def presicionTest(self, cv_data, res_label):
''' simplest presicion test : caculate the precentage of right labels'''
psn = []
i = 0
for sent_label in eachSent(cv_data, label=True):
count = 0
for ele in zip(sent_label, res_label[i]):
if ele[0] == ele[1]:
count += 1
psn.append(count / (len(sent_label)+0.0))
i += 1
return psn
def makePrediction(self, te_data):
''' viterbi algorithm '''
res = []
res_label = []
for sent in eachSent(te_data):
th_len = len(sent)
pai = np.zeros((th_len, self.label_num, self.label_num))
backpointer = np.zeros((th_len, self.label_num, self.label_num), dtype='int')
fir = np.zeros((self.label_num, self.label_num))
# move forward
begin_two = np.zeros(2)
for k in range(2):
try:
begin_two[k] = self.ele_dict[sent[k]]
except KeyError:
begin_two[k] = self.ele_num
for i in self.label:
ii = self.label_idx[i]
for j in self.label:
jj = self.label_idx[j]
fir[ii, jj] = \
self.linear_2nd[('*', '*', i)] * \
self.emission[ii, begin_two[0] ] * \
self.linear_2nd[('*', i, j)] * \
self.emission[jj, begin_two[1] ]
pai[1,:,:] = fir
for k in range(2, th_len):
try:
th_idx = self.ele_dict[sent[k]]
except KeyError:
th_idx = self.ele_num
for i in self.label:
ii = self.label_idx[i]
for j in self.label:
jj = self.label_idx[j]
candidate = np.zeros(self.label_num)
for w in self.label:
ww = self.label_idx[w]
candidate[ww] = pai[k-1, ww, ii] * \
self.linear_2nd[(w, i, j)] * \
self.emission[jj, th_idx]
pai[k, ii, jj] = candidate.max()
backpointer[k, ii, jj] = candidate.argmax()
# move backward
end_two_bp = np.unravel_index(pai[th_len-1, :, :].argmax(), \
pai.shape[1:3])
# first, add last two best labels
best_label_idx = [e for e in end_two_bp[::-1]]
# then loop
for k in range(2, th_len)[::-1] :
th_label_idx = backpointer[k, best_label_idx[-1], best_label_idx[-2] ]
best_label_idx.append(th_label_idx)
# reverse label
best_label = [self.label[e] for e in best_label_idx[::-1]]
res_label.append(best_label)
res.append(zip(sent, best_label))
return res_label, res
