Prepare for new release (#18)

CHANGES.rst

@@ -4,8 +4,13 @@ Changelog
 
 Unreleased
 ==========
+-
+
+Version 0.6
+===========
+
 - Add support for downloading, reading, reshuffling era5-land
-- Add support for reading, reshuffling points over land only
+- Add support for reading, reshuffling points over land only (era5 and era5-land)
 - Add function to create land definition files
 - Test with pinned environments
 

docs/ts_read.rst

@@ -10,7 +10,7 @@ can be passed as well:
 
 .. code-block:: python
 
-    from ecmwf_models.interface import ERATs
+    from ecmwf_models import ERATs
     ds = ERATs(ts_path, ioclass_kws={'read_bulk':True}) # read_bulk reads full files into memory
     # read_ts takes either lon, lat coordinates to perform a nearest neighbour search
     # or a grid point index (from the grid.nc file) and returns a pandas.DataFrame.

ecmwf_models/__init__.py

@@ -3,4 +3,6 @@
 try:
     __version__ = pkg_resources.get_distribution(__name__).version
 except:
-    __version__ = 'unknown'
+    __version__ = 'unknown'
+
+from ecmwf_models.interface import ERATs

ecmwf_models/era5/download.py

@@ -244,20 +244,21 @@ def parse_args(args):
                         help=("Enddate in format YYYY-MM-DD. "
                               "If not given then the current date is used."))
     parser.add_argument("-p", "--product", type=str, default='ERA5',
-                        help=("Choose either ERA5 or ERA5-Land. Default is ERA5."))
+                        help=("The ERA5 product to download. Choose either ERA5 or ERA5-Land. Default is ERA5."))
     parser.add_argument("-var", "--variables", metavar="variables", type=str, default=None,
                         nargs="+",
-                        help=("Name of variables to download. If None are passed, we use the default ones from the"
-                              "era5_lut.csv and era5-land_lut.csv files."
+                        help=("Name of variables to download. If None are passed, we use the default ones from the "
+                              "era5_lut.csv resp. era5-land_lut.csv files in this package. "
                               "See the ERA5/ERA5-LAND documentation for more variable names: "
                               "     https://confluence.ecmwf.int/display/CKB/ERA5+data+documentation "
                               "     https://confluence.ecmwf.int/display/CKB/ERA5-Land+data+documentation"))
     parser.add_argument("-keep", "--keep_original", type=str2bool, default='False',
-                        help=("Keep the originally, temporally downloaded file as it is instread of deleting it afterwards"))
+                        help=("Also keep the originally, temporarily downloaded image stack instead of deleting it "
+                              "after extracting single images. Default is False."))
     parser.add_argument("-grb", "--as_grib", type=str2bool, default='False',
-                        help=("Download data in grib format, instead of the default netcdf format"))
+                        help=("Download data in grib format instead of netcdf. Default is False."))
     parser.add_argument("--h_steps", type=int, default=[0,6,12,18], nargs='+',
-                        help=("Manually change the temporal resolution of downloaded images."
+                        help=("Temporal resolution of downloaded images. "
                               "Pass a set of full hours here, like '--h_steps 0 12'. "
                               "By default 6H images (starting at 0:00 UTC, i.e. 0 6 12 18) will be downloaded"))
 

ecmwf_models/era5/reshuffle.py

@@ -161,14 +161,14 @@ def parse_args(args):
                               "See documentation on image download for resp. ERA products, "
                               "for more information on variable names of the product. "))
     parser.add_argument("--land_points", type=str2bool, default='False',
-                        help=("Store only time series for points that are over land"))
+                        help=("Store only time series for points that are over land. Default is False."))
     parser.add_argument("--h_steps", type=int, default=None, nargs='+',
                         help=("Time steps (full hours) of images that will be reshuffled (must be in the images). "
-                              "By default 6H images (starting at 0:00 UTC) will be reshuffled."))
+                              "By default 6H images (starting at 0:00 UTC) will be reshuffled: 0 6 12 18"))
     parser.add_argument("--imgbuffer", type=int, default=50,
                         help=("How many images to read at once. Bigger numbers make the "
                               "conversion faster but consume more memory. Choose this according to your "
-                              "system and the size of a single image."))
+                              "system and the size of a single image. Default is 50."))
     args = parser.parse_args(args)
 
     print("Converting ERA5/ERA5-Land data from {} to {} into {}."
@@ -191,4 +191,4 @@ def main(args):
 
 
 def run():
-    main(sys.argv[1:])
+    main(sys.argv[1:])

ecmwf_models/interface.py

@@ -38,9 +38,10 @@
 except ImportError:
     warnings.warn("pygrib has not been imported")
 
-'''
-Base classes for reading downloaded ERA netcdf and grib images and 6H image stacks
-'''
+"""
+Base classes for reading downloaded ERA netcdf and grib images and stacks
+"""
+
 
 class ERANcImg(ImageBase):
     """
@@ -54,7 +55,7 @@ class ERANcImg(ImageBase):
         'era5' or 'era5-land' or 'eraint'
     parameter: list or str, optional (default: ['swvl1', 'swvl2'])
         Name of parameters to read from the image file.
-    subgrid: pygeogrids.CellGrid, optional (default:None)
+    subgrid: pygeogrids.CellGrid, optional (default: None)
         Read only data for points of this grid and not global values.
     mask_seapoints : bool, optional (default: False)
         Read the land-sea mask to mask points over water and set them to nan.
@@ -86,14 +87,14 @@ def __init__(self, filename, product, parameter=['swvl1', 'swvl2'],
                           "equal number of points in each line")
 
     def read(self, timestamp=None):
-        '''
+        """
         Read data from the loaded image file.
 
         Parameters
         ---------
         timestamp : datetime, optional (default: None)
             Specific date (time) to read the data for.
-        '''
+        """
         return_img = {}
         return_metadata = {}
 
@@ -186,7 +187,7 @@ class ERANcDs(MultiTemporalImageBase):
         Read only data for points of this grid and not global values.
     mask_seapoints : bool, optional (default: False)
         Use the land-sea-mask parameter in the file to mask points over water.
-    h_step : list, optional (default: [0,6,12,18])
+    h_steps : list, optional (default: [0,6,12,18])
         List of full hours for which images exist.
     array_1D: bool, optional (default: False)
         Read data as list, instead of 2D array, used for reshuffling.
@@ -439,42 +440,41 @@ def tstamps_for_daterange(self, start_date, end_date):
         return timestamps
 
 class ERATs(GriddedNcOrthoMultiTs):
-    '''
-     Time series reader for all reshuffled ERA reanalysis products in time
-     series format.
-     Use the read_ts(lon, lat) resp. read_ts(gpi) function of this class
-     to read data for locations (gpi or latlon)!
-
-     Parameters
-     ----------
-     ts_path : str
-         Directory where the netcdf time series files are stored
-     grid_path : str, optional (default: None)
-         Path to grid file, that is used to organize the location of time
-         series to read. If None is passed, grid.nc is searched for in the
-         ts_path.
-
-     Optional keyword arguments that are passed to the Gridded Base when used:
-     ------------------------------------------------------------------------
-         parameters : list, optional (default: None)
-             Specific variable names to read, if None are selected, all are read.
-         offsets : dict, optional (default: None)
-             Offsets (values) that are added to the parameters (keys)
-         scale_factors : dict, optional (default: None)
-             Offset (value) that the parameters (key) is multiplied with
-         ioclass_kws: dict, (optional)
-
-             Optional keyword arguments, passed to the OrthoMultiTs class when used:
-             ----------------------------------------------------------------
-                 read_bulk : boolean, optional (default: False)
-                     If set to True, the data of all locations is read into memory,
-                     and subsequent calls to read_ts then read from cache and
-                     not from disk. This makes reading complete files faster.
-                 read_dates : boolean, optional (default: False)
-                     If false, dates will not be read automatically but only on
-                     specific request useable for bulk reading because currently
-                     the netCDF num2date routine is very slow for big datasets.
-     '''
+    """
+    Time series reader for all reshuffled ERA reanalysis products in time
+    series format.
+    Use the read_ts(lon, lat) resp. read_ts(gpi) function of this class
+    to read data for locations!
+
+    Parameters
+    ----------
+    ts_path : str
+        Directory where the netcdf time series files are stored
+    grid_path : str, optional (default: None)
+        Path to grid file, that is used to organize the location of time
+        series to read. If None is passed, grid.nc is searched for in the
+        ts_path.
+
+    Optional keyword arguments that are passed to the Gridded Base when used:
+    ------------------------------------------------------------------------
+        parameters : list, optional (default: None)
+            Specific variable names to read, if None are selected, all are read.
+        offsets : dict, optional (default: None)
+            Offsets (values) that are added to the parameters (keys)
+        scale_factors : dict, optional (default: None)
+            Offset (value) that the parameters (key) is multiplied with
+        ioclass_kws: dict, (optional)
+            Optional keyword arguments, passed to the OrthoMultiTs class when used:
+            ----------------------------------------------------------------
+                read_bulk : boolean, optional (default: False)
+                    If set to True, the data of all locations is read into memory,
+                    and subsequent calls to read_ts then read from cache and
+                    not from disk. This makes reading complete files faster.
+                read_dates : boolean, optional (default: False)
+                    If false, dates will not be read automatically but only on
+                    specific request useable for bulk reading because currently
+                    the netCDF num2date routine is very slow for big datasets.
+    """
     def __init__(self, ts_path, grid_path=None, **kwargs):
 
         if grid_path is None:

tests/tests_era5/test_era5_reshuffle.py

@@ -32,7 +32,7 @@
 import numpy.testing as nptest
 
 from ecmwf_models.era5.reshuffle import main
-from ecmwf_models.interface import ERATs
+from ecmwf_models import ERATs
 import shutil
 
 def test_ERA5_reshuffle_nc():

tests/tests_eraint/test_eraint_reshuffle.py

@@ -32,7 +32,7 @@
 import numpy.testing as nptest
 
 from ecmwf_models.erainterim.reshuffle import main
-from ecmwf_models.interface import ERATs
+from ecmwf_models import ERATs
 import shutil
 
 def test_ERAInterim_reshuffle_grb():