core.py

import math
import os
import sys
import logging
import time
import copy
import shutil
import os.path as op
from string import Template

import numpy as num

from pyrocko.guts import load, Object, String, Float, Int, Bool, List, \
    StringChoice, Dict, Timestamp
from pyrocko import orthodrome as od, gf, trace, guts, util, weeding
from pyrocko import parimap, model, gui_util
from pyrocko.guts_array import Array

from grond import dataset

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

guts_prefix = 'grond'


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')

    def get_ydata(self):
        return self.ydata

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


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))


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)
    label = String.T(optional=True)

    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)

    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)

        return ' '.join(l)

    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

    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())
    apply_balancing_weights = Bool.T(default=True)
    base_source = gf.Source.T()

    def __init__(self, **kwargs):
        Object.__init__(self, **kwargs)
        self._bootstrap_weights = None
        self._target_weights = None
        self._engine = None
        self._group_mask = None

    def get_engine(self):
        return self._engine

    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)

    @property
    def parameter_names(self):
        return [p.name for p in self.combined]

    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, :]

    def set_engine(self, engine):
        self._engine = engine

    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

        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


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


class DomainChoice(StringChoice):
    choices = [
        'time_domain',
        'frequency_domain',
        'envelope',
        'absolute',
        'cc_max_norm']


class InnerMisfitConfig(Object):
    fmin = Float.T()
    fmax = Float.T()
    ffactor = Float.T(default=1.5)
    tmin = gf.Timing.T()
    tmax = gf.Timing.T()
    pick_synthetic_traveltime = gf.Timing.T(optional=True)
    pick_phasename = String.T(optional=True)
    domain = DomainChoice.T(default='time_domain')

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


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


class NoAnalysisResults(Exception):
    pass


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)


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)
    super_group = gf.StringID.T()
    group = gf.StringID.T()

    def __init__(self, **kwargs):
        gf.Target.__init__(self, **kwargs)
        self._ds = None
        self._result_mode = 'sparse'

    def string_id(self):
        return '.'.join(x for x in (
            self.super_group, self.group) + self.codes if x)

    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

    def set_result_mode(self, result_mode):
        self._result_mode = result_mode

    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)

        ds = self.get_dataset()

        tobs_shift = 0.0
        tsyn = None
        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

        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)

        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

        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)

            if tobs_shift != 0.0:
                tr_obs = tr_obs.copy()
                tr_obs.shift(-tobs_shift)

            mr = misfit(
                tr_obs, tr_syn,
                taper=trace.CosTaper(
                    tmin_fit - tfade,
                    tmin_fit,
                    tmax_fit,
                    tmax_fit + tfade),
                domain=config.domain,
                exponent=2,
                flip=self.flip_norm,
                result_mode=self._result_mode)

            mr.tobs_shift = float(tobs_shift)
            mr.tsyn_pick = float_or_none(tsyn)

            return mr

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


def misfit(
        tr_obs, tr_syn, taper, domain, exponent, flip, result_mode='sparse'):

    '''
    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*
    :param result_mode: ``'full'``, include traces and spectra or ``'sparse'``,
        include only misfit and normalization factor in result

    :returns: object of type :py:class:`MisfitResult`
    '''

    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)

    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)

    elif result_mode == 'sparse':
        result = MisfitResult(
            misfit_value=m,
            misfit_norm=n)
    else:
        assert False

    return result


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

    df = None
    trspec_proc = None

    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)

        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)

    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


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)

    def get_basepath(self):
        assert self._basepath is not None
        return self._basepath

    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:

            self.path_prefix = op.normpath(xjoin(xrelpath(
                self._basepath, new_basepath), self.path_prefix))

        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

    def expand_path(self, path):
        assert self._basepath is not None

        path_prefix = self.path_prefix or self._parent_path_prefix

        if path is None:
            return None
        elif isinstance(path, basestring):
            return op.normpath(xjoin(self._basepath, xjoin(path_prefix, path)))
        else:
            return [
                op.normpath(xjoin(self._basepath, xjoin(path_prefix, p)))
                for p in path]


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
        return 1.0 + freqs*(
            self._rstate.normal(scale=self.scale, size=n) +
            0.0J * self._rstate.normal(scale=self.scale, size=n))


class SyntheticWaveformNotAvailable(Exception):
    pass


class SyntheticTest(Object):
    inject_solution = Bool.T(default=False)
    respect_data_availability = Bool.T(default=False)
    add_real_noise = Bool.T(default=False)
    toffset_real_noise = Float.T(default=-3600.)
    x = Dict.T(String.T(), Float.T())

    def __init__(self, **kwargs):
        Object.__init__(self, **kwargs)
        self._problem = None
        self._synthetics = None

    def set_problem(self, problem):
        self._problem = problem
        self._synthetics = None

    def get_problem(self):
        if self._problem is None:
            raise SyntheticWaveformNotAvailable(
                'SyntheticTest.set_problem() has not been called yet')

        return self._problem

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

        else:
            x = problem.preconstrain(
                problem.pack(
                    problem.base_source))

        return x

    def get_synthetics(self):
        problem = self.get_problem()
        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)
                return tr

        return None


class DatasetConfig(HasPaths):

    stations_path = Path.T(optional=True)
    stations_stationxml_paths = List.T(Path.T())
    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)
    picks_paths = List.T(Path.T())
    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.')
    whitelist = List.T(
        String.T(),
        optional=True,
        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.')
    synthetic_test = SyntheticTest.T(optional=True)

    def __init__(self, *args, **kwargs):
        HasPaths.__init__(self, *args, **kwargs)
        self._ds = {}

    def get_dataset(self, event_name):
        if event_name not in self._ds:
            fp = self.expand_path
            ds = dataset.Dataset(event_name)
            ds.add_stations(
                pyrocko_stations_filename=fp(self.stations_path),
                stationxml_filenames=fp(self.stations_stationxml_paths))

            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

            for picks_path in self.picks_paths:
                ds.add_picks(
                    filename=fp(picks_path))

            ds.add_blacklist(self.blacklist)
            if self.whitelist:
                ds.add_whitelist(self.whitelist)

            ds.set_synthetic_test(copy.deepcopy(self.synthetic_test))
            self._ds[event_name] = ds

        return self._ds[event_name]


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):

    super_group = gf.StringID.T(default='', optional=True)
    group = gf.StringID.T(optional=True)
    distance_min = Float.T(optional=True)
    distance_max = Float.T(optional=True)
    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)

    def get_targets(self, ds, event, default_group):

        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,
                    depth=st.depth,
                    interpolation=self.interpolation,
                    store_id=self.store_id,
                    misfit_config=self.inner_misfit_config,
                    manual_weight=self.weight,
                    super_group=self.super_group,
                    group=self.group or default_group)

                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

                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)
    niter_transition = Int.T(default=0)
    niter_explorative = Int.T(default=10000)
    niter_non_explorative = Int.T(default=0)
    sampler_distribution = SamplerDistributionChoice.T(
        default='multivariate_normal')
    scatter_scale_transition = Float.T(default=2.0)
    scatter_scale = Float.T(default=1.0)

    def get_solver_kwargs(self):
        return dict(
            niter_uniform=self.niter_uniform,
            niter_transition=self.niter_transition,
            niter_explorative=self.niter_explorative,
            niter_non_explorative=self.niter_non_explorative,
            sampler_distribution=self.sampler_distribution,
            scatter_scale_transition=self.scatter_scale_transition,
            scatter_scale=self.scatter_scale)


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


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())
    engine_config = EngineConfig.T(default=EngineConfig.D())

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

    def get_dataset(self, event_name):
        return self.dataset_config.get_dataset(event_name)

    def get_targets(self, event):
        ds = self.get_dataset(event.name)

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

        return targets

    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())

    def get_problem(self, event):
        targets = self.get_targets(event)
        problem = self.problem_config.get_problem(event, targets)
        self.setup_modelling_environment(problem)
        return problem


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


def load_problem_info(dirname):
    fn = op.join(dirname, 'problem.yaml')
    return guts.load(filename=fn)


def load_problem_data(dirname, problem):
    fn = op.join(dirname, 'x')
    with open(fn, 'r') as f:
        nmodels = os.fstat(f.fileno()).st_size / (problem.nparameters * 8)
        data = num.fromfile(
            f, dtype='<f8',
            count=nmodels*problem.nparameters).astype(num.float)

    nmodels = data.size/problem.nparameters
    xs = data.reshape((nmodels, problem.nparameters))

    fn = op.join(dirname, 'misfits')
    with open(fn, 'r') as f:
        data = num.fromfile(
            f, dtype='<f8', count=nmodels*problem.ntargets*2).astype(num.float)