Modernize packaging and fix runtime warnings

.github/workflows/python-publish.yml

@@ -1,11 +1,6 @@
 # This workflow will upload a Python Package using Twine when a release is created
 # For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#publishing-to-package-registries
 
-# This workflow uses actions that are not certified by GitHub.
-# They are provided by a third-party and are governed by
-# separate terms of service, privacy policy, and support
-# documentation.
-
 name: Upload Python Package
 
 on:
@@ -18,9 +13,11 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
     - name: Set up Python
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v4
       with:
         python-version: '3.x'
     - name: Install dependencies
@@ -30,7 +27,7 @@ jobs:
     - name: Build package
       run: python -m build
     - name: Publish package
-      uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
+      uses: pypa/gh-action-pypi-publish@release/v1
       with:
         user: __token__
         password: ${{ secrets.PYPI_API_TOKEN }}

.github/workflows/test.yml

@@ -0,0 +1,29 @@
+name: Tests
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.11", "3.12"]
+
+    steps:
+    - uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v4
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -e ".[test]"
+    - name: Run tests
+      run: pytest

.gitignore

@@ -1,7 +1,8 @@
 *.swp
 *__pycache__
 python/*.pyc
-gfdlvitals.egg-info/
+*.egg-info/
+.venv/
 testing/test_data
 testing/db
 testing/db-esm2

.readthedocs.yml

@@ -9,8 +9,13 @@ version: 2
 sphinx:
   configuration: docs/source/conf.py
 
-# Optionally set the version of Python and requirements required to build your docs
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.11"
+
 python:
-  version: 3.8
   install:
+    - method: pip
+      path: .
     - requirements: docs/requirements.txt

docs/requirements.txt

@@ -1,10 +1,11 @@
-cftime<=1.2.1
+cftime
 ipython
 jupyter
 matplotlib>=3.3.3
-nc-time-axis<=1.2.0
-netCDF4 
+nc-time-axis
+netCDF4
 numpy
 pandas
 scipy
+sphinx-rtd-theme
 xarray

docs/source/conf.py

@@ -11,9 +11,7 @@
 # documentation root, use os.path.abspath to make it absolute, like shown here.
 #
 import os
-import sys
-print(os.getcwd())
-sys.path.insert(0, os.path.abspath('../../'))
+from importlib.metadata import version as _get_version
 
 
 # -- Project information -----------------------------------------------------
@@ -23,7 +21,8 @@
 author = 'John Krasting'
 
 # The full version, including alpha/beta/rc tags
-release = '3.0a1'
+release = _get_version("gfdlvitals")
+version = release
 
 
 # -- General configuration ---------------------------------------------------
@@ -67,4 +66,6 @@
 
 #-- Build api
 from sphinx.ext.apidoc import main
-main(['-f', '-M', '-e', '-T', '../../gfdlvitals', '-o', 'api' ])
+import gfdlvitals
+_pkg_dir = os.path.dirname(gfdlvitals.__file__)
+main(['-f', '-M', '-e', '-T', _pkg_dir, '-o', 'api' ])

docs/source/plotting.rst

@@ -15,6 +15,7 @@ options to smooth the data, overlay a trend line, and align offset
 time axes.
 
 .. ipython:: python
+   :okexcept:
 
    import gfdlvitals
 

docs/source/vitals_data_frame.rst

@@ -138,6 +138,7 @@ In the example below, the test historical dataset is artifically split
 into two 20-year epochs for comparison.
 
 .. ipython:: python
+   :okexcept:
 
    df_hist_t0 = df_hist[-40:-20]
    df_hist_t1 = df_hist[-20::]

gfdlvitals/__init__.py

@@ -1,6 +1,11 @@
 """gfdlvitals - a package for computing global mean metrics"""
 
-from .version import __version__
+from importlib.metadata import version, PackageNotFoundError
+
+try:
+    __version__ = version("gfdlvitals")
+except PackageNotFoundError:
+    __version__ = "unknown"
 
 from . import averagers
 from . import cli

gfdlvitals/cli.py

@@ -5,10 +5,11 @@
 import os
 import shutil
 import subprocess
+import sys
 import tempfile
 import gfdlvitals
 
-__all__ = ["arguments", "process_year", "run"]
+__all__ = ["arguments", "process_year", "run", "main"]
 
 
 def arguments(args=None):
@@ -195,3 +196,9 @@ def run(args):
     # -- Clean up
     os.chdir(cwd)
     shutil.rmtree(tempdir)
+
+
+def main():
+    """Entry point for the gfdlvitals command"""
+    sys.stdout.reconfigure(line_buffering=True)
+    run(sys.argv[1:])

scripts/db2nc → gfdlvitals/cli_db2nc.py

@@ -1,6 +1,4 @@
-#!/usr/bin/env python3
-
-""" Command line utility to convert SQLite to NetCDF """
+"""Command line utility to convert SQLite to NetCDF"""
 
 import argparse
 import os
@@ -12,7 +10,7 @@
 
 
 def arguments():
-    """Function captures the command-line aguments passed to this script"""
+    """Function captures the command-line arguments passed to this script"""
 
     description = """
     Program for converting .db file format to NetCDF format.
@@ -24,12 +22,10 @@ def arguments():
         description=description, formatter_class=argparse.RawTextHelpFormatter
     )
 
-    # -- Input tile
     parser.add_argument(
         "infile", type=str, help="Input file. Format must be sqlite (*.db)"
     )
 
-    # -- Output file
     parser.add_argument(
         "-o",
         "--outfile",
@@ -122,9 +118,6 @@ def write_nc(
     ncfile = nc.Dataset(outfile, "w", format=ncformat)
     ncfile.setncattr("source_file", dbfile)
     ncfile.setncattr("created", timestamp_str)
-    # ncfile.setncattr('experiment',expName)
-    # ncfile.setncattr('type',plotType)
-    # ncfile.setncattr('region',region)
     _ = ncfile.createDimension("time", 0)
     time = ncfile.createVariable("time", "f4", ("time",))
     time.calendar = "noleap"
@@ -134,9 +127,6 @@ def write_nc(
         if table not in ["long_name", "units", "cell_measure"]:
             data_array = np.ma.ones(len(years)) + 1.0e20
             data_array.mask = True
-            # if 'Land' in plotType:
-            #  extract_list = ['avg','sum']
-            # else:
             extract_list = ["value"]
             for k in extract_list:
                 count = 0
@@ -178,16 +168,15 @@ def write_nc(
     ncfile.close()
 
 
-if __name__ == "__main__":
-
-    # read command line arguments
+def main():
+    """Entry point for the db2nc command"""
     args = arguments()
-    # get the full path of the db file
     infile = os.path.realpath(args.infile)
-    # get list of variables and years in a file
     _tables, _years = tables_and_years(infile)
     write_nc(
         infile, args.outfile, _tables, _years, clobber=args.force, verbose=args.verbose
     )
 
-sys.exit()
+
+if __name__ == "__main__":
+    main()

scripts/plotdb → gfdlvitals/cli_plotdb.py

@@ -1,15 +1,10 @@
-#!/usr/bin/env python
-
-""" CLI script for plotting SQLite files """
+"""CLI script for plotting SQLite files"""
 
 import argparse
 import os
 
-import matplotlib.pyplot as plt
-
 import gfdlvitals
 
-COUNT = 1
 
 def arguments():
     """
@@ -79,7 +74,11 @@ def arguments():
     return args
 
 
-
-if __name__ == "__main__":
+def main():
+    """Entry point for the plotdb command"""
     cliargs = arguments()
     gfdlvitals.plot.run_plotdb(cliargs)
+
+
+if __name__ == "__main__":
+    main()

gfdlvitals/plot.py

@@ -5,7 +5,7 @@
 import nc_time_axis
 
 import numpy as np
-import pkg_resources as pkgr
+from importlib.resources import files
 
 import matplotlib
 import matplotlib.pyplot as plt
@@ -21,7 +21,7 @@
 def set_font():
     """Sets font style to Roboto"""
     # Add Roboto font
-    fonts_dir = pkgr.resource_filename("gfdlvitals", "resources/fonts")
+    fonts_dir = str(files("gfdlvitals").joinpath("resources/fonts"))
 
     font_dirs = [fonts_dir]
     font_files = font_manager.findSystemFonts(fontpaths=font_dirs)

gfdlvitals/sample.py

@@ -1,6 +1,6 @@
 """ Sample db files for demonstration """
 
-import pkg_resources as pkgr
+from importlib.resources import files
 
-historical = pkgr.resource_filename("gfdlvitals", "resources/historical.db")
-picontrol = pkgr.resource_filename("gfdlvitals", "resources/picontrol.db")
+historical = str(files("gfdlvitals").joinpath("resources/historical.db"))
+picontrol = str(files("gfdlvitals").joinpath("resources/picontrol.db"))

gfdlvitals/util/gmeantools.py

@@ -3,10 +3,11 @@
 import math
 import pickle
 import sqlite3
+import sys
 import warnings
 
 import numpy as np
-import pkg_resources as pkgr
+from importlib.resources import files
 
 __all__ = [
     "get_web_vars_dict",
@@ -29,9 +30,7 @@ def get_web_vars_dict():
     dict
         LM3 variable module mappings and metadata
     """
-    mapping_file = pkgr.resource_filename(
-        "gfdlvitals", "resources/LM3_variable_dictionary.pkl"
-    )
+    mapping_file = str(files("gfdlvitals").joinpath("resources/LM3_variable_dictionary.pkl"))
     return pickle.load(
         open(
             mapping_file,
@@ -285,16 +284,12 @@ def write_sqlite_data(
     # check if result is a nan and replace with a defined missing value
     if varmean is not None:
         if math.isnan(float(varmean)):
-            warnings.warn(
-                f"Could not update {sqlfile} variable {varname} with mean={varmean}"
-            )
+            print(f"  WARNING: {varname} mean is NaN in {sqlfile}, writing missing value", file=sys.stderr)
             varmean = missing_value
 
     if varsum is not None:
         if math.isnan(float(varsum)):
-            warnings.warn(
-                f"Could not update {sqlfile} variable {varname} with mean={varsum}"
-            )
+            print(f"  WARNING: {varname} sum is NaN in {sqlfile}, writing missing value", file=sys.stderr)
             varsum = missing_value
 
     conn = sqlite3.connect(sqlfile)

gfdlvitals/util/netcdf.py

@@ -73,10 +73,11 @@ def in_mem_xr(data):
         In-memory xarray dataset object
     """
 
+    time_coder = xr.coders.CFDatetimeCoder(use_cftime=True)
     if isinstance(data, netCDF4._netCDF4.Dataset):
-        dfile = xr.open_dataset(xr.backends.NetCDF4DataStore(data), use_cftime=True)
+        dfile = xr.open_dataset(xr.backends.NetCDF4DataStore(data), decode_times=time_coder, decode_timedelta=False)
     else:
-        dfile = xr.open_dataset(data, use_cftime=True)
+        dfile = xr.open_dataset(data, decode_times=time_coder, decode_timedelta=False)
 
     return dfile
 

gfdlvitals/util/xrtools.py

@@ -97,6 +97,6 @@ def xr_weighted_avg(dset, weights):
             _dset_weighted[x] = _dset_weighted[x].astype(dset[x].dtype)
             _dset_weighted[x].attrs = dset[x].attrs
 
-        result = result.merge(_dset_weighted)
+        result = result.merge(_dset_weighted, compat="override")
 
     return result