object at 0x7f31a0f50fa0> passed to `object_to_json` (of type <class 'wrapper.Wrapper'>, module: wrapper) is not registered with a corresponding encoder in ENCODER_REGISTRY.
[INFO 2023-08-09 19:03:20,496 MainProcess] boa: Saved JSON-serialized state of optimization to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/scheduler.json`.
Boa version: 0.8.8.dev0+gd6e453f.d20230809
[INFO 2023-08-09 19:03:20,523 MainProcess] boa: Saved optimization parametrization and objective to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/optimization.csv`.
[INFO 2023-08-09 19:03:20,551 MainProcess] boa: Trials so far: 50
Running trials:
Will Produce next trials from generation step: GPEI
Best trial so far: {44: {'Cosine8': -0.059944627346360344}}
[ERROR 2023-08-09 19:03:20,553 MainProcess] boa: Object <wrapper.Wrapper object at 0x7f31a0f50fa0> passed to `object_to_json` (of type <class 'wrapper.Wrapper'>, module: wrapper) is not registered with a corresponding encoder in ENCODER_REGISTRY.
[INFO 2023-08-09 19:03:20,605 MainProcess] boa: Saved JSON-serialized state of optimization to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/scheduler.json`.
Boa version: 0.8.8.dev0+gd6e453f.d20230809
[INFO 2023-08-09 19:03:20,631 MainProcess] boa: Saved optimization parametrization and objective to `/home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134/optimization.csv`.
[INFO 2023-08-09 19:03:20,660 MainProcess] boa: Trials so far: 50
Running trials:
Will Produce next trials from generation step: GPEI
Best trial so far: {44: {'Cosine8': -0.059944627346360344}}
[INFO 2023-08-09 19:03:20,692 MainProcess] boa:
##############################################
Trials Completed!
BOA Experiment Run
Output Experiment Dir: /home/docs/checkouts/readthedocs.org/user_builds/pyboa/checkouts/0.8.7/docs/examples/boa_runs_20230809T190134
Start Time: 20230809T190134
Version: 0.8.8.dev0+gd6e453f.d20230809
End Time: 20230809T190320
Total Run Time: 106.58260607719421
trial_index arm_name trial_status generation_method Cosine8 x0 \
0 0 0_0 COMPLETED Sobol 2.663157 0.312017
1 1 1_0 COMPLETED Sobol 3.472775 0.811599
2 2 2_0 COMPLETED Sobol 2.599138 0.513995
3 3 3_0 COMPLETED Sobol 1.135110 0.020953
4 4 4_0 COMPLETED Sobol 1.293105 0.049371
5 5 5_0 COMPLETED Sobol 1.457474 0.779954
6 6 6_0 COMPLETED Sobol 4.251037 0.869940
7 7 7_0 COMPLETED Sobol 1.981109 0.600472
8 8 8_0 COMPLETED Sobol 2.561738 0.507137
9 9 9_0 COMPLETED Sobol 4.313421 0.646849
10 10 10_0 COMPLETED Sobol 4.327585 0.508235
11 11 11_0 COMPLETED Sobol 1.960524 0.245657
12 12 12_0 COMPLETED Sobol 1.423228 0.252244
13 13 13_0 COMPLETED Sobol 1.470841 0.430965
14 14 14_0 COMPLETED Sobol 2.047706 0.825881
15 15 15_0 COMPLETED Sobol 3.829676 0.896006
16 16 16_0 COMPLETED GPEI 0.831562 0.036738
17 17 17_0 COMPLETED GPEI 1.411013 0.000000
18 18 18_0 COMPLETED GPEI 1.143500 0.212341
19 19 19_0 COMPLETED GPEI 0.463539 0.086164
20 20 20_0 COMPLETED GPEI 0.383194 0.034869
21 21 21_0 COMPLETED GPEI 0.688874 0.040416
22 22 22_0 COMPLETED GPEI 0.298763 0.000000
23 23 23_0 COMPLETED GPEI 0.283036 0.000000
24 24 24_0 COMPLETED GPEI 0.224499 0.000000
25 25 25_0 COMPLETED GPEI 0.473313 0.000000
26 26 26_0 COMPLETED GPEI 0.506551 0.000000
27 27 27_0 COMPLETED GPEI 0.606441 0.000000
28 28 28_0 COMPLETED GPEI 0.537491 0.000000
29 29 29_0 COMPLETED GPEI 0.350213 0.000000
30 30 30_0 COMPLETED GPEI 0.384968 0.000000
31 31 31_0 COMPLETED GPEI 0.399310 0.000000
32 32 32_0 COMPLETED GPEI 0.651089 0.000000
33 33 33_0 COMPLETED GPEI 0.133918 0.000000
34 34 34_0 COMPLETED GPEI 0.160010 0.134682
35 35 35_0 COMPLETED GPEI 0.607355 0.207752
36 36 36_0 COMPLETED GPEI 0.241903 0.000000
37 37 37_0 COMPLETED GPEI 0.132668 0.034296
38 38 38_0 COMPLETED GPEI 0.583685 0.085351
39 39 39_0 COMPLETED GPEI -0.023691 0.026875
40 40 40_0 COMPLETED GPEI -0.040379 0.000000
41 41 41_0 COMPLETED GPEI 0.115861 0.000000
42 42 42_0 COMPLETED GPEI 0.036092 0.047530
43 43 43_0 COMPLETED GPEI 0.601410 0.195682
44 44 44_0 COMPLETED GPEI -0.059945 0.000000
45 45 45_0 COMPLETED GPEI -0.036262 0.000000
46 46 46_0 COMPLETED GPEI -0.030902 0.000000
47 47 47_0 COMPLETED GPEI 2.587291 0.453197
48 48 48_0 COMPLETED GPEI 2.134270 0.492481
49 49 49_0 COMPLETED GPEI 1.029291 0.000000
x1 x2 x3 x4 x5 x6 x7
0 0.375450 0.518184 0.255694 0.707143 0.977300 0.627417 0.424752
1 0.102800 0.826156 0.586577 0.981025 0.461695 0.791734 0.264965
2 0.750892 0.365383 0.176387 0.993027 0.377566 0.549260 0.210662
3 0.352685 0.384740 0.598315 0.675668 0.320246 0.389470 0.386341
4 0.654408 0.467794 0.322839 0.333161 0.513854 0.134319 0.485225
5 0.080537 0.271937 0.845372 0.035978 0.263293 0.257189 0.118739
6 0.920247 0.434625 0.701204 0.696775 0.943400 0.606757 0.462032
7 0.356166 0.415501 0.840716 0.145596 0.444465 0.601179 0.432331
8 0.699582 0.326667 0.639318 0.389713 0.358486 0.544911 0.891967
9 0.827967 0.732573 0.994397 0.221591 0.797337 0.615998 0.755372
10 0.655068 0.893461 0.930283 0.624175 0.886251 0.679031 0.264030
11 0.174974 0.354753 0.424672 0.133220 0.951068 0.439949 0.566493
12 0.236526 0.581198 0.018938 0.773188 0.382626 0.166053 0.225524
13 0.535480 0.319732 0.225324 0.358769 0.215507 0.827910 0.112318
14 0.154236 0.244455 0.487318 0.748788 0.788026 0.309836 0.027160
15 0.323754 0.970113 0.600032 0.488128 0.843276 0.184945 0.638443
16 0.472569 0.397035 0.506163 0.458229 0.376407 0.258182 0.421778
17 0.522502 0.458266 0.426792 0.721061 0.422221 0.266576 0.507974
18 0.268985 0.330559 0.679346 0.434590 0.297060 0.349851 0.314136
19 0.361035 0.370711 0.297997 0.358246 0.348047 0.298517 0.293590
20 0.334433 0.375754 0.461653 0.441267 0.412602 0.036355 0.292011
21 0.495560 0.429553 0.433630 0.297753 0.193928 0.385047 0.349413
22 0.335533 0.382258 0.345978 0.332896 0.287420 0.047099 0.217264
23 0.211597 0.399096 0.342443 0.303916 0.345610 0.051221 0.387174
24 0.383919 0.361917 0.395714 0.365952 0.413164 0.139015 0.077381
25 0.213475 0.389053 0.377933 0.248060 0.433936 0.111913 0.129031
26 0.248434 0.243786 0.325343 0.303443 0.453504 0.044787 0.169293
27 0.246060 0.493610 0.393148 0.308101 0.375003 0.163087 0.117784
28 0.492178 0.306430 0.412458 0.239091 0.350907 0.177723 0.053241
29 0.385204 0.345878 0.297388 0.501700 0.405405 0.090237 0.057207
30 0.412547 0.370486 0.323259 0.277802 0.447566 0.046090 0.184052
31 0.326253 0.350303 0.384816 0.406117 0.384198 0.151564 0.170865
32 0.162394 0.357030 0.254357 0.404179 0.177300 0.038917 0.541337
33 0.367831 0.348879 0.466264 0.424930 0.415589 0.015454 0.000000
34 0.383295 0.376547 0.416497 0.363486 0.407027 0.000000 0.000000
35 0.261156 0.403849 0.292222 0.151493 0.273163 0.000000 0.408476
36 0.445157 0.420915 0.474798 0.422200 0.406699 0.000000 0.000000
37 0.369506 0.351920 0.429270 0.365676 0.470187 0.000000 0.000000
38 0.385241 0.324978 0.500865 0.407612 0.538656 0.033266 0.000000
39 0.366678 0.363851 0.414838 0.363992 0.364331 0.000000 0.000000
40 0.357151 0.374060 0.370617 0.328077 0.357097 0.000000 0.000000
41 0.344771 0.370551 0.454516 0.278565 0.331861 0.000000 0.000000
42 0.337711 0.337497 0.333073 0.329439 0.327415 0.000000 0.000000
43 0.091939 0.364800 0.288180 0.435749 0.463267 0.000000 0.459962
44 0.372064 0.373322 0.366009 0.367236 0.361431 0.000000 0.000000
45 0.407358 0.361476 0.360987 0.357513 0.352213 0.000000 0.000000
46 0.368343 0.386212 0.362645 0.380164 0.319139 0.000000 0.000000
47 0.682408 0.350890 0.612169 0.674319 0.550328 0.038512 0.847392
48 0.245022 0.685515 0.889154 0.622527 0.033786 0.109576 0.312552
49 0.134440 0.300564 0.563262 0.233928 0.387781 0.000000 0.615784
##############################################
Get the Best Trial and Output All Trials#
best_fitted_trials uses the data to do a fitting from all trials and with the noise levels you provided (or if no noise levels was provided, it assumed an unknown level of noise and inferred the noise level from the trial runs)
1trial = scheduler.best_fitted_trials()
2trial
{49: {'params': {'x0': 0.0,
'x1': 0.37206440392558554,
'x2': 0.37332223273644144,
'x3': 0.3660092554325016,
'x4': 0.3672361370154477,
'x5': 0.3614313634497034,
'x6': 0.0,
'x7': 0.0},
'means': {'Cosine8': -0.05988337288496104},
'cov_matrix': {'Cosine8': {'Cosine8': 1.509709462376499e-06}}}}
if you need the exact points of the best trial, maybe because you need the trial number of the best trial to plot results, or for any other reason, best_raw_trails does not do any fitting
1trial = scheduler.best_raw_trials()
2trial
{44: {'params': {'x0': 0.0,
'x1': 0.37206440392558554,
'x2': 0.37332223273644144,
'x3': 0.3660092554325016,
'x4': 0.3672361370154477,
'x5': 0.3614313634497034,
'x6': 0.0,
'x7': 0.0},
'means': {'Cosine8': -0.059944627346360344},
'cov_matrix': {'Cosine8': {'Cosine8': 0.0}}}}
Output a DataFrame of All Trials#
1boa.scheduler_to_df(scheduler)
| trial_index | arm_name | trial_status | generation_method | Cosine8 | x0 | x1 | x2 | x3 | x4 | x5 | x6 | x7 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 0 | 0_0 | COMPLETED | Sobol | 2.663157 | 0.312017 | 0.375450 | 0.518184 | 0.255694 | 0.707143 | 0.977300 | 0.627417 | 0.424752 |
| 1 | 1 | 1_0 | COMPLETED | Sobol | 3.472775 | 0.811599 | 0.102800 | 0.826156 | 0.586577 | 0.981025 | 0.461695 | 0.791734 | 0.264965 |
| 2 | 2 | 2_0 | COMPLETED | Sobol | 2.599138 | 0.513995 | 0.750892 | 0.365383 | 0.176387 | 0.993027 | 0.377566 | 0.549260 | 0.210662 |
| 3 | 3 | 3_0 | COMPLETED | Sobol | 1.135110 | 0.020953 | 0.352685 | 0.384740 | 0.598315 | 0.675668 | 0.320246 | 0.389470 | 0.386341 |
| 4 | 4 | 4_0 | COMPLETED | Sobol | 1.293105 | 0.049371 | 0.654408 | 0.467794 | 0.322839 | 0.333161 | 0.513854 | 0.134319 | 0.485225 |
| 5 | 5 | 5_0 | COMPLETED | Sobol | 1.457474 | 0.779954 | 0.080537 | 0.271937 | 0.845372 | 0.035978 | 0.263293 | 0.257189 | 0.118739 |
| 6 | 6 | 6_0 | COMPLETED | Sobol | 4.251037 | 0.869940 | 0.920247 | 0.434625 | 0.701204 | 0.696775 | 0.943400 | 0.606757 | 0.462032 |
| 7 | 7 | 7_0 | COMPLETED | Sobol | 1.981109 | 0.600472 | 0.356166 | 0.415501 | 0.840716 | 0.145596 | 0.444465 | 0.601179 | 0.432331 |
| 8 | 8 | 8_0 | COMPLETED | Sobol | 2.561738 | 0.507137 | 0.699582 | 0.326667 | 0.639318 | 0.389713 | 0.358486 | 0.544911 | 0.891967 |
| 9 | 9 | 9_0 | COMPLETED | Sobol | 4.313421 | 0.646849 | 0.827967 | 0.732573 | 0.994397 | 0.221591 | 0.797337 | 0.615998 | 0.755372 |
| 10 | 10 | 10_0 | COMPLETED | Sobol | 4.327585 | 0.508235 | 0.655068 | 0.893461 | 0.930283 | 0.624175 | 0.886251 | 0.679031 | 0.264030 |
| 11 | 11 | 11_0 | COMPLETED | Sobol | 1.960524 | 0.245657 | 0.174974 | 0.354753 | 0.424672 | 0.133220 | 0.951068 | 0.439949 | 0.566493 |
| 12 | 12 | 12_0 | COMPLETED | Sobol | 1.423228 | 0.252244 | 0.236526 | 0.581198 | 0.018938 | 0.773188 | 0.382626 | 0.166053 | 0.225524 |
| 13 | 13 | 13_0 | COMPLETED | Sobol | 1.470841 | 0.430965 | 0.535480 | 0.319732 | 0.225324 | 0.358769 | 0.215507 | 0.827910 | 0.112318 |
| 14 | 14 | 14_0 | COMPLETED | Sobol | 2.047706 | 0.825881 | 0.154236 | 0.244455 | 0.487318 | 0.748788 | 0.788026 | 0.309836 | 0.027160 |
| 15 | 15 | 15_0 | COMPLETED | Sobol | 3.829676 | 0.896006 | 0.323754 | 0.970113 | 0.600032 | 0.488128 | 0.843276 | 0.184945 | 0.638443 |
| 16 | 16 | 16_0 | COMPLETED | GPEI | 0.831562 | 0.036738 | 0.472569 | 0.397035 | 0.506163 | 0.458229 | 0.376407 | 0.258182 | 0.421778 |
| 17 | 17 | 17_0 | COMPLETED | GPEI | 1.411013 | 0.000000 | 0.522502 | 0.458266 | 0.426792 | 0.721061 | 0.422221 | 0.266576 | 0.507974 |
| 18 | 18 | 18_0 | COMPLETED | GPEI | 1.143500 | 0.212341 | 0.268985 | 0.330559 | 0.679346 | 0.434590 | 0.297060 | 0.349851 | 0.314136 |
| 19 | 19 | 19_0 | COMPLETED | GPEI | 0.463539 | 0.086164 | 0.361035 | 0.370711 | 0.297997 | 0.358246 | 0.348047 | 0.298517 | 0.293590 |
| 20 | 20 | 20_0 | COMPLETED | GPEI | 0.383194 | 0.034869 | 0.334433 | 0.375754 | 0.461653 | 0.441267 | 0.412602 | 0.036355 | 0.292011 |
| 21 | 21 | 21_0 | COMPLETED | GPEI | 0.688874 | 0.040416 | 0.495560 | 0.429553 | 0.433630 | 0.297753 | 0.193928 | 0.385047 | 0.349413 |
| 22 | 22 | 22_0 | COMPLETED | GPEI | 0.298763 | 0.000000 | 0.335533 | 0.382258 | 0.345978 | 0.332896 | 0.287420 | 0.047099 | 0.217264 |
| 23 | 23 | 23_0 | COMPLETED | GPEI | 0.283036 | 0.000000 | 0.211597 | 0.399096 | 0.342443 | 0.303916 | 0.345610 | 0.051221 | 0.387174 |
| 24 | 24 | 24_0 | COMPLETED | GPEI | 0.224499 | 0.000000 | 0.383919 | 0.361917 | 0.395714 | 0.365952 | 0.413164 | 0.139015 | 0.077381 |
| 25 | 25 | 25_0 | COMPLETED | GPEI | 0.473313 | 0.000000 | 0.213475 | 0.389053 | 0.377933 | 0.248060 | 0.433936 | 0.111913 | 0.129031 |
| 26 | 26 | 26_0 | COMPLETED | GPEI | 0.506551 | 0.000000 | 0.248434 | 0.243786 | 0.325343 | 0.303443 | 0.453504 | 0.044787 | 0.169293 |
| 27 | 27 | 27_0 | COMPLETED | GPEI | 0.606441 | 0.000000 | 0.246060 | 0.493610 | 0.393148 | 0.308101 | 0.375003 | 0.163087 | 0.117784 |
| 28 | 28 | 28_0 | COMPLETED | GPEI | 0.537491 | 0.000000 | 0.492178 | 0.306430 | 0.412458 | 0.239091 | 0.350907 | 0.177723 | 0.053241 |
| 29 | 29 | 29_0 | COMPLETED | GPEI | 0.350213 | 0.000000 | 0.385204 | 0.345878 | 0.297388 | 0.501700 | 0.405405 | 0.090237 | 0.057207 |
| 30 | 30 | 30_0 | COMPLETED | GPEI | 0.384968 | 0.000000 | 0.412547 | 0.370486 | 0.323259 | 0.277802 | 0.447566 | 0.046090 | 0.184052 |
| 31 | 31 | 31_0 | COMPLETED | GPEI | 0.399310 | 0.000000 | 0.326253 | 0.350303 | 0.384816 | 0.406117 | 0.384198 | 0.151564 | 0.170865 |
| 32 | 32 | 32_0 | COMPLETED | GPEI | 0.651089 | 0.000000 | 0.162394 | 0.357030 | 0.254357 | 0.404179 | 0.177300 | 0.038917 | 0.541337 |
| 33 | 33 | 33_0 | COMPLETED | GPEI | 0.133918 | 0.000000 | 0.367831 | 0.348879 | 0.466264 | 0.424930 | 0.415589 | 0.015454 | 0.000000 |
| 34 | 34 | 34_0 | COMPLETED | GPEI | 0.160010 | 0.134682 | 0.383295 | 0.376547 | 0.416497 | 0.363486 | 0.407027 | 0.000000 | 0.000000 |
| 35 | 35 | 35_0 | COMPLETED | GPEI | 0.607355 | 0.207752 | 0.261156 | 0.403849 | 0.292222 | 0.151493 | 0.273163 | 0.000000 | 0.408476 |
| 36 | 36 | 36_0 | COMPLETED | GPEI | 0.241903 | 0.000000 | 0.445157 | 0.420915 | 0.474798 | 0.422200 | 0.406699 | 0.000000 | 0.000000 |
| 37 | 37 | 37_0 | COMPLETED | GPEI | 0.132668 | 0.034296 | 0.369506 | 0.351920 | 0.429270 | 0.365676 | 0.470187 | 0.000000 | 0.000000 |
| 38 | 38 | 38_0 | COMPLETED | GPEI | 0.583685 | 0.085351 | 0.385241 | 0.324978 | 0.500865 | 0.407612 | 0.538656 | 0.033266 | 0.000000 |
| 39 | 39 | 39_0 | COMPLETED | GPEI | -0.023691 | 0.026875 | 0.366678 | 0.363851 | 0.414838 | 0.363992 | 0.364331 | 0.000000 | 0.000000 |
| 40 | 40 | 40_0 | COMPLETED | GPEI | -0.040379 | 0.000000 | 0.357151 | 0.374060 | 0.370617 | 0.328077 | 0.357097 | 0.000000 | 0.000000 |
| 41 | 41 | 41_0 | COMPLETED | GPEI | 0.115861 | 0.000000 | 0.344771 | 0.370551 | 0.454516 | 0.278565 | 0.331861 | 0.000000 | 0.000000 |
| 42 | 42 | 42_0 | COMPLETED | GPEI | 0.036092 | 0.047530 | 0.337711 | 0.337497 | 0.333073 | 0.329439 | 0.327415 | 0.000000 | 0.000000 |
| 43 | 43 | 43_0 | COMPLETED | GPEI | 0.601410 | 0.195682 | 0.091939 | 0.364800 | 0.288180 | 0.435749 | 0.463267 | 0.000000 | 0.459962 |
| 44 | 44 | 44_0 | COMPLETED | GPEI | -0.059945 | 0.000000 | 0.372064 | 0.373322 | 0.366009 | 0.367236 | 0.361431 | 0.000000 | 0.000000 |
| 45 | 45 | 45_0 | COMPLETED | GPEI | -0.036262 | 0.000000 | 0.407358 | 0.361476 | 0.360987 | 0.357513 | 0.352213 | 0.000000 | 0.000000 |
| 46 | 46 | 46_0 | COMPLETED | GPEI | -0.030902 | 0.000000 | 0.368343 | 0.386212 | 0.362645 | 0.380164 | 0.319139 | 0.000000 | 0.000000 |
| 47 | 47 | 47_0 | COMPLETED | GPEI | 2.587291 | 0.453197 | 0.682408 | 0.350890 | 0.612169 | 0.674319 | 0.550328 | 0.038512 | 0.847392 |
| 48 | 48 | 48_0 | COMPLETED | GPEI | 2.134270 | 0.492481 | 0.245022 | 0.685515 | 0.889154 | 0.622527 | 0.033786 | 0.109576 | 0.312552 |
| 49 | 49 | 49_0 | COMPLETED | GPEI | 1.029291 | 0.000000 | 0.134440 | 0.300564 | 0.563262 | 0.233928 | 0.387781 | 0.000000 | 0.615784 |