Merge pull request #16 from LIVVkit/mkstratos/mvkxx

Add MVKxx to K-S test

Author: mkstratos

.github/workflows/python-package.yml

@@ -16,7 +16,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
 
     steps:
     - uses: actions/checkout@v4

.pre-commit-config.yaml

@@ -1,21 +1,25 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.0.1
+    rev: v6.0.0
     hooks:
       - id: end-of-file-fixer
       - id: trailing-whitespace
       - id: check-toml
-  - repo: https://github.com/psf/black
-    rev: 22.3.0
-    hooks:
-      - id: black
-  - repo: https://github.com/pycqa/isort
-    rev: 5.13.2
-    hooks:
-      - id: isort
+      - id: check-yaml
+        args: [--unsafe]
+      - id: debug-statements
+      - id: destroyed-symlinks
+      - id: detect-private-key
   - repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: v0.3.7
+    rev: v0.13.0
     hooks:
       # Run the linter.
-      - id: ruff
+      - id: ruff-check
+      # Run the formatter.
+      - id: ruff-format
+        args: [--verbose]
+  - repo: https://github.com/pycqa/isort
+    rev: 6.0.1
+    hooks:
+      - id: isort

evv4esm/ensembles/e3sm.py

@@ -57,7 +57,6 @@ def file_date_str(case_file, style="short", hist_name="h0"):
         search_regex = r"{}\.[0-9]+-[0-9]+.nc".format(hist_name)
     else:
         search_regex = r"{}\.[0-9]+-[0-9]+.nc".format(hist_name)
-
     result = re.search(search_regex, case_file).group(0)
     return result.replace("{}.".format(hist_name), "").replace(".nc", "")
 
@@ -103,13 +102,13 @@ def get_variable_meta(dataset, var_name):
     return {"long_name": _name, "units": _units}
 
 
-def gather_monthly_averages(ensemble_files, variable_set=None):
+def gather_monthly_averages(ensemble_files, variable_set=None, hist_name="h0"):
     monthly_avgs = []
     for case, inst_dict in six.iteritems(ensemble_files):
         for inst, i_files in six.iteritems(inst_dict):
             # Get monthly averages from files
             for file_ in i_files:
-                date_str = file_date_str(file_)
+                date_str = file_date_str(file_, hist_name=hist_name)
 
                 data = None
                 try:

evv4esm/ensembles/tools.py

@@ -29,6 +29,7 @@
 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 """General tools for working with ensembles."""
+
 import os
 
 import matplotlib.pyplot as plt

evv4esm/extensions/ks.py

@@ -122,7 +122,7 @@ def parse_args(args=None):
         "--ninst",
         default=30,
         type=int,
-        help="The number of instances (should be the same for " "both cases).",
+        help="The number of instances (should be the same for both cases).",
     )
 
     parser.add_argument(
@@ -158,6 +158,13 @@ def parse_args(args=None):
         "--alpha", default=0.05, type=float, help="Alpha threshold for pass / fail"
     )
 
+    parser.add_argument(
+        "--hist-name",
+        default="h0",
+        help="History file extension [eam: h0, scream: h, mpas: hist], default: h0",
+        type=str,
+    )
+
     args, _ = parser.parse_known_args(args)
 
     # use config file arguments, but override with command line arguments
@@ -287,10 +294,13 @@ def case_files(args):
     if args.test_case == args.ref_case:
         key1 += "1"
         key2 += "2"
-
     f_sets = {
-        key1: e3sm.component_monthly_files(args.test_dir, args.component, args.ninst),
-        key2: e3sm.component_monthly_files(args.ref_dir, args.component, args.ninst),
+        key1: e3sm.component_monthly_files(
+            args.test_dir, args.component, args.ninst, hist_name=args.hist_name
+        ),
+        key2: e3sm.component_monthly_files(
+            args.ref_dir, args.component, args.ninst, hist_name=args.hist_name
+        ),
     }
 
     for key in f_sets:
@@ -428,7 +438,9 @@ def main(args):
         args.test_case = key1
         args.ref_case = key2
 
-    monthly_avgs = e3sm.gather_monthly_averages(ens_files, args.var_set)
+    monthly_avgs = e3sm.gather_monthly_averages(
+        ens_files, args.var_set, hist_name=args.hist_name
+    )
     annual_avgs = (
         monthly_avgs.groupby(["case", "variable", "instance"])
         .monthly_mean.aggregate(monthly_to_annual_avg)