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 form_objective_data
import pandas as pd
import numpy as np

from xopt.vocs import VOCS from xopt.vocs import form_objective_data import pandas as pd import numpy as np

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: 1234

"""

vocs = VOCS.from_yaml(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: 1234 """ vocs = VOCS.from_yaml(Y) vocs

Out[2]:

VOCS(variables={'a': (0.0, 1000.0), 'b': (-1.0, 1.0)}, constraints={'e': ('LESS_THAN', 2.0), 'f': ('GREATER_THAN', 0.0)}, objectives={'c': 'MAXIMIZE', 'd': 'MINIMIZE'}, constants={'g': 1234}, observables=[])

In [3]:

# as dict
dict(vocs)

# as dict dict(vocs)

Out[3]:

{'variables': {'a': (0.0, 1000.0), 'b': (-1.0, 1.0)},
 'constraints': {'e': ('LESS_THAN', 2.0), 'f': ('GREATER_THAN', 0.0)},
 'objectives': {'c': 'MAXIMIZE', 'd': 'MINIMIZE'},
 'constants': {'g': 1234},
 'observables': []}

In [4]:

#  re-parse dict
vocs2 = VOCS.from_dict(dict(vocs))

# re-parse dict vocs2 = VOCS.from_dict(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': (0.0, 1000.0), 'b': (-1.0, 1.0)}

In [7]:

vocs.objectives["c"] == "MAXIMIZE"

vocs.objectives["c"] == "MAXIMIZE"

Out[7]:

True

In [8]:

# json
vocs.to_json()

# json vocs.to_json()

Out[8]:

'{"variables":{"a":[0.0,1000.0],"b":[-1.0,1.0]},"constraints":{"e":["LESS_THAN",2.0],"f":["GREATER_THAN",0.0]},"objectives":{"c":"MAXIMIZE","d":"MINIMIZE"},"constants":{"g":1234},"observables":[]}'

Objective Evaluation¶

In [9]:

data = pd.DataFrame(vocs.random_inputs(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(vocs.random_inputs(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[9]:

	a	b	g	c	d	e	f
5	149.301121	0.789104	1234	150.090224	148.512017	300.180448	297.024034
6	161.256076	-0.589203	1234	160.666873	161.845279	321.333745	323.690557
7	938.235497	-0.317351	1234	937.918147	938.552848	1875.836294	1877.105696
8	435.604227	0.200648	1234	435.804875	435.403579	871.609749	870.807158
9	173.347787	-0.126612	1234	173.221175	173.474398	346.442350	346.948797
10	747.584289	-0.471892	1234	747.112397	748.056181	1494.224794	1496.112362
11	296.482495	-0.115261	1234	296.367234	296.597757	592.734468	593.195514
12	192.259903	0.040091	1234	192.299994	192.219812	384.599988	384.439624
13	69.311679	0.011982	1234	69.323661	69.299697	138.647322	138.599393
14	384.344417	-0.261956	1234	384.082461	384.606373	768.164923	769.212746

In [10]:

vocs.objectives

vocs.objectives

Out[10]:

{'c': 'MAXIMIZE', 'd': 'MINIMIZE'}

In [11]:

# These are in standard form for minimization
form_objective_data(vocs.objectives, data)

# These are in standard form for minimization form_objective_data(vocs.objectives, data)

Out[11]:

	objective_c	objective_d
5	-150.090224	148.512017
6	-160.666873	161.845279
7	-937.918147	938.552848
8	-435.804875	435.403579
9	-173.221175	173.474398
10	-747.112397	748.056181
11	-296.367234	296.597757
12	-192.299994	192.219812
13	-69.323661	69.299697
14	-384.082461	384.606373

In [12]:

# This is also available as a method
vocs.objective_data(data)

# This is also available as a method vocs.objective_data(data)

Out[12]:

	objective_c	objective_d
5	-150.090224	148.512017
6	-160.666873	161.845279
7	-937.918147	938.552848
8	-435.804875	435.403579
9	-173.221175	173.474398
10	-747.112397	748.056181
11	-296.367234	296.597757
12	-192.299994	192.219812
13	-69.323661	69.299697
14	-384.082461	384.606373

In [13]:

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

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

Out[13]:

array([[-150.09022424,  148.51201678],
       [-160.66687258,  161.8452786 ],
       [-937.91814694,  938.55284805],
       [-435.80487457,  435.40357914],
       [-173.22117499,  173.47439831],
       [-747.11239683,  748.05618119],
       [-296.36723393,  296.59775685],
       [-192.29999407,  192.2198119 ],
       [ -69.32366102,   69.29969668],
       [-384.08246139,  384.60637304]])

In [14]:

vocs.constraint_data(data)

vocs.constraint_data(data)

Out[14]:

	constraint_e	constraint_f
5	298.180448	-297.024034
6	319.333745	-323.690557
7	1873.836294	-1877.105696
8	869.609749	-870.807158
9	344.442350	-346.948797
10	1492.224794	-1496.112362
11	590.734468	-593.195514
12	382.599988	-384.439624
13	136.647322	-138.599393
14	766.164923	-769.212746

In [15]:

vocs.feasibility_data(data)

vocs.feasibility_data(data)

Out[15]:

	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 [16]:

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

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

Out[16]:

	a	b
5	0.149301	0.894552
6	0.161256	0.205398
7	0.938235	0.341325
8	0.435604	0.600324
9	0.173348	0.436694
10	0.747584	0.264054
11	0.296482	0.442369
12	0.192260	0.520046
13	0.069312	0.505991
14	0.384344	0.369022

In [17]:

# and denormalize
vocs.denormalize_inputs(normed_data)

# and denormalize vocs.denormalize_inputs(normed_data)

Out[17]:

	a	b
5	149.301121	0.789104
6	161.256076	-0.589203
7	938.235497	-0.317351
8	435.604227	0.200648
9	173.347787	-0.126612
10	747.584289	-0.471892
11	296.482495	-0.115261
12	192.259903	0.040091
13	69.311679	0.011982
14	384.344417	-0.261956

Error handling¶

In [18]:

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.from_yaml(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.from_yaml(Y)

In [19]:

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[19]:

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

In [20]:

data["a"] = np.nan

data["a"] = np.nan

In [21]:

a = 2


def f(x=a):
    return x


a = 99
f()

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

Out[21]:

2

In [22]:

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

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

Out[22]:

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

In [23]:

# These are in standard form for minimization

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

form_objective_data(vocs.objectives, data)

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

Out[23]:

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