def data_mining_run(designs, behavioral, non_behavioral, context):
client = DataMiningClient()
try:
# Start connection with data_mining
client.startConnection()
support_threshold = 0.002
confidence_threshold = 0.2
lift_threshold = 1
# features = client.getDrivingFeatures(behavioral, non_behavioral, designs, support_threshold, confidence_threshold, lift_threshold)
features = client.runAutomatedLocalSearch(behavioral, non_behavioral,
designs, support_threshold,
confidence_threshold,
lift_threshold)
# End the connection before return statement
client.endConnection()
result = []
max_features = 3
if len(features) > 3:
pass
else:
max_features = len(features)
for i in range(
max_features): # Generate answers for the first 3 features
advice = feature_expression_to_string(features[i]['name'], context)
result.append({"type": "Analyzer", "advice": advice})
return result
except Exception:
logger.exception('Exception in running data mining')
client.endConnection()
return None
def analyst_critic(self, this_design):
result = []
client = DataMiningClient()
problem = self.context.eosscontext.problem
if problem in self.assignation_problems:
problem_type = 'binary'
elif problem in self.partition_problems:
problem_type = 'discrete'
else:
problem_type = 'unknown'
try:
# Start connection with data_mining
client.startConnection()
support_threshold = 0.02
confidence_threshold = 0.2
lift_threshold = 1
behavioral = []
non_behavioral = []
dataset = Design.objects.filter(
eosscontext_id__exact=self.context.eosscontext.id).all()
if len(dataset) < 10:
raise ValueError(
"Could not run data mining: the number of samples is less than 10"
)
else:
utopiaPoint = [0.26, 0]
temp = []
# Select the top N% archs based on the distance to the utopia point
for design in dataset:
outputs = json.loads(this_design.outputs)
id = design.id
dist = math.sqrt((outputs[0] - utopiaPoint[0])**2 +
(outputs[1] - utopiaPoint[1])**2)
temp.append((id, dist))
# Sort the list based on the distance to the utopia point
temp = sorted(temp, key=lambda x: x[1])
for i in range(len(temp)):
if i <= len(
temp
) // 10: # Label the top 10% architectures as behavioral
behavioral.append(temp[i][0])
else:
non_behavioral.append(temp[i][0])
# Extract feature
# features = client.getDrivingFeatures(behavioral, non_behavioral, designs, support_threshold, confidence_threshold, lift_threshold)
features = client.runAutomatedLocalSearch(
problem, problem_type, behavioral, non_behavioral, dataset,
support_threshold, confidence_threshold, lift_threshold)
advices = []
if not len(features) == 0:
# Compare features to the current design
unsatisfied = get_feature_unsatisfied(features[0]['name'],
this_design,
self.context)
satisfied = get_feature_satisfied(features[0]['name'],
this_design, self.context)
if type(unsatisfied) is not list:
unsatisfied = [unsatisfied]
if type(satisfied) is not list:
satisfied = [satisfied]
for exp in unsatisfied:
if exp == "":
continue
advices.append(
"Based on the data mining result, I advise you to make the following change: "
+ feature_expression_to_string(
exp, is_critique=True, context=self.context))
for exp in satisfied:
if exp == "":
continue
advices.append(
"Based on the data mining result, these are the good features. Consider keeping them: "
+ feature_expression_to_string(
exp, is_critique=False, context=self.context))
# End the connection before return statement
client.endConnection()
for i in range(
len(advices)): # Generate answers for the first 5 features
advice = advices[i]
result.append({"type": "Analyst", "advice": advice})
except Exception as e:
print("Exc in generating critic from data mining: " + str(e))
traceback.print_exc(file=sys.stdout)
client.endConnection()
return result