add write_pp_df_parquets to WindUpConfig

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "res-wind-up"
-version = "0.4.5"
+version = "0.4.6"
 authors = [
     { name = "Alex Clerc", email = "alex.clerc@res-group.com" }
 ]
@@ -97,7 +97,7 @@ max-complexity = 12 # try to bring this down to 10
 
 [tool.ruff.lint.pylint]
 max-branches = 14 # try to bring this down to 12
-max-statements = 66 # try to bring this down to 50
+max-statements = 68 # try to bring this down to 50
 max-args = 17 # try to bring this down to 5
 
 [tool.ruff.lint.per-file-ignores]

wind_up/main_analysis.py

@@ -726,6 +726,12 @@ def _calc_test_ref_results(
         random_seed=random_seed,
     )
 
+    if cfg.write_pp_df_parquets:
+        (cfg.out_dir / "pp_df").mkdir(exist_ok=True)
+        pre_df.to_parquet(cfg.out_dir / "pp_df" / f"{test_wtg.name}_{ref_name}_pre_df.parquet")
+        post_df.to_parquet(cfg.out_dir / "pp_df" / f"{test_wtg.name}_{ref_name}_post_df.parquet")
+        _pp_df.to_parquet(cfg.out_dir / "pp_df" / f"{test_wtg.name}_{ref_name}_pp_df.parquet")
+
     other_results = ref_info | {
         "ref_ws_col": ref_ws_col,
         "distance_m": distance_m,
@@ -799,7 +805,6 @@ def run_wind_up_analysis(
     plot_input_data_timeline(
         assessment_inputs=inputs,
         save_to_folder=inputs.plot_cfg.plots_dir if inputs.plot_cfg.save_plots else None,
-        show_plots=inputs.plot_cfg.show_plots,
     )
 
     wf_df = inputs.wf_df

wind_up/models.py

@@ -174,6 +174,10 @@ class WindUpConfig(BaseModel):
         default=10 * 60,
         description="Timebase in seconds for SCADA data, other data is converted to this timebase",
     )
+    write_pp_df_parquets: bool = Field(
+        default=False,
+        description="If true the power performance parquet files are written along with other results and plots.",
+    )
     ignore_turbine_anemometer_data: bool = Field(
         default=False,
         description="If true do not use turbine anemometer data for anything",

wind_up/plots/input_data.py

@@ -81,10 +81,9 @@ def plot_input_data_timeline(
     figsize: tuple[int, int] | None = None,
     height_ratios: tuple[int, int] | None = None,
     save_to_folder: Path | None = None,
-    show_plots: bool = True,
     scada_data_column_for_power: str = DataColumns.active_power_mean,
     scada_data_column_for_yaw_angle: str = DataColumns.yaw_angle_mean,
-) -> plt.Figure:
+) -> None:
     """Plot timeline of input data with key milestones and data exclusions.
 
     This function does not do any data filtering itself, but instead only displays the data as it is provided.
@@ -93,7 +92,6 @@ def plot_input_data_timeline(
     :param figsize: size of the plot figure, if `None` it will be auto-sized based on the number of turbines
     :param height_ratios: ratios for the two subplots, if `None` it will be auto-sized based on the number of turbines
     :param save_to_folder: directory in which to save the plot
-    :param show_plots: whether to show the interactive plot or not
     :param scada_data_column_for_power: column name in the wind farm DataFrame to use for power data coverage plotting
     :param scada_data_column_for_yaw_angle: column name in the wind farm DataFrame to use for yaw data coverage plotting
     :return: figure object
@@ -281,14 +279,15 @@ def plot_input_data_timeline(
         box = a.get_position()
         a.set_position([box.x0, box.y0, box.width * 0.8, box.height])  # type: ignore[arg-type]
         handles, labels = a.get_legend_handles_labels()
+        # remove duplicate labels
+        handles_by_label = dict(zip(labels, handles, strict=True))  # type:ignore[call-overload]
+        handles = list(handles_by_label.values())
+        labels = list(handles_by_label.keys())
         a.legend(handles[::-1], labels[::-1], bbox_to_anchor=(1.04, 1), borderaxespad=0)
 
     if save_to_folder is not None:
         if not save_to_folder.is_dir():
             save_to_folder.mkdir(parents=True, exist_ok=True)
         fig.savefig(save_to_folder / "input_data_timeline_fig.png")
 
-    if not show_plots:
-        plt.close(fig)
-
-    return fig
+    plt.close(fig)