Bump to 0.3.1 (#321)

* Bumps the package to 0.3.1
* Updates the dependencies in the conda env yml files
* Updates the pre-commit hook versions
* Address `mypy` warnings
  * Remove `type: ignore` inline comments to silence mypy warnings related to xarray, can address in the future
  * Remove unused `type: ignore` based on latest version of mypy
* Update changelog with 0.3.1 and use names of contributors with link to GH user page

.pre-commit-config.yaml

@@ -4,14 +4,14 @@ fail_fast: true
 
 repos:
     - repo: https://github.com/pre-commit/pre-commit-hooks
-      rev: v4.1.0
+      rev: v4.3.0
       hooks:
           - id: trailing-whitespace
           - id: end-of-file-fixer
           - id: check-yaml
 
     - repo: https://github.com/psf/black
-      rev: 22.3.0
+      rev: 22.6.0
       hooks:
           - id: black
 
@@ -30,15 +30,15 @@ repos:
             additional_dependencies: [flake8-isort]
 
     - repo: https://github.com/pre-commit/mirrors-mypy
-      rev: v0.961
+      rev: v0.971
       hooks:
           - id: mypy
             args: ["--config=setup.cfg"]
             additional_dependencies:
                 [
-                    dask==2022.6.1,
+                    dask==2022.7.1,
                     numpy==1.22.4,
                     pandas==1.4.3,
-                    xarray==2022.3.0,
+                    xarray==2022.6.0,
                     types-python-dateutil==2.8.19,
                 ]

README.rst

@@ -42,7 +42,9 @@
 
 xCDAT is an extension of `xarray`_ for climate data analysis on structured grids. It serves as a spiritual successor to the Community Data Analysis Tools (`CDAT`_) library.
 
-The goal of xCDAT is to provide climate domain features and general utilities in xarray, which includes porting some core CDAT functionalities. xCDAT leverages several powerful libraries in the xarray ecosystem (e.g., `xESMF`_ and `cf_xarray`_) to deliver robust APIs. The xCDAT core team is aiming to provide a maintainable and extensible package that serves the needs of the climate community in the long-term.
+The goal of xCDAT is to provide generalizable climate domain features and general utilities in xarray, which includes porting some core CDAT functionalities. xCDAT leverages several powerful libraries in the xarray ecosystem (e.g., `xESMF`_ and `cf_xarray`_) to deliver robust APIs. The xCDAT core team is aiming to provide a maintainable and extensible package that serves the needs of the climate community in the long-term.
+
+A major design philosophy of xCDAT is streamlining the user experience while developing code to analyze climate data. This means reducing the complexity and number of lines required to achieve certain features with xarray.
 
 .. _xarray: https://github.com/pydata/xarray
 .. _CDAT: https://github.com/CDAT/cdat

conda-env/ci.yml

@@ -4,6 +4,7 @@ channels:
     - conda-forge
     - defaults
 dependencies:
+    # ==================
     # Base
     # ==================
     - python >=3.8

conda-env/dev.yml

@@ -1,50 +1,55 @@
-# Conda xcdat development environment
 name: xcdat_dev
 channels:
     - conda-forge
     - defaults
 dependencies:
+    # ==================
     # Base
     # ==================
+    # NOTE: If versions are updated, also `additional_dependencies` list for mypy in `.pre-commit-config.yaml`
     - python=3.9.13 # TODO: Update to >=3.10 once sphinxcontrib-napoleon supports it.
-    - pip=22.1.2
-    - cf_xarray=0.7.2
-    - cftime=1.6.0
-    - dask=2022.6.1
+    - pip=22.2.2
+    - cf_xarray=0.7.4
+    - cftime=1.6.1
+    - dask=2022.8.0
     - esmpy=8.2.0
-    - netcdf4=1.5.8
-    - numba=0.55.2 # TODO: Remove this pin once `numba` is properly patched with `numpy` compatability.
+    - netcdf4=1.6.0
+    - numba=0.55.2 # TODO: Remove this pin once `numba` is properly patched with `numpy` compatibility.
     - numpy=1.22.4
     - pandas=1.4.3
-    - xarray=2022.3.0
+    - xarray=2022.6.0
     - xesmf=0.6.3
     - python-dateutil=2.8.2
     - types-python-dateutil=2.8.19
+    # ==================
     # Documentation
     # ==================
     - sphinx=4.5.0
     - sphinxcontrib-napoleon=0.7
-    - sphinx-autosummary-accessors=2022-4-0
-    - sphinx-book-theme=0.3.2
+    - sphinx-autosummary-accessors=2022.4.0
+    - sphinx-book-theme=0.3.3
     - sphinx-copybutton=0.5.0
     - nbsphinx=0.8.9
-    - pandoc=2.18
+    - pandoc=2.19
+    # ==================
     # Quality Assurance
     # ==================
-    # If versions are updated, also update 'rev' in `.pre-commit.config.yaml`
-    - black=22.3.0
-    - flake8=4.0.1
-    - flake8-isort=4.1.1
+    # NOTE: If versions are updated, also update 'rev' in `.pre-commit.config.yaml`
+    - black=22.6.0
+    - flake8=5.0.4
+    - flake8-isort=4.2.0
     - isort=5.10.1
-    - mypy=0.961
-    - pre-commit=2.19.0
+    - mypy=0.971
+    - pre-commit=2.20.0
+    # ==================
     # Testing
     # ==================
     - pytest=7.1.2
     - pytest-cov=3.0.0
+    # ==================
     # Developer Tools
     # ==================
     - matplotlib=3.5.2
-    - jupyterlab=3.4.3
+    - jupyterlab=3.4.5
     - tbump=6.9.0
 prefix: /opt/miniconda3/envs/xcdat_dev

conda-env/readthedocs.yml

@@ -1,32 +1,34 @@
-# Conda xcdat readthedocs environment
 name: xcdat_rtd
 channels:
     - conda-forge
     - defaults
 dependencies:
+    # ==================
     # Base
     # ==================
+    # NOTE: If versions are updated, also `additional_dependencies` list for mypy in `.pre-commit-config.yaml`
     - python=3.9.13 # TODO: Update to >=3.10 once sphinxcontrib-napoleon supports it.
-    - pip=22.1.2
-    - cf_xarray=0.7.2
-    - cftime=1.6.0
-    - dask=2022.6.1
+    - pip=22.2.2
+    - cf_xarray=0.7.4
+    - cftime=1.6.1
+    - dask=2022.8.0
     - esmpy=8.2.0
-    - netcdf4=1.5.8
-    - numba=0.55.2 # TODO: Remove this pin once `numba` is properly patched with `numpy` compatability.
+    - netcdf4=1.6.0
+    - numba=0.55.2 # TODO: Remove this pin once `numba` is properly patched with `numpy` compatibility.
     - numpy=1.22.4
     - pandas=1.4.3
-    - xarray=2022.3.0
+    - xarray=2022.6.0
     - xesmf=0.6.3
     - python-dateutil=2.8.2
     - types-python-dateutil=2.8.19
+    # ==================
     # Documentation
     # ==================
     - sphinx=4.5.0
     - sphinxcontrib-napoleon=0.7
-    - sphinx-autosummary-accessors=2022-4-0
-    - sphinx-book-theme=0.3.2
+    - sphinx-autosummary-accessors=2022.4.0
+    - sphinx-book-theme=0.3.3
     - sphinx-copybutton=0.5.0
     - nbsphinx=0.8.9
-    - pandoc=2.18
+    - pandoc=2.19
 prefix: /opt/miniconda3/envs/xcdat_rtd

docs/index.rst

@@ -3,7 +3,9 @@ xCDAT: Xarray Climate Data Analysis Tools
 
 xCDAT is an extension of `xarray`_ for climate data analysis on structured grids. It serves as a spiritual successor to the Community Data Analysis Tools (`CDAT`_) library.
 
-The goal of xCDAT is to provide climate domain features and general utilities in xarray, which includes porting some core CDAT functionalities. xCDAT leverages several powerful libraries in the xarray ecosystem (e.g., `xESMF`_ and `cf_xarray`_) to deliver robust APIs. The xCDAT core team is aiming to provide a maintainable and extensible package that serves the needs of the climate community in the long-term.
+The goal of xCDAT is to provide generalizable climate domain features and general utilities in xarray, which includes porting some core CDAT functionalities. xCDAT leverages several powerful libraries in the xarray ecosystem (e.g., `xESMF`_ and `cf_xarray`_) to deliver robust APIs. The xCDAT core team is aiming to provide a maintainable and extensible package that serves the needs of the climate community in the long-term.
+
+A major design philosophy of xCDAT is streamlining the user experience while developing code to analyze climate data. This means reducing the complexity and number of lines required to achieve certain features with xarray.
 
 .. _xarray: https://github.com/pydata/xarray
 .. _CDAT: https://github.com/CDAT/cdat

setup.py

@@ -35,6 +35,6 @@
     test_suite="tests",
     tests_require=test_requires,
     url="https://github.com/xCDAT/xcdat",
-    version="0.3.0",
+    version="0.3.1",
     zip_safe=False,
 )

tbump.toml

@@ -2,7 +2,7 @@
 github_url = "https://github.com/xCDAT/xcdat"
 
 [version]
-current = "0.3.0"
+current = "0.3.1"
 
 # Example of a semver regexp.
 # Make sure this matches current_version before

xcdat/__init__.py

@@ -19,4 +19,4 @@
 from xcdat.temporal import TemporalAccessor  # noqa: F401
 from xcdat.utils import compare_datasets  # noqa: F401
 
-__version__ = "0.3.0"
+__version__ = "0.3.1"

xcdat/axis.py

@@ -305,8 +305,8 @@ def _align_lon_to_360(dataset: xr.Dataset, p_meridian_index: np.ndarray) -> xr.D
     # Create a Dataset with longitude data vars and merge it to the Dataset
     # without longitude data vars.
     ds_lon = xr.Dataset(data_vars={**lon_vars, lon_bounds.name: lon_bounds})
-    ds_no_lon = ds.get([v for v in ds.data_vars if lon.name not in ds[v].dims])
-    ds = xr.merge((ds_no_lon, ds_lon))  # type: ignore
+    ds_no_lon = ds.get([v for v in ds.data_vars if lon.name not in ds[v].dims])  # type: ignore
+    ds = xr.merge((ds_no_lon, ds_lon))
     return ds
 
 

xcdat/dataset.py

@@ -99,12 +99,12 @@ def open_dataset(
         cf_compliant_time: Optional[bool] = _has_cf_compliant_time(path)
         # xCDAT attempts to decode non-CF compliant time coordinates.
         if cf_compliant_time is False:
-            ds = xr.open_dataset(path, decode_times=False, **kwargs)
+            ds = xr.open_dataset(path, decode_times=False, **kwargs)  # type: ignore
             ds = decode_non_cf_time(ds)
         else:
-            ds = xr.open_dataset(path, decode_times=True, **kwargs)
+            ds = xr.open_dataset(path, decode_times=True, **kwargs)  # type: ignore
     else:
-        ds = xr.open_dataset(path, decode_times=False, **kwargs)
+        ds = xr.open_dataset(path, decode_times=False, **kwargs)  # type: ignore
 
     ds = _postprocess_dataset(ds, data_var, center_times, add_bounds, lon_orient)
 
@@ -225,7 +225,7 @@ def open_mfdataset(
         decode_times=decode_times,
         data_vars=data_vars,
         preprocess=preprocess,
-        **kwargs,
+        **kwargs,  # type: ignore
     )
     ds = _postprocess_dataset(ds, data_var, center_times, add_bounds, lon_orient)
 
@@ -489,7 +489,7 @@ def _has_cf_compliant_time(paths: Paths) -> Optional[bool]:
     compliance.
     """
     first_path = _get_first_path(paths)
-    ds = xr.open_dataset(first_path, decode_times=False)
+    ds = xr.open_dataset(first_path, decode_times=False)  # type: ignore
 
     if ds.cf.dims.get("T") is None:
         return None

xcdat/spatial.py

@@ -647,7 +647,8 @@ def _combine_weights(self, axis_weights: AxisWeights) -> xr.DataArray:
             (``axis``) in the region.
         """
         region_weights = reduce((lambda x, y: x * y), axis_weights.values())
-        region_weights.name = "_".join(sorted(region_weights.coords.keys())) + "_wts"
+        coord_keys = sorted(region_weights.coords.keys())  # type: ignore
+        region_weights.name = "_".join(coord_keys) + "_wts"  # type: ignore
 
         return region_weights
 

xcdat/temporal.py

@@ -806,8 +806,8 @@ def _drop_incomplete_djf(self, dataset: xr.Dataset) -> xr.Dataset:
         # method concatenates the time dimension to non-time dimension data
         # vars, which is not a desired behavior.
         ds = dataset.copy()
-        ds_time = ds.get([v for v in ds.data_vars if self._dim in ds[v].dims])
-        ds_no_time = ds.get([v for v in ds.data_vars if self._dim not in ds[v].dims])
+        ds_time = ds.get([v for v in ds.data_vars if self._dim in ds[v].dims])  # type: ignore
+        ds_no_time = ds.get([v for v in ds.data_vars if self._dim not in ds[v].dims])  # type: ignore
 
         start_year, end_year = (
             ds[self._dim].dt.year.values[0],
@@ -817,12 +817,12 @@ def _drop_incomplete_djf(self, dataset: xr.Dataset) -> xr.Dataset:
         for year_month in incomplete_seasons:
             try:
                 coord_pt = ds.loc[dict(time=year_month)][self._dim][0]
-                ds_time = ds_time.where(ds_time[self._dim] != coord_pt, drop=True)  # type: ignore
+                ds_time = ds_time.where(ds_time[self._dim] != coord_pt, drop=True)
                 self._time_bounds = ds_time[self._time_bounds.name]
             except (KeyError, IndexError):
                 continue
 
-        ds_final = xr.merge((ds_time, ds_no_time))  # type: ignore
+        ds_final = xr.merge((ds_time, ds_no_time))
 
         return ds_final
 
@@ -920,17 +920,17 @@ def _group_average(self, data_var: xr.DataArray) -> xr.DataArray:
         if self._weighted:
             self._weights = self._get_weights()
             dv *= self._weights
-            dv = self._group_data(dv).sum()  # type: ignore
+            dv = self._group_data(dv).sum()
         else:
-            dv = self._group_data(dv).mean()  # type: ignore
+            dv = self._group_data(dv).mean()
 
         # After grouping and aggregating the data variable values, the
         # original time dimension is replaced with the grouped time dimension.
         # For example, grouping on "year_season" replaces the time dimension
         # with "year_season". This dimension needs to be renamed back to
         # the original time dimension name before the data variable is added
         # back to the dataset so that the CF compliant name is maintained.
-        dv = dv.rename({self._labeled_time.name: self._dim})  # type: ignore
+        dv = dv.rename({self._labeled_time.name: self._dim})
 
         # After grouping and aggregating, the grouped time dimension's
         # attributes are removed. Xarray's `keep_attrs=True` option only keeps
@@ -988,11 +988,11 @@ def _get_weights(self) -> xr.DataArray:
         time_lengths = time_lengths.astype(np.float64)
 
         grouped_time_lengths = self._group_data(time_lengths)
-        weights: xr.DataArray = grouped_time_lengths / grouped_time_lengths.sum()  # type: ignore
+        weights: xr.DataArray = grouped_time_lengths / grouped_time_lengths.sum()
         weights.name = f"{self._dim}_wts"
 
         # Validate the sum of weights for each group is 1.0.
-        actual_sum = self._group_data(weights).sum().values  # type: ignore
+        actual_sum = self._group_data(weights).sum().values
         expected_sum = np.ones(len(grouped_time_lengths.groups))
         np.testing.assert_allclose(actual_sum, expected_sum)