core.py 57 KB
Newer Older
Sebastian Heimann's avatar
Sebastian Heimann committed
1
2
3
4
5
6
7
8
import math
import os
import sys
import logging
import time
import copy
import shutil
import os.path as op
9
from string import Template
Sebastian Heimann's avatar
Sebastian Heimann committed
10
11
12
13

import numpy as num

from pyrocko.guts import load, Object, String, Float, Int, Bool, List, \
Sebastian Heimann's avatar
Sebastian Heimann committed
14
    StringChoice, Dict, Timestamp
Sebastian Heimann's avatar
Sebastian Heimann committed
15
from pyrocko import orthodrome as od, gf, trace, guts, util, weeding
Sebastian Heimann's avatar
wip    
Sebastian Heimann committed
16
from pyrocko import parimap, model, gui_util
17
from pyrocko.guts_array import Array
Sebastian Heimann's avatar
Sebastian Heimann committed
18
19
20
21
22
23
24
25

from grond import dataset

logger = logging.getLogger('grond.core')

guts_prefix = 'grond'


26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
def float_or_none(x):
    if x is None:
        return x
    else:
        return float(x)


class Trace(Object):
    pass


class TraceSpectrum(Object):
    network = String.T()
    station = String.T()
    location = String.T()
    channel = String.T()
    deltaf = Float.T(default=1.0)
    fmin = Float.T(default=0.0)
    ydata = Array.T(shape=(None,), dtype=num.complex, serialize_as='list')

46
47
48
49
50
51
    def get_ydata(self):
        return self.ydata

    def get_xdata(self):
        return self.fmin + num.arange(self.ydata.size) * self.deltaf

52

Sebastian Heimann's avatar
Sebastian Heimann committed
53
54
55
56
57
58
59
def mahalanobis_distance(xs, mx, cov):
    imask = num.diag(cov) != 0.
    icov = num.linalg.inv(cov[imask, :][:, imask])
    temp = xs[:, imask] - mx[imask]
    return num.sqrt(num.sum(temp * num.dot(icov, temp.T).T, axis=1))


Sebastian Heimann's avatar
Sebastian Heimann committed
60
61
62
63
64
class Parameter(Object):
    name = String.T()
    unit = String.T(optional=True)
    scale_factor = Float.T(default=1., optional=True)
    scale_unit = String.T(optional=True)
65
    label = String.T(optional=True)
Sebastian Heimann's avatar
Sebastian Heimann committed
66
67
68
69
70
71
72
73
74

    def __init__(self, *args, **kwargs):
        if len(args) >= 1:
            kwargs['name'] = args[0]
        if len(args) >= 2:
            kwargs['unit'] = args[1]

        Object.__init__(self, **kwargs)

75
76
77
78
79
80
    def get_label(self, with_unit=True):
        l = [self.label or self.name]
        if with_unit:
            unit = self.get_unit_label()
            if unit:
                l.append('[%s]' % unit)
Sebastian Heimann's avatar
Sebastian Heimann committed
81
82
83

        return ' '.join(l)

84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
    def get_value_label(self, value, format='%(value)g%(unit)s'):
        value = self.scaled(value)
        unit = self.get_unit_suffix()
        return format % dict(value=value, unit=unit)

    def get_unit_label(self):
        if self.scale_unit is not None:
            return self.scale_unit
        elif self.unit:
            return self.unit
        else:
            return None

    def get_unit_suffix(self):
        unit = self.get_unit_label()
        if not unit:
            return ''
        else:
            return ' %s' % unit

Sebastian Heimann's avatar
Sebastian Heimann committed
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
    def scaled(self, x):
        if isinstance(x, tuple):
            return tuple(v/self.scale_factor for v in x)
        if isinstance(x, list):
            return list(v/self.scale_factor for v in x)
        else:
            return x/self.scale_factor


class ADict(dict):
    def __getattr__(self, k):
        return self[k]

    def __setattr__(self, k, v):
        self[k] = v


class Problem(Object):
    name = String.T()
    parameters = List.T(Parameter.T())
    dependants = List.T(Parameter.T())
125
    apply_balancing_weights = Bool.T(default=True)
126
    base_source = gf.Source.T()
Sebastian Heimann's avatar
Sebastian Heimann committed
127
128
129
130
131

    def __init__(self, **kwargs):
        Object.__init__(self, **kwargs)
        self._bootstrap_weights = None
        self._target_weights = None
Sebastian Heimann's avatar
Sebastian Heimann committed
132
        self._engine = None
133
        self._group_mask = None
Sebastian Heimann's avatar
Sebastian Heimann committed
134
135
136

    def get_engine(self):
        return self._engine
Sebastian Heimann's avatar
Sebastian Heimann committed
137
138
139
140
141
142
143
144
145
146
147
148
149

    def copy(self):
        o = copy.copy(self)
        o._bootstrap_weights = None
        o._target_weights = None
        return o

    def parameter_dict(self, x):
        return ADict((p.name, v) for (p, v) in zip(self.parameters, x))

    def parameter_array(self, d):
        return num.array([d[p.name] for p in self.parameters], dtype=num.float)

Sebastian Heimann's avatar
Sebastian Heimann committed
150
151
152
153
    @property
    def parameter_names(self):
        return [p.name for p in self.combined]

Sebastian Heimann's avatar
Sebastian Heimann committed
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
    def dump_problem_info(self, dirname):
        fn = op.join(dirname, 'problem.yaml')
        util.ensuredirs(fn)
        guts.dump(self, filename=fn)

    def dump_problem_data(self, dirname, x, ms, ns):
        fn = op.join(dirname, 'x')
        with open(fn, 'ab') as f:
            x.astype('<f8').tofile(f)

        fn = op.join(dirname, 'misfits')
        with open(fn, 'ab') as f:
            ms.astype('<f8').tofile(f)
            ns.astype('<f8').tofile(f)

    def name_to_index(self, name):
        pnames = [p.name for p in self.combined]
        return pnames.index(name)

    @property
    def nparameters(self):
        return len(self.parameters)

    @property
    def ntargets(self):
        return len(self.targets)

    @property
    def ndependants(self):
        return len(self.dependants)

    @property
    def ncombined(self):
        return len(self.parameters) + len(self.dependants)

    @property
    def combined(self):
        return self.parameters + self.dependants

    def make_bootstrap_weights(self, nbootstrap):
        ntargets = len(self.targets)
        ws = num.zeros((nbootstrap, ntargets))
        rstate = num.random.RandomState(23)
        for ibootstrap in xrange(nbootstrap):
            ii = rstate.randint(0, ntargets, size=self.ntargets)
            ws[ibootstrap, :] = num.histogram(
                ii, ntargets, (-0.5, ntargets - 0.5))[0]

        return ws

    def get_bootstrap_weights(self, ibootstrap=None):
        if self._bootstrap_weights is None:
            self._bootstrap_weights = self.make_bootstrap_weights(
                self.nbootstrap)

        if ibootstrap is None:
            return self._bootstrap_weights
        else:
            return self._bootstrap_weights[ibootstrap, :]

Sebastian Heimann's avatar
Sebastian Heimann committed
214
215
216
    def set_engine(self, engine):
        self._engine = engine

217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
    def make_group_mask(self):
        super_group_names = set()
        groups = num.zeros(len(self.targets), dtype=num.int)
        ngroups = 0
        for itarget, target in enumerate(self.targets):
            if target.super_group not in super_group_names:
                super_group_names.add(target.super_group)
                ngroups += 1

            groups[itarget] = ngroups - 1

        return groups, ngroups

    def get_group_mask(self):
        if self._group_mask is None:
            self._group_mask = self.make_group_mask()

        return self._group_mask

Sebastian Heimann's avatar
Sebastian Heimann committed
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253

class ProblemConfig(Object):
    name_template = String.T()
    apply_balancing_weights = Bool.T(default=True)


class Forbidden(Exception):
    pass


class DirectoryAlreadyExists(Exception):
    pass


class GrondError(Exception):
    pass


254
255
256
257
258
259
260
261
262
class DomainChoice(StringChoice):
    choices = [
        'time_domain',
        'frequency_domain',
        'envelope',
        'absolute',
        'cc_max_norm']


Sebastian Heimann's avatar
Sebastian Heimann committed
263
264
265
266
267
268
class InnerMisfitConfig(Object):
    fmin = Float.T()
    fmax = Float.T()
    ffactor = Float.T(default=1.5)
    tmin = gf.Timing.T()
    tmax = gf.Timing.T()
Sebastian Heimann's avatar
Sebastian Heimann committed
269
270
    pick_synthetic_traveltime = gf.Timing.T(optional=True)
    pick_phasename = String.T(optional=True)
271
    domain = DomainChoice.T(default='time_domain')
Sebastian Heimann's avatar
Sebastian Heimann committed
272

273
274
275
    def get_full_frequency_range(self):
        return self.fmin / self.ffactor, self.fmax * self.ffactor

Sebastian Heimann's avatar
Sebastian Heimann committed
276
277
278
279
280
281
282
283
284

class TargetAnalysisResult(Object):
    balancing_weight = Float.T()


class NoAnalysisResults(Exception):
    pass


285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
class MisfitResult(gf.Result):
    misfit_value = Float.T()
    misfit_norm = Float.T()
    processed_obs = Trace.T(optional=True)
    processed_syn = Trace.T(optional=True)
    filtered_obs = Trace.T(optional=True)
    filtered_syn = Trace.T(optional=True)
    spectrum_obs = TraceSpectrum.T(optional=True)
    spectrum_syn = TraceSpectrum.T(optional=True)
    taper = trace.Taper.T(optional=True)
    tobs_shift = Float.T(optional=True)
    tsyn_pick = Timestamp.T(optional=True)
    cc_shift = Float.T(optional=True)
    cc = Trace.T(optional=True)


Sebastian Heimann's avatar
Sebastian Heimann committed
301
302
303
304
305
class MisfitTarget(gf.Target):
    misfit_config = InnerMisfitConfig.T()
    flip_norm = Bool.T(default=False)
    manual_weight = Float.T(default=1.0)
    analysis_result = TargetAnalysisResult.T(optional=True)
306
307
    super_group = gf.StringID.T()
    group = gf.StringID.T()
Sebastian Heimann's avatar
Sebastian Heimann committed
308
309
310
311

    def __init__(self, **kwargs):
        gf.Target.__init__(self, **kwargs)
        self._ds = None
312
        self._result_mode = 'sparse'
313
314
315
316

    def string_id(self):
        return '.'.join(x for x in (
            self.super_group, self.group) + self.codes if x)
Sebastian Heimann's avatar
Sebastian Heimann committed
317
318
319
320
321
322
323
324
325
326
327
328

    def get_plain_target(self):
        d = dict(
            (k, getattr(self, k)) for k in gf.Target.T.propnames)
        return gf.Target(**d)

    def get_dataset(self):
        return self._ds

    def set_dataset(self, ds):
        self._ds = ds

329
330
331
    def set_result_mode(self, result_mode):
        self._result_mode = result_mode

Sebastian Heimann's avatar
Sebastian Heimann committed
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
    def get_combined_weight(self, apply_balancing_weights):
        w = self.manual_weight
        if apply_balancing_weights:
            w *= self.get_balancing_weight()

        return w

    def get_balancing_weight(self):
        if not self.analysis_result:
            raise NoAnalysisResults('no balancing weights available')

        return self.analysis_result.balancing_weight

    def get_taper_params(self, engine, source):
        store = engine.get_store(self.store_id)
        config = self.misfit_config
        tmin_fit = source.time + store.t(config.tmin, source, self)
        tmax_fit = source.time + store.t(config.tmax, source, self)
        tfade = 1.0/config.fmin
        return tmin_fit, tmax_fit, tfade

    def post_process(self, engine, source, tr_syn):

        tr_syn = tr_syn.pyrocko_trace()
        nslc = self.codes

        config = self.misfit_config

        tmin_fit, tmax_fit, tfade = self.get_taper_params(engine, source)

Sebastian Heimann's avatar
Sebastian Heimann committed
362
363
364
        ds = self.get_dataset()

        tobs_shift = 0.0
Sebastian Heimann's avatar
Sebastian Heimann committed
365
        tsyn = None
Sebastian Heimann's avatar
Sebastian Heimann committed
366
367
368
369
370
371
372
373
374
375
376
377
378
379
        if config.pick_synthetic_traveltime and config.pick_phasename:
            store = engine.get_store(self.store_id)
            tsyn = source.time + store.t(
                config.pick_synthetic_traveltime, source, self)

            marker = ds.get_pick(
                source.name,
                self.codes[:3],
                config.pick_phasename)

            if marker:
                tobs = marker.tmin
                tobs_shift = tobs - tsyn

Sebastian Heimann's avatar
Sebastian Heimann committed
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
        freqlimits = (
            config.fmin/config.ffactor,
            config.fmin, config.fmax,
            config.fmax*config.ffactor)

        tinc_obs = 1.0/config.fmin

        tr_syn.extend(
            tmin_fit - tfade * 2.0,
            tmax_fit + tfade * 2.0,
            fillmethod='repeat')

        tr_syn = tr_syn.transfer(
            freqlimits=freqlimits,
            tfade=tfade)

        tr_syn.chop(tmin_fit - 2*tfade, tmax_fit + 2*tfade)

Sebastian Heimann's avatar
Sebastian Heimann committed
398
399
400
401
        tmin_obs = (math.floor(
            (tmin_fit - tfade + tobs_shift) / tinc_obs) - 1.0) * tinc_obs
        tmax_obs = (math.ceil(
            (tmax_fit + tfade + tobs_shift) / tinc_obs) + 1.0) * tinc_obs
Sebastian Heimann's avatar
Sebastian Heimann committed
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420

        try:
            if nslc[-1] == 'R':
                backazimuth = self.azimuth + 180.
            elif nslc[-1] == 'T':
                backazimuth = self.azimuth + 90.
            else:
                backazimuth = None

            tr_obs = ds.get_waveform(
                nslc,
                tmin=tmin_obs,
                tmax=tmax_obs,
                tfade=tfade,
                freqlimits=freqlimits,
                deltat=tr_syn.deltat,
                cache=True,
                backazimuth=backazimuth)

Sebastian Heimann's avatar
Sebastian Heimann committed
421
422
423
424
            if tobs_shift != 0.0:
                tr_obs = tr_obs.copy()
                tr_obs.shift(-tobs_shift)

425
426
            mr = misfit(
                tr_obs, tr_syn,
Sebastian Heimann's avatar
Sebastian Heimann committed
427
428
429
430
                taper=trace.CosTaper(
                    tmin_fit - tfade,
                    tmin_fit,
                    tmax_fit,
431
432
433
                    tmax_fit + tfade),
                domain=config.domain,
                exponent=2,
434
435
                flip=self.flip_norm,
                result_mode=self._result_mode)
Sebastian Heimann's avatar
wip    
Sebastian Heimann committed
436

437
438
            mr.tobs_shift = float(tobs_shift)
            mr.tsyn_pick = float_or_none(tsyn)
Sebastian Heimann's avatar
Sebastian Heimann committed
439

440
            return mr
Sebastian Heimann's avatar
Sebastian Heimann committed
441
442
443
444
445
446

        except dataset.NotFound, e:
            logger.debug(str(e))
            raise gf.SeismosizerError('no waveform data, %s' % str(e))


447
448
def misfit(
        tr_obs, tr_syn, taper, domain, exponent, flip, result_mode='sparse'):
Sebastian Heimann's avatar
Sebastian Heimann committed
449

450
451
452
453
454
455
456
457
458
459
460
    '''
    Calculate misfit between observed and synthetic trace.

    :param tr_obs: observed trace as :py:class:`pyrocko.trace.Trace`
    :param tr_syn: synthetic trace as :py:class:`pyrocko.trace.Trace`
    :param taper: taper applied in timedomain as
        :py:class:`pyrocko.trace.Taper`
    :param domain: how to calculate difference, see :py:class:`DomainChoice`
    :param exponent: exponent of Lx type norms
    :param flip: ``bool``, if set to ``True``, normalization factor is
        computed against *tr_syn* rather than *tr_obs*
461
462
    :param result_mode: ``'full'``, include traces and spectra or ``'sparse'``,
        include only misfit and normalization factor in result
463
464
465

    :returns: object of type :py:class:`MisfitResult`
    '''
Sebastian Heimann's avatar
Sebastian Heimann committed
466

467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
    trace.assert_same_sampling_rate(tr_obs, tr_syn)
    tmin, tmax = taper.time_span()

    tr_proc_obs, trspec_proc_obs = _process(tr_obs, tmin, tmax, taper, domain)
    tr_proc_syn, trspec_proc_syn = _process(tr_syn, tmin, tmax, taper, domain)

    cc_shift = None
    ctr = None
    if domain in ('time_domain', 'envelope', 'absolute'):
        a, b = tr_proc_syn.ydata, tr_proc_obs.ydata
        if flip:
            b, a = a, b

        m, n = trace.Lx_norm(a, b, norm=exponent)

    elif domain == 'cc_max_norm':

        ctr = trace.correlate(
            tr_proc_syn,
            tr_proc_obs,
            mode='same',
            normalization='normal')

        cc_shift, cc_max = ctr.max()
        m = 0.5 - 0.5 * cc_max
        n = 0.5

    elif domain == 'frequency_domain':
        a, b = trspec_proc_syn.ydata, trspec_proc_obs.ydata
        if flip:
            b, a = a, b

        m, n = trace.Lx_norm(num.abs(a), num.abs(b), norm=exponent)

501
502
503
504
505
506
507
508
509
510
511
512
513
    if result_mode == 'full':
        result = MisfitResult(
            misfit_value=m,
            misfit_norm=n,
            processed_obs=tr_proc_obs,
            processed_syn=tr_proc_syn,
            filtered_obs=tr_obs.copy(),
            filtered_syn=tr_syn,
            spectrum_obs=trspec_proc_obs,
            spectrum_syn=trspec_proc_syn,
            taper=taper,
            cc_shift=cc_shift,
            cc=ctr)
514

515
516
517
518
519
520
    elif result_mode == 'sparse':
        result = MisfitResult(
            misfit_value=m,
            misfit_norm=n)
    else:
        assert False
521
522
523
524
525
526
527
528
529

    return result


def _process(tr, tmin, tmax, taper, domain):
    tr_proc = _extend_extract(tr, tmin, tmax)
    tr_proc.taper(taper)

    df = None
530
    trspec_proc = None
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545

    if domain == 'envelope':
        tr_proc = tr_proc.envelope(inplace=False)

    elif domain == 'absolute':
        tr_proc.set_ydata(num.abs(tr_proc.get_ydata()))

    elif domain == 'frequency_domain':
        ndata = tr_proc.ydata.size
        nfft = trace.nextpow2(ndata)
        padded = num.zeros(nfft, dtype=num.float)
        padded[:ndata] = tr_proc.ydata
        spectrum = num.fft.rfft(padded)
        df = 1.0 / (tr_proc.deltat * nfft)

546
547
548
549
550
551
552
553
        trspec_proc = TraceSpectrum(
            network=tr_proc.network,
            station=tr_proc.station,
            location=tr_proc.location,
            channel=tr_proc.channel,
            deltaf=df,
            fmin=0.0,
            ydata=spectrum)
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577

    return tr_proc, trspec_proc


def _extend_extract(tr, tmin, tmax):
    deltat = tr.deltat
    itmin_frame = int(math.floor(tmin/deltat))
    itmax_frame = int(math.ceil(tmax/deltat))
    nframe = itmax_frame - itmin_frame
    n = tr.data_len()
    a = num.empty(nframe, dtype=num.float)
    itmin_tr = int(round(tr.tmin / deltat))
    itmax_tr = itmin_tr + n
    icut1 = min(max(0, itmin_tr - itmin_frame), nframe)
    icut2 = min(max(0, itmax_tr - itmin_frame), nframe)
    icut1_tr = min(max(0, icut1 + itmin_frame - itmin_tr), n)
    icut2_tr = min(max(0, icut2 + itmin_frame - itmin_tr), n)
    a[:icut1] = tr.ydata[0]
    a[icut1:icut2] = tr.ydata[icut1_tr:icut2_tr]
    a[icut2:] = tr.ydata[-1]
    tr = tr.copy(data=False)
    tr.tmin = tmin
    tr.set_ydata(a)
    return tr
Sebastian Heimann's avatar
Sebastian Heimann committed
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615


def xjoin(basepath, path):
    if path is None and basepath is not None:
        return basepath
    elif op.isabs(path) or basepath is None:
        return path
    else:
        return op.join(basepath, path)


def xrelpath(path, start):
    if op.isabs(path):
        return path
    else:
        return op.relpath(path, start)


class Path(String):
    pass


class HasPaths(Object):
    path_prefix = Path.T(optional=True)

    def __init__(self, *args, **kwargs):
        Object.__init__(self, *args, **kwargs)
        self._basepath = None
        self._parent_path_prefix = None

    def set_basepath(self, basepath, parent_path_prefix=None):
        self._basepath = basepath
        self._parent_path_prefix = parent_path_prefix
        for (prop, val) in self.T.ipropvals(self):
            if isinstance(val, HasPaths):
                val.set_basepath(
                    basepath, self.path_prefix or self._parent_path_prefix)

Sebastian Heimann's avatar
Sebastian Heimann committed
616
617
618
619
    def get_basepath(self):
        assert self._basepath is not None
        return self._basepath

Sebastian Heimann's avatar
Sebastian Heimann committed
620
621
622
623
624
625
    def change_basepath(self, new_basepath, parent_path_prefix=None):
        assert self._basepath is not None

        self._parent_path_prefix = parent_path_prefix
        if self.path_prefix or not self._parent_path_prefix:

Sebastian Heimann's avatar
Sebastian Heimann committed
626
627
            self.path_prefix = op.normpath(xjoin(xrelpath(
                self._basepath, new_basepath), self.path_prefix))
Sebastian Heimann's avatar
Sebastian Heimann committed
628
629
630
631
632
633
634
635

        for val in self.T.ivals(self):
            if isinstance(val, HasPaths):
                val.change_basepath(
                    new_basepath, self.path_prefix or self._parent_path_prefix)

        self._basepath = new_basepath

636
    def expand_path(self, path, extra=None):
Sebastian Heimann's avatar
Sebastian Heimann committed
637
638
        assert self._basepath is not None

639
640
641
642
        if extra is None:
            def extra(path):
                return path

Sebastian Heimann's avatar
Sebastian Heimann committed
643
644
645
646
647
        path_prefix = self.path_prefix or self._parent_path_prefix

        if path is None:
            return None
        elif isinstance(path, basestring):
648
649
            return extra(
                op.normpath(xjoin(self._basepath, xjoin(path_prefix, path))))
Sebastian Heimann's avatar
Sebastian Heimann committed
650
651
        else:
            return [
652
653
                extra(
                    op.normpath(xjoin(self._basepath, xjoin(path_prefix, p))))
Sebastian Heimann's avatar
Sebastian Heimann committed
654
655
656
                for p in path]


Sebastian Heimann's avatar
wip    
Sebastian Heimann committed
657
658
659
660
661
662
663
664
665
class RandomResponse(trace.FrequencyResponse):

    scale = Float.T(default=0.0)

    def set_random_state(self, rstate):
        self._rstate = rstate

    def evaluate(self, freqs):
        n = freqs.size
Sebastian Heimann's avatar
wip    
Sebastian Heimann committed
666
667
        return 1.0 + freqs*(
            self._rstate.normal(scale=self.scale, size=n) +
Sebastian Heimann's avatar
wip    
Sebastian Heimann committed
668
669
670
671
672
673
674
            0.0J * self._rstate.normal(scale=self.scale, size=n))


class SyntheticWaveformNotAvailable(Exception):
    pass


Sebastian Heimann's avatar
Sebastian Heimann committed
675
676
class SyntheticTest(Object):
    inject_solution = Bool.T(default=False)
677
    respect_data_availability = Bool.T(default=False)
Sebastian Heimann's avatar
wip    
Sebastian Heimann committed
678
679
    add_real_noise = Bool.T(default=False)
    toffset_real_noise = Float.T(default=-3600.)
Sebastian Heimann's avatar
Sebastian Heimann committed
680
681
682
683
    x = Dict.T(String.T(), Float.T())

    def __init__(self, **kwargs):
        Object.__init__(self, **kwargs)
684
        self._problem = None
Sebastian Heimann's avatar
Sebastian Heimann committed
685
686
        self._synthetics = None

687
688
689
    def set_problem(self, problem):
        self._problem = problem
        self._synthetics = None
Sebastian Heimann's avatar
Sebastian Heimann committed
690
691

    def get_problem(self):
692
693
694
        if self._problem is None:
            raise SyntheticWaveformNotAvailable(
                'SyntheticTest.set_problem() has not been called yet')
Sebastian Heimann's avatar
Sebastian Heimann committed
695

696
        return self._problem
Sebastian Heimann's avatar
Sebastian Heimann committed
697
698
699
700
701
702
703
704

    def get_x(self):
        problem = self.get_problem()
        if self.x:
            x = problem.preconstrain(
                problem.parameter_array(self.x))

        else:
Sebastian Heimann's avatar
wip    
Sebastian Heimann committed
705
706
707
708
            x = problem.preconstrain(
                problem.pack(
                    problem.base_source))

Sebastian Heimann's avatar
Sebastian Heimann committed
709
710
711
        return x

    def get_synthetics(self):
712
        problem = self.get_problem()
Sebastian Heimann's avatar
Sebastian Heimann committed
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
        if self._synthetics is None:
            x = self.get_x()
            results = problem.forward(x)
            self._synthetics = results

        return self._synthetics

    def get_waveform(self, nslc, tmin, tmax, tfade=0., freqlimits=None):
        synthetics = self.get_synthetics()
        for result in synthetics:
            if result.trace.codes == nslc:
                tr = result.trace.pyrocko_trace()
                tr.extend(tmin - tfade * 2.0, tmax + tfade * 2.0)
                tr = tr.transfer(tfade=tfade, freqlimits=freqlimits)
                tr.chop(tmin, tmax)
728
                return tr
Sebastian Heimann's avatar
wip    
Sebastian Heimann committed
729
730

        return None
Sebastian Heimann's avatar
Sebastian Heimann committed
731
732
733
734


class DatasetConfig(HasPaths):

Sebastian Heimann's avatar
Sebastian Heimann committed
735
736
    stations_path = Path.T(optional=True)
    stations_stationxml_paths = List.T(Path.T())
Sebastian Heimann's avatar
Sebastian Heimann committed
737
738
739
740
741
742
743
744
    events_path = Path.T()
    waveform_paths = List.T(Path.T())
    clippings_path = Path.T(optional=True)
    responses_sacpz_path = Path.T(optional=True)
    responses_stationxml_paths = List.T(Path.T())
    station_corrections_path = Path.T(optional=True)
    apply_correction_factors = Bool.T(default=True)
    apply_correction_delays = Bool.T(default=True)
Sebastian Heimann's avatar
Sebastian Heimann committed
745
    picks_paths = List.T(Path.T())
746
747
748
749
    blacklist = List.T(
        String.T(),
        help='stations/components to be excluded according to their STA, '
             'NET.STA, NET.STA.LOC, or NET.STA.LOC.CHA codes.')
Sebastian Heimann's avatar
flake8    
Sebastian Heimann committed
750
751
752
    whitelist = List.T(
        String.T(),
        optional=True,
753
754
755
756
        help='if not None, list of stations/components to included according '
             'to their STA, NET.STA, NET.STA.LOC, or NET.STA.LOC.CHA codes. '
             'Note: ''when whitelisting on channel level, both, the raw and '
             'the processed channel codes have to be listed.')
Sebastian Heimann's avatar
Sebastian Heimann committed
757
758
759
760
    synthetic_test = SyntheticTest.T(optional=True)

    def __init__(self, *args, **kwargs):
        HasPaths.__init__(self, *args, **kwargs)
761
        self._ds = {}
Sebastian Heimann's avatar
Sebastian Heimann committed
762

763
764
    def get_dataset(self, event_name):
        if event_name not in self._ds:
765
766
767
768
769
770
771
            def extra(path):
                return expand_template(path, dict(
                    event_name=event_name))

            def fp(path):
                return self.expand_path(path, extra=extra)

772
            ds = dataset.Dataset(event_name)
Sebastian Heimann's avatar
Sebastian Heimann committed
773
774
775
776
            ds.add_stations(
                pyrocko_stations_filename=fp(self.stations_path),
                stationxml_filenames=fp(self.stations_stationxml_paths))

Sebastian Heimann's avatar
Sebastian Heimann committed
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
            ds.add_events(filename=fp(self.events_path))
            ds.add_waveforms(paths=fp(self.waveform_paths))
            if self.clippings_path:
                ds.add_clippings(markers_filename=fp(self.clippings_path))

            if self.responses_sacpz_path:
                ds.add_responses(
                    sacpz_dirname=fp(self.responses_sacpz_path))

            if self.responses_stationxml_paths:
                ds.add_responses(
                    stationxml_filenames=fp(self.responses_stationxml_paths))

            if self.station_corrections_path:
                ds.add_station_corrections(
                    filename=fp(self.station_corrections_path))

            ds.apply_correction_factors = self.apply_correction_factors
            ds.apply_correction_delays = self.apply_correction_delays

Sebastian Heimann's avatar
Sebastian Heimann committed
797
798
799
800
            for picks_path in self.picks_paths:
                ds.add_picks(
                    filename=fp(picks_path))

Sebastian Heimann's avatar
Sebastian Heimann committed
801
802
803
804
            ds.add_blacklist(self.blacklist)
            if self.whitelist:
                ds.add_whitelist(self.whitelist)

805
806
            ds.set_synthetic_test(copy.deepcopy(self.synthetic_test))
            self._ds[event_name] = ds
Sebastian Heimann's avatar
Sebastian Heimann committed
807

808
        return self._ds[event_name]
Sebastian Heimann's avatar
Sebastian Heimann committed
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832


def weed(origin, targets, limit, neighborhood=3):

    azimuths = num.zeros(len(targets))
    dists = num.zeros(len(targets))
    for i, target in enumerate(targets):
        _, azimuths[i] = target.azibazi_to(origin)
        dists[i] = target.distance_to(origin)

    badnesses = num.ones(len(targets), dtype=float)
    deleted, meandists_kept = weeding.weed(
        azimuths, dists, badnesses,
        nwanted=limit,
        neighborhood=neighborhood)

    targets_weeded = [
        target for (delete, target) in zip(deleted, targets) if not delete]

    return targets_weeded, meandists_kept, deleted


class TargetConfig(Object):

833
834
    super_group = gf.StringID.T(default='', optional=True)
    group = gf.StringID.T(optional=True)
Sebastian Heimann's avatar
Sebastian Heimann committed
835
836
    distance_min = Float.T(optional=True)
    distance_max = Float.T(optional=True)
837
838
    depth_min = Float.T(optional=True)
    depth_max = Float.T(optional=True)
Sebastian Heimann's avatar
Sebastian Heimann committed
839
840
841
842
843
844
845
    limit = Int.T(optional=True)
    channels = List.T(String.T())
    inner_misfit_config = InnerMisfitConfig.T()
    interpolation = gf.InterpolationMethod.T()
    store_id = gf.StringID.T()
    weight = Float.T(default=1.0)

846
    def get_targets(self, ds, event, default_group):
Sebastian Heimann's avatar
Sebastian Heimann committed
847
848
849
850
851
852
853
854
855
856
857

        origin = event

        targets = []
        for st in ds.get_stations():
            for cha in self.channels:
                target = MisfitTarget(
                    quantity='displacement',
                    codes=st.nsl() + (cha,),
                    lat=st.lat,
                    lon=st.lon,
858
                    depth=st.depth,
Sebastian Heimann's avatar
Sebastian Heimann committed
859
860
861
862
                    interpolation=self.interpolation,
                    store_id=self.store_id,
                    misfit_config=self.inner_misfit_config,
                    manual_weight=self.weight,
863
864
                    super_group=self.super_group,
                    group=self.group or default_group)
Sebastian Heimann's avatar
Sebastian Heimann committed
865
866
867
868
869
870
871
872
873

                if self.distance_min is not None and \
                        target.distance_to(origin) < self.distance_min:
                    continue

                if self.distance_max is not None and \
                        target.distance_to(origin) > self.distance_max:
                    continue

874
875
876
877
878
879
880
881
                if self.depth_min is not None and \
                        target.depth < self.depth_min:
                    continue

                if self.depth_max is not None and \
                        target.depth > self.depth_max:
                    continue

Sebastian Heimann's avatar
Sebastian Heimann committed
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
                azi, _ = target.azibazi_to(origin)
                if cha == 'R':
                    target.azimuth = azi - 180.
                    target.dip = 0.
                elif cha == 'T':
                    target.azimuth = azi - 90.
                    target.dip = 0.
                elif cha == 'Z':
                    target.azimuth = 0.
                    target.dip = -90.

                target.set_dataset(ds)
                targets.append(target)

        if self.limit:
            return weed(origin, targets, self.limit)[0]
        else:
            return targets


class AnalyserConfig(Object):
    niter = Int.T(default=1000)


class SamplerDistributionChoice(StringChoice):
    choices = ['multivariate_normal', 'normal']


class SolverConfig(Object):
    niter_uniform = Int.T(default=1000)
Sebastian Heimann's avatar
Sebastian Heimann committed
912
    niter_transition = Int.T(default=0)
Sebastian Heimann's avatar
Sebastian Heimann committed
913
914
915
916
    niter_explorative = Int.T(default=10000)
    niter_non_explorative = Int.T(default=0)
    sampler_distribution = SamplerDistributionChoice.T(
        default='multivariate_normal')
917
    scatter_scale_transition = Float.T(default=2.0)
918
    scatter_scale = Float.T(default=1.0)
Sebastian Heimann's avatar
Sebastian Heimann committed
919
920
921
922

    def get_solver_kwargs(self):
        return dict(
            niter_uniform=self.niter_uniform,
Sebastian Heimann's avatar
Sebastian Heimann committed
923
            niter_transition=self.niter_transition,
Sebastian Heimann's avatar
Sebastian Heimann committed
924
925
            niter_explorative=self.niter_explorative,
            niter_non_explorative=self.niter_non_explorative,
926
            sampler_distribution=self.sampler_distribution,
927
            scatter_scale_transition=self.scatter_scale_transition,
928
            scatter_scale=self.scatter_scale)
Sebastian Heimann's avatar
Sebastian Heimann committed
929
930


Sebastian Heimann's avatar
Sebastian Heimann committed
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
class EngineConfig(HasPaths):
    gf_stores_from_pyrocko_config = Bool.T(default=True)
    gf_store_superdirs = List.T(Path.T())
    gf_store_dirs = List.T(Path.T())

    def __init__(self, *args, **kwargs):
        HasPaths.__init__(self, *args, **kwargs)
        self._engine = None

    def get_engine(self):
        if self._engine is None:
            fp = self.expand_path
            self._engine = gf.LocalEngine(
                use_config=self.gf_stores_from_pyrocko_config,
                store_superdirs=fp(self.gf_store_superdirs),
                store_dirs=fp(self.gf_store_dirs))

        return self._engine


Sebastian Heimann's avatar
Sebastian Heimann committed
951
952
953
954
955
956
957
class Config(HasPaths):
    rundir_template = Path.T()
    dataset_config = DatasetConfig.T()
    target_configs = List.T(TargetConfig.T())
    problem_config = ProblemConfig.T()
    analyser_config = AnalyserConfig.T(default=AnalyserConfig.D())
    solver_config = SolverConfig.T(default=SolverConfig.D())
Sebastian Heimann's avatar
Sebastian Heimann committed
958
    engine_config = EngineConfig.T(default=EngineConfig.D())
Sebastian Heimann's avatar
Sebastian Heimann committed
959
960
961
962

    def __init__(self, *args, **kwargs):
        HasPaths.__init__(self, *args, **kwargs)

963
964
    def get_dataset(self, event_name):
        return self.dataset_config.get_dataset(event_name)
Sebastian Heimann's avatar
Sebastian Heimann committed
965
966

    def get_targets(self, event):
967
        ds = self.get_dataset(event.name)
Sebastian Heimann's avatar
Sebastian Heimann committed
968
969
970
971
972
973
974
975

        targets = []
        for igroup, target_config in enumerate(self.target_configs):
            targets.extend(target_config.get_targets(
                ds, event, 'group_%i' % igroup))

        return targets

976
977
978
979
980
981
982
983
    def setup_modelling_environment(self, problem):
        problem.set_engine(self.engine_config.get_engine())
        ds = self.get_dataset(problem.base_source.name)
        synt = ds.synthetic_test
        if synt:
            synt.set_problem(problem)
            problem.base_source = problem.unpack(synt.get_x())

Sebastian Heimann's avatar
Sebastian Heimann committed
984
985
    def get_problem(self, event):
        targets = self.get_targets(event)
Sebastian Heimann's avatar
Sebastian Heimann committed
986
        problem = self.problem_config.get_problem(event, targets)
987
        self.setup_modelling_environment(problem)
Sebastian Heimann's avatar
Sebastian Heimann committed
988
        return problem
Sebastian Heimann's avatar
Sebastian Heimann committed
989
990
991
992
993
994
995
996
997
998
999
1000


def sarr(a):
    return ' '.join('%15g' % x for x in a)


def load_problem_info_and_data(dirname, subset=None):
    problem = load_problem_info(dirname)
    xs, misfits = load_problem_data(xjoin(dirname, subset), problem)
    return problem, xs, misfits