示例#1
0
文件: fitter.py 项目: Hoptune/MOSFiT
    def fit_data(self,
                 event_name='',
                 method=None,
                 iterations=None,
                 frack_step=20,
                 num_walkers=None,
                 num_temps=1,
                 burn=None,
                 post_burn=None,
                 fracking=True,
                 gibbs=False,
                 pool=None,
                 output_path='',
                 suffix='',
                 write=False,
                 upload=False,
                 upload_token='',
                 check_upload_quality=True,
                 convergence_type=None,
                 convergence_criteria=None,
                 save_full_chain=False,
                 extra_outputs=None):
        """Fit the data for a given event.

        Fitting performed using a combination of emcee and fracking.
        """
        if self._speak:
            speak('Fitting ' + event_name, self._speak)
        from mosfit.__init__ import __version__
        global model
        model = self._model
        prt = self._printer

        upload_model = upload and iterations > 0

        if pool is not None:
            self._pool = pool

        if upload:
            try:
                import dropbox
            except ImportError:
                if self._test:
                    pass
                else:
                    prt.message('install_db', error=True)
                    raise

        if not self._pool.is_master():
            try:
                self._pool.wait()
            except (KeyboardInterrupt, SystemExit):
                pass
            return (None, None, None)

        self._method = method

        if self._method == 'nester':
            self._sampler = Nester(self, model, iterations, burn, post_burn,
                                   num_walkers, convergence_criteria,
                                   convergence_type, gibbs, fracking,
                                   frack_step)
        else:
            self._sampler = Ensembler(self, model, iterations, burn, post_burn,
                                      num_temps, num_walkers,
                                      convergence_criteria, convergence_type,
                                      gibbs, fracking, frack_step)

        self._sampler.run(self._walker_data)

        prt.message('constructing')

        if write:
            if self._speak:
                speak(prt._strings['saving_output'], self._speak)

        if self._event_path:
            entry = Entry.init_from_file(catalog=None,
                                         name=self._event_name,
                                         path=self._event_path,
                                         merge=False,
                                         pop_schema=False,
                                         ignore_keys=[ENTRY.MODELS],
                                         compare_to_existing=False)
            new_photometry = []
            for photo in entry.get(ENTRY.PHOTOMETRY, []):
                if PHOTOMETRY.REALIZATION not in photo:
                    new_photometry.append(photo)
            if len(new_photometry):
                entry[ENTRY.PHOTOMETRY] = new_photometry
        else:
            entry = Entry(name=self._event_name)

        uentry = Entry(name=self._event_name)
        data_keys = set()
        for task in model._call_stack:
            if model._call_stack[task]['kind'] == 'data':
                data_keys.update(
                    list(model._call_stack[task].get('keys', {}).keys()))
        entryhash = entry.get_hash(keys=list(sorted(list(data_keys))))

        # Accumulate all the sources and add them to each entry.
        sources = []
        for root in model._references:
            for ref in model._references[root]:
                sources.append(entry.add_source(**ref))
        sources.append(entry.add_source(**self._DEFAULT_SOURCE))
        source = ','.join(sources)

        usources = []
        for root in model._references:
            for ref in model._references[root]:
                usources.append(uentry.add_source(**ref))
        usources.append(uentry.add_source(**self._DEFAULT_SOURCE))
        usource = ','.join(usources)

        model_setup = OrderedDict()
        for ti, task in enumerate(model._call_stack):
            task_copy = deepcopy(model._call_stack[task])
            if (task_copy['kind'] == 'parameter'
                    and task in model._parameter_json):
                task_copy.update(model._parameter_json[task])
            model_setup[task] = task_copy
        modeldict = OrderedDict([(MODEL.NAME, model._model_name),
                                 (MODEL.SETUP, model_setup),
                                 (MODEL.CODE, 'MOSFiT'),
                                 (MODEL.DATE, time.strftime("%Y/%m/%d")),
                                 (MODEL.VERSION, __version__),
                                 (MODEL.SOURCE, source)])

        self._sampler.prepare_output(check_upload_quality, upload)

        self._sampler.append_output(modeldict)

        umodeldict = deepcopy(modeldict)
        umodeldict[MODEL.SOURCE] = usource
        modelhash = get_model_hash(umodeldict,
                                   ignore_keys=[MODEL.DATE, MODEL.SOURCE])
        umodelnum = uentry.add_model(**umodeldict)

        if self._sampler._upload_model is not None:
            upload_model = self._sampler._upload_model

        modelnum = entry.add_model(**modeldict)

        samples, probs, weights = self._sampler.get_samples()

        extras = OrderedDict()
        samples_to_plot = self._sampler._nwalkers

        if isinstance(self._sampler, Nester):
            icdf = np.cumsum(np.concatenate(([0.0], weights)))
            draws = np.random.rand(samples_to_plot)
            indices = np.searchsorted(icdf, draws) - 1
        else:
            indices = list(range(samples_to_plot))

        ri = 0
        selected_extra = False
        for xi, x in enumerate(samples):
            ri = ri + 1
            prt.message('outputting_walker', [ri, len(samples)],
                        inline=True,
                        min_time=0.2)
            if xi in indices:
                output = model.run_stack(x, root='output')
                if extra_outputs is not None:
                    if not extra_outputs and not selected_extra:
                        extra_options = list(output.keys())
                        prt.message('available_keys')
                        for opt in extra_options:
                            prt.prt('- {}'.format(opt))
                        selected_extra = True
                    for key in extra_outputs:
                        new_val = output.get(key, [])
                        new_val = all_to_list(new_val)
                        extras.setdefault(key, []).append(new_val)
                for i in range(len(output['times'])):
                    if not np.isfinite(output['model_observations'][i]):
                        continue
                    photodict = {
                        PHOTOMETRY.TIME:
                        output['times'][i] + output['min_times'],
                        PHOTOMETRY.MODEL: modelnum,
                        PHOTOMETRY.SOURCE: source,
                        PHOTOMETRY.REALIZATION: str(ri)
                    }
                    if output['observation_types'][i] == 'magnitude':
                        photodict[PHOTOMETRY.BAND] = output['bands'][i]
                        photodict[PHOTOMETRY.
                                  MAGNITUDE] = output['model_observations'][i]
                        photodict[PHOTOMETRY.
                                  E_MAGNITUDE] = output['model_variances'][i]
                    elif output['observation_types'][i] == 'magcount':
                        if output['model_observations'][i] == 0.0:
                            continue
                        photodict[PHOTOMETRY.BAND] = output['bands'][i]
                        photodict[PHOTOMETRY.
                                  COUNT_RATE] = output['model_observations'][i]
                        photodict[PHOTOMETRY.
                                  E_COUNT_RATE] = output['model_variances'][i]
                        photodict[PHOTOMETRY.MAGNITUDE] = -2.5 * np.log10(
                            output['model_observations']
                            [i]) + output['all_zeropoints'][i]
                        photodict[PHOTOMETRY.E_UPPER_MAGNITUDE] = 2.5 * (
                            np.log10(output['model_observations'][i] +
                                     output['model_variances'][i]) -
                            np.log10(output['model_observations'][i]))
                        if (output['model_variances'][i] >
                                output['model_observations'][i]):
                            photodict[PHOTOMETRY.UPPER_LIMIT] = True
                        else:
                            photodict[PHOTOMETRY.E_LOWER_MAGNITUDE] = 2.5 * (
                                np.log10(output['model_observations'][i]) -
                                np.log10(output['model_observations'][i] -
                                         output['model_variances'][i]))
                    elif output['observation_types'][i] == 'fluxdensity':
                        photodict[PHOTOMETRY.FREQUENCY] = output[
                            'frequencies'][i] * frequency_unit('GHz')
                        photodict[PHOTOMETRY.FLUX_DENSITY] = output[
                            'model_observations'][i] * flux_density_unit('µJy')
                        photodict[PHOTOMETRY.E_LOWER_FLUX_DENSITY] = (
                            photodict[PHOTOMETRY.FLUX_DENSITY] -
                            (10.0**
                             (np.log10(photodict[PHOTOMETRY.FLUX_DENSITY]) -
                              output['model_variances'][i] / 2.5)) *
                            flux_density_unit('µJy'))
                        photodict[PHOTOMETRY.E_UPPER_FLUX_DENSITY] = (
                            10.0**(np.log10(photodict[PHOTOMETRY.FLUX_DENSITY])
                                   + output['model_variances'][i] / 2.5) *
                            flux_density_unit('µJy') -
                            photodict[PHOTOMETRY.FLUX_DENSITY])
                        photodict[PHOTOMETRY.U_FREQUENCY] = 'GHz'
                        photodict[PHOTOMETRY.U_FLUX_DENSITY] = 'µJy'
                    elif output['observation_types'][i] == 'countrate':
                        photodict[PHOTOMETRY.
                                  COUNT_RATE] = output['model_observations'][i]
                        photodict[PHOTOMETRY.E_LOWER_COUNT_RATE] = (
                            photodict[PHOTOMETRY.COUNT_RATE] -
                            (10.0**(np.log10(photodict[PHOTOMETRY.COUNT_RATE])
                                    - output['model_variances'][i] / 2.5)))
                        photodict[PHOTOMETRY.E_UPPER_COUNT_RATE] = (
                            10.0**(np.log10(photodict[PHOTOMETRY.COUNT_RATE]) +
                                   output['model_variances'][i] / 2.5) -
                            photodict[PHOTOMETRY.COUNT_RATE])
                        photodict[PHOTOMETRY.U_COUNT_RATE] = 's^-1'
                    if ('model_upper_limits' in output
                            and output['model_upper_limits'][i]):
                        photodict[PHOTOMETRY.UPPER_LIMIT] = bool(
                            output['model_upper_limits'][i])
                    if self._limiting_magnitude is not None:
                        photodict[PHOTOMETRY.SIMULATED] = True
                    if 'telescopes' in output and output['telescopes'][i]:
                        photodict[
                            PHOTOMETRY.TELESCOPE] = output['telescopes'][i]
                    if 'systems' in output and output['systems'][i]:
                        photodict[PHOTOMETRY.SYSTEM] = output['systems'][i]
                    if 'bandsets' in output and output['bandsets'][i]:
                        photodict[PHOTOMETRY.BAND_SET] = output['bandsets'][i]
                    if 'instruments' in output and output['instruments'][i]:
                        photodict[
                            PHOTOMETRY.INSTRUMENT] = output['instruments'][i]
                    if 'modes' in output and output['modes'][i]:
                        photodict[PHOTOMETRY.MODE] = output['modes'][i]
                    entry.add_photometry(compare_to_existing=False,
                                         check_for_dupes=False,
                                         **photodict)

                    uphotodict = deepcopy(photodict)
                    uphotodict[PHOTOMETRY.SOURCE] = umodelnum
                    uentry.add_photometry(compare_to_existing=False,
                                          check_for_dupes=False,
                                          **uphotodict)
            else:
                output = model.run_stack(x, root='objective')

            parameters = OrderedDict()
            derived_keys = set()
            pi = 0
            for ti, task in enumerate(model._call_stack):
                # if task not in model._free_parameters:
                #     continue
                if model._call_stack[task]['kind'] != 'parameter':
                    continue
                paramdict = OrderedDict(
                    (('latex', model._modules[task].latex()),
                     ('log', model._modules[task].is_log())))
                if task in model._free_parameters:
                    poutput = model._modules[task].process(
                        **{'fraction': x[pi]})
                    value = list(poutput.values())[0]
                    paramdict['value'] = value
                    paramdict['fraction'] = x[pi]
                    pi = pi + 1
                else:
                    if output.get(task, None) is not None:
                        paramdict['value'] = output[task]
                parameters.update({model._modules[task].name(): paramdict})
                # Dump out any derived parameter keys
                derived_keys.update(model._modules[task].get_derived_keys())

            for key in list(sorted(list(derived_keys))):
                if (output.get(key, None) is not None
                        and key not in parameters):
                    parameters.update({key: {'value': output[key]}})

            realdict = {REALIZATION.PARAMETERS: parameters}
            if probs is not None:
                realdict[REALIZATION.SCORE] = str(probs[xi])
            else:
                realdict[REALIZATION.SCORE] = str(
                    ln_likelihood(x) + ln_prior(x))
            realdict[REALIZATION.ALIAS] = str(ri)
            realdict[REALIZATION.WEIGHT] = str(weights[xi])
            entry[ENTRY.MODELS][0].add_realization(check_for_dupes=False,
                                                   **realdict)
            urealdict = deepcopy(realdict)
            uentry[ENTRY.MODELS][0].add_realization(check_for_dupes=False,
                                                    **urealdict)
        prt.message('all_walkers_written', inline=True)

        entry.sanitize()
        oentry = {self._event_name: entry._ordered(entry)}
        uentry.sanitize()
        ouentry = {self._event_name: uentry._ordered(uentry)}

        uname = '_'.join([self._event_name, entryhash, modelhash])

        if output_path and not os.path.exists(output_path):
            os.makedirs(output_path)

        if not os.path.exists(model.get_products_path()):
            os.makedirs(model.get_products_path())

        if write:
            prt.message('writing_complete')
            with open_atomic(
                    os.path.join(model.get_products_path(), 'walkers.json'),
                    'w') as flast, open_atomic(
                        os.path.join(
                            model.get_products_path(), self._event_name +
                            (('_' + suffix) if suffix else '') + '.json'),
                        'w') as feven:
                entabbed_json_dump(oentry, flast, separators=(',', ':'))
                entabbed_json_dump(oentry, feven, separators=(',', ':'))

            if save_full_chain:
                prt.message('writing_full_chain')
                with open_atomic(
                        os.path.join(model.get_products_path(), 'chain.json'),
                        'w') as flast, open_atomic(
                            os.path.join(
                                model.get_products_path(),
                                self._event_name + '_chain' +
                                (('_' + suffix) if suffix else '') + '.json'),
                            'w') as feven:
                    entabbed_json_dump(self._sampler._all_chain.tolist(),
                                       flast,
                                       separators=(',', ':'))
                    entabbed_json_dump(self._sampler._all_chain.tolist(),
                                       feven,
                                       separators=(',', ':'))

            if extra_outputs is not None:
                prt.message('writing_extras')
                with open_atomic(
                        os.path.join(model.get_products_path(), 'extras.json'),
                        'w') as flast, open_atomic(
                            os.path.join(
                                model.get_products_path(),
                                self._event_name + '_extras' +
                                (('_' + suffix) if suffix else '') + '.json'),
                            'w') as feven:
                    entabbed_json_dump(extras, flast, separators=(',', ':'))
                    entabbed_json_dump(extras, feven, separators=(',', ':'))

            prt.message('writing_model')
            with open_atomic(
                    os.path.join(model.get_products_path(), 'upload.json'),
                    'w') as flast, open_atomic(
                        os.path.join(
                            model.get_products_path(), uname +
                            (('_' + suffix) if suffix else '') + '.json'),
                        'w') as feven:
                entabbed_json_dump(ouentry, flast, separators=(',', ':'))
                entabbed_json_dump(ouentry, feven, separators=(',', ':'))

        if upload_model:
            prt.message('ul_fit', [entryhash, self._sampler._modelhash])
            upayload = entabbed_json_dumps(ouentry, separators=(',', ':'))
            try:
                dbx = dropbox.Dropbox(upload_token)
                dbx.files_upload(upayload.encode(),
                                 '/' + uname + '.json',
                                 mode=dropbox.files.WriteMode.overwrite)
                prt.message('ul_complete')
            except Exception:
                if self._test:
                    pass
                else:
                    raise

        if upload:
            for ce in self._converter.get_converted():
                dentry = Entry.init_from_file(catalog=None,
                                              name=ce[0],
                                              path=ce[1],
                                              merge=False,
                                              pop_schema=False,
                                              ignore_keys=[ENTRY.MODELS],
                                              compare_to_existing=False)

                dentry.sanitize()
                odentry = {ce[0]: uentry._ordered(dentry)}
                dpayload = entabbed_json_dumps(odentry, separators=(',', ':'))
                text = prt.message('ul_devent', [ce[0]], prt=False)
                ul_devent = prt.prompt(text, kind='bool', message=False)
                if ul_devent:
                    dpath = '/' + slugify(
                        ce[0] + '_' + dentry[ENTRY.SOURCES][0].get(
                            SOURCE.BIBCODE, dentry[ENTRY.SOURCES][0].get(
                                SOURCE.NAME, 'NOSOURCE'))) + '.json'
                    try:
                        dbx = dropbox.Dropbox(upload_token)
                        dbx.files_upload(
                            dpayload.encode(),
                            dpath,
                            mode=dropbox.files.WriteMode.overwrite)
                        prt.message('ul_complete')
                    except Exception:
                        if self._test:
                            pass
                        else:
                            raise

        return (entry, samples, probs)
示例#2
0
    def generate_event_list(self, event_list):
        """Generate a list of events and/or convert events to JSON format."""
        prt = self._printer
        cidict = OrderedDict()
        intro_shown = False

        new_event_list = []
        previous_file = None
        for event in event_list:
            rsource = {SOURCE.NAME: self._DEFAULT_SOURCE}
            use_self_source = None
            new_events = []
            toffset = Decimal('0')
            if ('.' in event and os.path.isfile(event) and
                    not event.endswith('.json')):
                if not intro_shown:
                    prt.message('converter_info')
                    intro_shown = True

                prt.message('converting_to_json', [event])

                with open(event, 'r') as f:
                    ftxt = f.read()

                # Try a couple of table formats from astropy.
                table = None
                try:
                    table = read(ftxt, Reader=Cds, guess=False)
                except Exception:
                    pass
                else:
                    prt.message('convert_cds')
                    flines = [table.colnames] + [
                        list(x) for x in np.array(table).tolist()]
                    for i in range(len(flines)):
                        flines[i] = [str(x) for x in flines[i]]

                try:
                    table = read(ftxt, Reader=Latex, guess=False)
                except Exception:
                    pass
                else:
                    prt.message('convert_latex')
                    flines = [table.colnames] + [
                        list(x) for x in np.array(table).tolist()]

                if table is None:
                    # Count to try and determine delimiter.
                    delims = [' ', '\t', ',', ';', '|', '&']
                    delimnames = [
                        'Space: ` `', 'Tab: `\t`', 'Comma: `,`',
                        'Semi-colon: `;`', 'Bar: `|`', 'Ampersand: `&`']
                    delim = None
                    delimcounts = [ftxt.count(x) for x in delims]
                    maxdelimcount = max(delimcounts)
                    delim = delims[delimcounts.index(maxdelimcount)]
                    # If two delimiter options are close in count, ask user.
                    for i, x in enumerate(delimcounts):
                        if x > 0.5 * maxdelimcount and delims[i] != delim:
                            delim = None
                    if delim is None:
                        odelims = list(np.array(delimnames)[
                            np.array(delimcounts) > 0])
                        delim = delims[prt.prompt(
                            'delim', kind='option', options=odelims) - 1]
                    ad = list(delims)
                    ad.remove(delim)
                    ad = ''.join(ad)

                    fsplit = ftxt.splitlines()
                    fsplit = [
                        x.replace('$', '').replace('\\pm', delim)
                        .replace('±', delim).replace('(', delim + '(')
                        .strip(ad + '()# ').replace('′', "'")
                        for x in fsplit]
                    flines = []
                    for fs in fsplit:
                        flines.append(list(
                            csv.reader([fs], delimiter=delim))[0])

                    flines = [[
                        x.strip(ad + '#$()\\')
                        for x in y] for y in flines]

                    # Find band columns if they exist and insert error columns
                    # if they don't exist.
                    for fi, fl in enumerate(list(flines)):
                        flcopy = list(fl)
                        offset = 0
                        if not any([is_number(x) for x in fl]):
                            for fci, fc in enumerate(fl):
                                if (fc in self._band_names and
                                    (fci == len(fl) - 1 or
                                     fl[fci + 1] not in self._emagstrs)):
                                    flcopy.insert(fci + 1 + offset, 'e mag')
                                    offset += 1
                        flines[fi] = flcopy

                    # Find the most frequent column count. These are probably
                    # the tables we wish to read.
                    flens = [len(x) for x in flines]
                    ncols = Counter(flens).most_common(1)[0][0]

                    newlines = []
                    potential_name = None
                    for fi, fl in enumerate(flines):
                        if (len(fl) and flens[fi] == 1 and
                            fi < len(flines) - 1 and
                                flens[fi + 1] == ncols and not len(newlines)):
                            potential_name = fl[0]
                        if flens[fi] == ncols:
                            if potential_name is not None and any(
                                    [is_number(x) for x in fl]):
                                newlines.append([potential_name] + list(fl))
                            else:
                                newlines.append(list(fl))
                    flines = newlines
                    for fi, fl in enumerate(flines):
                        if len(fl) == ncols and potential_name is not None:
                            if not any([is_number(x) for x in fl]):
                                flines[fi] = ['name'] + list(fl)

                # If none of the rows contain numeric data, the file
                # is likely a list of transient names.
                if (len(flines) and
                    (not any(any([is_number(x) or x == '' for x in y])
                             for y in flines) or
                     len(flines) == 1)):
                    new_events = [
                        it for s in flines for it in s]

                # If last row is numeric, then likely this is a file with
                # transient data.
                elif (len(flines) > 1 and
                        any([is_number(x) for x in flines[-1]])):

                    # Check that each row has the same number of columns.
                    if len(set([len(x) for x in flines])) > 1:
                        print(set([len(x) for x in flines]))
                        raise ValueError(
                            'Number of columns in each row not '
                            'consistent!')

                    if len(cidict) and len(new_event_list):
                        msg = ('is_file_same' if
                               previous_file else 'is_event_same')
                        reps = [previous_file] if previous_file else [''.join(
                            new_event_list[-1].split('.')[:-1])]
                        text = prt.text(msg, reps)
                        is_same = prt.prompt(text, message=False,
                                             kind='bool')
                        if not is_same:
                            cidict = OrderedDict()

                    # If the first row has no numbers it is likely a header.
                    if not len(cidict):
                        self.assign_columns(cidict, flines)

                    perms = 1
                    for key in cidict:
                        if isinstance(cidict[key], list) and not isinstance(
                                cidict[key], string_types):
                            if cidict[key][0] != 'j':
                                perms = len(cidict[key])

                    # Get event name (if single event) or list of names from
                    # table.
                    event_names = []
                    if ENTRY.NAME in cidict:
                        for fi, fl in enumerate(flines):
                            flines[fi][cidict[ENTRY.NAME]] = name_clean(
                                fl[cidict[ENTRY.NAME]])
                        event_names = list(sorted(set([
                            x[cidict[ENTRY.NAME]] for x in flines[
                                self._first_data:]])))
                        new_events = [x + '.json' for x in event_names]
                    else:
                        new_event_name = '.'.join(event.split(
                            '.')[:-1]).split('/')[-1]
                        text = prt.message(
                            'is_event_name', [new_event_name], prt=False)
                        is_name = prt.prompt(text, message=False,
                                             kind='bool', default='y')
                        if not is_name:
                            new_event_name = ''
                            while new_event_name.strip() == '':
                                new_event_name = prt.prompt(
                                    'enter_name', kind='string')
                        event_names.append(new_event_name)
                        new_events = [new_event_name + '.json']

                    # Create a new event, populate the photometry, and dump
                    # to a JSON file in the run directory.
                    entries = OrderedDict([(x, Entry(name=x))
                                           for x in event_names])

                    # Clean up the data a bit now that we know the column
                    # identities.

                    # Strip common prefixes/suffixes from band names
                    if PHOTOMETRY.BAND in cidict:
                        bi = cidict[PHOTOMETRY.BAND]
                        for d in [True, False]:
                            if not isinstance(bi, (int, np.integer)):
                                break
                            strip_cols = []
                            lens = [len(x[bi])
                                    for x in flines[self._first_data:]]
                            llen = min(lens)
                            ra = range(llen) if d else range(-1, -llen - 1, -1)
                            for li in ra:
                                letter = None
                                for row in list(flines[self._first_data:]):
                                    if letter is None:
                                        letter = row[bi][li]
                                    elif row[bi][li] != letter:
                                        letter = None
                                        break
                                if letter is not None:
                                    strip_cols.append(li)
                                else:
                                    break
                            if len(strip_cols) == llen:
                                break
                            for ri in range(len(flines[self._first_data:])):
                                flines[self._first_data + ri][bi] = ''.join(
                                    [c for i, c in enumerate(flines[
                                        self._first_data + ri][bi])
                                     if (i if d else i - len(flines[
                                         self._first_data + ri][bi])) not in
                                     strip_cols])

                    if (PHOTOMETRY.TIME in cidict and
                            (not isinstance(cidict[PHOTOMETRY.TIME], list) or
                             len(cidict[PHOTOMETRY.TIME]) <= 2)):
                        bi = cidict[PHOTOMETRY.TIME]

                        if isinstance(bi, list) and not isinstance(
                            bi, string_types) and isinstance(
                                bi[0], string_types) and bi[0] == 'jd':
                            bi = bi[-1]

                        mmtimes = [float(x[bi])
                                   for x in flines[self._first_data:]]
                        mintime, maxtime = min(mmtimes), max(mmtimes)

                        if mintime < 10000:
                            while True:
                                try:
                                    response = prt.prompt(
                                        'small_time_offset', kind='string')
                                    if response is not None:
                                        toffset = Decimal(response)
                                    break
                                except Exception:
                                    pass
                        elif maxtime > 60000 and cidict[
                                PHOTOMETRY.TIME][0] != 'jd':
                            isjd = prt.prompt(
                                'large_time_offset',
                                kind='bool', default='y')
                            if isjd:
                                toffset = Decimal('-2400000.5')

                    for row in flines[self._first_data:]:
                        photodict = {}
                        rname = (row[cidict[ENTRY.NAME]]
                                 if ENTRY.NAME in cidict else event_names[0])
                        for pi in range(perms):
                            sources = set()
                            for key in cidict:
                                if key in self._bool_keys:
                                    rval = row[cidict[key]]

                                    if rval in self._FALSE_VALS:
                                        rval = False
                                    elif rval in self._TRUE_VALS:
                                        rval = True

                                    if type(rval) != 'bool':
                                        try:
                                            rval = bool(rval)
                                        except Exception:
                                            pass

                                    if type(rval) != 'bool':
                                        try:
                                            rval = bool(float(rval))
                                        except Exception:
                                            rval = True

                                    if not rval:
                                        continue
                                    row[cidict[key]] = rval
                                elif key == 'reference':
                                    if (isinstance(cidict[key],
                                                   string_types) and
                                            len(cidict[key]) == 19):
                                        new_src = entries[rname].add_source(
                                            bibcode=cidict[key])
                                        sources.update(new_src)
                                        row[
                                            cidict[key]] = new_src
                                elif key == ENTRY.NAME:
                                    continue
                                elif (isinstance(key, Key) and
                                        key.type == KEY_TYPES.TIME and
                                        isinstance(cidict[key], list) and not
                                        isinstance(cidict[key],
                                                   string_types)):
                                    tval = np.array(row)[np.array(cidict[key][
                                        1:], dtype=int)]
                                    if cidict[key][0] == 'j':
                                        date = '-'.join([x.zfill(2) for x in
                                                         tval])
                                        date = self._month_rep.sub(
                                            lambda x: self._MONTH_IDS[
                                                x.group()], date)
                                        photodict[key] = str(
                                            astrotime(date, format='isot').mjd)
                                    elif cidict[key][0] == 'jd':
                                        photodict[key] = str(
                                            jd_to_mjd(Decimal(tval[-1])))
                                    continue

                                val = cidict[key]
                                if (isinstance(val, list) and not
                                        isinstance(val, string_types)):
                                    val = val[pi]
                                    if isinstance(val, string_types):
                                        if val != '':
                                            photodict[key] = val
                                    else:
                                        photodict[key] = row[val]
                                else:
                                    if isinstance(val, string_types):
                                        if val != '':
                                            photodict[key] = val
                                    else:
                                        photodict[key] = row[val]
                            if self._data_type == 2:
                                if self._zp:
                                    photodict[PHOTOMETRY.ZERO_POINT] = self._zp
                                else:
                                    photodict[PHOTOMETRY.ZERO_POINT] = (
                                        row[cidict[PHOTOMETRY.ZERO_POINT][pi]]
                                        if isinstance(cidict[
                                            PHOTOMETRY.ZERO_POINT], list) else
                                        row[cidict[PHOTOMETRY.ZERO_POINT]])
                                zpp = photodict[PHOTOMETRY.ZERO_POINT]
                                cc = (
                                    row[cidict[PHOTOMETRY.COUNT_RATE][pi]] if
                                    isinstance(cidict[
                                        PHOTOMETRY.COUNT_RATE], list) else
                                    row[cidict[PHOTOMETRY.COUNT_RATE]])
                                ecc = (
                                    row[cidict[PHOTOMETRY.E_COUNT_RATE][pi]] if
                                    isinstance(cidict[
                                        PHOTOMETRY.E_COUNT_RATE], list) else
                                    row[cidict[PHOTOMETRY.E_COUNT_RATE]])
                                if '<' in cc:
                                    set_pd_mag_from_counts(
                                        photodict, ec=cc.strip('<'), zp=zpp)
                                else:
                                    set_pd_mag_from_counts(
                                        photodict, c=cc, ec=ecc, zp=zpp)
                            elif self._data_type == 3:
                                photodict[
                                    PHOTOMETRY.U_FLUX_DENSITY] = self._ufd
                                if PHOTOMETRY.U_FLUX_DENSITY in cidict:
                                    photodict[PHOTOMETRY.U_FLUX_DENSITY] = (
                                        row[cidict[
                                            PHOTOMETRY.U_FLUX_DENSITY][pi]]
                                        if isinstance(cidict[
                                            PHOTOMETRY.
                                            U_FLUX_DENSITY], list) else
                                        row[cidict[PHOTOMETRY.U_FLUX_DENSITY]])
                                if photodict[
                                        PHOTOMETRY.U_FLUX_DENSITY] == '':
                                    photodict[
                                        PHOTOMETRY.U_FLUX_DENSITY] = 'µJy'
                                fd = (
                                    row[cidict[PHOTOMETRY.FLUX_DENSITY][pi]] if
                                    isinstance(cidict[
                                        PHOTOMETRY.FLUX_DENSITY], list) else
                                    row[cidict[PHOTOMETRY.FLUX_DENSITY]])
                                efd = (
                                    row[cidict[
                                        PHOTOMETRY.E_FLUX_DENSITY][pi]] if
                                    isinstance(cidict[
                                        PHOTOMETRY.E_FLUX_DENSITY], list) else
                                    row[cidict[PHOTOMETRY.E_FLUX_DENSITY]])

                                mult = Decimal('1')
                                ufd = photodict[PHOTOMETRY.U_FLUX_DENSITY]
                                if ufd.lower() in [
                                        'mjy', 'millijy', 'millijansky']:
                                    mult = Decimal('1e3')
                                elif ufd.lower() in ['jy', 'jansky']:
                                    mult = Decimal('1e6')

                                if '<' in fd:
                                    set_pd_mag_from_flux_density(
                                        photodict, efd=str(
                                            Decimal(fd.strip('<')) * mult))
                                else:
                                    set_pd_mag_from_flux_density(
                                        photodict, fd=Decimal(fd) * mult,
                                        efd=Decimal(efd) * mult)
                            if not len(sources):
                                if use_self_source is None:
                                    sopts = [
                                        ('Bibcode', 'b'), ('Last name', 'l')]
                                    if self._require_source:
                                        sel_str = 'must_select_source'
                                    else:
                                        sel_str = 'select_source'
                                    text = prt.text(sel_str)
                                    skind = prt.prompt(
                                        text, kind='option',
                                        options=sopts, default='b',
                                        none_string=(
                                            None if self._require_source else
                                            'Neither, tag MOSFiT as source'))
                                    if skind == 'b':
                                        rsource = {}
                                        bibcode = ''

                                        while len(bibcode) != 19:
                                            bibcode = prt.prompt(
                                                'bibcode',
                                                kind='string',
                                                allow_blank=False
                                            )
                                            bibcode = bibcode.strip()
                                            if (re.search(
                                                '[0-9]{4}..........[\.0-9]{4}'
                                                '[A-Za-z]', bibcode)
                                                    is None):
                                                bibcode = ''
                                        rsource[
                                            SOURCE.BIBCODE] = bibcode
                                        use_self_source = False
                                    elif skind == 'l':
                                        rsource = {}
                                        last_name = prt.prompt(
                                            'last_name', kind='string'
                                        )
                                        rsource[
                                            SOURCE.NAME] = (
                                                last_name.strip().title() +
                                                ' et al., in preparation')
                                        use_self_source = False
                                    elif skind == 'n':
                                        use_self_source = True

                                photodict[
                                    PHOTOMETRY.SOURCE] = entries[
                                        rname].add_source(**rsource)

                            if any([x in photodict.get(
                                    PHOTOMETRY.MAGNITUDE, '')
                                    for x in ['<', '>']]):
                                photodict[PHOTOMETRY.UPPER_LIMIT] = True
                                photodict[
                                    PHOTOMETRY.MAGNITUDE] = photodict[
                                        PHOTOMETRY.MAGNITUDE].strip('<>')

                            if '<' in photodict.get(PHOTOMETRY.COUNT_RATE, ''):
                                photodict[PHOTOMETRY.UPPER_LIMIT] = True
                                photodict[
                                    PHOTOMETRY.COUNT_RATE] = photodict[
                                        PHOTOMETRY.COUNT_RATE].strip('<')
                                if PHOTOMETRY.E_COUNT_RATE in photodict:
                                    del(photodict[PHOTOMETRY.E_COUNT_RATE])

                            if '<' in photodict.get(
                                    PHOTOMETRY.FLUX_DENSITY, ''):
                                photodict[PHOTOMETRY.UPPER_LIMIT] = True
                                photodict[
                                    PHOTOMETRY.FLUX_DENSITY] = photodict[
                                        PHOTOMETRY.FLUX_DENSITY].strip('<')
                                if PHOTOMETRY.E_FLUX_DENSITY in photodict:
                                    del(photodict[PHOTOMETRY.E_FLUX_DENSITY])

                            # Apply offset time if set.
                            if (PHOTOMETRY.TIME in photodict and
                                    toffset != Decimal('0')):
                                photodict[PHOTOMETRY.TIME] = str(
                                    Decimal(photodict[PHOTOMETRY.TIME]) +
                                    toffset)

                            # Skip entries for which key values are not
                            # expected type.
                            if not all([
                                is_number(photodict.get(x, ''))
                                for x in photodict.keys() if
                                (PHOTOMETRY.get_key_by_name(x).type ==
                                 KEY_TYPES.NUMERIC)]):
                                continue

                            # Skip placeholder values.
                            if float(photodict.get(
                                    PHOTOMETRY.MAGNITUDE, 0.0)) > 50.0:
                                continue

                            # Add system if specified by user.
                            if (self._system is not None and
                                    PHOTOMETRY.SYSTEM not in photodict):
                                photodict[PHOTOMETRY.SYSTEM] = self._system

                            # Remove keys not in the `PHOTOMETRY` class.
                            for key in list(photodict.keys()):
                                if key not in PHOTOMETRY.vals():
                                    del(photodict[key])

                            # Add the photometry.
                            entries[rname].add_photometry(
                                **photodict)

                    merge_with_existing = None
                    for ei, entry in enumerate(entries):
                        entries[entry].sanitize()
                        if os.path.isfile(new_events[ei]):
                            if merge_with_existing is None:
                                merge_with_existing = prt.prompt(
                                    'merge_with_existing', default='y')
                            if merge_with_existing:
                                existing = Entry.init_from_file(
                                    catalog=None,
                                    name=event_names[ei],
                                    path=new_events[ei],
                                    merge=False,
                                    pop_schema=False,
                                    ignore_keys=[ENTRY.MODELS],
                                    compare_to_existing=False)
                                Catalog().copy_entry_to_entry(
                                    existing, entries[entry])

                        oentry = entries[entry]._ordered(entries[entry])
                        entabbed_json_dump(
                            {entry: oentry}, open(new_events[ei], 'w'),
                            separators=(',', ':'))

                    self._converted.extend([
                        [event_names[x], new_events[x]]
                        for x in range(len(event_names))])

                new_event_list.extend(new_events)
                previous_file = event
            else:
                new_event_list.append(event)

        return new_event_list