def start(self):
analyzer = Analyzer('id')
options = []
for k, v in self.labels.items():
opt = '[{}]'.format(Utilities.get_colored_text(v, k))
options.append(v.replace(k, opt) if k in v else "{} {}".format(opt, v))
choices = ', '.join(options)
while self.labeled_num_lines < self.original_num_lines:
line = self.labeled_num_lines + 1
# linecache provides random access to lines in (large) text files
raw_json = linecache.getline(self.dataset + '.json', line)
json_object = json.loads(raw_json)
message = json_object['body']
(label, disp, message) = analyzer.analyze(message)
print(Utilities.get_colored_text('head', '--- Labeling message {} (ID: {}) ---'.format(line, json_object['id'])))
print(message + '\n')
print('Guess: {}'.format(Utilities.get_colored_text(label)))
choice = '?'
while choice != '' and choice not in self.labels:
choice = raw_input('Label (Enter to confirm, or {}): '.format(choices))
if choice == 'q':
return
text = self.labels[choice] if choice is not '' else Utilities.score_to_label(label)
print('You entered: {}\n'.format(Utilities.get_colored_text(text, text)))
json_object['label'] = text
Utilities.write_json(self.dataset + '.labeled.json', json_object, ["id", "label"])
self.labeled_num_lines += 1
def analyze(self, message):
score = 0
found = 0
disp = ""
i = 0
# try:
parts = Utilities.split(message)
# except AttributeError as e:
# print message #None
for w in parts:
if w in self.words:
score += self.words[w]
found += 1
if self.display:
i = message.lower().find(w, i)
d = Utilities.get_colored_text(self.words[w], message[i:i+len(w)])
message = message[:i] + d + message[i+len(w):]
i = i + len(d)
disp += d + " "
label = score / float(found) if found != 0 else 0.0
return (label, disp, message)
def output(self, predictions):
for i in xrange(len(predictions)):
prediction = predictions[i]
message = ""
if self.display:
message = "\t" + Utilities.get_colored_text(prediction, self.test_data[i]).replace('\n', ' ')
g = "{}\t".format(self.test_group[i]) if self.group != "score" else ""
print("{}{:.2f}{}".format(g, prediction, message))
def analyze(self, message):
score = 0
found = 0
disp = ""
i = 0
parts = Utilities.split(message)
for w in parts:
if w in self.words:
score += self.words[w]
found += 1
if self.display:
i = message.lower().find(w, i)
d = Utilities.get_colored_text(self.words[w], message[i:i+len(w)])
message = message[:i] + d + message[i+len(w):]
i = i + len(d)
disp += d + " "
label = score / float(found) if found != 0 else 0.0
return (label, disp, message)
