Design of Experiment using OPTIMEO

Let’s create a parameters list, with their names, values and types

from optimeo.doe import *
import plotly.io as pio
pio.renderers.default = "notebook"

parameters = [
    {'name': 'Temperature', 'type': 'integer', 'values': [0, 50]},
    {'name': 'Pressure', 'type': 'float', 'values': [0, 50]},
    {'name': 'Catalyst', 'type': 'categorical', 'values': ['A', 'B', 'C']}
]
doe = DesignOfExperiments(
    # one of the following:
    # 'Full Factorial', 'Sobol sequence', 'Fractional Factorial', 
    # 'Definitive Screening Design', 'Space Filling Latin Hypercube', 
    # 'Randomized Latin Hypercube', 'Optimal', 'Plackett-Burman', 'Box-Behnken'
    type='Sobol sequence',
    parameters=parameters,
    Nexp=20,
    # 'Sobol sequence' supports **linear** constraints on the parameters
    # meaning that "Temperature**2 + Pressure**2 <= 250" won't work
    feature_constraints=["Temperature + 2*Pressure <= 250"]
)

Show a resume of the class:

doe

- Design of Experiments type: Sobol sequence
- Parameters:
{'name': 'Temperature', 'type': 'integer', 'values': [0, 50]}
{'name': 'Pressure', 'type': 'float', 'values': [0, 50]}
{'name': 'Catalyst', 'type': 'categorical', 'values': ['A', 'B', 'C'], 'encoder': None}
- Lows: {'Temperature': np.int64(0), 'Pressure': np.int64(0)}
- Highs: {'Temperature': np.int64(50), 'Pressure': np.int64(50)}
- If applicable:
    - Randomize: True
    - Number of Experiments: 20
    - Order: 2
    - Reduction: 2
- Design:
    run_order  Temperature   Pressure Catalyst
0           2            6  35.531425        B
1          18           27  21.355860        C
2          15           48  49.591119        A
3           9           19   7.290747        A
4          16           17  41.096456        A
5          20           41   2.116205        C
6          12           35  30.159282        C
7          10            7  13.054220        B
8           3           12  44.009413        B
9           8           33  11.309977        A
10         17           42  33.074693        B
11         19           13  22.250067        C
12          7           23  26.335362        C
13          5           47  18.440615        B
14          4           29  40.397563        A
15          6            1   4.377622        C
16         13            1  38.972786        A
17          1           31   6.096160        B
18         14           45  28.034797        A
19         11           23  17.033357        B

Just the design:

doe.design

	run_order	Temperature	Pressure	Catalyst
0	2	6	35.531425	B
1	18	27	21.355860	C
2	15	48	49.591119	A
3	9	19	7.290747	A
4	16	17	41.096456	A
5	20	41	2.116205	C
6	12	35	30.159282	C
7	10	7	13.054220	B
8	3	12	44.009413	B
9	8	33	11.309977	A
10	17	42	33.074693	B
11	19	13	22.250067	C
12	7	23	26.335362	C
13	5	47	18.440615	B
14	4	29	40.397563	A
15	6	1	4.377622	C
16	13	1	38.972786	A
17	1	31	6.096160	B
18	14	45	28.034797	A
19	11	23	17.033357	B

Make a plot of the design:

figs = doe.plot()
for fig in figs:
    fig.show()