/
run_pal5_abc.py
445 lines (436 loc) · 19.4 KB
/
run_pal5_abc.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
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
# run_pal5_abc.py: simple ABC method for constraining Nsubhalo from Pal 5 data
import os, os.path
import glob
import csv
import time
import pickle
from optparse import OptionParser
import numpy
from numpy.polynomial import Polynomial
from scipy import interpolate, signal
from galpy.util import save_pickles, bovy_conversion, bovy_coords
import simulate_streampepper
import bispectrum
import pal5_util
from gd1_util import R0,V0
_DATADIR= os.getenv('DATADIR')
_BISPECIND= 2
def get_options():
usage = "usage: %prog [options]"
parser = OptionParser(usage=usage)
# stream
parser.add_option("-s",dest='streamsavefilename',
default=None,
help="Filename to save the streampepperdf object in")
# savefilenames
parser.add_option("--outdens",dest='outdens',default=None,
help="Name of the output file for the density")
parser.add_option("--outomega",dest='outomega',default=None,
help="Name of the output file for the mean Omega")
parser.add_option("-o","--abcfile",dest='abcfile',default=None,
help="Name of the output file for the ABC")
parser.add_option("-b","--batch",dest='batch',default=None,
type='int',
help="If running batches of ABC simulations, batch number")
# Parameters of the subhalos simulation
parser.add_option("-t","--timpacts",dest='timpacts',default='256sampling',
help="Impact times in Gyr to consider; should be a comma separated list")
parser.add_option("-X",dest='Xrs',default=5.,
type='float',
help="Number of times rs to consider for the impact parameter")
parser.add_option("-l",dest='length_factor',default=1.,
type='float',
help="length_factor input to streampepperdf (consider impacts to length_factor x length)")
parser.add_option("-M",dest='mass',default='5,9',
help="Mass or mass range to consider; given as log10(mass)")
parser.add_option("--rsfac",dest='rsfac',default=1.,type='float',
help="Use a r_s(M) relation that is a factor of rsfac different from the fiducial one")
parser.add_option("--plummer",action="store_true",
dest="plummer",default=False,
help="If set, use a Plummer DM profile rather than Hernquist")
parser.add_option("--age",dest='age',default=5.,type='float',
help="Age of the stream in Gyr")
# Parallel angles at which to compute stuff
parser.add_option("--amin",dest='amin',default=0.,
type='float',
help="Minimum parallel angle to consider")
parser.add_option("--amax",dest='amax',default=1.75,
type='float',
help="Maximum parallel angle to consider (default: 2*meandO*mintimpact)")
parser.add_option("--da",dest='dapar',default=0.01,
type='float',
help="Step in apar to use")
# Data handling and continuum normalization
parser.add_option("--polydeg",dest='polydeg',default=0,
type='int',
help="Polynomial order to fit to smooth stream density")
parser.add_option("--minxi",dest='minxi',default=4.05,
type='float',
help="Minimum xi to consider")
parser.add_option("--maxxi",dest='maxxi',default=14.35,
type='float',
help="Maximum xi to consider")
parser.add_option("--nerrsim",dest='nerrsim',default=100,
type='int',
help="Simulate this many realizations of the errors per rate simulation")
parser.add_option("-m",dest='mockfilename',
default=None,
help="If set, filename of a mock Pal 5 simulation to use instead of real data")
# Parameters of the ABC simulation
parser.add_option("--ratemin",dest='ratemin',default=-1.,
type='float',
help="Minimum rate compared to CDM expectation; in log10")
parser.add_option("--ratemax",dest='ratemax',default=1.,
type='float',
help="Maximum rate compared to CDM expectation; in log10")
parser.add_option("-n","--nsamples",dest='nsamples',default=100,
type='int',
help="Number of simulations to run")
parser.add_option("-r","--recompute",action="store_true",
dest="recompute",default=False,
help="If set, do not run simulations, but recompute the tatistics for existing densities")
parser.add_option("--recomputeall",action="store_true",
dest="recomputeall",default=False,
help="If set, do not run simulations, but recompute the tatistics for existing densities for *all* existing batches")
return parser
def load_abc(filename):
"""
NAME:
load_abc
PURPOSE:
Load all ABC runs for a given filename (all batches)
INPUT:
filename - filename w/o batch
OUTPUT:
array with ABC outputs
HISTORY:
2016-04-10 - Written - Bovy (UofT)
"""
allfilenames= glob.glob(filename.replace('.dat','.*.dat'))
out= numpy.loadtxt(filename,delimiter=',')
for fname in allfilenames:
out= numpy.vstack((out,numpy.loadtxt(fname,delimiter=',')))
return out
# Convert track to xi, eta
def convert_dens_to_obs(sdf_pepper,apars,
dens,mO,dens_smooth,minxi=0.25,maxxi=14.35):
"""
NAME:
convert_dens_to_obs
PURPOSE:
Convert track to observed coordinates
INPUT:
sdf_pepper - streampepperdf object
apars - parallel angles
dens - density(apars)
dens_smooth - smooth density(apars)
mO= (None) mean parallel frequency (1D)
[needs to be set to get density on same grid as track]
minxi= (0.25) minimum xi to consider
OUTPUT:
(xi,dens/smooth)
"""
mT= sdf_pepper.meanTrack(apars,_mO=mO,coord='lb')
mradec= bovy_coords.lb_to_radec(mT[0],mT[1],degree=True)
mxieta= pal5_util.radec_to_pal5xieta(mradec[:,0],mradec[:,1],degree=True)
outll= numpy.arange(minxi,maxxi,0.1)
# Interpolate density
ipll= interpolate.InterpolatedUnivariateSpline(mxieta[:,0],apars)
ipdens= interpolate.InterpolatedUnivariateSpline(apars,dens/dens_smooth)
return (outll,ipdens(ipll(outll)))
def setup_densOmegaWriter(apar,options):
outdens= options.outdens
outomega= options.outomega
if not options.batch is None:
outdens= outdens.replace('.dat','.%i.dat' % options.batch)
if not options.batch is None:
outomega= outomega.replace('.dat','.%i.dat' % options.batch)
if os.path.exists(outdens):
# First read the file to check apar
apar_file= numpy.genfromtxt(outdens,delimiter=',',max_rows=1)
assert numpy.amax(numpy.fabs(apar_file-apar)) < 10.**-5., 'apar according to options does not correspond to apar already in outdens'
apar_file= numpy.genfromtxt(outomega,delimiter=',',max_rows=1)
assert numpy.amax(numpy.fabs(apar_file-apar)) < 10.**-5., 'apar according to options does not correspond to apar already in outomega'
csvdens= open(outdens,'a')
csvomega= open(outomega,'a')
denswriter= csv.writer(csvdens,delimiter=',')
omegawriter= csv.writer(csvomega,delimiter=',')
else:
csvdens= open(outdens,'w')
csvomega= open(outomega,'w')
denswriter= csv.writer(csvdens,delimiter=',')
omegawriter= csv.writer(csvomega,delimiter=',')
# First write apar
denswriter.writerow([a for a in apar])
omegawriter.writerow([a for a in apar])
csvdens.flush()
csvomega.flush()
return (denswriter,omegawriter,csvdens,csvomega)
def process_pal5_densdata(options):
# Read and prep data
backg= 400.
data= numpy.loadtxt('data/ibata_fig7b_raw.dat',delimiter=',')
sindx= numpy.argsort(data[:,0])
data= data[sindx]
data_lowerr= numpy.loadtxt('data/ibata_fig7b_rawlowerr.dat',delimiter=',')
sindx= numpy.argsort(data_lowerr[:,0])
data_lowerr= data_lowerr[sindx]
data_uperr= numpy.loadtxt('data/ibata_fig7b_rawuperr.dat',delimiter=',')
sindx= numpy.argsort(data_uperr[:,0])
data_uperr= data_uperr[sindx]
data_err= 0.5*(data_uperr-data_lowerr)
# CUTS
indx= (data[:,0] > options.minxi-0.05)*(data[:,0] < options.maxxi)
data= data[indx]
data_lowerr= data_lowerr[indx]
data_uperr= data_uperr[indx]
data_err= data_err[indx]
# Compute power spectrum
tdata= data[:,1]-backg
pp= Polynomial.fit(data[:,0],tdata,deg=options.polydeg,w=1./data_err[:,1])
tdata/= pp(data[:,0])
ll= data[:,0]
py= signal.csd(tdata,tdata,fs=1./(ll[1]-ll[0]),scaling='spectrum',
nperseg=len(ll))[1]
py= py.real
# Also compute the bispectrum
Bspec, Bpx= bispectrum.bispectrum(numpy.vstack((tdata,tdata)).T,
nfft=len(tdata),wind=7,nsamp=1,overlap=0)
ppyr= numpy.fabs(Bspec[len(Bspec)//2+_BISPECIND,len(Bspec)//2:].real)
ppyi= numpy.fabs(Bspec[len(Bspec)//2+_BISPECIND,len(Bspec)//2:].imag)
return (numpy.sqrt(py*(ll[-1]-ll[0])),data_err[:,1]/pp(data[:,0]),
ppyr,ppyi)
def process_mock_densdata(options):
print("Using mock Pal 5 data from %s" % options.mockfilename)
# Read and prep data for mocks
xvid= numpy.loadtxt(options.mockfilename)
xv= xvid[:,:6]
xv= xv[numpy.argsort(xvid[:,6])]
XYZ= bovy_coords.galcenrect_to_XYZ(xv[:,0],xv[:,1],xv[:,2],
Xsun=R0,Zsun=0.025)
lbd= bovy_coords.XYZ_to_lbd(XYZ[0],XYZ[1],XYZ[2],degree=True)
radec= bovy_coords.lb_to_radec(lbd[:,0],lbd[:,1],degree=True)
xieta= pal5_util.radec_to_pal5xieta(radec[:,0],radec[:,1],degree=True)
# make sure the progenitor is at (0,0)
xieta[:,0]-= numpy.median(xieta[:,0])
xieta[:,1]-= numpy.median(xieta[:,1])
h,e= numpy.histogram(xieta[:,0],range=[0.2,14.3],bins=141)
xdata= numpy.arange(0.25,14.35,0.1)
# Compute power spectrum
tdata= h-0.
pp= Polynomial.fit(xdata,tdata,deg=options.polydeg,w=1./numpy.sqrt(h+1.))
tdata/= pp(xdata)
ll= xdata
py= signal.csd(tdata,tdata,fs=1./(ll[1]-ll[0]),scaling='spectrum',
nperseg=len(ll))[1]
py= py.real
# Also compute the bispectrum
Bspec, Bpx= bispectrum.bispectrum(numpy.vstack((tdata,tdata)).T,
nfft=len(tdata),wind=7,nsamp=1,overlap=0)
ppyr= numpy.fabs(Bspec[len(Bspec)//2+_BISPECIND,len(Bspec)//2:].real)
ppyi= numpy.fabs(Bspec[len(Bspec)//2+_BISPECIND,len(Bspec)//2:].imag)
return (numpy.sqrt(py*(ll[-1]-ll[0])),numpy.sqrt(h+1.)/pp(xdata),
ppyr,ppyi)
def pal5_abc(sdf_pepper,sdf_smooth,options):
"""
"""
# Setup apar grid
apar= numpy.arange(options.amin,options.amax,options.dapar)
dens_unp= numpy.array([sdf_smooth._density_par(a) for a in apar])
if options.recompute:
# Load density and omega from file
outdens= options.outdens
outomega= options.outomega
if not options.batch is None:
outdens= outdens.replace('.dat','.%i.dat' % options.batch)
if not options.batch is None:
outomega= outomega.replace('.dat','.%i.dat' % options.batch)
densdata= numpy.genfromtxt(outdens,delimiter=',',skip_header=1)
omegadata= numpy.genfromtxt(outomega,delimiter=',',skip_header=1)
nd= 0
else:
# Setup saving of the densities and mean Omegas
denswriter, omegawriter, csvdens, csvomega=\
setup_densOmegaWriter(apar,options)
# Setup sampling
massrange= simulate_streampepper.parse_mass(options.mass)
rs= simulate_streampepper.rs
sample_GM= lambda: (10.**((-0.5)*massrange[0])\
+(10.**((-0.5)*massrange[1])\
-10.**((-0.5)*massrange[0]))\
*numpy.random.uniform())**(1./(-0.5))\
/bovy_conversion.mass_in_msol(V0,R0)
sample_rs= lambda x: rs(x*bovy_conversion.mass_in_1010msol(V0,R0)*10.**10.,
plummer=options.plummer)
rate_range= numpy.arange(massrange[0]+0.5,massrange[1]+0.5,1)
cdmrate= numpy.sum([simulate_streampepper.\
dNencdm(sdf_pepper,10.**r,Xrs=options.Xrs,
plummer=options.plummer,
rsfac=options.rsfac)
for r in rate_range])
print "Using an overall CDM rate of %f" % cdmrate
# Load Pal 5 data to compare to
if options.mockfilename is None:
power_data, data_err, data_ppyr, data_ppyi=\
process_pal5_densdata(options)
else:
power_data, data_err, data_ppyr, data_ppyi=\
process_mock_densdata(options)
# Run ABC
while True:
if not options.recompute:
# Simulate a rate
l10rate= (numpy.random.uniform()*(options.ratemax-options.ratemin)
+options.ratemin)
rate= 10.**l10rate*cdmrate
print l10rate, rate
# Simulate
sdf_pepper.simulate(rate=rate,sample_GM=sample_GM,sample_rs=sample_rs,
Xrs=options.Xrs)
# Compute density and meanOmega and save
try:
densOmega= numpy.array([\
sdf_pepper._densityAndOmega_par_approx(a) for a in apar]).T
except IndexError: # no hit
dens= numpy.array([sdf_smooth._density_par(a) for a in apar])
omega= numpy.array([sdf_smooth.meanOmega(a,oned=True) for a in apar])
else:
dens= densOmega[0]
omega= densOmega[1]
write_dens= [l10rate]
write_omega= [l10rate]
write_dens.extend(list(dens))
write_omega.extend(list(omega))
denswriter.writerow(write_dens)
omegawriter.writerow(write_omega)
csvdens.flush()
csvomega.flush()
else:
if nd >= len(densdata): break
l10rate= densdata[nd,0]
dens = densdata[nd,1:]
omega= omegadata[nd,1:]
nd+= 1
# Convert density to observed density
xixi,dens= convert_dens_to_obs(sdf_pepper,apar,
dens,omega,dens_unp,
minxi=options.minxi,
maxxi=options.maxxi)
# Add errors (Rao-Blackwellize...)
for ee in range(options.nerrsim):
tdens= dens+numpy.random.normal(size=len(xixi))*data_err
# Compute power spectrum
tcsd= signal.csd(tdens,tdens,fs=1./(xixi[1]-xixi[0]),
scaling='spectrum',nperseg=len(xixi))[1].real
power= numpy.sqrt(tcsd*(xixi[-1]-xixi[0]))
# Compute bispectrum
Bspec, Bpx= bispectrum.bispectrum(numpy.vstack((tdens,tdens)).T,
nfft=len(tdens),wind=7,
nsamp=1,overlap=0)
ppyr= numpy.fabs(Bspec[len(Bspec)//2+_BISPECIND,
len(Bspec)//2:].real)
ppyi= numpy.fabs(Bspec[len(Bspec)//2+_BISPECIND,
len(Bspec)//2:].imag)
yield (l10rate,
numpy.fabs(power[1]-power_data[1]),
numpy.fabs(power[2]-power_data[2]),
numpy.fabs(power[3]-power_data[3]),
numpy.fabs(numpy.log(numpy.mean(tdens[7:17])\
/numpy.mean(tdens[107:117]))),
numpy.fabs(ppyr-data_ppyr)[_BISPECIND],
numpy.fabs(ppyi-data_ppyi)[_BISPECIND],
ee)
def abcsims(sdf_pepper,sdf_smooth,options):
"""
NAME:
abcsims
PURPOSE:
Run a bunch of ABC simulations
INPUT:
sdf_pepper - streampepperdf object to compute peppering
sdf_smooth - streamdf object for smooth stream
options - the options dictionary
OUTPUT:
(none; just saves the simulations to a file)
HISTORY:
2016-04-08 - Written - Bovy (UofT)
"""
print("Running ABC sims ...")
abcfile= options.abcfile
if not options.batch is None:
abcfile= abcfile.replace('.dat','.%i.dat' % options.batch)
if os.path.exists(abcfile):
# First read the file to check apar
csvabc= open(abcfile,'a')
abcwriter= csv.writer(csvabc,delimiter=',')
else:
csvabc= open(abcfile,'w')
abcwriter= csv.writer(csvabc,delimiter=',')
nit= 0
for sim in pal5_abc(sdf_pepper,sdf_smooth,options):
abcwriter.writerow(list(sim)[:-1])
csvabc.flush()
nit+= 1
if nit >= options.nerrsim*options.nsamples: break
return None
def recompute(sdf_pepper,sdf_smooth,options):
"""
NAME:
recompute
PURPOSE:
Recompute the ABC summaries for existing simulations
INPUT:
sdf_pepper - streampepperdf object to compute peppering
sdf_smooth - streamdf object for smooth stream
options - the options dictionary
OUTPUT:
(none; just saves the simulations to a file)
HISTORY:
2016-04-14 - Written - Bovy (UofT)
"""
print("Recomputing ABC sims ...")
abcfile= options.abcfile
if not options.batch is None:
abcfile= abcfile.replace('.dat','.%i.dat' % options.batch)
if os.path.exists(abcfile):
raise IOError("ERROR: abcfile already exists, would be overridden...")
else:
csvabc= open(abcfile,'w')
abcwriter= csv.writer(csvabc,delimiter=',')
for sim in pal5_abc(sdf_pepper,sdf_smooth,options):
abcwriter.writerow(list(sim)[:-1])
csvabc.flush()
return None
if __name__ == '__main__':
parser= get_options()
options,args= parser.parse_args()
# Setup the streampepperdf object
if not os.path.exists(options.streamsavefilename):
timpacts= simulate_streampepper.parse_times(\
options.timpacts,options.age)
sdf_smooth= pal5_util.setup_pal5model(age=options.age)
sdf_pepper= pal5_util.setup_pal5model(timpact=timpacts,
hernquist=not options.plummer,
age=options.age,
length_factor=options.length_factor)
save_pickles(options.streamsavefilename,sdf_smooth,sdf_pepper)
else:
with open(options.streamsavefilename,'rb') as savefile:
sdf_smooth= pickle.load(savefile)
sdf_pepper= pickle.load(savefile)
if options.recomputeall:
options.recompute= True
# recompute basic
recompute(sdf_pepper,sdf_smooth,options)
# Find and recompute batches
allfilenames= glob.glob(options.outdens.replace('.dat','.*.dat'))
batches= numpy.array([int(fn.split('.dat')[0].split('.')[-1])
for fn in allfilenames],
dtype='int')
for batch in batches:
options.batch= batch
recompute(sdf_pepper,sdf_smooth,options)
elif options.recompute:
recompute(sdf_pepper,sdf_smooth,options)
else:
abcsims(sdf_pepper,sdf_smooth,options)