some more formatting

.pre-commit-config.yaml

@@ -6,7 +6,6 @@ repos:
       - id: end-of-file-fixer
       - id: check-yaml
       - id: debug-statements
-      - id: double-quote-string-fixer
       - id: check-docstring-first
       - id: check-json
 

cupid/read.py

@@ -21,21 +21,21 @@ def read_yaml(path_to_yaml):
 def get_collection(path_to_catalog, **kwargs):
     """Get collection of datasets from intake catalog"""
     cat = intake.open_esm_datastore(path_to_catalog)
-    ### note that the json file points to the csv, so the path that the
-    ### yaml file contains does not actually get used. this can cause issues
+    # note that the json file points to the csv, so the path that the
+    # yaml file contains does not actually get used. this can cause issues
 
     cat_subset = cat.search(**kwargs)
 
     if "variable" in kwargs.keys():
         # pylint: disable=invalid-name
         def preprocess(ds):
-            ## the double brackets return a Dataset rather than a DataArray
-            ## this is fragile and could cause issues, not sure what subsetting on time_bound does
+            # the double brackets return a Dataset rather than a DataArray
+            # this is fragile and could cause issues, not sure what subsetting on time_bound does
             return ds[[kwargs["variable"], "time_bound"]]
 
-        ## not sure what the chunking kwarg is doing here either
+        # not sure what the chunking kwarg is doing here either
         dsets = cat_subset.to_dataset_dict(
-            xarray_open_kwargs={"chunks": {"time": -1}}, preprocess=preprocess
+            xarray_open_kwargs={"chunks": {"time": -1}}, preprocess=preprocess,
         )
 
     else:

cupid/run.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python
-
 """
 Main script for running all notebooks and scripts specified in the configuration file.
 
@@ -24,9 +23,11 @@
 
 import os
 import warnings
+
 import click
 import intake
 import ploomber
+
 import cupid.timeseries
 import cupid.util
 

cupid/timeseries.py

@@ -14,6 +14,7 @@
 
 import xarray as xr
 
+
 def call_ncrcat(cmd):
     """This is an internal function to `create_time_series`
     It just wraps the subprocess.call() function, so it can be
@@ -124,7 +125,7 @@ def create_time_series(
         for year in range(start_year, end_year + 1):
             # Add files to main file list:
             for fname in starting_location.glob(
-                f"*{hist_str}.*{str(year).zfill(4)}*.nc"
+                f"*{hist_str}.*{str(year).zfill(4)}*.nc",
             ):
                 files_list.append(fname)
             # End for
@@ -135,7 +136,7 @@ def create_time_series(
 
         # Open an xarray dataset from the first model history file:
         hist_file_ds = xr.open_dataset(
-            hist_files[0], decode_cf=False, decode_times=False
+            hist_files[0], decode_cf=False, decode_times=False,
         )
 
         # Get a list of data variables in the 1st hist file:
@@ -227,7 +228,7 @@ def create_time_series(
             if var not in hist_file_var_list:
                 if component == "ocn":
                     print(
-                        "ocean vars seem to not be present in all files and thus cause errors"
+                        "ocean vars seem to not be present in all files and thus cause errors",
                     )
                     continue
                 if (
@@ -325,7 +326,7 @@ def create_time_series(
         if vars_to_derive:
             if component == "atm":
                 derive_cam_variables(
-                    vars_to_derive=vars_to_derive, ts_dir=ts_dir[case_idx]
+                    vars_to_derive=vars_to_derive, ts_dir=ts_dir[case_idx],
                 )
 
         if serial:
@@ -357,7 +358,7 @@ def derive_cam_variables(vars_to_derive=None, ts_dir=None, overwrite=None):
             # PRECT can be found by simply adding PRECL and PRECC
             # grab file names for the PRECL and PRECC files from the case ts directory
             if glob.glob(os.path.join(ts_dir, "*PRECC*")) and glob.glob(
-                os.path.join(ts_dir, "*PRECL*")
+                os.path.join(ts_dir, "*PRECL*"),
             ):
                 constit_files = sorted(glob.glob(os.path.join(ts_dir, "*PREC*")))
             else:
@@ -374,7 +375,7 @@ def derive_cam_variables(vars_to_derive=None, ts_dir=None, overwrite=None):
             else:
                 print(
                     f"[{__name__}] Warning: PRECT file was found and overwrite is False"
-                    + "Will use existing file."
+                    + "Will use existing file.",
                 )
                 continue
         # append PRECC to the file containing PRECL
@@ -385,7 +386,7 @@ def derive_cam_variables(vars_to_derive=None, ts_dir=None, overwrite=None):
             # RESTOM = FSNT-FLNT
             # Have to be more precise than with PRECT because FSNTOA, FSTNC, etc are valid variables
             if glob.glob(os.path.join(ts_dir, "*.FSNT.*")) and glob.glob(
-                os.path.join(ts_dir, "*.FLNT.*")
+                os.path.join(ts_dir, "*.FLNT.*"),
             ):
                 input_files = [
                     sorted(glob.glob(os.path.join(ts_dir, f"*.{v}.*")))
@@ -408,12 +409,12 @@ def derive_cam_variables(vars_to_derive=None, ts_dir=None, overwrite=None):
                 else:
                     print(
                         f"[{__name__}] Warning: RESTOM file was found and overwrite is False."
-                        + "Will use existing file."
+                        + "Will use existing file.",
                     )
                     continue
             # append FSNT to the file containing FLNT
             os.system(f"ncks -A -v FLNT {constit_files[0]} {constit_files[1]}")
             # create new file with the difference of FLNT and FSNT
             os.system(
-                f"ncap2 -s 'RESTOM=(FSNT-FLNT)' {constit_files[1]} {derived_file}"
+                f"ncap2 -s 'RESTOM=(FSNT-FLNT)' {constit_files[1]} {derived_file}",
             )

cupid/util.py

@@ -23,9 +23,8 @@
 import papermill as pm
 import ploomber
 import yaml
-from papermill.engines import NBClientEngine
 from jinja2 import Template
-
+from papermill.engines import NBClientEngine
 
 class MarkdownJinjaEngine(NBClientEngine):
     """Class for using the Jinja Engine to run notebooks"""
@@ -133,7 +132,7 @@ def setup_book(config_path):
 
 
 def create_ploomber_nb_task(
-    nb, info, cat_path, nb_path_root, output_dir, global_params, dag, dependency=None
+    nb, info, cat_path, nb_path_root, output_dir, global_params, dag, dependency=None,
 ):
     """
     Creates a ploomber task for running a notebook, including necessary parameters.
@@ -154,7 +153,7 @@ def create_ploomber_nb_task(
 
     parameter_groups = info["parameter_groups"]
 
-    ### passing in subset kwargs if they're provided
+    # passing in subset kwargs if they're provided
     if "subset" in info:
         subset_kwargs = info["subset"]
     else:
@@ -170,7 +169,7 @@ def create_ploomber_nb_task(
 
         output_path = f"{output_dir}/{output_name}"
 
-        ### all of these things should be optional
+        # all of these things should be optional
         parms_in = dict(**default_params)
         parms_in.update(**global_params)
         parms_in.update(dict(**parms))
@@ -207,7 +206,7 @@ def create_ploomber_nb_task(
 
 
 def create_ploomber_script_task(
-    script, info, cat_path, nb_path_root, global_params, dag, dependency=None
+    script, info, cat_path, nb_path_root, global_params, dag, dependency=None,
 ):
     """
     Creates a Ploomber task for running a script, including necessary parameters.
@@ -230,7 +229,7 @@ def create_ploomber_script_task(
 
     parameter_groups = info["parameter_groups"]
 
-    ### passing in subset kwargs if they're provided
+    # passing in subset kwargs if they're provided
     if "subset" in info:
         subset_kwargs = info["subset"]
     else:
@@ -246,7 +245,7 @@ def create_ploomber_script_task(
 
         # output_path = f"{output_dir}/{output_name}"
 
-        ### all of these things should be optional
+        # all of these things should be optional
         parms_in = dict(**default_params)
         parms_in.update(**global_params)
         parms_in.update(dict(**parms))

docs/conf.py

@@ -40,7 +40,7 @@
 project = "CUPiD"
 
 current_year = datetime.datetime.now().year
-copyright = "{}, University Corporation for Atmospheric Research".format(current_year)
+copyright = f"{current_year}, University Corporation for Atmospheric Research"
 
 author = "NSF NCAR"