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	39.902145	-0.129186	123	39.772959	40.031332	79.545918	80.062664
6	789.565345	0.351747	123	789.917092	789.213597	1579.834184	1578.427195
7	27.557468	-0.973207	123	26.584261	28.530675	53.168521	57.061349
8	801.707108	-0.227390	123	801.479718	801.934498	1602.959437	1603.868997
9	51.037609	-0.731112	123	50.306497	51.768721	100.612995	103.537442
10	15.444274	-0.562445	123	14.881828	16.006719	29.763656	32.013438
11	888.978608	0.560429	123	889.539037	888.418178	1779.078074	1776.836357
12	700.877660	-0.195022	123	700.682638	701.072683	1401.365276	1402.145365
13	979.350155	0.488276	123	979.838431	978.861879	1959.676861	1957.723757
14	516.954605	-0.364603	123	516.590002	517.319209	1033.180004	1034.638418

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	-39.772959	40.031332
6	-789.917092	789.213597
7	-26.584261	28.530675
8	-801.479718	801.934498
9	-50.306497	51.768721
10	-14.881828	16.006719
11	-889.539037	888.418178
12	-700.682638	701.072683
13	-979.838431	978.861879
14	-516.590002	517.319209

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([[ -39.77295909,   40.03133183],
       [-789.91709224,  789.2135973 ],
       [ -26.58426054,   28.53067459],
       [-801.47971828,  801.93449849],
       [ -50.30649741,   51.76872091],
       [ -14.88182815,   16.00671904],
       [-889.53903723,  888.41817837],
       [-700.68263796,  701.07268267],
       [-979.83843052,  978.86187864],
       [-516.59000193,  517.31920891]])

In [13]:

get_constraint_data(vocs, data)

get_constraint_data(vocs, data)

Out[13]:

	constraint_e	constraint_f
5	77.545918	-80.062664
6	1577.834184	-1578.427195
7	51.168521	-57.061349
8	1600.959437	-1603.868997
9	98.612995	-103.537442
10	27.763656	-32.013438
11	1777.078074	-1776.836357
12	1399.365276	-1402.145365
13	1957.676861	-1957.723757
14	1031.180004	-1034.638418

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	0.039902	0.435407
6	0.789565	0.675874
7	0.027557	0.013396
8	0.801707	0.386305
9	0.051038	0.134444
10	0.015444	0.218777
11	0.888979	0.780215
12	0.700878	0.402489
13	0.979350	0.744138
14	0.516955	0.317698

In [16]:

# and denormalize
denormalize_inputs(vocs, normed_data)

# and denormalize denormalize_inputs(vocs, normed_data)

Out[16]:

	a	b
5	39.902145	-0.129186
6	789.565345	0.351747
7	27.557468	-0.973207
8	801.707108	-0.227390
9	51.037609	-0.731112
10	15.444274	-0.562445
11	888.978608	0.560429
12	700.877660	-0.195022
13	979.350155	0.488276
14	516.954605	-0.364603

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