Source code for pycif.plugins.datastreams.fluxes.CMEMS.read

import numpy as np
import xarray as xr
from logging import debug
import xarray as xr
from netCDF4 import Dataset
import pandas as pd

from .....utils.hdf5 import _hdf5_lock




def read(
        self,
        name,
        varnames,
        dates,
        files,
        interpol_flx=False,
        tracer=None,
        model=None,
        ddi=None,
        **kwargs
):
    """Get fluxes from raw files and load them into a pyCIF
    variables.
    
    
    Args:
        name (str): name of the component
        varnames (list[str]): original names of variables to read; use `name`
            if `varnames` is empty
        dates (list): list of the date intervals to extract
        files (list): list of the files matching dates
        
    Return:
        xr.DataArray: the actual data with dimension:
            time, levels, latitudes, longitudes

    """

    var2extract = varnames if varnames != "" else name

    # Loop over dates/files and import data
    data = []
    out_dates = []
    for dd, ff in zip(dates, files):
        debug(
            f"Reading the file {ff} for the date interval {dd}"
        )

        # Read the file to fetch dates
        with _hdf5_lock:
            times = xr.open_dataset(ff)["time"].to_pandas().index
            times -= pd.to_timedelta(times.day - 1, unit="D")
            ind_time = np.where(times == np.datetime64(dd[0]))[0][0]

            ds = xr.open_dataset(ff)[var2extract][ind_time].values

        data.append(ds)
        out_dates.append(dd[0])
    
    # if only one level for emissions, create the axis
    dataout = np.array(data)[:, np.newaxis]
    dataout[np.isnan(dataout)] = 0
    xmod = xr.DataArray(
        dataout,
        coords={"time": out_dates},
        dims=("time", "lev", "lat", "lon"),
    )
    
    return xmod