def sentence_sentiment_score(dataset):
cuted_review = []
for cell in dataset:
cuted_review.append(tp.cut_sentence_2(cell))
single_review_count = []
all_review_count = []
for review in cuted_review:
for sent in review:
seg_sent = tp.segmentation(sent, "list") # 分词
i = 0 # word position counter
a = 0 # sentiment word position
poscount = 0 # count a pos word
negcount = 0
for word in seg_sent:
if word in posdict:
poscount += 1
for w in seg_sent[a:i]:
poscount = match(w, poscount)
a = i + 1
elif word in negdict:
negcount += 1
for w in seg_sent[a:i]:
negcount = match(w, negcount)
a = i + 1
elif word == "！".decode("utf8") or word == "!".decode("utf8"):
for w2 in seg_sent[::-1]:
if w2 in posdict:
poscount += 2
break
elif w2 in negdict:
negcount += 2
break
else:
pos = tp.postagger(word, "list")
for k in pos:
if k[1] == "a":
fo.write(word.encode("utf8") + "\n")
elif k[1] == "d":
fo.write(word.encode("utf8") + "\n")
elif k[1] == "v":
fo.write(word.encode("utf8") + "\n")
elif k[1] == "n":
fo.write(word.encode("utf8") + "\n")
i += 1
single_review_count.append(transform_to_positive_num(poscount, negcount)) # 评论分句子后，每条句子的正负权值
all_review_count.append(
single_review_count
) # [[[s11_score], [s12_score], ...], [[s21_score], [s22_score], ...], ...]
single_review_count = []
return all_review_count
def count_adj_adv(dataset):
adj_adv_num = []
a = 0
d = 0
v = 0
for review in dataset:
pos = tp.postagger(review, "list")
for i in pos:
if i[1] == "a":
a += 1
elif i[1] == "d":
d += 1
elif i[1] == "v":
v += 1
adj_adv_num.append((a, d, v))
a = 0
d = 0
v = 0
return adj_adv_num
def count_adj_adv(dataset):
adj_adv_num = []
a = 0
d = 0
v = 0
for review in dataset:
pos = tp.postagger(review, 'list')
for i in pos:
if i[1] == 'a':
a += 1
elif i[1] == 'd':
d += 1
elif i[1] == 'v':
v += 1
adj_adv_num.append((a, d, v))
a = 0
d = 0
v = 0
return adj_adv_num