Note

Go to the end to download the full example code

# Parallel coordinates¶

In this example, we illustrate the use of the
`ParallelCoordinates`

plot on the Sobieski’s SSBJ
problem.

```
from __future__ import annotations
from gemseo import configure_logger
from gemseo import create_discipline
from gemseo import create_scenario
from gemseo.problems.sobieski.core.problem import SobieskiProblem
```

## Import¶

The first step is to import some high-level functions and a method to get the design space.

```
configure_logger()
```

```
<RootLogger root (INFO)>
```

## Description¶

The `ParallelCoordinates`

post-processing
builds parallel coordinates plots among design
variables, outputs functions and constraints.

The `ParallelCoordinates`

portrays the design
variables history during the scenario execution. Each vertical coordinate is
dedicated to a design variable, normalized by its bounds.

A polyline joins all components of a given design vector and is colored by objective function values. This highlights the correlations between the values of the design variables and the values of the objective function.

## Create disciplines¶

At this point, we instantiate the disciplines of Sobieski’s SSBJ problem: Propulsion, Aerodynamics, Structure and Mission

```
disciplines = create_discipline(
[
"SobieskiPropulsion",
"SobieskiAerodynamics",
"SobieskiStructure",
"SobieskiMission",
]
)
```

## Create design space¶

We also read the design space from the `SobieskiProblem`

.

```
design_space = SobieskiProblem().design_space
```

## Create and execute scenario¶

The next step is to build an MDO scenario in order to maximize the range, encoded ‘y_4’, with respect to the design parameters, while satisfying the inequality constraints ‘g_1’, ‘g_2’ and ‘g_3’. We can use the MDF formulation, the SLSQP optimization algorithm and a maximum number of iterations equal to 100.

```
scenario = create_scenario(
disciplines,
formulation="MDF",
objective_name="y_4",
maximize_objective=True,
design_space=design_space,
)
scenario.set_differentiation_method()
for constraint in ["g_1", "g_2", "g_3"]:
scenario.add_constraint(constraint, "ineq")
scenario.execute({"algo": "SLSQP", "max_iter": 10})
```

```
INFO - 13:56:08:
INFO - 13:56:08: *** Start MDOScenario execution ***
INFO - 13:56:08: MDOScenario
INFO - 13:56:08: Disciplines: SobieskiAerodynamics SobieskiMission SobieskiPropulsion SobieskiStructure
INFO - 13:56:08: MDO formulation: MDF
INFO - 13:56:08: Optimization problem:
INFO - 13:56:08: minimize -y_4(x_shared, x_1, x_2, x_3)
INFO - 13:56:08: with respect to x_1, x_2, x_3, x_shared
INFO - 13:56:08: subject to constraints:
INFO - 13:56:08: g_1(x_shared, x_1, x_2, x_3) <= 0.0
INFO - 13:56:08: g_2(x_shared, x_1, x_2, x_3) <= 0.0
INFO - 13:56:08: g_3(x_shared, x_1, x_2, x_3) <= 0.0
INFO - 13:56:08: over the design space:
INFO - 13:56:08: +-------------+-------------+-------+-------------+-------+
INFO - 13:56:08: | name | lower_bound | value | upper_bound | type |
INFO - 13:56:08: +-------------+-------------+-------+-------------+-------+
INFO - 13:56:08: | x_shared[0] | 0.01 | 0.05 | 0.09 | float |
INFO - 13:56:08: | x_shared[1] | 30000 | 45000 | 60000 | float |
INFO - 13:56:08: | x_shared[2] | 1.4 | 1.6 | 1.8 | float |
INFO - 13:56:08: | x_shared[3] | 2.5 | 5.5 | 8.5 | float |
INFO - 13:56:08: | x_shared[4] | 40 | 55 | 70 | float |
INFO - 13:56:08: | x_shared[5] | 500 | 1000 | 1500 | float |
INFO - 13:56:08: | x_1[0] | 0.1 | 0.25 | 0.4 | float |
INFO - 13:56:08: | x_1[1] | 0.75 | 1 | 1.25 | float |
INFO - 13:56:08: | x_2 | 0.75 | 1 | 1.25 | float |
INFO - 13:56:08: | x_3 | 0.1 | 0.5 | 1 | float |
INFO - 13:56:08: +-------------+-------------+-------+-------------+-------+
INFO - 13:56:08: Solving optimization problem with algorithm SLSQP:
INFO - 13:56:08: ... 0%| | 0/10 [00:00<?, ?it]
INFO - 13:56:08: ... 10%|█ | 1/10 [00:00<00:01, 8.78 it/sec, obj=-536]
INFO - 13:56:08: ... 20%|██ | 2/10 [00:00<00:01, 6.45 it/sec, obj=-2.12e+3]
WARNING - 13:56:08: MDAJacobi has reached its maximum number of iterations but the normed residual 1.7130677857005655e-05 is still above the tolerance 1e-06.
INFO - 13:56:08: ... 30%|███ | 3/10 [00:00<00:01, 5.48 it/sec, obj=-3.75e+3]
INFO - 13:56:08: ... 40%|████ | 4/10 [00:00<00:01, 5.27 it/sec, obj=-3.96e+3]
INFO - 13:56:09: ... 50%|█████ | 5/10 [00:00<00:00, 5.15 it/sec, obj=-3.96e+3]
INFO - 13:56:09: Optimization result:
INFO - 13:56:09: Optimizer info:
INFO - 13:56:09: Status: 8
INFO - 13:56:09: Message: Positive directional derivative for linesearch
INFO - 13:56:09: Number of calls to the objective function by the optimizer: 6
INFO - 13:56:09: Solution:
INFO - 13:56:09: The solution is feasible.
INFO - 13:56:09: Objective: -3963.408265187933
INFO - 13:56:09: Standardized constraints:
INFO - 13:56:09: g_1 = [-0.01806104 -0.03334642 -0.04424946 -0.0518346 -0.05732607 -0.13720865
INFO - 13:56:09: -0.10279135]
INFO - 13:56:09: g_2 = 3.333278582928756e-06
INFO - 13:56:09: g_3 = [-7.67181773e-01 -2.32818227e-01 8.30379541e-07 -1.83255000e-01]
INFO - 13:56:09: Design space:
INFO - 13:56:09: +-------------+-------------+---------------------+-------------+-------+
INFO - 13:56:09: | name | lower_bound | value | upper_bound | type |
INFO - 13:56:09: +-------------+-------------+---------------------+-------------+-------+
INFO - 13:56:09: | x_shared[0] | 0.01 | 0.06000083331964572 | 0.09 | float |
INFO - 13:56:09: | x_shared[1] | 30000 | 60000 | 60000 | float |
INFO - 13:56:09: | x_shared[2] | 1.4 | 1.4 | 1.8 | float |
INFO - 13:56:09: | x_shared[3] | 2.5 | 2.5 | 8.5 | float |
INFO - 13:56:09: | x_shared[4] | 40 | 70 | 70 | float |
INFO - 13:56:09: | x_shared[5] | 500 | 1500 | 1500 | float |
INFO - 13:56:09: | x_1[0] | 0.1 | 0.4 | 0.4 | float |
INFO - 13:56:09: | x_1[1] | 0.75 | 0.75 | 1.25 | float |
INFO - 13:56:09: | x_2 | 0.75 | 0.75 | 1.25 | float |
INFO - 13:56:09: | x_3 | 0.1 | 0.1562448753887276 | 1 | float |
INFO - 13:56:09: +-------------+-------------+---------------------+-------------+-------+
INFO - 13:56:09: *** End MDOScenario execution (time: 0:00:01.106140) ***
{'max_iter': 10, 'algo': 'SLSQP'}
```

## Post-process scenario¶

Lastly, we post-process the scenario by means of the
`ParallelCoordinates`

plot which parallel
coordinates plots among design variables, objective function and constraints.

Tip

Each post-processing method requires different inputs and offers a variety
of customization options. Use the high-level function
`get_post_processing_options_schema()`

to print a table with
the options for any post-processing algorithm.
Or refer to our dedicated page:
Post-processing algorithms.

```
scenario.post_process("ParallelCoordinates", save=False, show=True)
```

```
<gemseo.post.para_coord.ParallelCoordinates object at 0x7f006beccd00>
```

**Total running time of the script:** (0 minutes 1.810 seconds)