from src.neti_neti_trainer import NetiNetiTrainer
from src.neti_neti import NetiNeti
if __name__ == '__main__':
print "Running NetiNeti Training, it might take a while..."
nnt = NetiNetiTrainer()
nn = NetiNeti(nnt)
print nn.find_names(
"A frog-killing fungus known as Batrachochytrium dendrobatidis, or Bd, has already led to the decline of more than 200 amphibian species including the now extinct-in-the-wild Panamanian golden frog."
)
self.end_headers()
self.wfile.write('hello world')
def do_POST(self):
form = cgi.FieldStorage(fp=self.rfile,
headers=self.headers,
environ={
'REQUEST_METHOD': 'POST',
'CONTENT_TYPE':
self.headers['Content-Type'],
})
self.send_response(200)
self.end_headers()
self.wfile.write(nn.find_names(form['data'].value))
return
def run(server_class=HTTPServer, handler_class=MyHandler):
server_address = (HOST, PORT)
print('Starting server, use <Ctrl-C> to stop')
httpd = server_class(server_address, handler_class)
httpd.serve_forever()
if __name__ == '__main__':
print "Running NetiNeti Training, it might take a while..."
nnt = NetiNetiTrainer()
nn = NetiNeti(nnt)
run()
# calculate the standard deviation of a population
# accepts: an array, the population
# returns: the standard deviation
def standard_deviation(population):
if len(population) == 1:
return 0
return math.sqrt(variance(population))
population = []
time_start = time.clock()
classifier = NetiNetiTrainer()
time_training = time.clock()
print ("Training time: %s" % (time_training - time_start))
nn = NetiNeti(classifier)
for i in range(1, num_cycles):
print ("going through the cycle %s" % i)
time_start = time.clock()
result = nn.find_names(open("data/test.txt").read())
print ("Name finding time: %s" % (time.clock() - time_start))
test_result_file = open("data/test_result_after_refactoring.txt", 'w')
for i in result[1]:
test_result_file.write(i + "\n")
test_result_file.close()
args = shlex.split('diff -d data/test_result_before_refactoring.txt data/test_result_after_refactoring.txt')
result = subprocess.Popen(args, stdout = subprocess.PIPE, stderr= subprocess.PIPE).communicate()
from src.neti_neti_trainer import NetiNetiTrainer
from src.neti_neti import NetiNeti
if __name__ == '__main__':
print "Running NetiNeti Training, it might take a while..."
nnt = NetiNetiTrainer()
nn = NetiNeti(nnt)
print nn.find_names("A frog-killing fungus known as Batrachochytrium dendrobatidis, or Bd, has already led to the decline of more than 200 amphibian species including the now extinct-in-the-wild Panamanian golden frog.")
from src.neti_neti_trainer import NetiNetiTrainer
from src.neti_neti import NetiNeti
from glob import glob
import sys
import os
nnt = NetiNetiTrainer()
nn = NetiNeti(nnt)
if len(sys.argv) >= 2:
input_dir = sys.argv[1]
result = []
for document in glob(os.path.join(input_dir, "*.txt")):
with open(document, 'rb') as f:
data = unicode(f.read(), 'utf8')
#data = data.replace("\r\n", "\n")
res = nn.find_names(data)
result += [os.path.basename(document) + " {}".format(res)]
print("\t".join(result))