Upper Confidence Bound BO¶

In [1]:

from xopt import Xopt

# Ignore all warnings
import warnings

warnings.filterwarnings("ignore")

from xopt import Xopt # Ignore all warnings import warnings warnings.filterwarnings("ignore")

The Xopt object can be instantiated from a JSON or YAML file, or a dict, with the proper structure.

Here we will make one

In [2]:

# Make a proper input file.
YAML = """
generator:
  name: upper_confidence_bound
  beta: 0.1
  vocs:
    variables:
      x1: [0, 6.28]
    objectives:
      y1: 'MINIMIZE'
evaluator:
  function: xopt.resources.test_functions.sinusoid_1d.evaluate_sinusoid


"""

# Make a proper input file. YAML = """ generator: name: upper_confidence_bound beta: 0.1 vocs: variables: x1: [0, 6.28] objectives: y1: 'MINIMIZE' evaluator: function: xopt.resources.test_functions.sinusoid_1d.evaluate_sinusoid """

In [3]:

X = Xopt.from_yaml(YAML)
X

X = Xopt.from_yaml(YAML) X

Out[3]:

            Xopt
________________________________
Version: 0.1.dev1+gb834d2348
Data size: 0
Config as YAML:
dump_file: null
evaluator:
  function: xopt.resources.test_functions.sinusoid_1d.evaluate_sinusoid
  function_kwargs: {}
  max_workers: 1
  vectorized: false
generator:
  beta: 0.1
  computation_time: null
  custom_objective: null
  fixed_features: null
  gp_constructor:
    covar_modules: {}
    custom_noise_prior: null
    mean_modules: {}
    name: standard
    train_config: null
    train_kwargs: null
    train_method: lbfgs
    train_model: true
    trainable_mean_keys: []
    transform_inputs: true
    use_cached_hyperparameters: false
    use_low_noise_prior: false
  max_travel_distances: null
  model: null
  n_candidates: 1
  n_interpolate_points: null
  n_monte_carlo_samples: 128
  name: upper_confidence_bound
  numerical_optimizer:
    max_iter: 2000
    max_time: 5.0
    n_restarts: 20
    name: LBFGS
  returns_id: false
  shift: 0.0
  supports_batch_generation: true
  supports_constraints: true
  supports_single_objective: true
  turbo_controller: null
  use_cuda: false
  vocs:
    constants: {}
    constraints: {}
    objectives:
      y1:
        dtype: null
        type: MinimizeObjective
    observables: {}
    variables:
      x1:
        default_value: null
        domain:
        - 0.0
        - 6.28
        dtype: null
        type: ContinuousVariable
serialize_inline: false
serialize_torch: false
stopping_condition: null
strict: true

Run Optimization¶

In [4]:

X.random_evaluate(3)
for i in range(5):
    print(i)
    X.step()

X.random_evaluate(3) for i in range(5): print(i) X.step()

0

1

2

3

4

View output data¶

In [5]:

X.data

X.data

Out[5]:

	x1	y1	c1	xopt_runtime	xopt_error
0	5.465420	-0.729619	-16.266000	0.000014	False
1	1.349261	0.975561	0.235567	0.000004	False
2	0.812785	0.726205	-2.797375	0.000003	False
3	6.040218	-0.240583	-12.897399	0.000008	False
4	4.838445	-0.992065	-18.785350	0.000009	False
5	4.710475	-0.999998	-18.500071	0.000009	False
6	4.738212	-0.999667	-18.512959	0.000009	False
7	4.738981	-0.999646	-18.513740	0.000008	False

Visualize model¶

In [6]:

fig, ax = X.generator.visualize_model(n_grid=100)

fig, ax = X.generator.visualize_model(n_grid=100)