質問編集履歴
1
追記
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -29,3 +29,195 @@
|
|
|
29
29
|
'∙', '）', '↓', '、', '│', '（', '»', '，', '♪', '╩', '╚', '³', '・', '╦', '╣', '╔', '╗', '▬', '❤', 'ï', 'Ø', '¹', '≤', '‡', '√', ]
|
|
30
30
|
|
|
31
31
|
```
|
|
32
|
+
|
|
33
|
+
|
|
34
|
+
|
|
35
|
+
### 追記
|
|
36
|
+
|
|
37
|
+
頂いた回答をもとに、次のように実行したところこのようなエラーが出ました。
|
|
38
|
+
|
|
39
|
+
position17というのは、punctsの17個目にエラーの原因があるということでしょうか？
|
|
40
|
+
|
|
41
|
+
|
|
42
|
+
|
|
43
|
+
```python
|
|
44
|
+
|
|
45
|
+
puncts= r',|.|"|:|)|(|-|!|?|;|""|$|&|/|[|]|\>|%|=|#|*|+|\|•|~|@|£|·|_|{|}|©|^|®|`|<|→|°|€|™|›|♥|←|×|§|″|′|Â|█|½|à|…|\n|\xa0|\t|“|★|”|–|●|â|►|−|¢|²|¬|░|¶|↑|±|¿|▾|═|¦|║|―|¥|▓|—|‹|─|\u3000|\u202f|▒|：|¼|⊕|▼|▪|†|■|’|▀|¨|▄|♫|☆|é|¯|♦|¤|▲|è|¸|¾|Ã|⋅|‘|∞|«|∙|）|↓|、|│|（|»|||♪|╩|╚|³|・|╦|╣|╔|╗|▬|❤|ï|Ø|¹|≤|‡|√'
|
|
46
|
+
|
|
47
|
+
|
|
48
|
+
|
|
49
|
+
def puncts_rm(s):
|
|
50
|
+
|
|
51
|
+
return re.sub(puncts, '', s)
|
|
52
|
+
|
|
53
|
+
|
|
54
|
+
|
|
55
|
+
(省略)
|
|
56
|
+
|
|
57
|
+
|
|
58
|
+
|
|
59
|
+
df["title2"] = df["title2"].apply(puncts_rm)
|
|
60
|
+
|
|
61
|
+
print(df["title2"])
|
|
62
|
+
|
|
63
|
+
```
|
|
64
|
+
|
|
65
|
+
```
|
|
66
|
+
|
|
67
|
+
(省略)
|
|
68
|
+
|
|
69
|
+
|
|
70
|
+
|
|
71
|
+
10 df["title2"] = df["title2"].apply(puncts_rm)
|
|
72
|
+
|
|
73
|
+
11 print(df["title2"])
|
|
74
|
+
|
|
75
|
+
|
|
76
|
+
|
|
77
|
+
~\anaconda3\lib\site-packages\pandas\core\series.py in apply(self, func, convert_dtype, args, **kwds)
|
|
78
|
+
|
|
79
|
+
3589 else:
|
|
80
|
+
|
|
81
|
+
3590 values = self.astype(object).values
|
|
82
|
+
|
|
83
|
+
-> 3591 mapped = lib.map_infer(values, f, convert=convert_dtype)
|
|
84
|
+
|
|
85
|
+
3592
|
|
86
|
+
|
|
87
|
+
3593 if len(mapped) and isinstance(mapped[0], Series):
|
|
88
|
+
|
|
89
|
+
|
|
90
|
+
|
|
91
|
+
pandas\_libs\lib.pyx in pandas._libs.lib.map_infer()
|
|
92
|
+
|
|
93
|
+
|
|
94
|
+
|
|
95
|
+
<ipython-input-84-2b440d6a84a2> in puncts_rm(s)
|
|
96
|
+
|
|
97
|
+
1 def puncts_rm(s):
|
|
98
|
+
|
|
99
|
+
----> 2 return re.sub(puncts, '', s)
|
|
100
|
+
|
|
101
|
+
3
|
|
102
|
+
|
|
103
|
+
4 def html_tags_rm(s):
|
|
104
|
+
|
|
105
|
+
5 return re.sub(html_tags, '', s)
|
|
106
|
+
|
|
107
|
+
|
|
108
|
+
|
|
109
|
+
~\anaconda3\lib\re.py in sub(pattern, repl, string, count, flags)
|
|
110
|
+
|
|
111
|
+
190 a callable, it's passed the Match object and must return
|
|
112
|
+
|
|
113
|
+
191 a replacement string to be used."""
|
|
114
|
+
|
|
115
|
+
--> 192 return _compile(pattern, flags).sub(repl, string, count)
|
|
116
|
+
|
|
117
|
+
193
|
|
118
|
+
|
|
119
|
+
194 def subn(pattern, repl, string, count=0, flags=0):
|
|
120
|
+
|
|
121
|
+
|
|
122
|
+
|
|
123
|
+
~\anaconda3\lib\re.py in _compile(pattern, flags)
|
|
124
|
+
|
|
125
|
+
284 if not sre_compile.isstring(pattern):
|
|
126
|
+
|
|
127
|
+
285 raise TypeError("first argument must be string or compiled pattern")
|
|
128
|
+
|
|
129
|
+
--> 286 p = sre_compile.compile(pattern, flags)
|
|
130
|
+
|
|
131
|
+
287 if not (flags & DEBUG):
|
|
132
|
+
|
|
133
|
+
288 if len(_cache) >= _MAXCACHE:
|
|
134
|
+
|
|
135
|
+
|
|
136
|
+
|
|
137
|
+
~\anaconda3\lib\sre_compile.py in compile(p, flags)
|
|
138
|
+
|
|
139
|
+
762 if isstring(p):
|
|
140
|
+
|
|
141
|
+
763 pattern = p
|
|
142
|
+
|
|
143
|
+
--> 764 p = sre_parse.parse(p, flags)
|
|
144
|
+
|
|
145
|
+
765 else:
|
|
146
|
+
|
|
147
|
+
766 pattern = None
|
|
148
|
+
|
|
149
|
+
|
|
150
|
+
|
|
151
|
+
~\anaconda3\lib\sre_parse.py in parse(str, flags, pattern)
|
|
152
|
+
|
|
153
|
+
922
|
|
154
|
+
|
|
155
|
+
923 try:
|
|
156
|
+
|
|
157
|
+
--> 924 p = _parse_sub(source, pattern, flags & SRE_FLAG_VERBOSE, 0)
|
|
158
|
+
|
|
159
|
+
925 except Verbose:
|
|
160
|
+
|
|
161
|
+
926 # the VERBOSE flag was switched on inside the pattern. to be
|
|
162
|
+
|
|
163
|
+
|
|
164
|
+
|
|
165
|
+
~\anaconda3\lib\sre_parse.py in _parse_sub(source, state, verbose, nested)
|
|
166
|
+
|
|
167
|
+
418 while True:
|
|
168
|
+
|
|
169
|
+
419 itemsappend(_parse(source, state, verbose, nested + 1,
|
|
170
|
+
|
|
171
|
+
--> 420 not nested and not items))
|
|
172
|
+
|
|
173
|
+
421 if not sourcematch("|"):
|
|
174
|
+
|
|
175
|
+
422 break
|
|
176
|
+
|
|
177
|
+
|
|
178
|
+
|
|
179
|
+
~\anaconda3\lib\sre_parse.py in _parse(source, state, verbose, nested, first)
|
|
180
|
+
|
|
181
|
+
808 sub_verbose = ((verbose or (add_flags & SRE_FLAG_VERBOSE)) and
|
|
182
|
+
|
|
183
|
+
809 not (del_flags & SRE_FLAG_VERBOSE))
|
|
184
|
+
|
|
185
|
+
--> 810 p = _parse_sub(source, state, sub_verbose, nested + 1)
|
|
186
|
+
|
|
187
|
+
811 if not source.match(")"):
|
|
188
|
+
|
|
189
|
+
812 raise source.error("missing ), unterminated subpattern",
|
|
190
|
+
|
|
191
|
+
|
|
192
|
+
|
|
193
|
+
~\anaconda3\lib\sre_parse.py in _parse_sub(source, state, verbose, nested)
|
|
194
|
+
|
|
195
|
+
418 while True:
|
|
196
|
+
|
|
197
|
+
419 itemsappend(_parse(source, state, verbose, nested + 1,
|
|
198
|
+
|
|
199
|
+
--> 420 not nested and not items))
|
|
200
|
+
|
|
201
|
+
421 if not sourcematch("|"):
|
|
202
|
+
|
|
203
|
+
422 break
|
|
204
|
+
|
|
205
|
+
|
|
206
|
+
|
|
207
|
+
~\anaconda3\lib\sre_parse.py in _parse(source, state, verbose, nested, first)
|
|
208
|
+
|
|
209
|
+
643 if not item or item[0][0] is AT:
|
|
210
|
+
|
|
211
|
+
644 raise source.error("nothing to repeat",
|
|
212
|
+
|
|
213
|
+
--> 645 source.tell() - here + len(this))
|
|
214
|
+
|
|
215
|
+
646 if item[0][0] in _REPEATCODES:
|
|
216
|
+
|
|
217
|
+
647 raise source.error("multiple repeat",
|
|
218
|
+
|
|
219
|
+
|
|
220
|
+
|
|
221
|
+
error: nothing to repeat at position 17
|
|
222
|
+
|
|
223
|
+
```
|