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	598.652161	-0.444124	123	598.208037	599.096284	1196.416074	1198.192569
6	11.581156	0.156237	123	11.737393	11.424919	23.474786	22.849839
7	220.193831	0.498774	123	220.692605	219.695057	441.385209	439.390115
8	214.979753	-0.120580	123	214.859173	215.100333	429.718347	430.200666
9	427.199147	-0.718312	123	426.480834	427.917459	852.961668	855.834918
10	207.636396	0.028019	123	207.664415	207.608378	415.328830	415.216755
11	246.370346	0.412049	123	246.782395	245.958297	493.564791	491.916594
12	472.466460	-0.633447	123	471.833013	473.099907	943.666025	946.199815
13	75.980021	-0.402053	123	75.577968	76.382074	151.155936	152.764148
14	741.842219	0.707269	123	742.549488	741.134949	1485.098976	1482.269899

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	-598.208037	599.096284
6	-11.737393	11.424919
7	-220.692605	219.695057
8	-214.859173	215.100333
9	-426.480834	427.917459
10	-207.664415	207.608378
11	-246.782395	245.958297
12	-471.833013	473.099907
13	-75.577968	76.382074
14	-742.549488	741.134949

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([[-598.20803684,  599.09628434],
       [ -11.73739313,   11.42491935],
       [-220.6926047 ,  219.69505737],
       [-214.85917335,  215.10033311],
       [-426.4808341 ,  427.91745907],
       [-207.66441491,  207.60837761],
       [-246.78239538,  245.95829725],
       [-471.8330126 ,  473.09990735],
       [ -75.57796817,   76.38207398],
       [-742.54948818,  741.13494931]])

In [13]:

get_constraint_data(vocs, data)

get_constraint_data(vocs, data)

Out[13]:

	constraint_e	constraint_f
5	1194.416074	-1198.192569
6	21.474786	-22.849839
7	439.385209	-439.390115
8	427.718347	-430.200666
9	850.961668	-855.834918
10	413.328830	-415.216755
11	491.564791	-491.916594
12	941.666025	-946.199815
13	149.155936	-152.764148
14	1483.098976	-1482.269899

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	0.598652	0.277938
6	0.011581	0.578118
7	0.220194	0.749387
8	0.214980	0.439710
9	0.427199	0.140844
10	0.207636	0.514009
11	0.246370	0.706025
12	0.472466	0.183276
13	0.075980	0.298974
14	0.741842	0.853635

In [16]:

# and denormalize
denormalize_inputs(vocs, normed_data)

# and denormalize denormalize_inputs(vocs, normed_data)

Out[16]:

	a	b
5	598.652161	-0.444124
6	11.581156	0.156237
7	220.193831	0.498774
8	214.979753	-0.120580
9	427.199147	-0.718312
10	207.636396	0.028019
11	246.370346	0.412049
12	472.466460	-0.633447
13	75.980021	-0.402053
14	741.842219	0.707269

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