Source code for pycif.plugins.obsvects.standard.utils.dump

import copy
import os

import numpy as np

from .....utils.datastores.dump import dump_datastore
from .....utils.iterators import iter_tracers




def dump(obsvect, dir_dump):
    """Write the populated observation vector to ``monitor.nc`` files.

    For each observation tracer, creates a copy of its datastore, fills the
    ``maindata`` columns (``obs``, ``obserror``, ``sim``, ``sim_tl``) from
    the flat obsvect arrays, optionally adds an ``orig_index`` column, and
    serialises the result to:

    .. code-block:: text

        <dir_dump>/<component>/<tracer>/monitor.nc

    The file format is controlled by ``obsvect.dump_type`` (``'nc'`` or
    ``'csv'``).  Global NetCDF attributes recording the run dates and model
    configuration are written as ``nc_attributes``.

    Args:
        obsvect (Plugin): obsvect plugin instance.  Must have been
            initialised (``yobs``, ``ysim``, ``dy``, ``yobs_err`` filled).
        dir_dump (str): root directory under which the per-tracer sub-
            directories are created.
    """
    datavect = obsvect.datavect

    # If no definition is specified for the control vector in the Yaml,
    # return empty control vector
    if not hasattr(datavect, "components"):
        return obsvect

    # Else, carry on initializing
    for (component_name, tracer_name), tracer in iter_tracers(datavect):
        # Skip tracers that are not control variables
        if not tracer.isobs:
            continue

        ds = copy.deepcopy(tracer.datastore)

        ds[("maindata", "obs")] = obsvect.yobs[tracer.ypointer:
                                               tracer.ypointer + tracer.dim]
        ds[("maindata", "obserror")] = obsvect.yobs_err[tracer.ypointer:
                                                        tracer.ypointer + tracer.dim]
        ds[("maindata", "sim")] = obsvect.ysim[tracer.ypointer:
                                               tracer.ypointer + tracer.dim]
        ds[("maindata", "sim_tl")] = obsvect.dy[tracer.ypointer:
                                                tracer.ypointer + tracer.dim]

        if obsvect.dump_index:
            ds[("metadata", "orig_index")] = np.arange(tracer.ypointer,
                                                       tracer.ypointer + tracer.dim)

        # Attributes to keep in the monitor if NetCDF format (recommanded!)
        model_name = ""
        model_version = ""
        model_nlon = ""
        model_nlat = ""

        if hasattr(obsvect.model, "plugin"):
            model_name = obsvect.model.plugin.name
            model_version = obsvect.model.plugin.version
            model_nlon = str(obsvect.model.domain.nlon)
            model_nlat = str(obsvect.model.domain.nlat)

        nc_attributes = {
            "datei": tracer.datei.strftime("%d-%m-%Y %H:%M:%S"),
            "datef": tracer.datef.strftime("%d-%m-%Y %H:%M:%S"),
            "model name": model_name,
            "model version": model_version,
            "domain nlon": model_nlon,
            "domain nlat": model_nlat
        }

        file_monitor = os.path.join(
            dir_dump, component_name, tracer_name, "monitor.nc")

        dump_datastore(
            ds, file_monitor, mode="w",
            dump_type=obsvect.dump_type,
            nc_attributes=nc_attributes,
            col2dump=ds.columns,
            dump_default=False
        )