Merge pull request #138 from WISDEM/develop

v0.9.3: Minor Bug Fix and Formatting Updates

.pre-commit-config.yaml

@@ -8,13 +8,21 @@ repos:
           name: isort
           stages: [commit]
 
-- repo: https://github.com/psf/black
-  rev: 23.12.0
+- repo: https://github.com/asottile/pyupgrade
+  rev: v3.15.0
   hooks:
-  - id: black
-    name: black
+  - id: pyupgrade
+    args: [--py39-plus]
     stages: [commit]
 
+- repo: https://github.com/charliermarsh/ruff-pre-commit
+  rev: v0.1.8
+  hooks:
+  - id: ruff
+    args: [--fix]
+  - id: ruff-format
+    types_or: [python, pyi, jupyter]
+
 - repo: https://github.com/pre-commit/mirrors-mypy
   rev: 'v1.7.1'  # Use the sha / tag you want to point at
   hooks:
@@ -38,13 +46,6 @@ repos:
   -   id: pretty-format-json
       args: [--autofix]
 
-
-- repo: https://github.com/charliermarsh/ruff-pre-commit
-  rev: v0.1.8
-  hooks:
-  - id: ruff
-    args: [--fix]
-
 # -   repo: local
 #     hooks:
 #     - id: pytest

CHANGELOG.md

@@ -1,3 +1,11 @@
+## v0.9.3 (15 February 2024)
+
+- Reinstate the original time-based availability methodology, which is based on all
+  turbines, not the wind farm total.
+- Replace the `black` formatter with `ruff`.
+- Adopt `pyupgrade` to ensure modern Python language usage.
+- Add the NumPy 2.0 integration tool to Ruff.
+
 ## v0.9.2 (13 November 2023)
 
 ### General

pyproject.toml

@@ -2,6 +2,9 @@
 requires = ["setuptools", "setuptools-scm"]
 build-backend = "setuptools.build_meta"
 
+[metadata]
+version = "attr: wombat.__version__"
+
 [project]
 name = "wombat"
 dynamic = ["version"]
@@ -62,12 +65,12 @@ changelog = "https://github.com/WISDEM/WOMBAT/blob/main/CHANGELOG.md"
 [project.optional-dependencies]
 dev = [
     "pre-commit>=2.20",
-    "black>=22.1",
     "isort>=5.10",
     "pytest>=7",
     "pytest-cov>=4",
     "mypy==0.991",
-    "ruff==0.0.246",
+    "ruff>=0.2",
+    "pyupgrade",
 ]
 docs = [
     "jupyter-book>=0.15",
@@ -161,36 +164,27 @@ length_sort = true
 lines_after_imports = 2
 line_length = 88
 
-
-[tool.black]
-target-version=["py39", "py310"]
-line-length=88
-
-include = '\.pyi?$'
-exclude = '''
-/(
-    \.git
-  | \.hg
-  | \.mypy_cache
-  | \.tox
-  | \.venv
-  | _build
-  | buck-out
-  | build
-  | dist
-)/
-'''
+[tool.numpydoc_validation]
+checks = [
+  "all",
+  "ES01",
+  "SA01",
+  "EX01",
+]
+exclude = ["*__pycache__"]
 
 [tool.ruff]
 src = ["wombat", "tests"]
 line-length = 88
 target-version = "py39"
-ignore-init-module-imports = true
+fix = true
 
+[tool.ruff.lint]
 # See https://github.com/charliermarsh/ruff#supported-rules
 # for rules included and matching to prefix.
 # TODO: "FBT", "B", "PIE, "T20", "SIM", "PTH", "PD", "I", "PL"
-select = ["F", "E", "W", "C4", "D", "UP"]
+ignore-init-module-imports = true
+select = ["F", "E", "W", "C4", "D", "UP", "NPY201"]
 
 # D205: not using summary lines and descriptions, just descriptions
 # D401: don't believe enough in imperative mode to make all the changes currently
@@ -226,7 +220,7 @@ exclude = [
 # Allow unused variables when underscore-prefixed.
 dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
 
-[tool.ruff.per-file-ignores]
+[tool.ruff.lint.per-file-ignores]
 "setup.py" = ["D104"]
 "library/__init__.py" = ["D104"]
 "library/code_comparison/__init__.py" = ["D104"]
@@ -278,5 +272,5 @@ dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
 "wombat/windfarm/__init__.py" = ["F401"]
 "wombat/windfarm/system/__init__.py" = ["F401"]
 
-[tool.ruff.pydocstyle]
+[tool.ruff.lint.pydocstyle]
 convention = "numpy"

wombat/__init__.py

@@ -4,4 +4,4 @@
 from wombat.core.library import create_library_structure
 
 
-__version__ = "0.9.2"
+__version__ = "0.9.3"

wombat/core/data_classes.py

@@ -250,7 +250,9 @@ def check_start_stop_dates(
 
 
 def valid_hour(
-    instance: Any, attribute: Attribute, value: int  # pylint: disable=W0613
+    instance: Any,
+    attribute: Attribute,
+    value: int,  # pylint: disable=W0613
 ) -> None:
     """Validate that the input is a valid time or null value (-1).
 
@@ -275,7 +277,9 @@ def valid_hour(
 
 
 def valid_reduction(
-    instance, attribute: Attribute, value: int | float  # pylint: disable=W0613
+    instance,
+    attribute: Attribute,
+    value: int | float,  # pylint: disable=W0613
 ) -> None:
     """Check to see if the reduction factor is between 0 and 1, inclusive.
 

wombat/core/post_processor.py

@@ -53,21 +53,17 @@ def _check_frequency(frequency: str, which: str = "all") -> str:
 def _calculate_time_availability(
     availability: pd.DataFrame,
     by_turbine: bool = False,
-    turbine_id: list[str] | None = None,
 ) -> float | np.ndarray:
     """Calculates the availability ratio of the whole timeseries or the whole
     timeseries, by turbine.
 
     Parameters
     ----------
     availability : pd.DataFrame
-        Timeseries array of operating ratios.
+        Timeseries array of operating ratios for all turbines.
     by_turbine : bool, optional
         If True, calculates the availability rate of each column, otherwise across the
         whole array, by default False.
-    turbine_id : list[str], optional
-        A list of turbine IDs that is required if :py:attr:`by_turbine` is ``True``, by
-        default None.
 
     Returns
     -------
@@ -77,8 +73,8 @@ def _calculate_time_availability(
     """
     availability = availability > 0
     if by_turbine:
-        return availability[turbine_id].values.sum(axis=0) / availability.shape[0]
-    return availability.windfarm.values.sum() / availability.windfarm.size
+        return availability.values.sum(axis=0) / availability.shape[0]
+    return availability.values.sum() / availability.size
 
 
 class Metrics:
@@ -375,15 +371,13 @@ def time_based_availability(self, frequency: str, by: str) -> pd.DataFrame:
         for sub, val in self.substation_turbine_map.items():
             turbine_operations[val["turbines"]] *= self.operations[[sub]].values
 
-        hourly = turbine_operations.loc[:, ["windfarm"] + self.turbine_id]
+        hourly = turbine_operations.loc[:, self.turbine_id]
 
         # TODO: The below should be better summarized as:
         # (availability > 0).groupby().sum() / groupby().count()
 
         if frequency == "project":
-            availability = _calculate_time_availability(
-                hourly, by_turbine=by_turbine, turbine_id=self.turbine_id
-            )
+            availability = _calculate_time_availability(hourly, by_turbine=by_turbine)
             if not by_turbine:
                 return pd.DataFrame([availability], columns=["windfarm"])
 
@@ -401,7 +395,6 @@ def time_based_availability(self, frequency: str, by: str) -> pd.DataFrame:
                 _calculate_time_availability(
                     hourly[date_time.year == year],
                     by_turbine=by_turbine,
-                    turbine_id=self.turbine_id,
                 )
                 for year in counts.index
             ]
@@ -414,7 +407,6 @@ def time_based_availability(self, frequency: str, by: str) -> pd.DataFrame:
                 _calculate_time_availability(
                     hourly[date_time.month == month],
                     by_turbine=by_turbine,
-                    turbine_id=self.turbine_id,
                 )
                 for month in counts.index
             ]
@@ -427,7 +419,6 @@ def time_based_availability(self, frequency: str, by: str) -> pd.DataFrame:
                 _calculate_time_availability(
                     hourly[(date_time.year == year) & (date_time.month == month)],
                     by_turbine=by_turbine,
-                    turbine_id=self.turbine_id,
                 )
                 for year, month in counts.index
             ]

wombat/windfarm/windfarm.py

@@ -345,7 +345,8 @@ def _create_wind_farm_map(self) -> None:
                 downstream=graph.nodes[s_id]["connection"],
             )
         self.wind_farm_map = WindFarmMap(
-            substation_map=wind_map, export_cables=export  # type: ignore
+            substation_map=wind_map,
+            export_cables=export,  # type: ignore
         )
 
     def finish_setup(self) -> None: