def split_into_sentences(line):
tokens = []
en_token = []
def close_token(token):
if token:
tokens.append(''.join(token))
del (token[:])
for c in line:
if is_terminator(c):
# close current token
if not tokens: continue
close_token(en_token)
tokens.append(c)
yield tokens
tokens = []
elif is_punct(c):
close_token(en_token)
tokens.append(c)
elif is_zh(c):
close_token(en_token)
tokens.append(c)
elif c == u' ' or c == u'\t':
close_token(en_token)
else:
en_token.append(c)
if tokens:
yield tokens
def split_into_sentences(line):
tokens = []
en_token = []
def close_token(token):
if token:
tokens.append("".join(token))
del (token[:])
for c in line:
if is_terminator(c):
# close current token
if not tokens:
continue
close_token(en_token)
tokens.append(c)
yield tokens
tokens = []
elif is_punct(c):
close_token(en_token)
tokens.append(c)
elif is_zh(c):
close_token(en_token)
tokens.append(c)
elif c == u" " or c == u"\t":
close_token(en_token)
else:
en_token.append(c)
if tokens:
yield tokens
def st_trainMatrix(trainfile):
with open(trainfile) as fin:
for line in fin:
line = line.strip()
line_items = line.split()
for item in line_items:
if hanzi_util.is_terminator(item) or ( len(item) ==1 and hanzi_util.is_punct(item) ):
line_items.remove(item);
# whether exists elements
if not line_items:
continue
# BEMS encode
# line_hits <--> line_items
# 进行字符和处理结果的对应
line_hits = [] # every char status
for i_index in range(len(line_items)):
if len(line_items[i_index]) == 1:
line_hits += 'S'
else:
for j_index in range(len(line_items[i_index])):
if j_index == 0:
line_hits += 'B'
elif j_index == len(line_items[i_index]) - 1:
line_hits += 'E'
else:
line_hits += 'M'
if len(''.join(line_items)) != len(line_hits):
print("EEEEEEE %d<->%d" %(len(''.join(line_items)),len(line_hits)));
#print(''.join(line_items))
#print(line_hits)
line_items = ''.join(line_items)
for i in range(len(line_hits)-1):
# for calc trans matrix P[I][J]
count_trans[line_hits[i]][line_hits[i+1]] += 1
for i in range(len(line_hits)-1):
# for calc mixed_matrix
if line_items[i] not in count_mixed[line_hits[i]].keys():
count_mixed[line_hits[i]][line_items[i]] = 1
else:
count_mixed[line_hits[i]][line_items[i]] += 1
for (k_i, v_i) in count_trans.items():
count = sum(v_i.values())
for (k_j, v_j) in v_i.items():
P_transMatrix[k_i][k_j] = v_j / count
for (k_i, v_i) in count_mixed.items():
for item in enumo:
if item not in v_i.keys():
count_mixed[k_i][item] = 1 #针对没有出现的词，将其出现频次设置为1
for (k_i, v_i) in count_mixed.items():
count = sum(v_i.values())
for (k_j, v_j) in v_i.items():
P_mixedMatrix[k_i][k_j] = (v_j +1) / count #添加1进行平滑
return
def prep_word_dict():
CURRENT_W = None
with open(IN_FILE) as fin:
while True:
try:
line = fin.readline()
except:
print("READ ERROR:%d" %(LINE_NUM) )
continue
if not line:
print("PROCESS DONE!")
break
if line[:4] == '[DDv' :
CURRENT_W = line[5: line.index(']')]
term_to_id(CURRENT_W)
continue
if CURRENT_W and line[0] == '【' and ('=】' in line):
line_x = line[line.index('】')+1:]
line_x = line_x.split()
if line_x:
for item in line_x:
term_to_id(item)
continue
LINE_NUM = 0
with open(YL_FILE) as fin, open(YLP_FILE, 'w') as fout:
while True:
try:
line = fin.readline()
except:
print("READ ERROR:%d" %(LINE_NUM) )
continue
if not line:
print("PROCESS DONE!")
break
LINE_NUM += 1
if not (LINE_NUM % 5000): print('C:%d' %(LINE_NUM))
if len(line) > 30: continue
seg_list = pynlpir.segment(line, pos_tagging=False)
for i in range(len(seg_list)):
if is_zhs(seg_list[i]):
term_to_id(seg_list[i])
elif len(seg_list[i]) == 1 and is_punct(seg_list[i]):
seg_list[i] = PUNCING
else:
seg_list[i] = PADDING
fout.write(' '.join(seg_list) + '\n')
term_to_id(PADDING)
#term_to_id(PUNCING)
print('SEN DONE!')
def prep_word_dict():
CURRENT_W = None
with open(IN_FILE) as fin:
while True:
try:
line = fin.readline()
except:
print("READ ERROR:%d" % (LINE_NUM))
continue
if not line:
print("PROCESS DONE!")
break
if line[:4] == '[DDv':
CURRENT_W = line[5:line.index(']')]
term_to_id(CURRENT_W)
continue
if CURRENT_W and line[0] == '【' and ('=】' in line):
line_x = line[line.index('】') + 1:]
line_x = line_x.split()
if line_x:
for item in line_x:
term_to_id(item)
continue
LINE_NUM = 0
with open(YL_FILE) as fin, open(YLP_FILE, 'w') as fout:
while True:
try:
line = fin.readline()
except:
print("READ ERROR:%d" % (LINE_NUM))
continue
if not line:
print("PROCESS DONE!")
break
LINE_NUM += 1
if not (LINE_NUM % 5000): print('C:%d' % (LINE_NUM))
if len(line) > 30: continue
seg_list = pynlpir.segment(line, pos_tagging=False)
for i in range(len(seg_list)):
if is_zhs(seg_list[i]):
term_to_id(seg_list[i])
elif len(seg_list[i]) == 1 and is_punct(seg_list[i]):
seg_list[i] = PUNCING
else:
seg_list[i] = PADDING
fout.write(' '.join(seg_list) + '\n')
term_to_id(PADDING)
#term_to_id(PUNCING)
print('SEN DONE!')
