def main():
tool.preprocess('../data/POS/train', '../data/POS/ptrain')
tool.preprocess('../data/NPC/train', '../data/NPC/ptrain')
e0 = em.emission()
t0 = tr.transition()
print "without preprocessor"
e0.compute('../data/POS/train')
t0.compute('../data/POS/train')
e0.predict('../data/POS/dev.in','../data/POS/dev.p2.out',p=False)
print "POS,MLE:", tool.evaluate('../data/POS/dev.p2.out','../data/POS/dev.out')
viterbi_best(e0,t0,'../data/POS/dev.in','../data/POS/dev.p3.out',p=False)
print "POS,DP:", tool.evaluate('../data/POS/dev.p3.out','../data/POS/dev.out')
def main():
tool.preprocess('../data/POS/train', '../data/POS/ptrain')
tool.preprocess('../data/NPC/train', '../data/NPC/ptrain')
e0 = em.emission()
bt0 = bitr.bi_transition()
tt0 = tritr.tri_transition()
# print "without preprocessor"
# e0.compute('../data/POS/train')
# t0.compute('../data/POS/train')
# e0.predict('../data/POS/dev.in','../data/POS/dev.p2.out',p=False)
# print "POS,MLE:", tool.evaluate('../data/POS/dev.p2.out','../data/POS/dev.out')
# print "POS,MLE likelihood:", e0.filelikelihood("../data/POS/dev.p2.out",p=False)
# viterbi_best(e0,t0,'../data/POS/dev.in','../data/POS/dev.p3.out',p=False)
# print "POS,DP:", tool.evaluate('../data/POS/dev.p3.out','../data/POS/dev.out')
# print "POS,DP likelihood:", e0.filelikelihood("../data/POS/dev.p3.out", p=False)
# start = time.clock()
# viterbi_Nbest(e0, t0, '../data/POS/dev.in', '../data/POS/dev.p4.out', best=1, p=False)
# print "runtime:",time.clock()-start
# c = 1
# while c<=1:
# print c,":POS, DP2:", tool.evaluate('../data/POS/dev.p4.out', '../data/POS/dev.out',col=c)
# print c,":POS, DP2 likelihood:", e0.filelikelihood("../data/POS/dev.p4.out",p=False, col=c)
# c+=1
print "with preprocessor"
e0.compute('../data/POS/ptrain')
bt0.compute('../data/POS/ptrain')
tt0.compute('../data/POS/ptrain')
# e0.predict('../data/POS/test.in','../data/POS/test.p1.out')
# era,eno= tool.evaluate('../data/POS/dev.p2.out','../data/POS/dev.out',col=1,pr=True)
# print "error rate:",era
# print "POS, MLE, likelihood:",e0.filelikelihood("../data/POS/dev.p2.out")
# with new smoothing 0.27637
# viterbi_best(e0,bt0,'../data/POS/dev.in','../data/POS/dev.p2.out')
# era,eno = tool.evaluate('../data/POS/dev.p2.out','../data/POS/dev.out',pr=True)
# print "POS, DP:", era
# print "POS, DP likelihood:", e0.filelikelihood("../data/POS/dev.p3.out")
# start = time.clock()
# 0.5 1.5 0: 0.2574
# 1 10 1: 0.2422
# 1 15 1: 0.2422
# 1 20 1: 0.239
# 1 25 1: 0.2369
# 1 30 1: 0.235
# 1 35 1: 0.2334
# viterbi_Nbest(e0, bt0, tt0, '../data/POS/dev.in', '../data/POS/dev.p5.out',lambda0=1.0, lambda1=30.0, lambda2=1.0, best=1)
# print "runtime:",time.clock() - start
c = 1
while c <= 1:
era, eno = tool.evaluate('../data/POS/dev.p5.out',
'../data/POS/dev.out',
col=c,
pr=True)
print c, ":POS, DP2:", era # print c,":POS, DP2 likelihood:", e0.filelikelihood("../data/POS/dev.p4.out",col=c)
c += 1
def main():
tool.preprocess('../data/POS/train', '../data/POS/ptrain')
tool.preprocess('../data/NPC/train', '../data/NPC/ptrain')
e0 = em.emission()
t0 = tr.transition()
print "without preprocessor"
e0.compute('../data/POS/train')
t0.compute('../data/POS/train')
e0.predict('../data/POS/dev.in', '../data/POS/dev.p2.out', p=False)
print "POS,MLE:", tool.evaluate('../data/POS/dev.p2.out',
'../data/POS/dev.out')
viterbi_best(e0,
t0,
'../data/POS/dev.in',
'../data/POS/dev.p3.out',
p=False)
print "POS,DP:", tool.evaluate('../data/POS/dev.p3.out',
'../data/POS/dev.out')
def main():
tool.preprocess('../data/POS/train', '../data/POS/ptrain')
tool.preprocess('../data/NPC/train', '../data/NPC/ptrain')
e0 = em.emission()
bt0 = bitr.bi_transition()
tt0 = tritr.tri_transition()
# print "without preprocessor"
# e0.compute('../data/POS/train')
# t0.compute('../data/POS/train')
# e0.predict('../data/POS/dev.in','../data/POS/dev.p2.out',p=False)
# print "POS,MLE:", tool.evaluate('../data/POS/dev.p2.out','../data/POS/dev.out')
# print "POS,MLE likelihood:", e0.filelikelihood("../data/POS/dev.p2.out",p=False)
# viterbi_best(e0,t0,'../data/POS/dev.in','../data/POS/dev.p3.out',p=False)
# print "POS,DP:", tool.evaluate('../data/POS/dev.p3.out','../data/POS/dev.out')
# print "POS,DP likelihood:", e0.filelikelihood("../data/POS/dev.p3.out", p=False)
# start = time.clock()
# viterbi_Nbest(e0, t0, '../data/POS/dev.in', '../data/POS/dev.p4.out', best=1, p=False)
# print "runtime:",time.clock()-start
# c = 1
# while c<=1:
# print c,":POS, DP2:", tool.evaluate('../data/POS/dev.p4.out', '../data/POS/dev.out',col=c)
# print c,":POS, DP2 likelihood:", e0.filelikelihood("../data/POS/dev.p4.out",p=False, col=c)
# c+=1
print "with preprocessor"
e0.compute('../data/POS/ptrain')
bt0.compute('../data/POS/ptrain')
tt0.compute('../data/POS/ptrain')
# e0.predict('../data/POS/test.in','../data/POS/test.p1.out')
# era,eno= tool.evaluate('../data/POS/dev.p2.out','../data/POS/dev.out',col=1,pr=True)
# print "error rate:",era
# print "POS, MLE, likelihood:",e0.filelikelihood("../data/POS/dev.p2.out")
# with new smoothing 0.27637
# viterbi_best(e0,bt0,'../data/POS/dev.in','../data/POS/dev.p2.out')
# era,eno = tool.evaluate('../data/POS/dev.p2.out','../data/POS/dev.out',pr=True)
# print "POS, DP:", era
# print "POS, DP likelihood:", e0.filelikelihood("../data/POS/dev.p3.out")
# start = time.clock()
# 0.5 1.5 0: 0.2574
# 1 10 1: 0.2422
# 1 15 1: 0.2422
# 1 20 1: 0.239
# 1 25 1: 0.2369
# 1 30 1: 0.235
# 1 35 1: 0.2334
# viterbi_Nbest(e0, bt0, tt0, '../data/POS/dev.in', '../data/POS/dev.p5.out',lambda0=1.0, lambda1=30.0, lambda2=1.0, best=1)
# print "runtime:",time.clock() - start
c = 1
while c <= 1:
era, eno = tool.evaluate('../data/POS/dev.p5.out', '../data/POS/dev.out',col=c,pr=True)
print c,":POS, DP2:",era # print c,":POS, DP2 likelihood:", e0.filelikelihood("../data/POS/dev.p4.out",col=c)
c += 1
def eaSteadyState(toolbox, population, ngen, halloffame=None):
"""The is the steady-state evolutionary algorithm
"""
_logger.info("Start of evolution")
# Evaluate the individuals with an invalid fitness
invalid_ind = [ind for ind in population if not ind.fitness.valid]
fitnesses = toolbox.map(toolbox.evaluate, invalid_ind)
for ind, fit in zip(invalid_ind, fitnesses):
ind.fitness.values = fit
if halloffame is not None:
halloffame.update(population)
# Begin the generational process
for gen in range(ngen):
_logger.info("Evolving generation %i", gen)
p1, p2 = toolbox.select(population, 2)
p1 = toolbox.clone(p1)
p2 = toolbox.clone(p2)
toolbox.mate(p1, p2)
child = random.choice([p1, p2])
toolbox.mutate(child)
child.fitness.values = toolbox.evaluate(child)
if halloffame is not None:
halloffame.update(child)
# Select the next generation population
population[:] = toolbox.select(population + [child], len(population))
# Gather all the fitnesses in one list and print the stats
fits = [ind.fitness.values for ind in population]
fits_t = zip(*fits) # Transpose fitnesses for analysis
minimums = map(min, fits_t)
maximums = map(max, fits_t)
length = len(population)
sums = map(sum, fits_t)
sums2 = [sum(x*x for x in fit) for fit in fits_t]
means = [sum_ / length for sum_ in sums]
std_devs = [abs(sum2 / length - mean**2)**0.5 for sum2, mean in zip(sums2, means)]
_logger.debug("Min %s", ", ".join(map(str, minimums)))
_logger.debug("Max %s", ", ".join(map(str, maximums)))
_logger.debug("Avg %s", ", ".join(map(str, means)))
_logger.debug("Std %s", ", ".join(map(str, std_devs)))
_logger.info("End of (successful) evolution")
return population