Maintenance: Upgrade Outdated Python Style (NREL#274)

* run pyupgrade --py38-plus against codebase * add pyupgrade to pre-commit workflow * fix bad fix
RHammond2 · Feb 16, 2024 · c0485c8 · c0485c8
1 parent 1d4074e
commit c0485c8
Show file tree

Hide file tree

Showing 11 changed files with 44 additions and 54 deletions.
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -14,6 +14,11 @@ repos:
         additional_dependencies: [toml]
         types: [pyi]
 
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v3.15.0
+    hooks:
+    - id: pyupgrade
+      args: [--py38-plus]
 
   - repo: https://github.com/psf/black
     rev: 23.3.0

diff --git a/openoa/analysis/aep.py b/openoa/analysis/aep.py
@@ -234,7 +234,7 @@ def __attrs_post_init__(self):
         else:
             analysis_type = "MonteCarloAEP"
 
-        if set((analysis_type, "all")).intersection(self.plant.analysis_type) == set():
+        if {analysis_type, "all"}.intersection(self.plant.analysis_type) == set():
             self.plant.analysis_type.append(analysis_type)
 
         # Ensure the data are up to spec before continuing with initialization
@@ -377,7 +377,7 @@ def run(
             num_sim=self.num_sim,
             reanalysis_products=self.reanalysis_products,
         )
-        logger.info("Running with parameters: {}".format(logged_params))
+        logger.info(f"Running with parameters: {logged_params}")
 
         # Start the computation
         self.calculate_long_term_losses()
@@ -572,11 +572,9 @@ def process_reanalysis_data(self):
 
             if self.end_date_lt > end_date:
                 raise ValueError(
-                    (
-                        "Invalid end date for long-term correction. The end date cannot exceed the "
-                        "last full time period (defined by the time resolution) in the provided "
-                        "reanalysis data."
-                    )
+                    "Invalid end date for long-term correction. The end date cannot exceed the "
+                    "last full time period (defined by the time resolution) in the provided "
+                    "reanalysis data."
                 )
             else:
                 # replace end date
@@ -601,17 +599,13 @@ def process_reanalysis_data(self):
         if self._reanalysis_aggregate.index[0] > start_date_required:
             if self.end_date_lt is not None:
                 raise ValueError(
-                    (
-                        "Invalid end date argument for long-term correction. This end date does not "
-                        "provide enough reanalysis data for the long-term correction."
-                    )
+                    "Invalid end date argument for long-term correction. This end date does not "
+                    "provide enough reanalysis data for the long-term correction."
                 )
             else:
                 raise ValueError(
-                    (
-                        "The date range of the provided reanalysis data is not long enough to "
-                        "perform the long-term correction."
-                    )
+                    "The date range of the provided reanalysis data is not long enough to "
+                    "perform the long-term correction."
                 )
 
         # Correct each reanalysis product, density-correct wind speeds, and take monthly averages

diff --git a/openoa/analysis/electrical_losses.py b/openoa/analysis/electrical_losses.py
@@ -108,7 +108,7 @@ def __attrs_post_init__(self):
         """
         Initialize logging and post-initialization setup steps.
         """
-        if set(("ElectricalLosses", "all")).intersection(self.plant.analysis_type) == set():
+        if {"ElectricalLosses", "all"}.intersection(self.plant.analysis_type) == set():
             self.plant.analysis_type.append("ElectricalLosses")
 
         # Ensure the data are up to spec before continuing with initialization
@@ -371,7 +371,7 @@ def plot_monthly_losses(
         std = losses.std()
         ax.plot(
             losses * 100,
-            label=f"Electrical Losses\n$\mu$={mean:.2%}, $\sigma$={std:.2%}",  # noqa: W605
+            label=f"Electrical Losses\n$\\mu$={mean:.2%}, $\\sigma$={std:.2%}",  # noqa: W605
             **plot_kwargs,
         )
 

diff --git a/openoa/analysis/turbine_long_term_gross_energy.py b/openoa/analysis/turbine_long_term_gross_energy.py
@@ -155,10 +155,7 @@ def __attrs_post_init__(self):
         """
         Runs any non-automated setup steps for the analysis class.
         """
-        if (
-            set(("TurbineLongTermGrossEnergy", "all")).intersection(self.plant.analysis_type)
-            == set()
-        ):
+        if {"TurbineLongTermGrossEnergy", "all"}.intersection(self.plant.analysis_type) == set():
             self.plant.analysis_type.append("TurbineLongTermGrossEnergy")
 
         # Ensure the data are up to spec before continuing with initialization
@@ -400,7 +397,7 @@ def setup_daily_reanalysis_data(self) -> None:
 
         # Capture the runs reanalysis data set and ensure the U/V components exist
         reanalysis_df = self.plant.reanalysis[self._run.reanalysis_product]
-        if len(set(("WMETR_HorWdSpdU", "WMETR_HorWdSpdV")).intersection(reanalysis_df.columns)) < 2:
+        if len({"WMETR_HorWdSpdU", "WMETR_HorWdSpdV"}.intersection(reanalysis_df.columns)) < 2:
             (
                 reanalysis_df["WMETR_HorWdSpdU"],
                 reanalysis_df["WMETR_HorWdSpdV"],

diff --git a/openoa/analysis/wake_losses.py b/openoa/analysis/wake_losses.py
@@ -322,10 +322,10 @@ def __attrs_post_init__(self):
         logger.info("Initializing WakeLosses analysis object")
 
         if self.wind_direction_data_type == "scada":
-            if set(("WakeLosses-scada", "all")).intersection(self.plant.analysis_type) == set():
+            if {"WakeLosses-scada", "all"}.intersection(self.plant.analysis_type) == set():
                 self.plant.analysis_type.append("WakeLosses-scada")
         if self.wind_direction_data_type == "tower":
-            if set(("WakeLosses-tower", "all")).intersection(self.plant.analysis_type) == set():
+            if {"WakeLosses-tower", "all"}.intersection(self.plant.analysis_type) == set():
                 self.plant.analysis_type.append("WakeLosses-tower")
 
         # Ensure the data are up to spec before continuing with initialization

diff --git a/openoa/analysis/yaw_misalignment.py b/openoa/analysis/yaw_misalignment.py
@@ -223,7 +223,7 @@ def __attrs_post_init__(self):
         """
         Initialize logging and post-initialization setup steps.
         """
-        if set(("StaticYawMisalignment", "all")).intersection(self.plant.analysis_type) == set():
+        if {"StaticYawMisalignment", "all"}.intersection(self.plant.analysis_type) == set():
             self.plant.analysis_type.append("StaticYawMisalignment")
 
         # Ensure the data are up to spec before continuing with initialization

diff --git a/openoa/logging.py b/openoa/logging.py
@@ -37,7 +37,7 @@ def _wrapper(self, *args, **kwargs):
 def logged_function_call(the_function, msg="call"):
     def _wrapper(*args, **kwargs):
         logger = logging.getLogger(the_function.__module__)
-        logger.debug("{}: {}".format(the_function.__name__, msg))
+        logger.debug(f"{the_function.__name__}: {msg}")
         return the_function(*args, **kwargs)
 
     return _wrapper

diff --git a/openoa/plant.py b/openoa/plant.py
@@ -79,10 +79,10 @@ def _analysis_filter(
             for k in reanalysis_keys:
                 name = k.split("-")[1]
                 col_map = getattr(metadata, key)[name].col_map
-                _add[k] = set([col_map[v] for v in value])
+                _add[k] = {col_map[v] for v in value}
         else:
             col_map = getattr(metadata, key).col_map
-            column_requirements.update({key: set([col_map[v] for v in value])})
+            column_requirements.update({key: {col_map[v] for v in value}})
     column_requirements.update(_add)
 
     # Filter the missing columns, so only analysis-specific columns are provided
@@ -148,7 +148,7 @@ def _compose_error_message(
 @logged_method_call
 def frequency_validator(
     actual_freq: str | int | float | None,
-    desired_freq: Optional[str | None | set[str]],
+    desired_freq: str | set[str] | None,
     exact: bool,
 ) -> bool:
     """Helper function to check if the actual datetime stamp frequency is valid compared
@@ -173,11 +173,11 @@ def frequency_validator(
         return False
 
     if isinstance(desired_freq, str):
-        desired_freq = set([desired_freq])
+        desired_freq = {desired_freq}
 
     # If an offset alias couldn't be found, then convert the desired frequency strings to seconds
     if not isinstance(actual_freq, str):
-        desired_freq = set([ts.offset_to_seconds(el) for el in desired_freq])
+        desired_freq = {ts.offset_to_seconds(el) for el in desired_freq}
 
     if exact:
         return actual_freq in desired_freq
@@ -987,7 +987,7 @@ def _validate_frequency(self, category: str = "all") -> list[str]:
         return invalid_freq
 
     @logged_method_call
-    def validate(self, metadata: Optional[dict | str | Path | PlantMetaData] = None) -> None:
+    def validate(self, metadata: dict | str | Path | PlantMetaData | None = None) -> None:
         """Secondary method to validate the plant data objects after loading or changing
         data with option to provide an updated `metadata` object/file as well
 

diff --git a/openoa/utils/imputing.py b/openoa/utils/imputing.py
@@ -67,7 +67,7 @@ def impute_data(
     """
     final_col_name = deepcopy(target_col)
     if data is None:
-        if any((not isinstance(x, pd.DataFrame) for x in (target_data, reference_data))):
+        if any(not isinstance(x, pd.DataFrame) for x in (target_data, reference_data)):
             raise TypeError(
                 "If `data` is not provided, then `ref_data` and `target_data` must be provided as pandas DataFrames."
             )

diff --git a/openoa/utils/plot.py b/openoa/utils/plot.py
@@ -1179,10 +1179,8 @@ def plot_wake_losses(
             plot_norm_energy = True
         else:
             raise ValueError(
-                (
-                    "The inputs `energy_data_por` and `energy_data_lt` must both have the same dimensions"
-                    "as `efficiency_data_por` and `efficiency_data_lt`."
-                )
+                "The inputs `energy_data_por` and `energy_data_lt` must both have the same dimensions"
+                "as `efficiency_data_por` and `efficiency_data_lt`."
             )
     elif (energy_data_por is None) & (energy_data_lt is None):
         plot_norm_energy = False
@@ -1511,18 +1509,16 @@ def plot_yaw_misalignment(
                 ],
                 color=curve_fit_color_code,
                 linestyle="--",
-                label=f"Max. Power Vane Angle = {round(curve_fit_params_ws[:,i,1].mean(),1)}$^\circ$",  # noqa: W605
+                label=rf"Max. Power Vane Angle = {round(curve_fit_params_ws[:,i,1].mean(),1)}$^\circ$",  # noqa: W605
             )
 
             yaw_mis_mean = np.round(np.mean(yaw_misalignment_ws[:, i]), 1)
             yaw_mis_lb = np.round(np.percentile(yaw_misalignment_ws[:, i], 2.5), 1)
             yaw_mis_ub = np.round(np.percentile(yaw_misalignment_ws[:, i], 97.5), 1)
 
             ax.set_title(
-                (
-                    f"{ws} m/s\nYaw Misalignment = "
-                    f"{yaw_mis_mean}$^\circ$ [{yaw_mis_lb}$^\circ$, {yaw_mis_ub}$^\circ$]"  # noqa: W605
-                )
+                f"{ws} m/s\nYaw Misalignment = "
+                rf"{yaw_mis_mean}$^\circ$ [{yaw_mis_lb}$^\circ$, {yaw_mis_ub}$^\circ$]"  # noqa: W605
             )
         else:
             norm_factor = curve_fit_params_ws[i, 0]
@@ -1557,11 +1553,11 @@ def plot_yaw_misalignment(
                 ],
                 color=curve_fit_color_code,
                 linestyle="--",
-                label=f"Max. Power Vane Angle = {round(curve_fit_params_ws[i,1],1)}$^\circ$",  # noqa: W605
+                label=rf"Max. Power Vane Angle = {round(curve_fit_params_ws[i,1],1)}$^\circ$",  # noqa: W605
             )
 
             ax.set_title(
-                f"{ws} m/s\nYaw Misalignment = {np.round(yaw_misalignment_ws[i],1)}$^\circ$"  # noqa: W605
+                f"{ws} m/s\nYaw Misalignment = {np.round(yaw_misalignment_ws[i],1)}$^\\circ$"  # noqa: W605
             )
 
         ax.plot(
@@ -1572,7 +1568,7 @@ def plot_yaw_misalignment(
             ],
             color=mean_vane_color_code,
             linestyle="--",
-            label=f"Mean Vane Angle = {round(mean_vane_angle_ws[i],1)}$^\circ$",  # noqa: W605
+            label=rf"Mean Vane Angle = {round(mean_vane_angle_ws[i],1)}$^\circ$",  # noqa: W605
         )
 
         ax.grid("on")
@@ -1598,28 +1594,26 @@ def plot_yaw_misalignment(
         for i in range(len(ws_bins) % 3, 3):
             axs[last_row][i].remove()
             axs[last_row - 1][i].tick_params(labelbottom=True)
-            axs[last_row - 1][i].set_xlabel("Wind Vane Angle ($^\circ$)")  # noqa: W605
+            axs[last_row - 1][i].set_xlabel(r"Wind Vane Angle ($^\circ$)")  # noqa: W605
 
         for i in range(len(ws_bins) % 3):
-            axs[last_row][i].set_xlabel("Wind Vane Angle ($^\circ$)")  # noqa: W605
+            axs[last_row][i].set_xlabel(r"Wind Vane Angle ($^\circ$)")  # noqa: W605
     else:
         for i in range(N_col):
-            axs[last_row][i].set_xlabel("Wind Vane Angle ($^\circ$)")  # noqa: W605
+            axs[last_row][i].set_xlabel(r"Wind Vane Angle ($^\circ$)")  # noqa: W605
 
     mean_yaw_mis = np.round(np.mean(yaw_misalignment_ws), 1)
     if UQ:
         yaw_misalignment_95CI = np.round(
             np.percentile(np.mean(yaw_misalignment_ws, 1), [2.5, 97.5]), 1
         )
         fig.suptitle(
-            (
-                f"Turbine {turbine_id}, Yaw Misalignment = {mean_yaw_mis}$^\circ$ "  # noqa: W605
-                f"[{yaw_misalignment_95CI[0]}$^\circ$, {yaw_misalignment_95CI[1]}$^\circ$]"  # noqa: W605
-            )
+            rf"Turbine {turbine_id}, Yaw Misalignment = {mean_yaw_mis}$^\circ$ "  # noqa: W605
+            rf"[{yaw_misalignment_95CI[0]}$^\circ$, {yaw_misalignment_95CI[1]}$^\circ$]"  # noqa: W605
         )
     else:
         fig.suptitle(
-            f"Turbine {turbine_id}, Mean Yaw Misalignment = {str(mean_yaw_mis)}$^\circ$"  # noqa: W605
+            rf"Turbine {turbine_id}, Mean Yaw Misalignment = {str(mean_yaw_mis)}$^\circ$"  # noqa: W605
         )
 
     plt.tight_layout()

diff --git a/openoa/utils/qa.py b/openoa/utils/qa.py
@@ -24,7 +24,7 @@
 set_styling()
 
 
-def _remove_tz(df: pd.DataFrame, t_local_column: str) -> Tuple[np.ndarray, np.ndarray]:
+def _remove_tz(df: pd.DataFrame, t_local_column: str) -> tuple[np.ndarray, np.ndarray]:
     """Identify the non-timestamp elements in the DataFrame timestamp column and return
     a truth array for filtering the values and the timezone-naive timestamps.