回答編集履歴
5
追記
test
CHANGED
@@ -235,3 +235,55 @@
|
|
235
235
|
Y 2
|
236
236
|
|
237
237
|
```
|
238
|
+
|
239
|
+
|
240
|
+
|
241
|
+
コメントを受けて
|
242
|
+
|
243
|
+
---
|
244
|
+
|
245
|
+
> date[-1][-1] += len(line)の[-1][-1]の意味
|
246
|
+
|
247
|
+
|
248
|
+
|
249
|
+
data は、リストを要素に持つリストです。
|
250
|
+
|
251
|
+
まずdataの末尾のリストを取り出し、その結果の末尾の要素を取り出しています。
|
252
|
+
|
253
|
+
```Python
|
254
|
+
|
255
|
+
>>> tmp = [[11, 12], [21, 22], [31, 32]]
|
256
|
+
|
257
|
+
>>> print(tmp[-1])
|
258
|
+
|
259
|
+
[31, 32]
|
260
|
+
|
261
|
+
>>> print(tmp[-1][-1])
|
262
|
+
|
263
|
+
32
|
264
|
+
|
265
|
+
```
|
266
|
+
|
267
|
+
|
268
|
+
|
269
|
+
> 最後の for datum in date: print(*datum) がわからない
|
270
|
+
|
271
|
+
|
272
|
+
|
273
|
+
この例に限っては、次のように書くのと同じです。
|
274
|
+
|
275
|
+
```Python
|
276
|
+
|
277
|
+
for datum in data:
|
278
|
+
|
279
|
+
for e in datum:
|
280
|
+
|
281
|
+
print(e)
|
282
|
+
|
283
|
+
```
|
284
|
+
|
285
|
+
|
286
|
+
|
287
|
+
なぜこのように書き換えられるか知りたいならこちらをどうぞ。
|
288
|
+
|
289
|
+
[Qiita - Python3.xのアスタリスク逆引き](https://qiita.com/LouiS0616/items/1bbe0a9bb93054f6c380#%E9%96%A2%E6%95%B0%E3%82%92%E5%91%BC%E3%81%B3%E5%87%BA%E3%81%99%E3%81%A8%E3%81%8D)
|
4
修正
test
CHANGED
@@ -108,23 +108,27 @@
|
|
108
108
|
|
109
109
|
if line.startswith('>'):
|
110
110
|
|
111
|
-
data.append([line,
|
111
|
+
data.append([line, Counter()])
|
112
112
|
|
113
113
|
else:
|
114
114
|
|
115
|
-
data[-1][-1]
|
115
|
+
data[-1][-1].update(line)
|
116
116
|
|
117
117
|
|
118
118
|
|
119
|
-
for tag,
|
119
|
+
for tag, counter in data:
|
120
120
|
|
121
121
|
print(tag)
|
122
122
|
|
123
123
|
|
124
124
|
|
125
|
-
print(
|
125
|
+
print(
|
126
|
+
|
126
|
-
|
127
|
+
sum(1 for _ in counter.elements())
|
128
|
+
|
129
|
+
)
|
130
|
+
|
127
|
-
for k, count in
|
131
|
+
for k, count in counter.most_common():
|
128
132
|
|
129
133
|
print(k, count)
|
130
134
|
|
@@ -132,11 +136,13 @@
|
|
132
136
|
|
133
137
|
print()
|
134
138
|
|
139
|
+
|
140
|
+
|
135
|
-
```
|
141
|
+
```
|
136
|
-
|
137
|
-
|
138
|
-
|
142
|
+
|
143
|
+
|
144
|
+
|
139
|
-
**実行結果** [Wandbox](https://wandbox.org/permlink/
|
145
|
+
**実行結果** [Wandbox](https://wandbox.org/permlink/82BAo4GshvqsO6Ua)
|
140
146
|
|
141
147
|
```
|
142
148
|
|
3
追記
test
CHANGED
@@ -79,3 +79,153 @@
|
|
79
79
|
85
|
80
80
|
|
81
81
|
```
|
82
|
+
|
83
|
+
|
84
|
+
|
85
|
+
---
|
86
|
+
|
87
|
+
少しリファクタして、さらに高級にしてみた。
|
88
|
+
|
89
|
+
```Python
|
90
|
+
|
91
|
+
from collections import Counter
|
92
|
+
|
93
|
+
|
94
|
+
|
95
|
+
|
96
|
+
|
97
|
+
data = []
|
98
|
+
|
99
|
+
with open('short.sequ.txt') as fin:
|
100
|
+
|
101
|
+
for line in map(str.rstrip, fin):
|
102
|
+
|
103
|
+
if not line:
|
104
|
+
|
105
|
+
continue
|
106
|
+
|
107
|
+
|
108
|
+
|
109
|
+
if line.startswith('>'):
|
110
|
+
|
111
|
+
data.append([line, ''])
|
112
|
+
|
113
|
+
else:
|
114
|
+
|
115
|
+
data[-1][-1] += line
|
116
|
+
|
117
|
+
|
118
|
+
|
119
|
+
for tag, line in data:
|
120
|
+
|
121
|
+
print(tag)
|
122
|
+
|
123
|
+
|
124
|
+
|
125
|
+
print(len(line))
|
126
|
+
|
127
|
+
for k, count in Counter(line).most_common():
|
128
|
+
|
129
|
+
print(k, count)
|
130
|
+
|
131
|
+
|
132
|
+
|
133
|
+
print()
|
134
|
+
|
135
|
+
```
|
136
|
+
|
137
|
+
|
138
|
+
|
139
|
+
**実行結果** [Wandbox](https://wandbox.org/permlink/XbS7h2hBNMcXxc6L)
|
140
|
+
|
141
|
+
```
|
142
|
+
|
143
|
+
>YP_009518834.1 putative uncharacterized protein YjiT [Escherichia coli str. K-12 substr. MG1655]
|
144
|
+
|
145
|
+
505
|
146
|
+
|
147
|
+
L 50
|
148
|
+
|
149
|
+
S 46
|
150
|
+
|
151
|
+
V 37
|
152
|
+
|
153
|
+
R 36
|
154
|
+
|
155
|
+
E 35
|
156
|
+
|
157
|
+
G 33
|
158
|
+
|
159
|
+
A 31
|
160
|
+
|
161
|
+
T 29
|
162
|
+
|
163
|
+
I 27
|
164
|
+
|
165
|
+
D 25
|
166
|
+
|
167
|
+
P 24
|
168
|
+
|
169
|
+
Q 23
|
170
|
+
|
171
|
+
F 23
|
172
|
+
|
173
|
+
K 19
|
174
|
+
|
175
|
+
N 19
|
176
|
+
|
177
|
+
Y 14
|
178
|
+
|
179
|
+
C 12
|
180
|
+
|
181
|
+
W 10
|
182
|
+
|
183
|
+
H 8
|
184
|
+
|
185
|
+
M 4
|
186
|
+
|
187
|
+
|
188
|
+
|
189
|
+
>YP_009518833.1 uncharacterized protein YtiA [Escherichia coli str. K-12 substr. MG1655]
|
190
|
+
|
191
|
+
85
|
192
|
+
|
193
|
+
G 9
|
194
|
+
|
195
|
+
L 7
|
196
|
+
|
197
|
+
I 7
|
198
|
+
|
199
|
+
V 6
|
200
|
+
|
201
|
+
R 6
|
202
|
+
|
203
|
+
T 5
|
204
|
+
|
205
|
+
Q 5
|
206
|
+
|
207
|
+
P 5
|
208
|
+
|
209
|
+
C 5
|
210
|
+
|
211
|
+
E 4
|
212
|
+
|
213
|
+
F 4
|
214
|
+
|
215
|
+
S 4
|
216
|
+
|
217
|
+
A 4
|
218
|
+
|
219
|
+
D 3
|
220
|
+
|
221
|
+
W 3
|
222
|
+
|
223
|
+
M 2
|
224
|
+
|
225
|
+
K 2
|
226
|
+
|
227
|
+
H 2
|
228
|
+
|
229
|
+
Y 2
|
230
|
+
|
231
|
+
```
|
2
修正
test
CHANGED
@@ -32,7 +32,7 @@
|
|
32
32
|
|
33
33
|
---
|
34
34
|
|
35
|
-
|
35
|
+
要件を考えれば、もっとシンプルに書けそうです。
|
36
36
|
|
37
37
|
```Python
|
38
38
|
|
1
追記
test
CHANGED
@@ -25,3 +25,57 @@
|
|
25
25
|
|
26
26
|
|
27
27
|
おそらく内包表記の意味を勘違いして覚えています。
|
28
|
+
|
29
|
+
|
30
|
+
|
31
|
+
書いてみた
|
32
|
+
|
33
|
+
---
|
34
|
+
|
35
|
+
メモリを潤沢に使って良いのなら、もっとシンプルに書けます。
|
36
|
+
|
37
|
+
```Python
|
38
|
+
|
39
|
+
data = []
|
40
|
+
|
41
|
+
with open('short.sequ.txt') as fin:
|
42
|
+
|
43
|
+
for line in map(str.rstrip, fin):
|
44
|
+
|
45
|
+
if not line:
|
46
|
+
|
47
|
+
continue
|
48
|
+
|
49
|
+
|
50
|
+
|
51
|
+
if line.startswith('>'):
|
52
|
+
|
53
|
+
data.append([line, 0])
|
54
|
+
|
55
|
+
else:
|
56
|
+
|
57
|
+
data[-1][-1] += len(line)
|
58
|
+
|
59
|
+
|
60
|
+
|
61
|
+
for datum in data:
|
62
|
+
|
63
|
+
print(*datum, sep='\n')
|
64
|
+
|
65
|
+
```
|
66
|
+
|
67
|
+
|
68
|
+
|
69
|
+
**実行結果** [Wandbox](https://wandbox.org/permlink/oDw1bHFZaPRhwlWo)
|
70
|
+
|
71
|
+
```
|
72
|
+
|
73
|
+
>YP_009518834.1 putative uncharacterized protein YjiT [Escherichia coli str. K-12 substr. MG1655]
|
74
|
+
|
75
|
+
505
|
76
|
+
|
77
|
+
>YP_009518833.1 uncharacterized protein YtiA [Escherichia coli str. K-12 substr. MG1655]
|
78
|
+
|
79
|
+
85
|
80
|
+
|
81
|
+
```
|