原始代码
# -*- coding:utf-8 -*-
import pandas as pd
import jieba
def cut_msg(ustr):
# ustr = ustr.encode("raw_unicode_escape").decode("raw_unicode_escape").encode("utf8")
return " ".join(jieba.lcut(str(ustr)))
fp = "gray.xlsx"
df = pd.read_excel(fp)
df["msg"] = df["msg"].map(cut_msg)
li = df["msg"]
with file(fp.replace(".xlsx", ".txt"), "wb") as wf:
for e in li:
wf.write(e.encode("utf8")+"\n")
报错信息
---------------------------------------------------------------------------
UnicodeEncodeError Traceback (most recent call last)
<ipython-input-28-b71365cb72a8> in <module>()
1 fp = "gray.xlsx"
2 df = pd.read_excel(fp)
----> 3 df["msg"] = df["msg"].map(cut_msg)
4 li = df["msg"]
5 with file(fp.replace(".xlsx", ".txt"), "wb") as wf:
/Users/yipu.si/anaconda/lib/python2.7/site-packages/pandas/core/series.pyc in map(self, arg, na_action)
2156 else:
2157 # arg is a function
-> 2158 new_values = map_f(values, arg)
2159
2160 return self._constructor(new_values,
pandas/_libs/src/inference.pyx in pandas._libs.lib.map_infer (pandas/_libs/lib.c:66440)()
<ipython-input-26-f92cd72f89b6> in cut_msg(ustr)
4 import jieba
5 def cut_msg(ustr):
----> 6 return " ".join(jieba.lcut(str(ustr)))
7
UnicodeEncodeError: 'ascii' codec can't encode characters in position 0-1: ordinal not in range(128)
解决方案
加入编码和解码语句
ustr.encode("raw\_unicode\_escape").decode("raw\_unicode\_escape").encode("utf8") # 这里的 utf8 根据实际数据编码而定
如下:
# -*- coding:utf-8 -*-
import pandas as pd
import jieba
def cut_msg(ustr):
ustr = ustr.encode("raw_unicode_escape").decode("raw_unicode_escape").encode("utf8") # 这里的 utf8 根据实际数据编码而定
return " ".join(jieba.lcut(str(ustr)))
后记
汉字编码问题一直困扰着处理文本数据的童鞋,我也在不断探索中,在此抛砖引玉,往路过大神指点迷津。