param = [0 for i in range(24)]
# print 'Profiling started'
# prof = cProfile.Profile()
# prof.enable()
memm = MEMM(
data,
tag,
all_tag,
param,
wsj.tagged_sents()[:no_of_sentences],
[f1, f2, f3, f4, f5, f6, f7, f8, f9, f10, f11, f12, f13, f14],
0,
)
memm.train()
print "For", memm.num_calls_cost, "calls to cost total time taken is", memm.tot_time_cost
print "Per call avg time taken is", memm.tot_time_cost / memm.num_calls_cost
print "For", memm.num_calls_gradient, "calls to gradient total time taken is", memm.tot_time_gradient
print "Per call avg time taken is", memm.tot_time_gradient / memm.num_calls_gradient
# dt1 = datetime.datetime.now()
# print 'before training: ', dt1
# memm.cost(param)
# dt2 = datetime.datetime.now()
# print 'after training: ', dt2, ' total time = ', (dt2 - dt1).total_seconds()
# prof.disable()
# s = StringIO.StringIO()
# sortby = 'cumulative'
def f9(x, y):
return round(random.random())
def f10(x, y):
return round(random.random())
if __name__ == '__main__':
data, tag = create_dataset()
tag1 = list(set(tag))
punctuations = ['.', ',', ':', ';', '\"', '\'', '``', '\'\'']
all_tag = []
for t in tag1:
if t not in punctuations:
all_tag.append(t)
param = [0 for i in range(10)]
print 'Profiling started'
# prof = cProfile.Profile()
# prof.enable()
memm = MEMM(data, tag, all_tag, param,
[f1, f2, f3, f4, f5, f6, f7, f8, f9, f10], 0)
memm.train()
# prof.disable()
# s = StringIO.StringIO()
# sortby = 'cumulative'
# ps = pstats.Stats(prof, stream=s).sort_stats(sortby)
# ps.print_stats()
# print s.getvalue()
