/
dataset.py
211 lines (203 loc) · 6.38 KB
/
dataset.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
#!/usr/bin/env python
# encoding: utf-8
"""
dataset.py --- simplified replacement for old module; for legacy purposes only
(use gvar.dataset for new stuff).
"""
# Created by G. Peter Lepage, Cornell University, on 2012-05-22.
# Copyright (c) 2010-2012 G. Peter Lepage.
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# any later version (see <http://www.gnu.org/licenses/>).
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
import gvar
import numpy
def flexargfcn(f):
""" decorator for Dataset analysis functions """
def newf(self,arg=None):
if arg is not None:
if (hasattr(arg,"__hash__") and arg.__hash__ is not None
and arg in self):
return f(self,self[arg])
else:
ans = {}
for k in arg:
ans[k] = f(self,self[k])
return ans
else:
ans = {}
for k in self:
ans[k] = f(self,self[k])
return ans
##
newf.__doc__ = f.__doc__
return newf
##
class Dataset(gvar.dataset.Dataset):
""" legacy class --- don't use otherwise """
def __init__(self, *args,**kargs):
if 'bstrap' in kargs:
bstrap = kargs['bstrap']
del kargs['bstrap']
else:
bstrap = False
super(Dataset, self).__init__(*args,**kargs)
self.bstrap = bstrap
##
def copy(self,dlist):
if type(dlist) not in [list,tuple]:
dlist = [dlist]
for d in dlist:
self.extend(d)
##
def nmeas(self):
dlen = [len(self[k]) for k in self]
return min(dlen),max(dlen)
##
@flexargfcn
def avg(self,x):
return numpy.mean(x,axis=0)
##
@flexargfcn
def median(self,x):
return gvar.dataset.avg_data(x,median=True,spread=self.bstrap)
##
@flexargfcn
def sdev(self,x):
if self.bstrap:
return numpy.std(xx,axis=0)
else:
return numpy.std(xx,axis=0)/math.sqrt(len(xx))
##
@flexargfcn
def cov(self,d):
oldshape = d[0].shape
d = [di.flatten() for di in d]
# d = d.reshape((d.shape[0],-1)) # flatten all other dimensions
dcov = numpy.cov(d,rowvar=False,bias=True)
if self.bstrap:
return dcov.reshape(oldshape+oldshape)
else:
return dcov.reshape(oldshape+oldshape)/float(len(d))
##
def gdev(self,arg=None):
if arg is None:
arg = self.keys()
strip_ans = False
elif (hasattr(arg,'__hash__') and arg.__hash__ is not None
and arg in self):
arg = [arg]
strip_ans = True
if len(arg)==0:
return dict()
dd = dict()
for k in arg:
dd[k] = self[k]
ans = gvar.dataset.avg_data(dd,spread=self.bstrap)
return ans[arg[0]] if strip_ans else ans
##
def bin(self,nbin=2):
return gvar.bin_data(self,binsize=nbin)
##
def bootstrap_iter(self,n=None):
return gvar.dataset.bootstrap_iter(self,n)
##
def assemble(self,template,newtag=''):
ans = Dataset()
ans[newtag] = self.arrayzip(template)
return ans
##
def tabulate_avg(avgout,format=(6,3)):
""" Tabulates averages and standard deviations.
tabulate_avg(...) creates a nicely formatted table displaying the
output from functions like ``dataset.Dataset.gdev``. Here ``avgout`` is
the output. Parameter ``format`` specifies the output format:
``format=(N,D)`` implies that format ``'%N.Df(%Dd)'`` is used to print
``avg,int(10**D * std_dev)``. The table is returned as a single string,
for printing.
"""
table = []
output = avgout.items()
output.sort()
for tag,avsd in output:
try:
av = avsd.mean
sd = avsd.sdev
except AttributeError:
av = gvar.mean(avsd)
sd = gvar.sdev(avsd)
lines = ''
line = '%15s' % str(tag)
try:
sdfac = 10**format[1]
fmt = (' %'+str(format[0])+'.'+str(format[1])+
'f(%'+str(format[1])+'d)')
def avgfmt(av,sd,fmt=fmt,sdfac=sdfac):
try:
return fmt % (av,int(sdfac*sd+0.5))
except:
return (' %g (%.4g)' % (av,sd))
##
except:
def avgfmt(av,sd):
return (' %g (%.4g)' % (av,sd))
##
na = len(av)
if len(sd)<na:
na = len(sd)
if na>=1:
for i in xrange(na):
if len(sd.shape)==2:
sdi = math.sqrt(sd[i][i])
else:
sdi = sd[i]
nextfield = avgfmt(av[i],sdi)
if (len(nextfield)+len(line))>78:
lines = lines + line + '\n'
line = ''.ljust(15) + nextfield
else:
line = line + nextfield
table.append(lines + line +'\n')
return '\n'.join(table)
##
if __name__ == '__main__':
import gvar
gvar.ranseed((1950,1))
r1 = gvar.gvar(8.,1.)
r2 = gvar.gvar([-10.,-9.],[2.,3.])
r3 = gvar.gvar([[0.,1.],[2.,3.]],[[1.,2.],[3.,4.]])
r3_iter = gvar.raniter(r3)
r2_iter = gvar.raniter(r2)
N = 1001
d = Dataset(bstrap=False)
for x in range(N):
d.append('x',r3_iter.next())
for x in range(N):
d.append('y',r2_iter.next())
d2 = Dataset(bstrap=False)
for x in range(N):
d2.append('z',r1())
d.copy(d2)
med = d.gdev()
for k in med:
print( k,med[k])
avg = d.avg()
for k in avg:
print( k,avg)
print( d.nmeas())
nd = d.assemble(['y','y'],'yy')
print( nd.avg())
nd = d.grep('x|y')
print( nd.keys())
output = """
y [-10.0069 +- 0.00632473 -8.98159 +- 0.00949937]
x [[-0.00311314 +- 0.00316463 1.00027 +- 0.00634238]
[2.00083 +- 0.00950991 2.99893 +- 0.0126476]]
z 8.00641 +- 0.00315755
""" # 15.5 sec with N = 100001