def test_hmm_2States_3Sym_1Char(self):
hmm = HMM(2, 3, False)
hmm.emission_matrix = [[0.1, 0.5, 0.2, 0.2], [0, 0, 0.5, 0.5]]
hmm.initial_matrix = [0.2, 0.8]
hmm.transition_matrix = [[0.8, 0.2], [0.8, 0.2]]
self.assertAlmostEqual(hmm.calc_probability([0]), 0.0052, 7)
self.assertAlmostEqual(hmm.calc_probability([1]), 0.026, 7)
self.assertAlmostEqual(hmm.calc_probability([2]), 0.1144, 7)
self.assertAlmostEqual(hmm.calc_probability([]), 0.44, 7)
import metric
from Models.crf import CRFModel
from Models.bilstm import BiLSTM
from torch.optim import Adamax
import torch
import torch.nn.functional as F
trainWordLists,trainTagLists,word2id,tag2id=utils.create('train.txt',make_vocab=True)
devWordLists,devTagList=utils.create('dev.txt',make_vocab=False)
#隐马尔科夫模型训练
print('HMM************************')
if os.path.exists('ckpts/hmm.pkl'):
hmm=utils.loadModel('ckpts/hmm.pkl')
predictTags = hmm.test(devWordLists, word2id, tag2id)
else:
hmm=HMM(len(tag2id),len(word2id))
hmm.train(trainWordLists,trainTagLists,tag2id,word2id)
utils.saveModel('ckpts/hmm.pkl',hmm)
predictTags=hmm.test(devWordLists,word2id,tag2id)
accuracy=metric.accuracy(predictTags,devTagList)
print('accuracy: ',accuracy)
print('CRF****************************')
# #条件随机序列场模型训练
if os.path.exists('ckpts/crf.pkl'):
crf=utils.loadModel('ckpts/crf.pkl')
print(crf)
predictTags=crf.test(devWordLists)
else:
crf=CRFModel()
crf.train(trainWordLists,trainTagLists)
utils.saveModel('ckpts/crf.pkl',crf)
def test_hmm_3States_2Sym_1Char(self):
hmm = HMM(3, 2, False)
hmm.emission_matrix = [[0.5, 0.3, 0.2], [0, 1, 0], [0.1, 0.1, 0.8]]
hmm.initial_matrix = [0.1, 0.2, 0.7]
hmm.transition_matrix = [[0, 1, 0], [0.85, 0.1, 0.05], [0.3, 0.2, 0.5]]
self.assertAlmostEqual(hmm.calc_probability([0]), 0.0322, 7)
