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	88.265550	0.130760	1234	88.396311	88.134790	176.792621	176.269580
6	514.128139	-0.649280	1234	513.478860	514.777419	1026.957719	1029.554838
7	388.300575	-0.951967	1234	387.348608	389.252541	774.697215	778.505083
8	808.994432	-0.958273	1234	808.036160	809.952705	1616.072319	1619.905410
9	715.343610	-0.156711	1234	715.186899	715.500321	1430.373799	1431.000642
10	521.458748	0.106343	1234	521.565091	521.352405	1043.130181	1042.704811
11	15.915948	-0.431274	1234	15.484674	16.347222	30.969348	32.694443
12	684.997792	0.790394	1234	685.788186	684.207397	1371.576372	1368.414795
13	924.539210	0.918710	1234	925.457919	923.620500	1850.915839	1847.241000
14	692.592235	-0.469057	1234	692.123179	693.061292	1384.246357	1386.122585

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	-88.396311	88.134790
6	-513.478860	514.777419
7	-387.348608	389.252541
8	-808.036160	809.952705
9	-715.186899	715.500321
10	-521.565091	521.352405
11	-15.484674	16.347222
12	-685.788186	684.207397
13	-925.457919	923.620500
14	-692.123179	693.061292

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	-88.396311	88.134790
6	-513.478860	514.777419
7	-387.348608	389.252541
8	-808.036160	809.952705
9	-715.186899	715.500321
10	-521.565091	521.352405
11	-15.484674	16.347222
12	-685.788186	684.207397
13	-925.457919	923.620500
14	-692.123179	693.061292

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([[ -88.39631051,   88.13478981],
       [-513.47885972,  514.77741905],
       [-387.34860763,  389.25254146],
       [-808.0361596 ,  809.95270489],
       [-715.18689947,  715.500321  ],
       [-521.56509071,  521.35240537],
       [ -15.48467381,   16.34722152],
       [-685.78818594,  684.20739743],
       [-925.45791949,  923.62049982],
       [-692.12317852,  693.06129245]])

In [14]:

vocs.constraint_data(data)

vocs.constraint_data(data)

Out[14]:

	constraint_e	constraint_f
5	174.792621	-176.269580
6	1024.957719	-1029.554838
7	772.697215	-778.505083
8	1614.072319	-1619.905410
9	1428.373799	-1431.000642
10	1041.130181	-1042.704811
11	28.969348	-32.694443
12	1369.576372	-1368.414795
13	1848.915839	-1847.241000
14	1382.246357	-1386.122585

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	0.088266	0.565380
6	0.514128	0.175360
7	0.388301	0.024017
8	0.808994	0.020864
9	0.715344	0.421645
10	0.521459	0.553171
11	0.015916	0.284363
12	0.684998	0.895197
13	0.924539	0.959355
14	0.692592	0.265472

In [17]:

# and denormalize
vocs.denormalize_inputs(normed_data)

# and denormalize vocs.denormalize_inputs(normed_data)

Out[17]:

	a	b
5	88.265550	0.130760
6	514.128139	-0.649280
7	388.300575	-0.951967
8	808.994432	-0.958273
9	715.343610	-0.156711
10	521.458748	0.106343
11	15.915948	-0.431274
12	684.997792	0.790394
13	924.539210	0.918710
14	692.592235	-0.469057

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