def evaluate(self):
"""
Display all tweets collected for training
"""
self.process_tweets()
cli = Cli()
cli.training_title()
for t in self.tweets:
print "@%s say:" % t['user']
print "\n"
print t['original']
cli.training()
evaluation = cli.waiting_input()
t['evaluation'] = evaluation[0]
if t['evaluation'] != 4:
self.tuples.append(t)
cli.divider()
cli.clear_terminal()
cli.dashboard()
return self.tuples
def training():
data = Storage('collected').load()
tweets = Training(data).evaluate()
Storage('trained').save(tweets)
def prediction():
collect_files = Storage('collected').load()
trained_files = Storage('trained').load()
Mining(collect_files, trained_files).start()
if __name__ == '__main__':
"""
Human-Machine Interface
"""
cli = Cli()
start(cli)
while cli.option != 'x':
if cli.option == 'h':
display_help(cli)
elif cli.option == 'c' or cli.option == "collect":
collect(cli)
elif cli.option == 't' or cli.option == "training":
training()
elif cli.option == 'p' or cli.option == "prediction":
prediction()
elif cli.option == 'tweets':
data = Storage('collected').load()
cli.tweets_colleted(data)
elif cli.option == 'tweets trained':
def evaluate(self):
"""
Display all tweets collected for training
"""
self.process_tweets()
cli = Cli()
cli.training_title()
for t in self.tweets:
print "@%s say:" % t['user']
print "\n"
print t['original']
cli.training()
evaluation = cli.waiting_input()
t['evaluation'] = evaluation[0]
if t['evaluation'] != 4:
self.tuples.append(t)
cli.divider()
cli.clear_terminal()
cli.dashboard()
return self.tuples
tweets = Training(data).evaluate()
Storage('trained').save(tweets)
def prediction():
collect_files = Storage('collected').load()
trained_files = Storage('trained').load()
Mining(collect_files, trained_files).start()
if __name__ == '__main__':
"""
Human-Machine Interface
"""
cli = Cli()
start(cli)
while cli.option != 'x':
if cli.option == 'h':
display_help(cli)
elif cli.option == 'c' or cli.option == "collect":
collect(cli)
elif cli.option == 't' or cli.option == "training":
training()
elif cli.option == 'p' or cli.option == "prediction":
prediction()
elif cli.option == 'tweets':
data = Storage('collected').load()
cli.tweets_colleted(data)
elif cli.option == 'tweets trained':
