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	686.111729	0.404091	123	686.515819	685.707638	1373.031639	1371.415276
6	828.513441	0.495985	123	829.009426	828.017456	1658.018851	1656.034912
7	987.710668	-0.362235	123	987.348433	988.072903	1974.696866	1976.145807
8	693.327213	0.064971	123	693.392184	693.262242	1386.784367	1386.524484
9	842.746407	0.188921	123	842.935328	842.557486	1685.870656	1685.114972
10	413.414235	0.527608	123	413.941843	412.886628	827.883685	825.773255
11	84.452671	0.289725	123	84.742396	84.162946	169.484792	168.325892
12	564.509208	-0.893571	123	563.615637	565.402779	1127.231274	1130.805559
13	496.084695	-0.318707	123	495.765989	496.403402	991.531978	992.806804
14	215.556041	-0.694029	123	214.862012	216.250069	429.724023	432.500139

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	-686.515819	685.707638
6	-829.009426	828.017456
7	-987.348433	988.072903
8	-693.392184	693.262242
9	-842.935328	842.557486
10	-413.941843	412.886628
11	-84.742396	84.162946
12	-563.615637	565.402779
13	-495.765989	496.403402
14	-214.862012	216.250069

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([[-686.51581927,  685.70763784],
       [-829.00942556,  828.01745576],
       [-987.34843323,  988.07290339],
       [-693.39218364,  693.26224186],
       [-842.93532825,  842.55748606],
       [-413.94184264,  412.88662751],
       [ -84.74239594,   84.16294619],
       [-563.61563694,  565.40277949],
       [-495.76598884,  496.4034021 ],
       [-214.86201169,  216.25006938]])

In [13]:

get_constraint_data(vocs, data)

get_constraint_data(vocs, data)

Out[13]:

	constraint_e	constraint_f
5	1371.031639	-1371.415276
6	1656.018851	-1656.034912
7	1972.696866	-1976.145807
8	1384.784367	-1386.524484
9	1683.870656	-1685.114972
10	825.883685	-825.773255
11	167.484792	-168.325892
12	1125.231274	-1130.805559
13	989.531978	-992.806804
14	427.724023	-432.500139

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	0.686112	0.702045
6	0.828513	0.747992
7	0.987711	0.318882
8	0.693327	0.532485
9	0.842746	0.594461
10	0.413414	0.763804
11	0.084453	0.644862
12	0.564509	0.053214
13	0.496085	0.340647
14	0.215556	0.152986

In [16]:

# and denormalize
denormalize_inputs(vocs, normed_data)

# and denormalize denormalize_inputs(vocs, normed_data)

Out[16]:

	a	b
5	686.111729	0.404091
6	828.513441	0.495985
7	987.710668	-0.362235
8	693.327213	0.064971
9	842.746407	0.188921
10	413.414235	0.527608
11	84.452671	0.289725
12	564.509208	-0.893571
13	496.084695	-0.318707
14	215.556041	-0.694029

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