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:
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 MDODiscipline
of AnalyticDiscipline
type
from a Python function:
expressions = {"y": "x1+x2"}
discipline = create_discipline("AnalyticDiscipline", expressions=expressions)
Now, we want to minimize this MDODiscipline
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", l_b=-5, u_b=5, var_type="integer")
design_space.add_variable("x2", l_b=-5, u_b=5, var_type="integer")
Define the DOE scenario¶
Then, by means of the create_scenario()
API function,
we define a DOEScenario
from the MDODiscipline
and the DesignSpace
defined above:
scenario = create_scenario(
discipline, "DisciplinaryOpt", "y", design_space, scenario_type="DOE"
)
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": "fullfact", "n_samples": 11**2})
INFO - 16:25:24:
INFO - 16:25:24: *** Start DOEScenario execution ***
INFO - 16:25:24: DOEScenario
INFO - 16:25:24: Disciplines: AnalyticDiscipline
INFO - 16:25:24: MDO formulation: DisciplinaryOpt
INFO - 16:25:24: Optimization problem:
INFO - 16:25:24: minimize y(x1, x2)
INFO - 16:25:24: with respect to x1, x2
INFO - 16:25:24: over the design space:
INFO - 16:25:24: +------+-------------+-------+-------------+---------+
INFO - 16:25:24: | name | lower_bound | value | upper_bound | type |
INFO - 16:25:24: +------+-------------+-------+-------------+---------+
INFO - 16:25:24: | x1 | -5 | None | 5 | integer |
INFO - 16:25:24: | x2 | -5 | None | 5 | integer |
INFO - 16:25:24: +------+-------------+-------+-------------+---------+
INFO - 16:25:24: Solving optimization problem with algorithm fullfact:
INFO - 16:25:24: ... 0%| | 0/121 [00:00<?, ?it]
INFO - 16:25:24: ... 1%| | 1/121 [00:00<00:00, 335.97 it/sec, obj=-10]
INFO - 16:25:24: ... 2%|▏ | 2/121 [00:00<00:00, 541.51 it/sec, obj=-9]
INFO - 16:25:24: ... 2%|▏ | 3/121 [00:00<00:00, 687.10 it/sec, obj=-8]
INFO - 16:25:24: ... 3%|▎ | 4/121 [00:00<00:00, 792.28 it/sec, obj=-7]
INFO - 16:25:24: ... 4%|▍ | 5/121 [00:00<00:00, 868.35 it/sec, obj=-6]
INFO - 16:25:24: ... 5%|▍ | 6/121 [00:00<00:00, 935.01 it/sec, obj=-5]
INFO - 16:25:24: ... 6%|▌ | 7/121 [00:00<00:00, 990.59 it/sec, obj=-4]
INFO - 16:25:24: ... 7%|▋ | 8/121 [00:00<00:00, 1036.56 it/sec, obj=-3]
INFO - 16:25:24: ... 7%|▋ | 9/121 [00:00<00:00, 1075.59 it/sec, obj=-2]
INFO - 16:25:24: ... 8%|▊ | 10/121 [00:00<00:00, 1106.47 it/sec, obj=-1]
INFO - 16:25:24: ... 9%|▉ | 11/121 [00:00<00:00, 1132.07 it/sec, obj=0]
INFO - 16:25:24: ... 10%|▉ | 12/121 [00:00<00:00, 1157.05 it/sec, obj=-9]
INFO - 16:25:24: ... 11%|█ | 13/121 [00:00<00:00, 1179.30 it/sec, obj=-8]
INFO - 16:25:24: ... 12%|█▏ | 14/121 [00:00<00:00, 1198.98 it/sec, obj=-7]
INFO - 16:25:24: ... 12%|█▏ | 15/121 [00:00<00:00, 1216.56 it/sec, obj=-6]
INFO - 16:25:24: ... 13%|█▎ | 16/121 [00:00<00:00, 1230.72 it/sec, obj=-5]
INFO - 16:25:24: ... 14%|█▍ | 17/121 [00:00<00:00, 1241.29 it/sec, obj=-4]
INFO - 16:25:24: ... 15%|█▍ | 18/121 [00:00<00:00, 1253.99 it/sec, obj=-3]
INFO - 16:25:24: ... 16%|█▌ | 19/121 [00:00<00:00, 1266.13 it/sec, obj=-2]
INFO - 16:25:24: ... 17%|█▋ | 20/121 [00:00<00:00, 1277.27 it/sec, obj=-1]
INFO - 16:25:24: ... 17%|█▋ | 21/121 [00:00<00:00, 1287.69 it/sec, obj=0]
INFO - 16:25:24: ... 18%|█▊ | 22/121 [00:00<00:00, 1295.94 it/sec, obj=1]
INFO - 16:25:24: ... 19%|█▉ | 23/121 [00:00<00:00, 1302.33 it/sec, obj=-8]
INFO - 16:25:24: ... 20%|█▉ | 24/121 [00:00<00:00, 1310.72 it/sec, obj=-7]
INFO - 16:25:24: ... 21%|██ | 25/121 [00:00<00:00, 1318.42 it/sec, obj=-6]
INFO - 16:25:24: ... 21%|██▏ | 26/121 [00:00<00:00, 1325.47 it/sec, obj=-5]
INFO - 16:25:24: ... 22%|██▏ | 27/121 [00:00<00:00, 1332.18 it/sec, obj=-4]
INFO - 16:25:24: ... 23%|██▎ | 28/121 [00:00<00:00, 1337.27 it/sec, obj=-3]
INFO - 16:25:24: ... 24%|██▍ | 29/121 [00:00<00:00, 1341.59 it/sec, obj=-2]
INFO - 16:25:24: ... 25%|██▍ | 30/121 [00:00<00:00, 1342.92 it/sec, obj=-1]
INFO - 16:25:24: ... 26%|██▌ | 31/121 [00:00<00:00, 1347.60 it/sec, obj=0]
INFO - 16:25:24: ... 26%|██▋ | 32/121 [00:00<00:00, 1352.63 it/sec, obj=1]
INFO - 16:25:24: ... 27%|██▋ | 33/121 [00:00<00:00, 1357.50 it/sec, obj=2]
INFO - 16:25:24: ... 28%|██▊ | 34/121 [00:00<00:00, 1361.03 it/sec, obj=-7]
INFO - 16:25:24: ... 29%|██▉ | 35/121 [00:00<00:00, 1363.28 it/sec, obj=-6]
INFO - 16:25:24: ... 30%|██▉ | 36/121 [00:00<00:00, 1367.35 it/sec, obj=-5]
INFO - 16:25:24: ... 31%|███ | 37/121 [00:00<00:00, 1371.38 it/sec, obj=-4]
INFO - 16:25:24: ... 31%|███▏ | 38/121 [00:00<00:00, 1375.17 it/sec, obj=-3]
INFO - 16:25:24: ... 32%|███▏ | 39/121 [00:00<00:00, 1378.73 it/sec, obj=-2]
INFO - 16:25:24: ... 33%|███▎ | 40/121 [00:00<00:00, 1381.08 it/sec, obj=-1]
INFO - 16:25:24: ... 34%|███▍ | 41/121 [00:00<00:00, 1382.97 it/sec, obj=0]
INFO - 16:25:24: ... 35%|███▍ | 42/121 [00:00<00:00, 1386.04 it/sec, obj=1]
INFO - 16:25:24: ... 36%|███▌ | 43/121 [00:00<00:00, 1389.25 it/sec, obj=2]
INFO - 16:25:24: ... 36%|███▋ | 44/121 [00:00<00:00, 1392.33 it/sec, obj=3]
INFO - 16:25:24: ... 37%|███▋ | 45/121 [00:00<00:00, 1394.84 it/sec, obj=-6]
INFO - 16:25:24: ... 38%|███▊ | 46/121 [00:00<00:00, 1396.52 it/sec, obj=-5]
INFO - 16:25:24: ... 39%|███▉ | 47/121 [00:00<00:00, 1397.94 it/sec, obj=-4]
INFO - 16:25:24: ... 40%|███▉ | 48/121 [00:00<00:00, 1400.45 it/sec, obj=-3]
INFO - 16:25:24: ... 40%|████ | 49/121 [00:00<00:00, 1403.07 it/sec, obj=-2]
INFO - 16:25:24: ... 41%|████▏ | 50/121 [00:00<00:00, 1405.46 it/sec, obj=-1]
INFO - 16:25:24: ... 42%|████▏ | 51/121 [00:00<00:00, 1407.91 it/sec, obj=0]
INFO - 16:25:24: ... 43%|████▎ | 52/121 [00:00<00:00, 1409.73 it/sec, obj=1]
INFO - 16:25:24: ... 44%|████▍ | 53/121 [00:00<00:00, 1410.74 it/sec, obj=2]
INFO - 16:25:24: ... 45%|████▍ | 54/121 [00:00<00:00, 1412.58 it/sec, obj=3]
INFO - 16:25:24: ... 45%|████▌ | 55/121 [00:00<00:00, 1414.64 it/sec, obj=4]
INFO - 16:25:24: ... 46%|████▋ | 56/121 [00:00<00:00, 1416.71 it/sec, obj=-5]
INFO - 16:25:24: ... 47%|████▋ | 57/121 [00:00<00:00, 1418.72 it/sec, obj=-4]
INFO - 16:25:24: ... 48%|████▊ | 58/121 [00:00<00:00, 1420.06 it/sec, obj=-3]
INFO - 16:25:24: ... 49%|████▉ | 59/121 [00:00<00:00, 1420.55 it/sec, obj=-2]
INFO - 16:25:24: ... 50%|████▉ | 60/121 [00:00<00:00, 1422.26 it/sec, obj=-1]
INFO - 16:25:24: ... 50%|█████ | 61/121 [00:00<00:00, 1423.97 it/sec, obj=0]
INFO - 16:25:24: ... 51%|█████ | 62/121 [00:00<00:00, 1425.73 it/sec, obj=1]
INFO - 16:25:24: ... 52%|█████▏ | 63/121 [00:00<00:00, 1427.54 it/sec, obj=2]
INFO - 16:25:24: ... 53%|█████▎ | 64/121 [00:00<00:00, 1428.78 it/sec, obj=3]
INFO - 16:25:24: ... 54%|█████▎ | 65/121 [00:00<00:00, 1429.43 it/sec, obj=4]
INFO - 16:25:24: ... 55%|█████▍ | 66/121 [00:00<00:00, 1430.78 it/sec, obj=5]
INFO - 16:25:24: ... 55%|█████▌ | 67/121 [00:00<00:00, 1432.07 it/sec, obj=-4]
INFO - 16:25:24: ... 56%|█████▌ | 68/121 [00:00<00:00, 1433.42 it/sec, obj=-3]
INFO - 16:25:24: ... 57%|█████▋ | 69/121 [00:00<00:00, 1426.39 it/sec, obj=-2]
INFO - 16:25:24: ... 58%|█████▊ | 70/121 [00:00<00:00, 1426.64 it/sec, obj=-1]
INFO - 16:25:24: ... 59%|█████▊ | 71/121 [00:00<00:00, 1426.56 it/sec, obj=0]
INFO - 16:25:24: ... 60%|█████▉ | 72/121 [00:00<00:00, 1427.82 it/sec, obj=1]
INFO - 16:25:24: ... 60%|██████ | 73/121 [00:00<00:00, 1429.10 it/sec, obj=2]
INFO - 16:25:24: ... 61%|██████ | 74/121 [00:00<00:00, 1430.41 it/sec, obj=3]
INFO - 16:25:24: ... 62%|██████▏ | 75/121 [00:00<00:00, 1431.56 it/sec, obj=4]
INFO - 16:25:24: ... 63%|██████▎ | 76/121 [00:00<00:00, 1432.27 it/sec, obj=5]
INFO - 16:25:24: ... 64%|██████▎ | 77/121 [00:00<00:00, 1432.30 it/sec, obj=6]
INFO - 16:25:24: ... 64%|██████▍ | 78/121 [00:00<00:00, 1433.50 it/sec, obj=-3]
INFO - 16:25:24: ... 65%|██████▌ | 79/121 [00:00<00:00, 1434.74 it/sec, obj=-2]
INFO - 16:25:24: ... 66%|██████▌ | 80/121 [00:00<00:00, 1428.97 it/sec, obj=-1]
INFO - 16:25:24: ... 67%|██████▋ | 81/121 [00:00<00:00, 1429.11 it/sec, obj=0]
INFO - 16:25:24: ... 68%|██████▊ | 82/121 [00:00<00:00, 1430.36 it/sec, obj=1]
INFO - 16:25:24: ... 69%|██████▊ | 83/121 [00:00<00:00, 1431.78 it/sec, obj=2]
INFO - 16:25:24: ... 69%|██████▉ | 84/121 [00:00<00:00, 1432.88 it/sec, obj=3]
INFO - 16:25:24: ... 70%|███████ | 85/121 [00:00<00:00, 1429.94 it/sec, obj=4]
INFO - 16:25:24: ... 71%|███████ | 86/121 [00:00<00:00, 1430.63 it/sec, obj=5]
INFO - 16:25:24: ... 72%|███████▏ | 87/121 [00:00<00:00, 1431.17 it/sec, obj=6]
INFO - 16:25:24: ... 73%|███████▎ | 88/121 [00:00<00:00, 1431.48 it/sec, obj=7]
INFO - 16:25:24: ... 74%|███████▎ | 89/121 [00:00<00:00, 1432.07 it/sec, obj=-2]
INFO - 16:25:24: ... 74%|███████▍ | 90/121 [00:00<00:00, 1433.07 it/sec, obj=-1]
INFO - 16:25:24: ... 75%|███████▌ | 91/121 [00:00<00:00, 1434.05 it/sec, obj=0]
INFO - 16:25:24: ... 76%|███████▌ | 92/121 [00:00<00:00, 1435.08 it/sec, obj=1]
INFO - 16:25:24: ... 77%|███████▋ | 93/121 [00:00<00:00, 1435.56 it/sec, obj=2]
INFO - 16:25:24: ... 78%|███████▊ | 94/121 [00:00<00:00, 1429.86 it/sec, obj=3]
INFO - 16:25:24: ... 79%|███████▊ | 95/121 [00:00<00:00, 1430.34 it/sec, obj=4]
INFO - 16:25:24: ... 79%|███████▉ | 96/121 [00:00<00:00, 1431.22 it/sec, obj=5]
INFO - 16:25:24: ... 80%|████████ | 97/121 [00:00<00:00, 1432.10 it/sec, obj=6]
INFO - 16:25:24: ... 81%|████████ | 98/121 [00:00<00:00, 1432.95 it/sec, obj=7]
INFO - 16:25:24: ... 82%|████████▏ | 99/121 [00:00<00:00, 1433.34 it/sec, obj=8]
INFO - 16:25:24: ... 83%|████████▎ | 100/121 [00:00<00:00, 1433.23 it/sec, obj=-1]
INFO - 16:25:24: ... 83%|████████▎ | 101/121 [00:00<00:00, 1434.12 it/sec, obj=0]
INFO - 16:25:24: ... 84%|████████▍ | 102/121 [00:00<00:00, 1434.99 it/sec, obj=1]
INFO - 16:25:24: ... 85%|████████▌ | 103/121 [00:00<00:00, 1435.82 it/sec, obj=2]
INFO - 16:25:24: ... 86%|████████▌ | 104/121 [00:00<00:00, 1436.63 it/sec, obj=3]
INFO - 16:25:24: ... 87%|████████▋ | 105/121 [00:00<00:00, 1437.05 it/sec, obj=4]
INFO - 16:25:24: ... 88%|████████▊ | 106/121 [00:00<00:00, 1436.99 it/sec, obj=5]
INFO - 16:25:24: ... 88%|████████▊ | 107/121 [00:00<00:00, 1437.83 it/sec, obj=6]
INFO - 16:25:24: ... 89%|████████▉ | 108/121 [00:00<00:00, 1438.70 it/sec, obj=7]
INFO - 16:25:24: ... 90%|█████████ | 109/121 [00:00<00:00, 1439.49 it/sec, obj=8]
INFO - 16:25:24: ... 91%|█████████ | 110/121 [00:00<00:00, 1440.40 it/sec, obj=9]
INFO - 16:25:24: ... 92%|█████████▏| 111/121 [00:00<00:00, 1440.55 it/sec, obj=0]
INFO - 16:25:24: ... 93%|█████████▎| 112/121 [00:00<00:00, 1440.14 it/sec, obj=1]
INFO - 16:25:24: ... 93%|█████████▎| 113/121 [00:00<00:00, 1440.81 it/sec, obj=2]
INFO - 16:25:24: ... 94%|█████████▍| 114/121 [00:00<00:00, 1441.57 it/sec, obj=3]
INFO - 16:25:24: ... 95%|█████████▌| 115/121 [00:00<00:00, 1442.35 it/sec, obj=4]
INFO - 16:25:24: ... 96%|█████████▌| 116/121 [00:00<00:00, 1443.09 it/sec, obj=5]
INFO - 16:25:24: ... 97%|█████████▋| 117/121 [00:00<00:00, 1443.52 it/sec, obj=6]
INFO - 16:25:24: ... 98%|█████████▊| 118/121 [00:00<00:00, 1444.39 it/sec, obj=7]
INFO - 16:25:24: ... 98%|█████████▊| 119/121 [00:00<00:00, 1445.34 it/sec, obj=8]
INFO - 16:25:24: ... 99%|█████████▉| 120/121 [00:00<00:00, 1446.00 it/sec, obj=9]
INFO - 16:25:24: ... 100%|██████████| 121/121 [00:00<00:00, 1446.73 it/sec, obj=10]
INFO - 16:25:24: Optimization result:
INFO - 16:25:24: Optimizer info:
INFO - 16:25:24: Status: None
INFO - 16:25:24: Message: None
INFO - 16:25:24: Number of calls to the objective function by the optimizer: 121
INFO - 16:25:24: Solution:
INFO - 16:25:24: Objective: -10.0
INFO - 16:25:24: Design space:
INFO - 16:25:24: +------+-------------+-------+-------------+---------+
INFO - 16:25:24: | name | lower_bound | value | upper_bound | type |
INFO - 16:25:24: +------+-------------+-------+-------------+---------+
INFO - 16:25:24: | x1 | -5 | -5 | 5 | integer |
INFO - 16:25:24: | x2 | -5 | -5 | 5 | integer |
INFO - 16:25:24: +------+-------------+-------+-------------+---------+
INFO - 16:25:24: *** End DOEScenario execution (time: 0:00:00.095297) ***
{'eval_jac': False, 'n_samples': 121, 'algo': 'fullfact'}
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
print(
"The solution of P is "
f"(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:
algo_list = get_available_doe_algorithms()
print(f"Available algorithms: {algo_list}")
Available algorithms: ['CustomDOE', 'DiagonalDOE', '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', 'fullfact', 'ff2n', 'pbdesign', 'bbdesign', 'ccdesign', 'lhs']
Available post-processing¶
In order to get the list of available post-processing algorithms, use:
post_list = get_available_post_processings()
print(f"Available algorithms: {post_list}")
Available algorithms: ['Animation', 'BasicHistory', 'Compromise', 'ConstraintsHistory', 'Correlations', 'GradientSensitivity', '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 0.110 seconds)