feat: add timeline plot for wind-up input data

Plot includes key milestones, analysis and exclusion periods. This
provides a useful overview of the configuration used for an analysis.

.gitignore

@@ -81,3 +81,5 @@ output/
 /tests/**/*.log
 /tests/test_data/wedowind/Pitch Angle/
 /tests/test_data/wedowind/Vortex Generator/
+# matplotlib testing
+**/result_images/

examples/smarteole_example.py

@@ -296,18 +296,15 @@ def _download_data_from_zenodo(analysis_timebase_s: int, cache_dir: Path, zip_fi
     return SmarteoleData(scada_df=scada_df, metadata_df=metadata_df, toggle_df=toggle_df)
 
 
-def main_smarteole_analysis(
+def _construct_assessment_inputs(
     *,
     smarteole_data: SmarteoleData,
+    logger: logging.Logger,
     analysis_timebase_s: int = ANALYSIS_TIMEBASE_S,
-    check_results: bool = CHECK_RESULTS,
     analysis_output_dir: Path = ANALYSIS_OUTPUT_DIR,
-    cache_sub_dir: Path = CACHE_SUBDIR,
     reanalysis_file_path: Path | str = REANALYSIS_DATA_FILE_PATH,
-) -> None:
-    setup_logger(ANALYSIS_OUTPUT_DIR / "analysis.log")
-    logger = logging.getLogger(__name__)
-
+    cache_sub_dir: Path = CACHE_SUBDIR,
+) -> AssessmentInputs:
     logger.info("Merging SMV6 yaw offset command signal into SCADA data")
     toggle_df_no_tz = smarteole_data.toggle_df.copy()
     toggle_df_no_tz.index = toggle_df_no_tz.index.tz_localize(None)
@@ -317,19 +314,19 @@ def main_smarteole_analysis(
     scada_df["yaw_offset_command"] = scada_df["yaw_offset_command"].where(scada_df["TurbineName"] == "SMV6", 0)
     del toggle_df_no_tz
 
-    logger.info("Loading reference reanalysis data")
-    reanalysis_dataset = ReanalysisDataset(
-        id="ERA5T_50.00N_2.75E_100m_1hr",
-        data=pd.read_parquet(reanalysis_file_path),
-    )
-
     logger.info("Defining Assessment Configuration")
     cfg = define_smarteole_example_config(
         analysis_timebase_s=analysis_timebase_s, analysis_output_dir=analysis_output_dir
     )
     plot_cfg = PlotConfig(show_plots=False, save_plots=True, plots_dir=cfg.out_dir / "plots")
 
-    assessment_inputs = AssessmentInputs.from_cfg(
+    logger.info("Loading reference reanalysis data")
+    reanalysis_dataset = ReanalysisDataset(
+        id="ERA5T_50.00N_2.75E_100m_1hr",
+        data=pd.read_parquet(reanalysis_file_path),
+    )
+
+    return AssessmentInputs.from_cfg(
         cfg=cfg,
         plot_cfg=plot_cfg,
         toggle_df=smarteole_data.toggle_df,
@@ -338,6 +335,29 @@ def main_smarteole_analysis(
         reanalysis_datasets=[reanalysis_dataset],
         cache_dir=cache_sub_dir,
     )
+
+
+def main_smarteole_analysis(
+    *,
+    smarteole_data: SmarteoleData,
+    analysis_timebase_s: int = ANALYSIS_TIMEBASE_S,
+    check_results: bool = CHECK_RESULTS,
+    analysis_output_dir: Path = ANALYSIS_OUTPUT_DIR,
+    cache_sub_dir: Path = CACHE_SUBDIR,
+    reanalysis_file_path: Path | str = REANALYSIS_DATA_FILE_PATH,
+) -> None:
+    setup_logger(analysis_output_dir / "analysis.log")
+    logger = logging.getLogger(__name__)
+
+    assessment_inputs = _construct_assessment_inputs(
+        smarteole_data=smarteole_data,
+        logger=logger,
+        analysis_timebase_s=analysis_timebase_s,
+        analysis_output_dir=analysis_output_dir,
+        reanalysis_file_path=reanalysis_file_path,
+        cache_sub_dir=cache_sub_dir,
+    )
+
     results_per_test_ref_df = run_wind_up_analysis(assessment_inputs)
 
     net_p50, net_p95, net_p5 = calc_net_uplift(results_per_test_ref_df, confidence=0.9)

tests/conftest.py

@@ -1,14 +1,33 @@
 from __future__ import annotations
 
+import logging
+import shutil
 from pathlib import Path
+from typing import TYPE_CHECKING
 
 import pytest
 
+from examples.smarteole_example import (
+    SmarteoleData,
+    _construct_assessment_inputs,
+    unpack_smarteole_metadata,
+    unpack_smarteole_scada,
+    unpack_smarteole_toggle_data,
+)
 from wind_up.models import WindUpConfig
 
+if TYPE_CHECKING:
+    from wind_up.interface import AssessmentInputs
+
 TEST_DATA_FLD = Path(__file__).parent / "test_data"
 TEST_CONFIG_DIR = TEST_DATA_FLD / "config"
 
+SMARTEOLE_DATA_DIR = TEST_DATA_FLD / "smarteole"
+SMARTEOLE_CACHE_DIR = Path(__file__).parent / "timebase_600"
+SMARTEOLE_OUTPUT_DIR = Path(__file__).parent / "output"
+
+logger = logging.getLogger(__name__)
+
 
 @pytest.fixture
 def test_lsa_t13_config() -> WindUpConfig:
@@ -55,3 +74,42 @@ def test_homer_with_t00_config() -> WindUpConfig:
     cfg.asset.wtgs[-1].latitude = -58.601587635380
     cfg.asset.wtgs[-1].longitude = 103.692588907983
     return cfg
+
+
+@pytest.fixture(scope="session")
+def smarteole_assessment_inputs() -> tuple[AssessmentInputs, SmarteoleData]:
+    timebase_s = 600
+    output_dir = SMARTEOLE_OUTPUT_DIR
+    output_dir.mkdir(parents=True, exist_ok=True)
+    cache_subdir = SMARTEOLE_CACHE_DIR
+    cache_subdir.mkdir(parents=True, exist_ok=True)
+
+    scada_df = unpack_smarteole_scada(
+        timebase_s=timebase_s, scada_data_file=SMARTEOLE_DATA_DIR / "SMARTEOLE_WakeSteering_SCADA_1minData.csv"
+    )
+    metadata_df = unpack_smarteole_metadata(
+        timebase_s=timebase_s, metadata_file=SMARTEOLE_DATA_DIR / "SMARTEOLE_WakeSteering_Coordinates_staticData.csv"
+    )
+    toggle_df = unpack_smarteole_toggle_data(
+        timebase_s=timebase_s, toggle_file=SMARTEOLE_DATA_DIR / "SMARTEOLE_WakeSteering_ControlLog_1minData.csv"
+    )
+    smarteole_data = SmarteoleData(scada_df=scada_df, metadata_df=metadata_df, toggle_df=toggle_df)
+
+    return _construct_assessment_inputs(
+        smarteole_data=smarteole_data,
+        logger=logger,
+        reanalysis_file_path=SMARTEOLE_DATA_DIR / "ERA5T_50.00N_2.75E_100m_1hr_20200201_20200531.parquet",
+        analysis_timebase_s=timebase_s,
+        analysis_output_dir=output_dir,
+        cache_sub_dir=cache_subdir,
+    ), smarteole_data
+
+
+def pytest_sessionfinish(session, exitstatus) -> None:  # noqa: ARG001,ANN001
+    # remove directories created during tests
+    plot_testing = [
+        Path(__file__).parents[1] / "result_images",  # if pytest run from root dir
+    ]
+    for d in [SMARTEOLE_OUTPUT_DIR, SMARTEOLE_CACHE_DIR, *plot_testing]:
+        if d.is_dir():
+            shutil.rmtree(d)

tests/plots/test_input_data.py

@@ -0,0 +1,101 @@
+import copy
+import logging
+import re
+
+import numpy as np
+import pandas as pd
+import pytest
+from matplotlib.testing.decorators import image_comparison
+
+from examples.smarteole_example import SmarteoleData
+from wind_up.interface import AssessmentInputs
+from wind_up.plots.input_data import plot_input_data_timeline
+
+logger = logging.getLogger(__name__)
+
+
+class TestInputDataTimeline:
+    @pytest.mark.slow
+    @pytest.mark.filterwarnings("ignore")
+    @pytest.mark.parametrize("exclusion_period_attribute_name", ["yaw_data_exclusions_utc", "exclusion_periods_utc"])
+    def test_data_is_present_within_an_exclusion_period(
+        self, exclusion_period_attribute_name: str, smarteole_assessment_inputs: tuple[AssessmentInputs, SmarteoleData]
+    ) -> None:
+        """Test that a ValueError is raised if any non-NaN data is present within any exclusion period."""
+
+        assessment_inputs = copy.deepcopy(smarteole_assessment_inputs[0])
+
+        setattr(
+            assessment_inputs.cfg,
+            exclusion_period_attribute_name,
+            [
+                ("SMV1", pd.Timestamp("2020-03-01T00:00:00+0000"), pd.Timestamp("2020-03-03T00:00:00+0000")),
+            ],
+        )
+
+        with pytest.raises(
+            ValueError,
+            match=re.escape(
+                "Data is not all NaN within exclusion period "
+                f"{getattr(assessment_inputs.cfg, exclusion_period_attribute_name)[0]}"
+            ),
+        ):
+            plot_input_data_timeline(assessment_inputs)
+
+    @pytest.mark.slow
+    @pytest.mark.filterwarnings("ignore")
+    @image_comparison(
+        baseline_images=["input_data_timeline_fig_toggle"], remove_text=False, extensions=["png"], style="mpl20"
+    )
+    def test_toggle(self, smarteole_assessment_inputs: tuple[AssessmentInputs, SmarteoleData]) -> None:
+        """Test plotting timeline of input data on the Smarteole wind farm."""
+
+        assessment_inputs = copy.deepcopy(smarteole_assessment_inputs[0])
+
+        assessment_inputs.cfg.yaw_data_exclusions_utc = [
+            ("SMV1", pd.Timestamp("2020-03-01T00:00:00+0000"), pd.Timestamp("2020-03-03T00:00:00+0000")),
+            ("SMV4", pd.Timestamp("2020-04-02T00:00:00+0000"), pd.Timestamp("2020-05-20T00:00:00+0000")),
+        ]
+
+        assessment_inputs.cfg.exclusion_periods_utc = [
+            ("SMV3", pd.Timestamp("2020-04-01T00:00:00+0000"), pd.Timestamp("2020-04-10T00:00:00+0000")),
+            ("SMV6", pd.Timestamp("2020-03-10T00:00:00+0000"), pd.Timestamp("2020-03-12T00:00:00+0000")),
+        ]
+
+        for exclusion in [*assessment_inputs.cfg.yaw_data_exclusions_utc, *assessment_inputs.cfg.exclusion_periods_utc]:
+            turbine_name = exclusion[0]
+            start, end = exclusion[1], exclusion[2]
+            assessment_inputs.wf_df.loc[pd.IndexSlice[turbine_name, start:end], "ActivePowerMean"] = np.nan
+
+        plot_input_data_timeline(assessment_inputs)
+
+    @pytest.mark.slow
+    @pytest.mark.filterwarnings("ignore")
+    @image_comparison(
+        baseline_images=["input_data_timeline_fig_prepost"], remove_text=False, extensions=["png"], style="mpl20"
+    )
+    def test_prepost(self, smarteole_assessment_inputs: tuple[AssessmentInputs, SmarteoleData]) -> None:
+        """Test plotting timeline of input data on the Smarteole wind farm."""
+
+        assessment_inputs = copy.deepcopy(smarteole_assessment_inputs[0])
+
+        # manual adjustments to the configuration for the test
+        assessment_inputs.cfg.toggle = None
+        assessment_inputs.cfg.upgrade_first_dt_utc_start = pd.Timestamp("2020-03-01T00:00:00+0000")
+
+        assessment_inputs.cfg.yaw_data_exclusions_utc = [
+            ("SMV1", pd.Timestamp("2020-03-01T00:00:00+0000"), pd.Timestamp("2020-03-03T00:00:00+0000")),
+            ("SMV4", pd.Timestamp("2020-04-02T00:00:00+0000"), pd.Timestamp("2020-05-20T00:00:00+0000")),
+        ]
+
+        assessment_inputs.cfg.exclusion_periods_utc = [
+            ("SMV3", pd.Timestamp("2020-04-01T00:00:00+0000"), pd.Timestamp("2020-04-10T00:00:00+0000")),
+            ("SMV6", pd.Timestamp("2020-03-10T00:00:00+0000"), pd.Timestamp("2020-03-12T00:00:00+0000")),
+        ]
+
+        for exclusion in [*assessment_inputs.cfg.yaw_data_exclusions_utc, *assessment_inputs.cfg.exclusion_periods_utc]:
+            turbine_name = exclusion[0]
+            start, end = exclusion[1], exclusion[2]
+            assessment_inputs.wf_df.loc[pd.IndexSlice[turbine_name, start:end], "ActivePowerMean"] = np.nan
+
+        plot_input_data_timeline(assessment_inputs)

tests/test_smarteole.py

@@ -1,45 +1,30 @@
 """Tests running the Smarteole dataset through wind-up analysis."""
 
+import copy
 from pathlib import Path
 
 import pytest
 
-from examples.smarteole_example import (
-    SmarteoleData,
-    main_smarteole_analysis,
-    unpack_smarteole_metadata,
-    unpack_smarteole_scada,
-    unpack_smarteole_toggle_data,
-)
+from examples.smarteole_example import SmarteoleData, main_smarteole_analysis
+from tests.conftest import SMARTEOLE_CACHE_DIR
+from wind_up.interface import AssessmentInputs
 
 SMARTEOLE_DATA_DIR = Path(__file__).parents[1] / "tests/test_data/smarteole"
 
 
 @pytest.mark.slow
 @pytest.mark.filterwarnings("ignore")
-def test_smarteole_analysis(tmp_path: Path) -> None:
+def test_smarteole_analysis(
+    smarteole_assessment_inputs: tuple[AssessmentInputs, SmarteoleData], tmp_path: Path
+) -> None:
     """Test running the Smarteole analysis."""
-
-    timebase_s = 600
-    cache_subdir = tmp_path / f"timebase_{timebase_s}"
-    cache_subdir.mkdir(parents=True, exist_ok=True)
-
-    scada_df = unpack_smarteole_scada(
-        timebase_s=timebase_s, scada_data_file=SMARTEOLE_DATA_DIR / "SMARTEOLE_WakeSteering_SCADA_1minData.csv"
-    )
-    metadata_df = unpack_smarteole_metadata(
-        timebase_s=timebase_s, metadata_file=SMARTEOLE_DATA_DIR / "SMARTEOLE_WakeSteering_Coordinates_staticData.csv"
-    )
-    toggle_df = unpack_smarteole_toggle_data(
-        timebase_s=timebase_s, toggle_file=SMARTEOLE_DATA_DIR / "SMARTEOLE_WakeSteering_ControlLog_1minData.csv"
-    )
-    smarteole_data = SmarteoleData(scada_df=scada_df, metadata_df=metadata_df, toggle_df=toggle_df)
+    smarteole_data = copy.deepcopy(smarteole_assessment_inputs[1])
 
     main_smarteole_analysis(
         smarteole_data=smarteole_data,
         reanalysis_file_path=SMARTEOLE_DATA_DIR / "ERA5T_50.00N_2.75E_100m_1hr_20200201_20200531.parquet",
-        analysis_timebase_s=timebase_s,
+        analysis_timebase_s=600,
         check_results=True,  # asserts expected results
         analysis_output_dir=tmp_path,
-        cache_sub_dir=cache_subdir,
+        cache_sub_dir=SMARTEOLE_CACHE_DIR,
     )