-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathutil.py
291 lines (255 loc) · 7.67 KB
/
util.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
# util.py
# ----------
# HMM_TMRCA Project
# Licensing Information: Please do not distribute.
# You are free to use and extend these code for educational purposes.
# ProblemSet written by professor Yun S. Song
# Solution and code written by Jae Young Ryoo (jay.ryoo@gmail.com) and Saba Khalilnaji
# Class counter is taken from course CS188 Artifical Intelligence from UC Berkeley
import sys, math
def getSequenceList(path):
fastaFile = open(path)
sequences = []
sequence = None
for line in fastaFile:
if ">" in line and not sequence:
sequence = ""
elif ">" in line and sequence:
sequences.append(sequence)
sequence = ""
else:
sequence += line.strip('\n')
sequences.append(sequence)
return sequences
"""
Takes in a fastaFile that contains two sequences and outputs a list of
comparison values at each position.
If different: output "D"
If identital: output "I"
INPUT: fastaFile
OUTPUT: (list) of emissions
"""
def compareSequences(fastaFile):
fFile = open(fastaFile)
seq1 = ""
seq2 = ""
seqID = 1
if fFile.readline() == ">Sequence 1\n":
seqID = 1
for line in fFile:
if line == ">Sequence 1\n":
seqID = 1
continue
elif line == ">Sequence 2\n":
seqID = 2
continue
if seqID == 1:
seq1 += line.strip()
elif seqID == 2:
seq2 += line.strip()
seqCompare = []
for i in range(len(seq1)):
if seq1[i] == seq2[i]:
seqCompare.append('I')
else:
seqCompare.append('D')
fFile.close()
return seqCompare
"""
This class is taken from CS188
"""
class Counter(dict):
"""
A counter keeps track of counts for a set of keys.
The counter class is an extension of the standard python
dictionary type. It is specialized to have number values
(integers or floats), and includes a handful of additional
functions to ease the task of counting data. In particular,
all keys are defaulted to have value 0. Using a dictionary:
a = {}
print a['test']
would give an error, while the Counter class analogue:
>>> a = Counter()
>>> print a['test']
0
returns the default 0 value. Note that to reference a key
that you know is contained in the counter,
you can still use the dictionary syntax:
>>> a = Counter()
>>> a['test'] = 2
>>> print a['test']
2
This is very useful for counting things without initializing their counts,
see for example:
>>> a['blah'] += 1
>>> print a['blah']
1
The counter also includes additional functionality useful in implementing
the classifiers for this assignment. Two counters can be added,
subtracted or multiplied together. See below for details. They can
also be normalized and their total count and arg max can be extracted.
"""
def __getitem__(self, idx):
self.setdefault(idx, 0)
return dict.__getitem__(self, idx)
def incrementAll(self, keys, count):
"""
Increments all elements of keys by the same count.
>>> a = Counter()
>>> a.incrementAll(['one','two', 'three'], 1)
>>> a['one']
1
>>> a['two']
1
"""
for key in keys:
self[key] += count
def argMax(self):
"""
Returns the key with the highest value.
"""
if len(self.keys()) == 0: return None
all = self.items()
values = [x[1] for x in all]
maxIndex = values.index(max(values))
return all[maxIndex][0]
def argMin(self):
"""
Returns the key with the lowest value.
"""
if len(self.keys()) == 0: return None
all = self.items()
values = [x[1] for x in all]
minIndex = values.index(min(values))
return all[minIndex][0]
def sortedKeys(self):
"""
Returns a list of keys sorted by their values. Keys
with the highest values will appear first.
>>> a = Counter()
>>> a['first'] = -2
>>> a['second'] = 4
>>> a['third'] = 1
>>> a.sortedKeys()
['second', 'third', 'first']
"""
sortedItems = self.items()
compare = lambda x, y: sign(y[1] - x[1])
sortedItems.sort(cmp=compare)
return [x[0] for x in sortedItems]
def totalCount(self):
"""
Returns the sum of counts for all keys.
"""
return sum(self.values())
def normalize(self):
"""
Edits the counter such that the total count of all
keys sums to 1. The ratio of counts for all keys
will remain the same. Note that normalizing an empty
Counter will result in an error.
"""
total = float(self.totalCount())
if total == 0: return
for key in self.keys():
self[key] = self[key] / total
def divideAll(self, divisor):
"""
Divides all counts by divisor
"""
divisor = float(divisor)
for key in self:
self[key] /= divisor
def copy(self):
"""
Returns a copy of the counter
"""
return Counter(dict.copy(self))
def __mul__(self, y ):
"""
Multiplying two counters gives the dot product of their vectors where
each unique label is a vector element.
>>> a = Counter()
>>> b = Counter()
>>> a['first'] = -2
>>> a['second'] = 4
>>> b['first'] = 3
>>> b['second'] = 5
>>> a['third'] = 1.5
>>> a['fourth'] = 2.5
>>> a * b
14
"""
sum = 0
x = self
if len(x) > len(y):
x,y = y,x
for key in x:
if key not in y:
continue
sum += x[key] * y[key]
return sum
def __radd__(self, y):
"""
Adding another counter to a counter increments the current counter
by the values stored in the second counter.
>>> a = Counter()
>>> b = Counter()
>>> a['first'] = -2
>>> a['second'] = 4
>>> b['first'] = 3
>>> b['third'] = 1
>>> a += b
>>> a['first']
1
"""
for key, value in y.items():
self[key] += value
def __add__( self, y ):
"""
Adding two counters gives a counter with the union of all keys and
counts of the second added to counts of the first.
>>> a = Counter()
>>> b = Counter()
>>> a['first'] = -2
>>> a['second'] = 4
>>> b['first'] = 3
>>> b['third'] = 1
>>> (a + b)['first']
1
"""
addend = Counter()
for key in self:
if key in y:
addend[key] = self[key] + y[key]
else:
addend[key] = self[key]
for key in y:
if key in self:
continue
addend[key] = y[key]
return addend
def __sub__( self, y ):
"""
Subtracting a counter from another gives a counter with the union of all keys and
counts of the second subtracted from counts of the first.
>>> a = Counter()
>>> b = Counter()
>>> a['first'] = -2
>>> a['second'] = 4
>>> b['first'] = 3
>>> b['third'] = 1
>>> (a - b)['first']
-5
"""
addend = Counter()
for key in self:
if key in y:
addend[key] = self[key] - y[key]
else:
addend[key] = self[key]
for key in y:
if key in self:
continue
addend[key] = -1 * y[key]
return addend