/
GetDist.py
355 lines (285 loc) · 12.9 KB
/
GetDist.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
#!/usr/bin/env python
from __future__ import absolute_import
from __future__ import print_function
import os
import subprocess
import getdist
import io
from getdist import MCSamples, chains, IniFile
def runScript(fname):
subprocess.Popen(['python', fname])
def doError(msg):
if __name__ == '__main__':
import sys
print(msg)
sys.exit()
raise ValueError(msg)
def main(args):
no_plots = False
chain_root = args.chain_root
if args.ini_file is None and chain_root is None:
doError('Must give either a .ini file of parameters or a chain file root name. Run "GetDist.py -h" for help.')
if not '.ini' in args.ini_file and chain_root is None:
# use default settings acting on chain_root, no plots
chain_root = args.ini_file
args.ini_file = getdist.default_getdist_settings
no_plots = True
if not os.path.isfile(args.ini_file):
doError('Parameter file does not exist: ' + args.ini_file)
if chain_root and chain_root.endswith('.txt'):
chain_root = chain_root[:-4]
# Input parameters
ini = IniFile(args.ini_file)
# File root
if chain_root is not None:
in_root = chain_root
else:
in_root = ini.params['file_root']
if not in_root:
doError('Chain Root file name not given ')
rootname = os.path.basename(in_root)
if args.ignore_rows is not None:
ignorerows = args.ignore_rows
else:
ignorerows = ini.float('ignore_rows', 0.0)
samples_are_chains = ini.bool('samples_are_chains', True)
paramnames = ini.string('parameter_names', '')
# Create instance of MCSamples
mc = MCSamples(in_root, ini=ini, files_are_chains=samples_are_chains, paramNamesFile=paramnames)
if ini.bool('adjust_priors', False) or ini.bool('map_params', False):
doError(
'To adjust priors or define new parameters, use a separate python script; see the python getdist docs for examples')
plot_ext = ini.string('plot_ext', 'py')
finish_run_command = ini.string('finish_run_command', '')
no_plots = ini.bool('no_plots', no_plots)
plots_only = ini.bool('plots_only', False)
no_tests = plots_only or ini.bool('no_tests', False)
thin_factor = ini.int('thin_factor', 0)
thin_cool = ini.float('thin_cool', 1.0)
make_single_samples = ini.bool('make_single_samples', False)
single_thin = ini.int('single_thin', 1)
cool = ini.float('cool', 1.0)
chain_exclude = ini.int_list('exclude_chain')
shade_meanlikes = ini.bool('shade_meanlikes', False)
plot_meanlikes = ini.bool('plot_meanlikes', False)
dumpNDbins = ini.bool('dump_ND_bins', False)
out_dir = ini.string('out_dir', './')
if out_dir:
if not os.path.isdir(out_dir):
os.mkdir(out_dir)
print('producing files in directory ', out_dir)
mc.out_dir = out_dir
out_root = ini.string('out_root', '')
if out_root:
rootname = out_root
print('producing files with with root ', out_root)
mc.rootname = rootname
rootdirname = os.path.join(out_dir, rootname)
mc.rootdirname = rootdirname
if 'do_minimal_1d_intervals' in ini.params:
doError('do_minimal_1d_intervals no longer used; set credible_interval_threshold instead')
line = ini.string('PCA_params', '')
if line.lower() == 'all':
PCA_params = mc.paramNames.list()
else:
PCA_params = line.split()
PCA_num = ini.int('PCA_num', len(PCA_params))
if PCA_num != 0:
if PCA_num < 2:
doError('Can only do PCA for 2 or more parameters')
PCA_func = ini.string('PCA_func', '')
# Characters representing functional mapping
if PCA_func == '':
PCA_func = ['N'] * PCA_num # No mapping
PCA_NormParam = ini.string('PCA_normparam', '') or None
make_scatter_samples = ini.bool('make_scatter_samples', False)
# ==============================================================================
first_chain = ini.int('first_chain', 0)
last_chain = ini.int('chain_num', -1)
# -1 means keep reading until one not found
# Chain files
chain_files = chains.chainFiles(in_root, first_chain=first_chain, last_chain=last_chain,
chain_exclude=chain_exclude)
mc.loadChains(in_root, chain_files)
mc.removeBurnFraction(ignorerows)
if chains.print_load_details:
if ignorerows:
print('Removed %s as burn in' % ignorerows)
else:
print('Removed no burn in')
mc.deleteFixedParams()
mc.makeSingle()
def filterParList(namestring, num=None):
if not namestring.strip():
pars = mc.paramNames.list()
else:
pars = []
for name in namestring.split():
if '?' in name or '*' in name:
pars += mc.paramNames.getMatches(name, strings=True)
elif mc.paramNames.parWithName(name):
pars.append(name)
if num is not None and len(pars) != num:
print('%iD plot has missing parameter or wrong number of parameters: %s' % (num, pars))
pars = None
return pars
if cool != 1:
print('Cooling chains by ', cool)
mc.cool(cool)
mc.updateBaseStatistics()
if not no_tests:
mc.getConvergeTests(mc.converge_test_limit, writeDataToFile=True, feedback=True)
mc.writeCovMatrix()
mc.writeCorrelationMatrix()
# Output thinned data if requested
# Must do this with unsorted output
if thin_factor != 0:
thin_ix = mc.thin_indices(thin_factor)
filename = rootdirname + '_thin.txt'
mc.writeThinData(filename, thin_ix, thin_cool)
print(mc.getNumSampleSummaryText().strip())
if mc.likeStats: print(mc.likeStats.likeSummary().strip())
if PCA_num > 0 and not plots_only:
mc.PCA(PCA_params, PCA_func, PCA_NormParam, writeDataToFile=True)
if not no_plots or dumpNDbins:
# set plot_data_dir before we generate the 1D densities below
plot_data_dir = ini.string('plot_data_dir', default='', allowEmpty=True)
if plot_data_dir and not os.path.isdir(plot_data_dir):
os.mkdir(plot_data_dir)
else:
plot_data_dir = None
mc.plot_data_dir = plot_data_dir
# Do 1D bins
mc._setDensitiesandMarge1D(writeDataToFile=not no_plots and plot_data_dir, meanlikes=plot_meanlikes)
if not no_plots:
# Output files for 1D plots
if plot_data_dir: print('Calculating plot data...')
plotparams = []
line = ini.string('plot_params', '')
if line not in ['', '0']:
plotparams = filterParList(line)
line = ini.string('plot_2D_param', '').strip()
plot_2D_param = None
if line and line != '0':
plot_2D_param = line
cust2DPlots = []
if not plot_2D_param:
# Use custom array of specific plots
num_cust2D_plots = ini.int('plot_2D_num', 0)
for i in range(1, num_cust2D_plots + 1):
line = ini.string('plot' + str(i))
pars = filterParList(line, 2)
if pars is not None:
cust2DPlots.append(pars)
else:
num_cust2D_plots -= 1
triangle_params = []
triangle_plot = ini.bool('triangle_plot', False)
if triangle_plot:
line = ini.string('triangle_params', '')
triangle_params = filterParList(line)
triangle_num = len(triangle_params)
triangle_plot = triangle_num > 1
num_3D_plots = ini.int('num_3D_plots', 0)
plot_3D = []
for ix in range(1, num_3D_plots + 1):
line = ini.string('3D_plot' + str(ix))
pars = filterParList(line, 3)
if pars is not None:
plot_3D.append(pars)
else:
num_3D_plots -= 1
# Produce file of weight-1 samples if requested
if (num_3D_plots and not make_single_samples or make_scatter_samples) and not no_plots:
make_single_samples = True
single_thin = max(1, int(round(mc.norm / mc.max_mult)) // mc.max_scatter_points)
if plot_data_dir:
if make_single_samples:
filename = os.path.join(plot_data_dir, rootname.strip() + '_single.txt')
mc.makeSingleSamples(filename, single_thin)
# Write paramNames file
mc.getParamNames().saveAsText(os.path.join(plot_data_dir, rootname + '.paramnames'))
mc.getBounds().saveToFile(os.path.join(plot_data_dir, rootname + '.bounds'))
make_plots = ini.bool('make_plots', False) or args.make_plots
done2D = {}
filename = rootdirname + '.' + plot_ext
mc.writeScriptPlots1D(filename, plotparams)
if make_plots: runScript(filename)
# Do 2D bins
if plot_2D_param == 'corr':
# In this case output the most correlated variable combinations
print('...doing 2D plots for most correlated variables')
cust2DPlots = mc.getCorrelatedVariable2DPlots()
plot_2D_param = None
elif plot_2D_param:
mc.paramNames.parWithName(plot_2D_param, error=True) # just check
if cust2DPlots or plot_2D_param:
print('...producing 2D plots')
filename = rootdirname + '_2D.' + plot_ext
done2D = mc.writeScriptPlots2D(filename, plot_2D_param, cust2DPlots,
writeDataToFile=plot_data_dir, shade_meanlikes=shade_meanlikes)
if make_plots: runScript(filename)
if triangle_plot:
# Add the off-diagonal 2D plots
print('...producing triangle plot')
filename = rootdirname + '_tri.' + plot_ext
mc.writeScriptPlotsTri(filename, triangle_params)
for i, p2 in enumerate(triangle_params):
for p1 in triangle_params[i + 1:]:
if not done2D.get((p1, p2)) and plot_data_dir:
mc.get2DDensityGridData(p1, p2, writeDataToFile=True, meanlikes=shade_meanlikes)
if make_plots: runScript(filename)
# Do 3D plots (i.e. 2D scatter plots with coloured points)
if num_3D_plots:
print('...producing ', num_3D_plots, '2D colored scatter plots')
filename = rootdirname + '_3D.' + plot_ext
mc.writeScriptPlots3D(filename, plot_3D)
if make_plots: runScript(filename)
if not plots_only:
# Write out stats marginalized
mc.getMargeStats().saveAsText(rootdirname + '.margestats')
# Limits from global likelihood
if mc.loglikes is not None: mc.getLikeStats().saveAsText(rootdirname + '.likestats')
if dumpNDbins:
num_bins_ND = ini.int('num_bins_ND', 10)
line = ini.string('ND_params', '')
if line not in ["", '0']:
ND_params = filterParList(line)
print(ND_params)
ND_dim = len(ND_params)
print(ND_dim)
mc.getRawNDDensityGridData(ND_params, writeDataToFile=True,
meanlikes=shade_meanlikes)
# System command
if finish_run_command:
finish_run_command = finish_run_command.replace('%ROOTNAME%', rootname)
finish_run_command = finish_run_command.replace('%PLOTDIR%', plot_data_dir)
finish_run_command = finish_run_command.replace('%PLOTROOT%', os.path.join(plot_data_dir, rootname))
os.system(finish_run_command)
if __name__ == '__main__':
try:
import argparse
except ImportError:
print('Make sure you are using python 2.7+')
raise
parser = argparse.ArgumentParser(description='GetDist sample analyser')
parser.add_argument('ini_file', nargs='?',
help='.ini file with analysis settings (optional, if omitted uses defaults)')
parser.add_argument('chain_root', nargs='?',
help='Root name of chain to analyse (e.g. chains/test), required unless file_root specified in ini_file')
parser.add_argument('--ignore_rows',
help='set initial fraction of chains to cut as burn in (fraction of total rows, or >1 number of rows); overrides any value in ini_file if set')
parser.add_argument('--make_param_file',
help='Produce a sample distparams.ini file that you can edit and use when running GetDist')
parser.add_argument('--make_plots', action='store_true', help='Make PDFs from any requested plot script files')
parser.add_argument('-V', '--version', action='version', version='%(prog)s ' + getdist.__version__)
args = parser.parse_args()
if args.make_param_file:
content = io.open(getdist.distparam_template).read()
analysis = io.open(getdist.default_getdist_settings).read()
content = content.replace('%%%ANALYSIS_DEFAULTS%%%', analysis)
with io.open(args.make_param_file, 'w') as f:
f.write(content)
print('Template .ini file written to ' + args.make_param_file)
else:
main(args)