def execute_all(method, template, show_images):
""" Start a benchmark for the given method for every avaiable file. """
benchmark = Benchmark(method(), template)
benchmark.execute_all(show_images)
print "Recall: " + str(benchmark.recall())
print "Precision: " + str(benchmark.precision())
print "F-Measure: " + str(benchmark.fmeasure())
def execute_all(method, template, show_images):
""" Start a benchmark for the given method for every avaiable file. """
benchmark = Benchmark(method(), template)
benchmark.execute_all(show_images)
print "Recall: " + str(benchmark.recall())
print "Precision: " + str(benchmark.precision())
print "F-Measure: " + str(benchmark.fmeasure())
#
from benchmark import Benchmark
def bmm_seg(sentence, word_bank, max_len=100):
seg = []
ind = 0 if len(sentence) < max_len else len(sentence) - max_len
while (len(sentence)):
while (ind != len(sentence) and sentence[ind:] not in word_bank):
ind += 1
if ind == len(sentence):
ind = len(sentence) - 1
seg.append(sentence[ind:])
sentence = sentence[:ind]
ind = 0 if len(sentence) < max_len else len(sentence) - max_len
seg.reverse()
return seg
if __name__ == '__main__':
bmm_model = Benchmark('bmm')
sentences, word_bank, max_len = bmm_model.get_data()
for sentence, ans in sentences:
seg = bmm_seg(sentence, word_bank, max_len)
bmm_model.add(seg, ans)
bmm_model.precision()
bmm_model.recall()
bmm_model.F_measure()
# An instance of Backward Maximum Match Algorithm
# All right reversd.
# Hank Wang @bupt
#
from benchmark import Benchmark
def fmm_seg(sentence,word_bank,max_len=100):
seg = []
ind=len(sentence) if len(sentence)<max_len else max_len
while (len(sentence)):
while (ind and sentence[:ind] not in word_bank):
ind-=1
if ind==0:
ind=1
seg.append(sentence[:ind])
sentence = sentence[ind:]
ind=len(sentence) if len(sentence)<max_len else max_len
return seg
if __name__ == '__main__':
fmm_model = Benchmark('fmm')
sentences, word_bank, max_len = fmm_model.get_data()
for sentence,ans in sentences:
seg = fmm_seg(sentence,word_bank,max_len)
fmm_model.add(seg,ans)
fmm_model.precision()
fmm_model.recall()
fmm_model.F_measure()
#
import random
from benchmark import Benchmark
from bmm import bmm_seg
from fmm import fmm_seg
def bdmm_seg(sentence, word_bank, max_len=100, unit=3):
seg1 = fmm_seg(sentence, word_bank, max_len)
seg2 = bmm_seg(sentence, word_bank, max_len)
if len(seg1) == len(seg2):
best_seg = seg1 if random.randint(0, 1) == 0 else seg2
elif len([x for x in seg1 if len(x) == unit]) < len(
[x for x in seg2 if len(x) == unit]):
best_seg = seg1
else:
best_seg = seg2
return best_seg
if __name__ == '__main__':
bdmm_model = Benchmark('bdmm')
sentences, word_bank, max_len = bdmm_model.get_data()
for sentence, ans in sentences:
seg = bdmm_seg(sentence, word_bank, max_len)
bdmm_model.add(seg, ans)
bdmm_model.precision()
bdmm_model.recall()
bdmm_model.F_measure()
