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	677.206382	0.349897	1234	677.556279	676.856485	1355.112558	1353.712970
6	640.383761	-0.122515	1234	640.261246	640.506277	1280.522493	1281.012553
7	21.886752	-0.733619	1234	21.153133	22.620370	42.306265	45.240741
8	771.002422	0.757296	1234	771.759718	770.245127	1543.519436	1540.490253
9	172.645586	-0.014281	1234	172.631305	172.659867	345.262610	345.319735
10	246.693018	-0.992276	1234	245.700742	247.685294	491.401483	495.370589
11	3.109655	-0.497302	1234	2.612353	3.606957	5.224706	7.213914
12	245.394749	-0.975014	1234	244.419736	246.369763	488.839471	492.739526
13	149.887366	0.760326	1234	150.647693	149.127040	301.295385	298.254080
14	941.212874	0.780296	1234	941.993169	940.432578	1883.986339	1880.865156

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	-677.556279	676.856485
6	-640.261246	640.506277
7	-21.153133	22.620370
8	-771.759718	770.245127
9	-172.631305	172.659867
10	-245.700742	247.685294
11	-2.612353	3.606957
12	-244.419736	246.369763
13	-150.647693	149.127040
14	-941.993169	940.432578

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	-677.556279	676.856485
6	-640.261246	640.506277
7	-21.153133	22.620370
8	-771.759718	770.245127
9	-172.631305	172.659867
10	-245.700742	247.685294
11	-2.612353	3.606957
12	-244.419736	246.369763
13	-150.647693	149.127040
14	-941.993169	940.432578

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([[-677.55627895,  676.85648497],
       [-640.26124637,  640.50627655],
       [ -21.15313259,   22.62037049],
       [-771.7597181 ,  770.24512668],
       [-172.63130502,  172.65986741],
       [-245.70074162,  247.68529437],
       [  -2.61235303,    3.6069568 ],
       [-244.41973571,  246.36976293],
       [-150.64769257,  149.12704009],
       [-941.99316938,  940.43257794]])

In [14]:

vocs.constraint_data(data)

vocs.constraint_data(data)

Out[14]:

	constraint_e	constraint_f
5	1353.112558	-1353.712970
6	1278.522493	-1281.012553
7	40.306265	-45.240741
8	1541.519436	-1540.490253
9	343.262610	-345.319735
10	489.401483	-495.370589
11	3.224706	-7.213914
12	486.839471	-492.739526
13	299.295385	-298.254080
14	1881.986339	-1880.865156

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	0.677206	0.674948
6	0.640384	0.438742
7	0.021887	0.133191
8	0.771002	0.878648
9	0.172646	0.492859
10	0.246693	0.003862
11	0.003110	0.251349
12	0.245395	0.012493
13	0.149887	0.880163
14	0.941213	0.890148

In [17]:

# and denormalize
vocs.denormalize_inputs(normed_data)

# and denormalize vocs.denormalize_inputs(normed_data)

Out[17]:

	a	b
5	677.206382	0.349897
6	640.383761	-0.122515
7	21.886752	-0.733619
8	771.002422	0.757296
9	172.645586	-0.014281
10	246.693018	-0.992276
11	3.109655	-0.497302
12	245.394749	-0.975014
13	149.887366	0.760326
14	941.212874	0.780296

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