VOCS data structure¶

Variables, Objectives, Constraints, and other Settings (VOCS) helps define our optimization problems.

In [1]:

from xopt.vocs import VOCS
from xopt.vocs import (
    get_objective_data,
    random_inputs,
    get_constraint_data,
    get_feasibility_data,
    normalize_inputs,
    denormalize_inputs,
)
from gest_api.vocs import MaximizeObjective
import pandas as pd
import numpy as np
import yaml

from xopt.vocs import VOCS from xopt.vocs import ( get_objective_data, random_inputs, get_constraint_data, get_feasibility_data, normalize_inputs, denormalize_inputs, ) from gest_api.vocs import MaximizeObjective import pandas as pd import numpy as np import yaml

In [2]:

Y = """
variables:
  a: [0, 1e3] # Note that 1e3 usually parses as a str with YAML. 
  b: [-1, 1]
objectives:
  c: maximize
  d: minimize 
constraints:
  e: ['Less_than', 2]
  f: ['greater_than', 0]
constants:
  g: 123

"""

vocs = VOCS(**yaml.safe_load(Y))
vocs

Y = """ variables: a: [0, 1e3] # Note that 1e3 usually parses as a str with YAML. b: [-1, 1] objectives: c: maximize d: minimize constraints: e: ['Less_than', 2] f: ['greater_than', 0] constants: g: 123 """ vocs = VOCS(**yaml.safe_load(Y)) vocs

Out[2]:

VOCS(variables={'a': ContinuousVariable(dtype=None, default_value=None, domain=[0.0, 1000.0]), 'b': ContinuousVariable(dtype=None, default_value=None, domain=[-1.0, 1.0])}, objectives={'c': MaximizeObjective(dtype=None), 'd': MinimizeObjective(dtype=None)}, constraints={'e': LessThanConstraint(dtype=None, value=2.0), 'f': GreaterThanConstraint(dtype=None, value=0.0)}, constants={'g': Constant(dtype=None, value=123)}, observables={})

In [3]:

# as dict
dict(vocs)

# as dict dict(vocs)

Out[3]:

{'variables': {'a': ContinuousVariable(dtype=None, default_value=None, domain=[0.0, 1000.0]),
  'b': ContinuousVariable(dtype=None, default_value=None, domain=[-1.0, 1.0])},
 'objectives': {'c': MaximizeObjective(dtype=None),
  'd': MinimizeObjective(dtype=None)},
 'constraints': {'e': LessThanConstraint(dtype=None, value=2.0),
  'f': GreaterThanConstraint(dtype=None, value=0.0)},
 'constants': {'g': Constant(dtype=None, value=123)},
 'observables': {}}

In [4]:

#  re-parse dict
vocs2 = VOCS(**dict(vocs))

# re-parse dict vocs2 = VOCS(**dict(vocs))

In [5]:

# Check that these are the same
vocs2 == vocs

# Check that these are the same vocs2 == vocs

Out[5]:

True

In [6]:

# This replaces the old vocs["variables"]
getattr(vocs, "variables")

# This replaces the old vocs["variables"] getattr(vocs, "variables")

Out[6]:

{'a': ContinuousVariable(dtype=None, default_value=None, domain=[0.0, 1000.0]),
 'b': ContinuousVariable(dtype=None, default_value=None, domain=[-1.0, 1.0])}

In [7]:

vocs.objectives["c"]

vocs.objectives["c"]

Out[7]:

MaximizeObjective(dtype=None)

In [8]:

isinstance(vocs.objectives["c"], MaximizeObjective)

isinstance(vocs.objectives["c"], MaximizeObjective)

Out[8]:

True

In [9]:

# json
vocs.model_dump_json()

# json vocs.model_dump_json()

Out[9]:

'{"variables":{"a":{"dtype":null,"default_value":null,"domain":[0.0,1000.0],"type":"ContinuousVariable"},"b":{"dtype":null,"default_value":null,"domain":[-1.0,1.0],"type":"ContinuousVariable"}},"objectives":{"c":{"dtype":null,"type":"MaximizeObjective"},"d":{"dtype":null,"type":"MinimizeObjective"}},"constraints":{"e":{"dtype":null,"value":2.0,"type":"LessThanConstraint"},"f":{"dtype":null,"value":0.0,"type":"GreaterThanConstraint"}},"constants":{"g":{"dtype":null,"value":123,"type":"Constant"}},"observables":{}}'

Objective Evaluation¶

In [10]:

data = pd.DataFrame(random_inputs(vocs, 10))
# Add some outputs
data["c"] = data["a"] + data["b"]
data["d"] = data["a"] - data["b"]
data["e"] = data["a"] * 2 + data["b"] * 2
data["f"] = data["a"] * 2 - data["b"] * 2
data.index = np.arange(len(data)) + 5  # custom index
data

data = pd.DataFrame(random_inputs(vocs, 10)) # Add some outputs data["c"] = data["a"] + data["b"] data["d"] = data["a"] - data["b"] data["e"] = data["a"] * 2 + data["b"] * 2 data["f"] = data["a"] * 2 - data["b"] * 2 data.index = np.arange(len(data)) + 5 # custom index data

Out[10]:

	a	b	g	c	d	e	f
5	693.863870	0.846466	123	694.710336	693.017404	1389.420673	1386.034808
6	965.781767	-0.666693	123	965.115074	966.448460	1930.230148	1932.896920
7	36.306300	-0.624779	123	35.681521	36.931078	71.363042	73.862156
8	19.157938	-0.271400	123	18.886537	19.429338	37.773075	38.858676
9	749.953216	0.007086	123	749.960302	749.946131	1499.920604	1499.892261
10	634.456002	-0.411894	123	634.044108	634.867896	1268.088216	1269.735791
11	602.130186	-0.137566	123	601.992620	602.267753	1203.985240	1204.535505
12	888.036290	0.459396	123	888.495686	887.576894	1776.991373	1775.153788
13	490.837988	-0.927419	123	489.910570	491.765407	979.821140	983.530814
14	234.442751	0.427139	123	234.869891	234.015612	469.739781	468.031224

In [11]:

# These are in standard form for minimization, available as a function
get_objective_data(vocs, data)

# These are in standard form for minimization, available as a function get_objective_data(vocs, data)

Out[11]:

	objective_c	objective_d
5	-694.710336	693.017404
6	-965.115074	966.448460
7	-35.681521	36.931078
8	-18.886537	19.429338
9	-749.960302	749.946131
10	-634.044108	634.867896
11	-601.992620	602.267753
12	-888.495686	887.576894
13	-489.910570	491.765407
14	-234.869891	234.015612

In [12]:

# use the to_numpy() method to convert for low level use.
get_objective_data(vocs, data).to_numpy()

# use the to_numpy() method to convert for low level use. get_objective_data(vocs, data).to_numpy()

Out[12]:

array([[-694.71033642,  693.01740382],
       [-965.11507381,  966.44846011],
       [ -35.68152092,   36.93107818],
       [ -18.88653729,   19.42933804],
       [-749.96030224,  749.9461306 ],
       [-634.04410804,  634.86789551],
       [-601.99261986,  602.26775266],
       [-888.49568649,  887.57689402],
       [-489.91056988,  491.7654071 ],
       [-234.8698905 ,  234.01561217]])

In [13]:

get_constraint_data(vocs, data)

get_constraint_data(vocs, data)

Out[13]:

	constraint_e	constraint_f
5	1387.420673	-1386.034808
6	1928.230148	-1932.896920
7	69.363042	-73.862156
8	35.773075	-38.858676
9	1497.920604	-1499.892261
10	1266.088216	-1269.735791
11	1201.985240	-1204.535505
12	1774.991373	-1775.153788
13	977.821140	-983.530814
14	467.739781	-468.031224

In [14]:

get_feasibility_data(vocs, data)

get_feasibility_data(vocs, data)

Out[14]:

	feasible_e	feasible_f	feasible
5	False	True	False
6	False	True	False
7	False	True	False
8	False	True	False
9	False	True	False
10	False	True	False
11	False	True	False
12	False	True	False
13	False	True	False
14	False	True	False

In [15]:

# normalize inputs to unit domain [0,1]
normed_data = normalize_inputs(vocs, data)
normed_data

# normalize inputs to unit domain [0,1] normed_data = normalize_inputs(vocs, data) normed_data

Out[15]:

	a	b
5	0.693864	0.923233
6	0.965782	0.166653
7	0.036306	0.187611
8	0.019158	0.364300
9	0.749953	0.503543
10	0.634456	0.294053
11	0.602130	0.431217
12	0.888036	0.729698
13	0.490838	0.036291
14	0.234443	0.713570

In [16]:

# and denormalize
denormalize_inputs(vocs, normed_data)

# and denormalize denormalize_inputs(vocs, normed_data)

Out[16]:

	a	b
5	693.863870	0.846466
6	965.781767	-0.666693
7	36.306300	-0.624779
8	19.157938	-0.271400
9	749.953216	0.007086
10	634.456002	-0.411894
11	602.130186	-0.137566
12	888.036290	0.459396
13	490.837988	-0.927419
14	234.442751	0.427139

Error handling¶

In [17]:

Y = """
variables:
  a: [0, 1e3] # Note that 1e3 usually parses as a str with YAML. 
  b: [-1, 1]
objectives:
  c: maximize
  d: minimize 
constraints:
  e: ['Less_than', 2]
  f: ['greater_than', 0]
constants:
  g: 1234

"""

vocs = VOCS(**yaml.safe_load(Y))

Y = """ variables: a: [0, 1e3] # Note that 1e3 usually parses as a str with YAML. b: [-1, 1] objectives: c: maximize d: minimize constraints: e: ['Less_than', 2] f: ['greater_than', 0] constants: g: 1234 """ vocs = VOCS(**yaml.safe_load(Y))

In [18]:

d = {"a": [1, 2, 3]}

df = pd.DataFrame(d)
df2 = pd.DataFrame(df).copy()

df2["b"] = np.nan
df2["b"] - 1

d = {"a": [1, 2, 3]} df = pd.DataFrame(d) df2 = pd.DataFrame(df).copy() df2["b"] = np.nan df2["b"] - 1

Out[18]:

0   NaN
1   NaN
2   NaN
Name: b, dtype: float64

In [19]:

data["a"] = np.nan

data["a"] = np.nan

In [20]:

a = 2


def f(x=a):
    return x


a = 99
f()

a = 2 def f(x=a): return x a = 99 f()

Out[20]:

2

In [21]:

pd.DataFrame(6e66, index=[1, 2, 3], columns=["A"])

pd.DataFrame(6e66, index=[1, 2, 3], columns=["A"])

Out[21]:

	A
1	6.000000e+66
2	6.000000e+66
3	6.000000e+66

In [22]:

# These are in standard form for minimization

data = pd.DataFrame({"c": [1, 2, 3, 4]}, index=[9, 3, 4, 5])

get_objective_data(vocs, data)

# These are in standard form for minimization data = pd.DataFrame({"c": [1, 2, 3, 4]}, index=[9, 3, 4, 5]) get_objective_data(vocs, data)

Out[22]:

	objective_c	objective_d
9	-1.0	inf
3	-2.0	inf
4	-3.0	inf
5	-4.0	inf