def contains_training_instance(self, part):
try:
part = delete(part, self.fitness.exclude_from_regression, 0)
except:
pass
contains, index = numpy_array_index(self.training_set, part)
return contains
def get_training_instance(self, part):
contains, index = numpy_array_index(self.training_set, part)
if self.training_set is None:
logging.error('cannot call get_training_instance if training_set is empty')
return False
elif contains:
return self.training_fitness[index]
else :
logging.error('cannot call get_training_instance if training_set does not contain the particle')
return False
def get_training_instance(self, part):
try:
part = delete(part, self.fitness.exclude_from_regression, 0)
except:
pass
contains, index = numpy_array_index(self.training_set, part)
if self.training_set is None:
logging.error("cannot call get_training_instance if training_set is empty")
return False
elif contains:
return self.training_fitness[index]
else:
logging.error("cannot call get_training_instance if training_set does not contain the particle")
return False
def bitstream_was_generated(self, part):
software_axis = [i for i, dimension in enumerate(self.fitness.designSpace) if dimension["set"] == "s"]
pruned_training_set = delete(self.hard_regressor.get_training_set(),software_axis,1)
pruned_part = delete([part],software_axis,1)
contains, index = numpy_array_index(pruned_training_set, pruned_part[0])
return contains
def contains_training_instance(self, part):
contains, index = numpy_array_index(self.training_set, part)
return contains