def formEnsembleClassifiers(training_class, training_data, max_attribute_values, k, max_run=5):
num_training_data = len(training_class)
ensemble_classifiers = []
errors_Mi = []
tuple_weights = [(1.0 / len(training_data)) for i in range(0, len(training_data))]
#tuple_ids = [i for i in range(0, len(training_class))]
for rk in range(0, k):
run_emis = []
run_classifiers = []
run_predictions = []
run_training_class = []
current_run = 0
while True:
new_training_data = []
new_training_class = []
prefixed_weights = prefixScan(tuple_weights)
for i in range(0, num_training_data):
pick_id = drawRandomPD(prefixed_weights)#random.choice(tuple_ids)
new_training_data.append(training_data[pick_id])
new_training_class.append(training_class[pick_id])
Mi = nb.makeClassifier(new_training_class, new_training_data, max_attribute_values)
predicted_class = nb.predictClass(new_training_data, Mi)
eMi = findMiError(predicted_class, new_training_class, tuple_weights)
if eMi < 0.5:# and (errors_Mi != [] and eMi < min(errors_Mi)):
ensemble_classifiers.append(Mi)
errors_Mi.append(eMi)
break
run_emis.append(eMi)
run_classifiers.append(Mi)
run_predictions.append(predicted_class)
run_training_class.append(new_training_class)
current_run += 1
#
# if current_run == max_run:
# eMi = max(run_emis)
# min_run_id = run_emis.index(eMi)
# ensemble_classifiers.append(run_classifiers[min_run_id])
# predicted_class = run_predictions[min_run_id]
# new_training_class = run_training_class[min_run_id]
# errors_Mi.append(eMi)
# break
print eMi
new_tuple_weights = assignNewTupleWeights(tuple_weights, eMi, predicted_class, new_training_class)
if new_tuple_weights == None:
rk -= 1
continue
tuple_weights = new_tuple_weights
#tuple_ids = makeNewTupleIds(tuple_weights, num_training_data)
return ensemble_classifiers, errors_Mi