def batch_test(self, train_file):
try:
self.data_path
except:
print(
"ERROR: invoke batch_input(data_path, start_dir, end_dir) before batch testing"
)
return
self.classifier = Classifier([])
self.parser = Parser()
accuracy = 0
min_accuracy = 100
count = 0
self.classifier.prefetch(*self.fetch(train_file))
for i in self.dirs:
flag = True
path = self.data_path + self.enum(5, i) + "/"
# One initModel.xml per dir
try:
self.parser.parse_initM(path + self.enum(5, i) + ".xml")
except:
flag = False
print("File not found : " + path + self.enum(5, i) + ".xml")
continue
for file in os.listdir(path):
if file.endswith(".aggt"):
try:
if os.stat(path + file + ".plan").st_size != 0:
self.parser.parse_target(path + file)
self.prb_distrb = self.normalize(
self.classifier.predict(self.parser.attr_link +
self.parser.attr_node))
accuracy += self.get_accuracy(path + file +
".plan")
count += 1
except:
pass
print("At dir : ", i)
try:
accuracy /= count
print("Accuracy : " + str(accuracy) + "%")
except ZeroDivisionError:
pass
def mono_test(self, init_file, target_file, train_file):
'''
For singleton testing pass pickled data from train.py . "python fileName initModel.xml target.aggt learning_file"
'''
self.classifier = Classifier([])
self.parser = Parser()
# .xml file
self.parser.parse_initM(init_file)
# .aggt file
self.parser.parse_target(target_file)
# train_file contains relevant trained data (pickled)
self.classifier.prefetch(*self.fetch(train_file))
# for action in self.classifier.action_count:
# print action
# print self.classifier.attr_count[action]
self.classifier.make_square()
return NaiveBayesClassifier(
self.classifier.attr_count,
self.classifier.action_count).predict(self.parser.attr_link +
self.parser.attr_node)
# self.prb_distrb = self.normalize(self.classifier.predict(self.parser.attr_link + self.parser.attr_node))
def mono_test(self, init_file, target_file, train_file):
'''
For singleton testing pass pickled data from train.py . "python fileName initModel.xml target.aggt learning_file"
'''
self.classifier = Classifier([])
self.parser = Parser()
accuracy = 0
min_accuracy = 100
# .xml file
self.parser.parse_initM(init_file)
# .aggt file
self.parser.parse_target(target_file)
# train_file contains relevant trained data (pickled)
self.classifier.prefetch(*self.fetch(train_file))
self.prb_distrb = self.normalize(
self.classifier.predict(self.parser.attr_link +
self.parser.attr_node))
#
# print self.classifier.total_count
#
return self.prb_distrb
def get_distrb(self, targetVariables_types, targetVariables_binary,
targetVariables_unary, train_file):
'''
For singleton testing pass pickled data from train.py . "python fileName initModel.xml target.aggt learning_file"
'''
self.classifier = Classifier([])
self.parser = Parser()
accuracy = 0
min_accuracy = 100
# .xml file
# self.parser.parse_initM(init_file)
# .aggt file
for typeName in list(targetVariables_types):
self.parser.attr_node.append((typeName, typeName))
for var in list(targetVariables_binary):
rel = var[0]
type1 = var[1]
type2 = var[2]
self.parser.attr_link.append((type1, rel, type2))
for id_pair in self.parser.relMap:
if type1 == self.parser.typeMap[id_pair[
0]] and type2 == self.parser.typeMap[id_pair[1]]:
for relation in self.parser.relMap[id_pair]:
self.parser.attr_link.append((type1, relation, type2))
self.parser.attr_link.append(
(type1, relation, rel, type2))
# train_file contains relevant trained data (pickled)
self.classifier.prefetch(*self.fetch(train_file))
self.prb_distrb = self.normalize(
self.classifier.predict(self.parser.attr_link +
self.parser.attr_node))
with ignored(Exception):
del self.prb_distrb['types']
del self.prb_distrb['===']
return self.prb_distrb
# Enter all the directories to be trained here.
start_dir = 1
end_dir = 540
dirs = range(start_dir, end_dir + 1)
def enum(num_digits, count):
numero = [0] * num_digits
for i in range(num_digits):
numero[i] = count % 10
count = int(count / 10)
return ''.join(str(digit) for digit in reversed(numero))
p = Parser()
p.parse_domain(data_path + "domain.aggl")
c = Classifier(p.action_list)
for i in dirs:
path = data_path + enum(5, i) + "/"
# One initModel.xml per dir
flag = True
try:
p.parse_initM(path + enum(5, i) + ".xml")
except:
flag = False
print("File not found : " + path + enum(5, i) + ".xml")
if flag:
for file in os.listdir(path):
if file.endswith(".aggt"):