def _getSamples(w):
nonlocal idf
global df
if idf is None:
idf = ef.get_idf(fm.getFile('building'), fm.getFile('idd'),
fm.getFile('epw'))
with results:
print('Simulating...')
df = sampling.dist_sampler(samplerType.value, transformers,
samplesBox.value)
df['energy use'] = ef.Evaluator(transformers, idf).df_apply(df)
print('Done')
display(df)
def test_init(building, parameters):
"""Testing the initialization and functionality of an adaptive surrogate model"""
problem = EPProblem(parameters)
evaluator = EvaluatorEP(problem, building)
inputs = sampling.dist_sampler(sampling.seeded_sampler, problem, 10)
inputs = sampling.add_extremes(inputs, problem)
#using the custom class for our own model training
k = KirgingEval(reference=evaluator)
k.do_infill(inputs)
k.model.train()
k.infill(5)
#change this to 0 to see stdout and stderr
assert 1
def test_objectives(building, parameters):
"""Testing custom functions and basic objective creation"""
def variance(result):
return result.data['Value'].var()
objectives = [MeterReader('Electricity:Facility', name='Electricity Usage'),
MeterReader('Electricity:Facility',func=variance, name='Electricity Variance')]
problem = EPProblem(inputs=parameters, outputs=objectives)
evaluator = EvaluatorEP(problem, building)
samples = sampling.dist_sampler(sampling.seeded_sampler, problem, 10)
results = evaluator.df_apply(samples, keep_input=True)
value = results.iloc[0]['Electricity Variance']
assert np.isclose(value, 829057663033101.1), f'Unexpected value when using custom function:{value}'
#change this to 0 to see stdout and stderr
assert 1
def test_custom_evaluation():
"""check to see if descriptors display as intended, and check to make sure custom evaluations work with EvaluatorSR"""
#create the descriptors
zero_to_nine = RangeParameter(min_val = 0, max_val=9)
single_digit_integers = CategoryParameter(options=[0,1,2,3,4,5,6,7,8,9])
text_example = CategoryParameter(options=['a', 'b', 'c', 'other'])
#create the parameters and the problem
parameters = [
Parameter(value_descriptor=zero_to_nine, name='0-9'),
Parameter(value_descriptor=single_digit_integers, name='single digit'),
Parameter(value_descriptor=text_example, name='text')
]
problem = Problem(parameters, outputs=['output'])
#create the sampling distribution (seeded with only one output that should give 4.939321535345923 7 c 34.575251 after evaluating)
samples = sampling.dist_sampler(sampling.seeded_sampler, problem, num_samples=1)
values = [samples.iloc[0]['0-9'], samples.iloc[0]['single digit'], samples.iloc[0]['text']]
assert np.isclose(values[0], 4.939321535345923) and values[1:] == [7, 'c'], f'Unexpected sample values: {values}'
#custom evaluation function from the jupyter notebook
def evaluation_function(values):
x,y,z = values
if z == 'other':
return (0,), ()
else:
return (x * y,), ()
evaluator = EvaluatorSR(evaluation_function, problem)
# The evaluator will use this objective by default
outputs = evaluator.df_apply(samples ,keep_input=True)
result = outputs.iloc[0]['output']
print(result)
assert np.isclose(result, 34.57525074742146), f'Unexpected evaluation result: {result}'
#change this to 0 to see stdout and stderr
assert 1
def samples(problem):
samples = sampling.dist_sampler(sampling.seeded_sampler, problem, 10)
return samples
def samples(problem):
#seeded_sampler results in indexes 0-3 being Invalid Material and 4 being HW CONCRETE
samples = sampling.dist_sampler(sampling.seeded_sampler, problem, 5)
return samples