数据
最尼玛 -6.70400012637 扰民 -6.49756445867 fuck... -6.32963390433 RNM -6.21861284426 wcnmlgb -5.96710044003 2.5: -5.90459648251 Fxxk -5.87247473641 MLP -5.87247473641 吃哑巴亏 -5.77120419579 IAQI -5.77107837123 MLGBD -5.69408191501 NNND -5.66228462641 MLGB. -5.60457743583
代码
import codecs
f = codecs.open('BosonNLP_sentiment_score.txt', mode='r', encoding='utf-8') # 打开txt文件,以‘utf-8’编码读取
line = f.readline() # 以行的形式进行读取文件
list1 = []
list2 = []
while line:
a = line.split()
print(a)
b = a[0] # 这是选取需要读取的位数
c = float(a[1])
if c >= 0:
list1.append(b) # 将其添加在列表之中
# list2.append(c) # 将其添加在列表之中
line = f.readline()
f.close()
out_positive = codecs.open('out_positiveBosonNLP_sentiment_score.txt', mode='w', encoding='utf-8')
# out_negative = codecs.open('out_negativeBosonNLP_sentiment_score.txt', mode='w', encoding='utf-8')
for i in list1:
print(i)
out_positive.write(i)
out_positive.write('\n')
结果
最尼玛 扰民 fuck... RNM wcnmlgb 2.5: Fxxk MLP 吃哑巴亏 IAQI MLGBD NNND MLGB.