def train_and_evaluate(self):
all_ids = list(range(1, 2501))
random.shuffle(all_ids)
training_ids, labeling_ids = all_ids[:2250], all_ids[2250:]
with open("{0}/labels.csv".format(self.path), "r") as labels_csv:
reader = csv.DictReader(labels_csv)
for row in reader:
label = row["Prediction"]
filename = "%s/TR/TRAIN_%s.eml" % (path, row["Id"])
if int(row["Id"]) in training_ids:
try:
body = extract_body(filename)
self.naive_bayes.train(int(label), body)
except Exception as e:
logger.info("Error training email %s: %s", row["Id"], e.message)
correct, incorrect = 0, 0
with open("%s/labels.csv" % self.path, "r") as labels_csv:
reader = csv.DictReader(labels_csv)
for row in reader:
label = row["Prediction"]
filename = "%s/TR/TRAIN_%s.eml" % (path, row["Id"])
if int(row["Id"]) in labeling_ids:
try:
test_body = extract_body(filename)
result = self.naive_bayes.classify(test_body)
if result == int(label):
correct += 1
else:
incorrect += 1
except Exception as e:
logger.info("Error classifying email %s: %s", row["Id"], e.message)
return self._calculate_results(correct, incorrect)
def train(self):
with open("{0}/labels.csv".format(self.path), "r") as labels_csv:
reader = csv.DictReader(labels_csv)
for row in reader:
label = row["Prediction"]
filename = "%s/TR/TRAIN_%s.eml" % (path, row["Id"])
try:
body = extract_body(filename)
self.naive_bayes.train(int(label), body)
except Exception as e:
logger.info("Error training email %s: %s", row["Id"], e.message)
def train(self):
with open('%s/labels.csv' % self.path, 'r') as labels_csv:
reader = csv.DictReader(labels_csv)
for row in reader:
label = (row['Prediction'])
filename = '%s/TR/TRAIN_%s.eml' % (path, row['Id'])
try:
body = extract_body(filename)
self.naive_bayes.train(int(label), body)
except Exception as e:
logger.info("Error training email %s: %s", row['Id'],
e.message)
def classify(self, size):
counter = 1
test = self.path + "/TT/TEST_%s.eml"
while counter < size + 1:
try:
test_body = extract_body(test % counter)
self.classified_examples[str(counter)] = str(self.naive_bayes.classify(test_body))
except Exception as e:
logger.info("Error classifying email %s: %s", counter, e.message)
counter += 1
self._store_results()
def classify(self, size):
counter = 1
test = self.path + '/TT/TEST_%s.eml'
while counter < size + 1:
try:
test_body = extract_body(test % counter)
self.classified_examples[str(counter)] = str(
self.naive_bayes.classify(test_body))
except Exception as e:
logger.info("Error classifying email %s: %s", counter,
e.message)
counter += 1
self._store_results()
def train_and_evaluate(self):
all_ids = list(range(1, 2501))
random.shuffle(all_ids)
training_ids, labeling_ids = all_ids[:2250], all_ids[2250:]
with open('%s/labels.csv' % self.path, 'r') as labels_csv:
reader = csv.DictReader(labels_csv)
for row in reader:
label = (row['Prediction'])
filename = '%s/TR/TRAIN_%s.eml' % (path, row['Id'])
if int(row['Id']) in training_ids:
try:
body = extract_body(filename)
self.naive_bayes.train(int(label), body)
except Exception as e:
logger.info("Error training email %s: %s", row['Id'],
e.message)
correct, incorrect = 0, 0
with open('%s/labels.csv' % self.path, 'r') as labels_csv:
reader = csv.DictReader(labels_csv)
for row in reader:
label = (row['Prediction'])
filename = '%s/TR/TRAIN_%s.eml' % (path, row['Id'])
if int(row['Id']) in labeling_ids:
try:
test_body = extract_body(filename)
result = self.naive_bayes.classify(test_body)
if result == int(label):
correct += 1
else:
incorrect += 1
except Exception as e:
logger.info("Error classifying email %s: %s",
row['Id'], e.message)
return self._calculate_results(correct, incorrect)
