Merge branch 'main' into mean_clim_upgrade_lee1043_20240812

pcmdi_metrics/io/xcdat_openxml.py

@@ -7,9 +7,11 @@
 import xcdat as xc
 import xmltodict
 
+from pcmdi_metrics.io.xcdat_dataset_io import get_calendar
+
 
 def xcdat_open(
-    infile: Union[str, list], data_var: str = None, decode_times: bool = True
+    infile: Union[str, list], data_var: str = None, decode_times: bool = True, chunks={}
 ) -> xr.Dataset:
     """
     Open input file (netCDF, or xml generated by cdscan)
@@ -24,6 +26,8 @@ def xcdat_open(
     decode_times : bool, optional
         If True, attempt to decode times encoded in the standard NetCDF datetime format into cftime.datetime objects.
         Otherwise, leave them encoded as numbers. This keyword may not be supported by all the backends, by default True.
+    chunks : int, "auto", dict, or None, optional
+        The chunk size used to load data into dask arrays.
 
     Returns
     -------
@@ -45,16 +49,67 @@ def xcdat_open(
     >>> ds = xcdat_open('mydata.xml')
     """
     if isinstance(infile, list) or "*" in infile:
-        ds = xc.open_mfdataset(infile, data_var=data_var, decode_times=decode_times)
+        try:
+            ds = xc.open_mfdataset(
+                infile, data_var=data_var, decode_times=decode_times, chunks=chunks
+            )
+        except (
+            ValueError
+        ):  # Could be due to non-cf-compliant calendar or other attribute
+            ds = xc.open_mfdataset(
+                infile, data_var=data_var, decode_times=False, chunks=chunks
+            )
+            ds = fix_noncompliant_attr(ds)
     else:
         if infile.split(".")[-1].lower() == "xml":
-            ds = _xcdat_openxml(infile, data_var=data_var, decode_times=decode_times)
+            try:
+                ds = _xcdat_openxml(
+                    infile, data_var=data_var, decode_times=decode_times, chunks=chunks
+                )
+            except (
+                ValueError
+            ):  # Could be due to non-cf-compliant calendar or other attribute
+                ds = _xcdat_openxml(
+                    infile, data_var=data_var, decode_times=False, chunks=chunks
+                )
+                ds = fix_noncompliant_attr(ds)
         else:
-            ds = xc.open_dataset(infile, data_var=data_var, decode_times=decode_times)
+            try:
+                ds = xc.open_dataset(
+                    infile, data_var=data_var, decode_times=decode_times, chunks=chunks
+                )
+            except (
+                ValueError
+            ):  # Could be due to non-cf-compliant calendar or other attribute
+                ds = xc.open_dataset(
+                    infile, data_var=data_var, decode_times=False, chunks=chunks
+                )
+                ds = fix_noncompliant_attr(ds)
 
     return ds.bounds.add_missing_bounds()
 
 
+def fix_noncompliant_attr(ds: xr.Dataset) -> xr.Dataset:
+    """Fix dataset attributes that do not meet cf standards
+
+    Parameters
+    ----------
+    ds: xr.Dataset
+        xarray dataset to fix
+
+    Returns
+    -------
+    xr.Dataset
+        xarray dataset with updated attributes
+    """
+    # Add any calendar fixes here
+    cal = get_calendar(ds)
+    cal = cal.replace("-", "_")
+    ds.time.attrs["calendar"] = cal
+    ds = xc.decode_time(ds)
+    return ds
+
+
 def _xcdat_openxml(
     xmlfile: str, data_var: str = None, decode_times: bool = True
 ) -> xr.Dataset:

pcmdi_metrics/variability_mode/lib/__init__.py

@@ -33,5 +33,5 @@
     variability_metrics_to_json,
     write_nc_output,
 )
-from .plot_map import plot_map  # noqa
+from .plot_map import plot_map, plot_map_multi_panel  # noqa
 from .north_test import north_test

pcmdi_metrics/variability_mode/lib/eof_analysis.py

@@ -115,10 +115,14 @@ def eof_analysis_get_variance_mode(
             pc_Nth *= -1.0
 
         # Supplement NetCDF attributes
+        eof_Nth.attrs["variable"] = data_var
+        eof_Nth.attrs["eof_mode"] = n + 1
         frac_Nth.attrs["units"] = "ratio"
         pc_Nth.attrs[
             "comment"
         ] = f"Non-scaled time series for principal component of {eofn}th variance mode"
+        pc_Nth.attrs["variable"] = data_var
+        pc_Nth.attrs["eof_mode"] = n + 1
 
         # append to lists for returning
         eof_list.append(eof_Nth)
@@ -258,6 +262,14 @@ def linear_regression_on_globe_for_teleconnection(
 
     eof_lr = (slope * factor) + intercept
 
+    eof_lr.attrs["variable"] = data_var
+    eof_lr.attrs["description"] = "linear regression on global field for teleconnection"
+    eof_lr.attrs[
+        "comment"
+    ] = "Reconstructed EOF pattern with teleconnection considerations"
+    if "eof_mode" in pc.attrs:
+        eof_lr.attrs["eof_mode"] = pc.attrs["eof_mode"]
+
     debug_print("linear regression done", debug)
 
     return eof_lr, slope, intercept
@@ -346,10 +358,12 @@ def gain_pseudo_pcs(
         pseudo_pcs = solver.projectField(
             field_to_be_projected, neofs=eofn, eofscaling=0
         )
+        pseudo_pcs.attrs["comment"] = "Non-scaled pseudo principal components"
     else:
         pseudo_pcs = solver.projectField(
             field_to_be_projected, neofs=eofn, eofscaling=1
         )
+        pseudo_pcs.attrs["comment"] = "Scaled pseudo principal components"
     # Get CBF PC (pseudo pcs in the code) for given eofs
     pseudo_pcs = pseudo_pcs[:, eofn - 1]
     # Arbitrary sign control, attempt to make all plots have the same sign

pcmdi_metrics/variability_mode/lib/lib_variability_mode.py

@@ -33,7 +33,9 @@ def tree():
     return defaultdict(tree)
 
 
-def write_nc_output(output_file_name, eofMap, pc, frac, slopeMap, interceptMap):
+def write_nc_output(
+    output_file_name, eofMap, pc, frac, slopeMap, interceptMap, identifier=None
+):
     # Create a dataset
     ds = xr.Dataset(
         {
@@ -46,6 +48,23 @@ def write_nc_output(output_file_name, eofMap, pc, frac, slopeMap, interceptMap):
             ),  # single number having no axis
         }
     )
+    # Add global attributes
+    ds.attrs[
+        "title"
+    ] = "PCMDI Metrics Package Extratropical Modes of Variability diagnostics"
+    ds.attrs["author"] = "PCMDI"
+    ds.attrs["contact"] = "[email protected]"
+    ds.attrs["creation_date"] = strftime("%Y-%m-%d %H:%M:%S", gmtime())
+    ds.attrs[
+        "references"
+    ] = """
+    Lee, J., K. Sperber, P. Gleckler, C. Bonfils, and K. Taylor, 2019: Quantifying the Agreement Between Observed and Simulated Extratropical Modes of Interannual Variability. Climate Dynamics, 52, 4057-4089, doi: 10.1007/s00382-018-4355-4,
+    Lee, J., K. Sperber, P. Gleckler, K. Taylor, and C. Bonfils, 2021: Benchmarking performance changes in the simulation of extratropical modes of variability across CMIP generations. Journal of Climate, 34, 6945–6969, doi: 10.1175/JCLI-D-20-0832.1,
+    Lee, J., P. J. Gleckler, M.-S. Ahn, A. Ordonez, P. Ullrich, K. R. Sperber, K. E. Taylor, Y. Y. Planton, E. Guilyardi, P. Durack, C. Bonfils, M. D. Zelinka, L.-W. Chao, B. Dong, C. Doutriaux, C. Zhang, T. Vo, J. Boutte, M. F. Wehner, A. G. Pendergrass, D. Kim, Z. Xue, A. T. Wittenberg, and J. Krasting, 2024: Systematic and Objective Evaluation of Earth System Models: PCMDI Metrics Package (PMP) version 3. Geoscientific Model Development, 17, 3919–3948, doi: 10.5194/gmd-17-3919-2024
+    """
+    if identifier is not None:
+        ds.attrs["identifier"] = identifier
+    # Save the dataset to a netcdf file
     ds.to_netcdf(output_file_name + ".nc")
     ds.close()