Note

Go to the end to download the full example code.

Create a DOE Scenario#

from __future__ import annotations

from gemseo import configure_logger
from gemseo import create_design_space
from gemseo import create_discipline
from gemseo import create_scenario
from gemseo import get_available_doe_algorithms
from gemseo import get_available_post_processings

configure_logger()

<RootLogger root (INFO)>

Let \((P)\) be a simple optimization problem:

\[\begin{split}(P) = \left\{ \begin{aligned} & \underset{x\in\mathbb{N}^2}{\text{minimize}} & & f(x) = x_1 + x_2 \\ & \text{subject to} & & -5 \leq x \leq 5 \end{aligned} \right.\end{split}\]

In this example, we will see how to use GEMSEO to solve this problem \((P)\) by means of a Design Of Experiments (DOE)

Define the discipline#

Firstly, by means of the create_discipline() API function, we create an Discipline of AnalyticDiscipline type from a Python function:

expressions = {"y": "x1+x2"}
discipline = create_discipline("AnalyticDiscipline", expressions=expressions)

Now, we want to minimize this Discipline over a design of experiments (DOE).

Define the design space#

For that, by means of the create_design_space() API function, we define the DesignSpace \([-5, 5]\times[-5, 5]\) by using its DesignSpace.add_variable() method.

design_space = create_design_space()
design_space.add_variable("x1", lower_bound=-5, upper_bound=5, type_="integer")
design_space.add_variable("x2", lower_bound=-5, upper_bound=5, type_="integer")

Define the DOE scenario#

Then, by means of the create_scenario() API function, we define a DOEScenario from the Discipline and the DesignSpace defined above:

scenario = create_scenario(
    discipline,
    "y",
    design_space,
    scenario_type="DOE",
    formulation_name="DisciplinaryOpt",
)

Note that the formulation settings passed to create_scenario() can be provided via a Pydantic model. For more information, see Formulation Settings.

Execute the DOE scenario#

Lastly, we solve the OptimizationProblem included in the DOEScenario defined above by minimizing the objective function over a design of experiments included in the DesignSpace. Precisely, we choose a full factorial design of size \(11^2\):

scenario.execute(algo_name="PYDOE_FULLFACT", n_samples=11**2)

INFO - 20:38:29: *** Start DOEScenario execution ***
INFO - 20:38:29: DOEScenario
INFO - 20:38:29:    Disciplines: AnalyticDiscipline
INFO - 20:38:29:    MDO formulation: DisciplinaryOpt
INFO - 20:38:29: Optimization problem:
INFO - 20:38:29:    minimize y(x1, x2)
INFO - 20:38:29:    with respect to x1, x2
INFO - 20:38:29:    over the design space:
INFO - 20:38:29:       +------+-------------+-------+-------------+---------+
INFO - 20:38:29:       | Name | Lower bound | Value | Upper bound | Type    |
INFO - 20:38:29:       +------+-------------+-------+-------------+---------+
INFO - 20:38:29:       | x1   |      -5     |  None |      5      | integer |
INFO - 20:38:29:       | x2   |      -5     |  None |      5      | integer |
INFO - 20:38:29:       +------+-------------+-------+-------------+---------+
INFO - 20:38:29: Solving optimization problem with algorithm PYDOE_FULLFACT:
INFO - 20:38:29:      1%|          | 1/121 [00:00<00:00, 543.87 it/sec, obj=-10]
INFO - 20:38:29:      2%|▏         | 2/121 [00:00<00:00, 926.10 it/sec, obj=-9]
INFO - 20:38:29:      2%|▏         | 3/121 [00:00<00:00, 1257.03 it/sec, obj=-8]
INFO - 20:38:29:      3%|▎         | 4/121 [00:00<00:00, 1542.59 it/sec, obj=-7]
INFO - 20:38:29:      4%|▍         | 5/121 [00:00<00:00, 1791.52 it/sec, obj=-6]
INFO - 20:38:29:      5%|▍         | 6/121 [00:00<00:00, 1990.81 it/sec, obj=-5]
INFO - 20:38:29:      6%|▌         | 7/121 [00:00<00:00, 2183.40 it/sec, obj=-4]
INFO - 20:38:29:      7%|▋         | 8/121 [00:00<00:00, 2357.51 it/sec, obj=-3]
INFO - 20:38:29:      7%|▋         | 9/121 [00:00<00:00, 2511.39 it/sec, obj=-2]
INFO - 20:38:29:      8%|▊         | 10/121 [00:00<00:00, 2655.97 it/sec, obj=-1]
INFO - 20:38:29:      9%|▉         | 11/121 [00:00<00:00, 2775.85 it/sec, obj=0]
INFO - 20:38:29:     10%|▉         | 12/121 [00:00<00:00, 2889.30 it/sec, obj=-9]
INFO - 20:38:29:     11%|█         | 13/121 [00:00<00:00, 2993.46 it/sec, obj=-8]
INFO - 20:38:29:     12%|█▏        | 14/121 [00:00<00:00, 3093.80 it/sec, obj=-7]
INFO - 20:38:29:     12%|█▏        | 15/121 [00:00<00:00, 3187.48 it/sec, obj=-6]
INFO - 20:38:29:     13%|█▎        | 16/121 [00:00<00:00, 3237.13 it/sec, obj=-5]
INFO - 20:38:29:     14%|█▍        | 17/121 [00:00<00:00, 3307.20 it/sec, obj=-4]
INFO - 20:38:29:     15%|█▍        | 18/121 [00:00<00:00, 3381.75 it/sec, obj=-3]
INFO - 20:38:29:     16%|█▌        | 19/121 [00:00<00:00, 3453.60 it/sec, obj=-2]
INFO - 20:38:29:     17%|█▋        | 20/121 [00:00<00:00, 3521.22 it/sec, obj=-1]
INFO - 20:38:29:     17%|█▋        | 21/121 [00:00<00:00, 3583.85 it/sec, obj=0]
INFO - 20:38:29:     18%|█▊        | 22/121 [00:00<00:00, 3627.29 it/sec, obj=1]
INFO - 20:38:29:     19%|█▉        | 23/121 [00:00<00:00, 3680.06 it/sec, obj=-8]
INFO - 20:38:29:     20%|█▉        | 24/121 [00:00<00:00, 3732.83 it/sec, obj=-7]
INFO - 20:38:29:     21%|██        | 25/121 [00:00<00:00, 3781.79 it/sec, obj=-6]
INFO - 20:38:29:     21%|██▏       | 26/121 [00:00<00:00, 3830.15 it/sec, obj=-5]
INFO - 20:38:29:     22%|██▏       | 27/121 [00:00<00:00, 3859.66 it/sec, obj=-4]
INFO - 20:38:29:     23%|██▎       | 28/121 [00:00<00:00, 3901.29 it/sec, obj=-3]
INFO - 20:38:29:     24%|██▍       | 29/121 [00:00<00:00, 3940.23 it/sec, obj=-2]
INFO - 20:38:29:     25%|██▍       | 30/121 [00:00<00:00, 3978.16 it/sec, obj=-1]
INFO - 20:38:29:     26%|██▌       | 31/121 [00:00<00:00, 4015.42 it/sec, obj=0]
INFO - 20:38:29:     26%|██▋       | 32/121 [00:00<00:00, 4041.97 it/sec, obj=1]
INFO - 20:38:29:     27%|██▋       | 33/121 [00:00<00:00, 4072.14 it/sec, obj=2]
INFO - 20:38:29:     28%|██▊       | 34/121 [00:00<00:00, 4104.84 it/sec, obj=-7]
INFO - 20:38:29:     29%|██▉       | 35/121 [00:00<00:00, 4137.21 it/sec, obj=-6]
INFO - 20:38:29:     30%|██▉       | 36/121 [00:00<00:00, 4169.29 it/sec, obj=-5]
INFO - 20:38:29:     31%|███       | 37/121 [00:00<00:00, 4196.57 it/sec, obj=-4]
INFO - 20:38:29:     31%|███▏      | 38/121 [00:00<00:00, 4214.82 it/sec, obj=-3]
INFO - 20:38:29:     32%|███▏      | 39/121 [00:00<00:00, 4241.83 it/sec, obj=-2]
INFO - 20:38:29:     33%|███▎      | 40/121 [00:00<00:00, 4266.19 it/sec, obj=-1]
INFO - 20:38:29:     34%|███▍      | 41/121 [00:00<00:00, 4289.94 it/sec, obj=0]
INFO - 20:38:29:     35%|███▍      | 42/121 [00:00<00:00, 4315.02 it/sec, obj=1]
INFO - 20:38:29:     36%|███▌      | 43/121 [00:00<00:00, 4331.29 it/sec, obj=2]
INFO - 20:38:29:     36%|███▋      | 44/121 [00:00<00:00, 4349.60 it/sec, obj=3]
INFO - 20:38:29:     37%|███▋      | 45/121 [00:00<00:00, 4369.17 it/sec, obj=-6]
INFO - 20:38:29:     38%|███▊      | 46/121 [00:00<00:00, 4389.44 it/sec, obj=-5]
INFO - 20:38:29:     39%|███▉      | 47/121 [00:00<00:00, 4407.55 it/sec, obj=-4]
INFO - 20:38:29:     40%|███▉      | 48/121 [00:00<00:00, 4426.12 it/sec, obj=-3]
INFO - 20:38:29:     40%|████      | 49/121 [00:00<00:00, 4431.43 it/sec, obj=-2]
INFO - 20:38:29:     41%|████▏     | 50/121 [00:00<00:00, 4449.81 it/sec, obj=-1]
INFO - 20:38:29:     42%|████▏     | 51/121 [00:00<00:00, 4468.36 it/sec, obj=0]
INFO - 20:38:29:     43%|████▎     | 52/121 [00:00<00:00, 4487.27 it/sec, obj=1]
INFO - 20:38:29:     44%|████▍     | 53/121 [00:00<00:00, 4502.61 it/sec, obj=2]
INFO - 20:38:29:     45%|████▍     | 54/121 [00:00<00:00, 4512.16 it/sec, obj=3]
INFO - 20:38:29:     45%|████▌     | 55/121 [00:00<00:00, 4526.29 it/sec, obj=4]
INFO - 20:38:29:     46%|████▋     | 56/121 [00:00<00:00, 4542.19 it/sec, obj=-5]
INFO - 20:38:29:     47%|████▋     | 57/121 [00:00<00:00, 4557.03 it/sec, obj=-4]
INFO - 20:38:29:     48%|████▊     | 58/121 [00:00<00:00, 4573.94 it/sec, obj=-3]
INFO - 20:38:29:     49%|████▉     | 59/121 [00:00<00:00, 4590.49 it/sec, obj=-2]
INFO - 20:38:29:     50%|████▉     | 60/121 [00:00<00:00, 4553.83 it/sec, obj=-1]
INFO - 20:38:29:     50%|█████     | 61/121 [00:00<00:00, 4562.36 it/sec, obj=0]
INFO - 20:38:29:     51%|█████     | 62/121 [00:00<00:00, 4574.34 it/sec, obj=1]
INFO - 20:38:29:     52%|█████▏    | 63/121 [00:00<00:00, 4585.85 it/sec, obj=2]
INFO - 20:38:29:     53%|█████▎    | 64/121 [00:00<00:00, 4590.37 it/sec, obj=3]
INFO - 20:38:29:     54%|█████▎    | 65/121 [00:00<00:00, 4601.19 it/sec, obj=4]
INFO - 20:38:29:     55%|█████▍    | 66/121 [00:00<00:00, 4614.12 it/sec, obj=5]
INFO - 20:38:29:     55%|█████▌    | 67/121 [00:00<00:00, 4625.89 it/sec, obj=-4]
INFO - 20:38:29:     56%|█████▌    | 68/121 [00:00<00:00, 4639.26 it/sec, obj=-3]
INFO - 20:38:29:     57%|█████▋    | 69/121 [00:00<00:00, 4652.10 it/sec, obj=-2]
INFO - 20:38:29:     58%|█████▊    | 70/121 [00:00<00:00, 4654.43 it/sec, obj=-1]
INFO - 20:38:29:     59%|█████▊    | 71/121 [00:00<00:00, 4666.18 it/sec, obj=0]
INFO - 20:38:29:     60%|█████▉    | 72/121 [00:00<00:00, 4678.60 it/sec, obj=1]
INFO - 20:38:29:     60%|██████    | 73/121 [00:00<00:00, 4690.32 it/sec, obj=2]
INFO - 20:38:29:     61%|██████    | 74/121 [00:00<00:00, 4702.92 it/sec, obj=3]
INFO - 20:38:29:     62%|██████▏   | 75/121 [00:00<00:00, 4709.81 it/sec, obj=4]
INFO - 20:38:29:     63%|██████▎   | 76/121 [00:00<00:00, 4719.75 it/sec, obj=5]
INFO - 20:38:29:     64%|██████▎   | 77/121 [00:00<00:00, 4730.03 it/sec, obj=6]
INFO - 20:38:29:     64%|██████▍   | 78/121 [00:00<00:00, 4742.21 it/sec, obj=-3]
INFO - 20:38:29:     65%|██████▌   | 79/121 [00:00<00:00, 4754.35 it/sec, obj=-2]
INFO - 20:38:29:     66%|██████▌   | 80/121 [00:00<00:00, 4765.44 it/sec, obj=-1]
INFO - 20:38:29:     67%|██████▋   | 81/121 [00:00<00:00, 4767.86 it/sec, obj=0]
INFO - 20:38:29:     68%|██████▊   | 82/121 [00:00<00:00, 4775.85 it/sec, obj=1]
INFO - 20:38:29:     69%|██████▊   | 83/121 [00:00<00:00, 4783.54 it/sec, obj=2]
INFO - 20:38:29:     69%|██████▉   | 84/121 [00:00<00:00, 4793.56 it/sec, obj=3]
INFO - 20:38:29:     70%|███████   | 85/121 [00:00<00:00, 4800.85 it/sec, obj=4]
INFO - 20:38:29:     71%|███████   | 86/121 [00:00<00:00, 4807.61 it/sec, obj=5]
INFO - 20:38:29:     72%|███████▏  | 87/121 [00:00<00:00, 4809.16 it/sec, obj=6]
INFO - 20:38:29:     73%|███████▎  | 88/121 [00:00<00:00, 4817.58 it/sec, obj=7]
INFO - 20:38:29:     74%|███████▎  | 89/121 [00:00<00:00, 4825.84 it/sec, obj=-2]
INFO - 20:38:29:     74%|███████▍  | 90/121 [00:00<00:00, 4833.63 it/sec, obj=-1]
INFO - 20:38:29:     75%|███████▌  | 91/121 [00:00<00:00, 4841.71 it/sec, obj=0]
INFO - 20:38:29:     76%|███████▌  | 92/121 [00:00<00:00, 4842.88 it/sec, obj=1]
INFO - 20:38:29:     77%|███████▋  | 93/121 [00:00<00:00, 4848.36 it/sec, obj=2]
INFO - 20:38:29:     78%|███████▊  | 94/121 [00:00<00:00, 4855.30 it/sec, obj=3]
INFO - 20:38:29:     79%|███████▊  | 95/121 [00:00<00:00, 4863.47 it/sec, obj=4]
INFO - 20:38:29:     79%|███████▉  | 96/121 [00:00<00:00, 4854.11 it/sec, obj=5]
INFO - 20:38:29:     80%|████████  | 97/121 [00:00<00:00, 4854.87 it/sec, obj=6]
INFO - 20:38:29:     81%|████████  | 98/121 [00:00<00:00, 4860.89 it/sec, obj=7]
INFO - 20:38:29:     82%|████████▏ | 99/121 [00:00<00:00, 4868.29 it/sec, obj=8]
INFO - 20:38:29:     83%|████████▎ | 100/121 [00:00<00:00, 4874.77 it/sec, obj=-1]
INFO - 20:38:29:     83%|████████▎ | 101/121 [00:00<00:00, 4881.09 it/sec, obj=0]
INFO - 20:38:29:     84%|████████▍ | 102/121 [00:00<00:00, 4888.63 it/sec, obj=1]
INFO - 20:38:29:     85%|████████▌ | 103/121 [00:00<00:00, 4889.63 it/sec, obj=2]
INFO - 20:38:29:     86%|████████▌ | 104/121 [00:00<00:00, 4895.65 it/sec, obj=3]
INFO - 20:38:29:     87%|████████▋ | 105/121 [00:00<00:00, 4901.96 it/sec, obj=4]
INFO - 20:38:29:     88%|████████▊ | 106/121 [00:00<00:00, 4908.92 it/sec, obj=5]
INFO - 20:38:29:     88%|████████▊ | 107/121 [00:00<00:00, 4914.43 it/sec, obj=6]
INFO - 20:38:29:     89%|████████▉ | 108/121 [00:00<00:00, 4917.44 it/sec, obj=7]
INFO - 20:38:29:     90%|█████████ | 109/121 [00:00<00:00, 4922.47 it/sec, obj=8]
INFO - 20:38:29:     91%|█████████ | 110/121 [00:00<00:00, 4928.68 it/sec, obj=9]
INFO - 20:38:29:     92%|█████████▏| 111/121 [00:00<00:00, 4935.16 it/sec, obj=0]
INFO - 20:38:29:     93%|█████████▎| 112/121 [00:00<00:00, 4941.48 it/sec, obj=1]
INFO - 20:38:29:     93%|█████████▎| 113/121 [00:00<00:00, 4947.35 it/sec, obj=2]
INFO - 20:38:29:     94%|█████████▍| 114/121 [00:00<00:00, 4946.93 it/sec, obj=3]
INFO - 20:38:29:     95%|█████████▌| 115/121 [00:00<00:00, 4951.95 it/sec, obj=4]
INFO - 20:38:29:     96%|█████████▌| 116/121 [00:00<00:00, 4956.85 it/sec, obj=5]
INFO - 20:38:29:     97%|█████████▋| 117/121 [00:00<00:00, 4962.17 it/sec, obj=6]
INFO - 20:38:29:     98%|█████████▊| 118/121 [00:00<00:00, 4968.26 it/sec, obj=7]
INFO - 20:38:29:     98%|█████████▊| 119/121 [00:00<00:00, 4969.55 it/sec, obj=8]
INFO - 20:38:29:     99%|█████████▉| 120/121 [00:00<00:00, 4974.37 it/sec, obj=9]
INFO - 20:38:29:    100%|██████████| 121/121 [00:00<00:00, 4979.31 it/sec, obj=10]
INFO - 20:38:29: Optimization result:
INFO - 20:38:29:    Optimizer info:
INFO - 20:38:29:       Status: None
INFO - 20:38:29:       Message: None
INFO - 20:38:29:       Number of calls to the objective function by the optimizer: 0
INFO - 20:38:29:    Solution:
INFO - 20:38:29:       Objective: -10.0
INFO - 20:38:29:       Design space:
INFO - 20:38:29:          +------+-------------+-------+-------------+---------+
INFO - 20:38:29:          | Name | Lower bound | Value | Upper bound | Type    |
INFO - 20:38:29:          +------+-------------+-------+-------------+---------+
INFO - 20:38:29:          | x1   |      -5     |   -5  |      5      | integer |
INFO - 20:38:29:          | x2   |      -5     |   -5  |      5      | integer |
INFO - 20:38:29:          +------+-------------+-------+-------------+---------+
INFO - 20:38:29: *** End DOEScenario execution ***

Note that the algorithm settings passed to execute() can be provided via a Pydantic model. For more information, see Algorithm Settings.

The optimum results can be found in the execution log. It is also possible to access them with Scenario.optimization_result:

optimization_result = scenario.optimization_result
f"The solution of P is (x*, f(x*)) = ({optimization_result.x_opt}, {optimization_result.f_opt})"

'The solution of P is (x*, f(x*)) = ([-5. -5.], -10.0)'

Available DOE algorithms#

In order to get the list of available DOE algorithms, use:

get_available_doe_algorithms()

['CustomDOE', 'DiagonalDOE', 'MorrisDOE', 'OATDOE', 'OT_SOBOL', 'OT_RANDOM', 'OT_HASELGROVE', 'OT_REVERSE_HALTON', 'OT_HALTON', 'OT_FAURE', 'OT_MONTE_CARLO', 'OT_FACTORIAL', 'OT_COMPOSITE', 'OT_AXIAL', 'OT_OPT_LHS', 'OT_LHS', 'OT_LHSC', 'OT_FULLFACT', 'OT_SOBOL_INDICES', 'PYDOE_BBDESIGN', 'PYDOE_CCDESIGN', 'PYDOE_FF2N', 'PYDOE_FULLFACT', 'PYDOE_LHS', 'PYDOE_PBDESIGN', 'Halton', 'LHS', 'MC', 'PoissonDisk', 'Sobol']

Available post-processing#

In order to get the list of available post-processing algorithms, use:

get_available_post_processings()

['Animation', 'BasicHistory', 'Compromise', 'ConstraintsHistory', 'Correlations', 'DataVersusModel', 'GradientSensitivity', 'HessianHistory', 'HighTradeOff', 'MultiObjectiveDiagram', 'ObjConstrHist', 'OptHistoryView', 'ParallelCoordinates', 'ParetoFront', 'Petal', 'QuadApprox', 'Radar', 'RadarChart', 'Robustness', 'SOM', 'ScatterPareto', 'ScatterPlotMatrix', 'TopologyView', 'VariableInfluence']

You can also look at the examples:

Total running time of the script: (0 minutes 0.034 seconds)

Gallery generated by Sphinx-Gallery