import pandas as pd
datapath = './jdpl.csv'
data = pd.read_csv(datapath,encoding='utf-8')
print('原始数据')
print(data)
print(len(data))
print(data.columns)
print('----------------------------------------------------------')
print('评论数据信息')
data= data[[u'评论']]
print(data)
print(data.columns)
print('---------------------------------------------------')
#清除缺失数据
data = data.dropna() #清除缺失数据 nan为缺失数据
print('清除缺失数据后')
print(len(data))
print(data)
print(data.columns)
print('----------------------------------------------------------')
#情感分析
from snownlp import SnowNLP
coms = []
coms = data.apply(lambda x:SnowNLP(x).sentiments)#词性及评分
print(type(coms))
print(coms)
print('情感分析后')
print('-----------------------------------')
#分类
data1 = data[coms>0.66]
data2 = data[(0.33<=coms) & (coms<=0.66)]
data3 = data[coms<0.33]
print(type(data1))
print('分类后')
E:\Python\python练习\douban\venv\Scripts\python.exe E:/Python/python练习/douban/jingdong/fruit/情感分析.py
原始数据
Unnamed: 0 评论
0 0.0 送货速度:送货速度和以前一样的快速，京东的速度，很放心。\n食用感受:食用起来甜甜的，农夫山...
1 NaN 评论
2 0.0 去年吃过一次后就爱上了这款苹果，今年看到又有货后果断下单购买了两箱。物流是没的说：次日达。\...
3 NaN 评论
4 0.0 苹果真的很好吃，农夫山泉的还有标志一下子买了三箱，买三箱还打了折，真的很划算。我们家都爱吃苹...
.. ... ...
94 0.0 第一次买17.5°的苹果，个大脆甜多汁！没有坏果！非常满意！
95 NaN 评论
96 0.0 京东，我最信赖的电商平台! 京东生鲜,连接果园和千家万户，足不出户就能享受新鲜的蔬果! 农夫...
97 NaN 评论
98 0.0 宝贝收到后很满意，外形颜色也很喜欢，挑选好多家，果然没看错，希望把好物分享给大家??一整箱马...
[99 rows x 2 columns]
99
Index(['Unnamed: 0', '评论'], dtype='object')
----------------------------------------------------------
评论数据信息
评论
0 送货速度:送货速度和以前一样的快速，京东的速度，很放心。\n食用感受:食用起来甜甜的，农夫山...
1 评论
2 去年吃过一次后就爱上了这款苹果，今年看到又有货后果断下单购买了两箱。物流是没的说：次日达。\...
3 评论
4 苹果真的很好吃，农夫山泉的还有标志一下子买了三箱，买三箱还打了折，真的很划算。我们家都爱吃苹...
.. ...
94 第一次买17.5°的苹果，个大脆甜多汁！没有坏果！非常满意！
95 评论
96 京东，我最信赖的电商平台! 京东生鲜,连接果园和千家万户，足不出户就能享受新鲜的蔬果! 农夫...
97 评论
98 宝贝收到后很满意，外形颜色也很喜欢，挑选好多家，果然没看错，希望把好物分享给大家??一整箱马...
[99 rows x 1 columns]
Index(['评论'], dtype='object')
---------------------------------------------------
清除缺失数据后
99
评论
0 送货速度:送货速度和以前一样的快速，京东的速度，很放心。\n食用感受:食用起来甜甜的，农夫山...
1 评论
2 去年吃过一次后就爱上了这款苹果，今年看到又有货后果断下单购买了两箱。物流是没的说：次日达。\...
3 评论
4 苹果真的很好吃，农夫山泉的还有标志一下子买了三箱，买三箱还打了折，真的很划算。我们家都爱吃苹...
.. ...
94 第一次买17.5°的苹果，个大脆甜多汁！没有坏果！非常满意！
95 评论
96 京东，我最信赖的电商平台! 京东生鲜,连接果园和千家万户，足不出户就能享受新鲜的蔬果! 农夫...
97 评论
98 宝贝收到后很满意，外形颜色也很喜欢，挑选好多家，果然没看错，希望把好物分享给大家??一整箱马...
[99 rows x 1 columns]
Index(['评论'], dtype='object')
----------------------------------------------------------
Traceback (most recent call last):
File "E:\Python\python练习\douban\jingdong\fruit\情感分析.py", line 55, in <module>
coms = data.apply(lambda x:SnowNLP(x).sentiments)#词性及评分
File "E:\Python\python练习\douban\venv\lib\site-packages\pandas\core\frame.py", line 7765, in apply
return op.get_result()
File "E:\Python\python练习\douban\venv\lib\site-packages\pandas\core\apply.py", line 185, in get_result
return self.apply_standard()
File "E:\Python\python练习\douban\venv\lib\site-packages\pandas\core\apply.py", line 276, in apply_standard
results, res_index = self.apply_series_generator()
File "E:\Python\python练习\douban\venv\lib\site-packages\pandas\core\apply.py", line 290, in apply_series_generator
results[i] = self.f(v)
File "E:\Python\python练习\douban\jingdong\fruit\情感分析.py", line 55, in <lambda>
coms = data.apply(lambda x:SnowNLP(x).sentiments)#词性及评分
File "E:\Python\python练习\douban\venv\lib\site-packages\snownlp\__init__.py", line 37, in sentiments
return sentiment.classify(self.doc)
File "E:\Python\python练习\douban\venv\lib\site-packages\snownlp\sentiment\__init__.py", line 67, in classify
return classifier.classify(sent)
File "E:\Python\python练习\douban\venv\lib\site-packages\snownlp\sentiment\__init__.py", line 40, in classify
ret, prob = self.classifier.classify(self.handle(sent))
File "E:\Python\python练习\douban\venv\lib\site-packages\snownlp\sentiment\__init__.py", line 27, in handle
words = seg.seg(doc)
File "E:\Python\python练习\douban\venv\lib\site-packages\snownlp\seg\__init__.py", line 18, in seg
for s in re_zh.split(sent):
TypeError: expected string or bytes-like object
Process finished with exit code 1
