Refine climate metrics and data pipeline

This commit is contained in:
2026-07-24 22:55:14 -04:00
parent 016f7386d8
commit 4e2d878e5b
32 changed files with 3557 additions and 3347 deletions
+97
View File
@@ -0,0 +1,97 @@
from __future__ import annotations
import csv
import sys
import unittest
from pathlib import Path
from tempfile import TemporaryDirectory
SCRIPTS_DIR = Path(__file__).resolve().parents[1] / "scripts"
sys.path.insert(0, str(SCRIPTS_DIR))
from apply_nsrdb_cloud_metric_to_climate_data import ( # noqa: E402
POLYGON_SOURCE_TAG,
REPRESENTATIVE_POINT_SOURCE_TAG,
merge_metric,
)
def write_csv(path: Path, fieldnames: list[str], rows: list[dict[str, str]]) -> None:
with path.open("w", encoding="utf-8", newline="") as handle:
writer = csv.DictWriter(handle, fieldnames=fieldnames)
writer.writeheader()
writer.writerows(rows)
class ApplyNsrdbCloudMetricTests(unittest.TestCase):
def test_polygon_area_weighted_value_wins_with_representative_fallback(self) -> None:
with TemporaryDirectory() as temp_dir:
base = Path(temp_dir)
climate_data = base / "climate-data.csv"
polygon_summary = base / "polygon-cloud.csv"
representative_summary = base / "representative-cloud.csv"
write_csv(
climate_data,
["countyFips", "meanDailyGlobalHorizontalRadiationKwhM2Day", "clearSkyGhiReductionIndex", "source"],
[
{
"countyFips": "01001",
"meanDailyGlobalHorizontalRadiationKwhM2Day": "4.8",
"clearSkyGhiReductionIndex": "0.9999",
"source": f"base + {REPRESENTATIVE_POINT_SOURCE_TAG}",
},
{
"countyFips": "01003",
"meanDailyGlobalHorizontalRadiationKwhM2Day": "4.9",
"clearSkyGhiReductionIndex": "",
"source": "base",
},
{
"countyFips": "01005",
"meanDailyGlobalHorizontalRadiationKwhM2Day": "5.0",
"clearSkyGhiReductionIndex": "",
"source": "base",
},
],
)
write_csv(
polygon_summary,
[
"county_fips",
"clearSkyGhiReductionIndex",
"areaWeightedClearSkyGhiReductionIndex",
],
[
{
"county_fips": "01001",
"clearSkyGhiReductionIndex": "0.1111",
"areaWeightedClearSkyGhiReductionIndex": "0.2222",
},
],
)
write_csv(
representative_summary,
["county_fips", "clearSkyGhiReductionIndex"],
[
{"county_fips": "01001", "clearSkyGhiReductionIndex": "0.3333"},
{"county_fips": "01003", "clearSkyGhiReductionIndex": "0.4444"},
],
)
result = merge_metric(climate_data, polygon_summary, representative_summary)
self.assertEqual(result, (3, 1, 1, 1))
with climate_data.open("r", encoding="utf-8", newline="") as handle:
rows = {row["countyFips"]: row for row in csv.DictReader(handle)}
self.assertEqual(rows["01001"]["clearSkyGhiReductionIndex"], "0.2222")
self.assertIn(POLYGON_SOURCE_TAG, rows["01001"]["source"])
self.assertNotIn(REPRESENTATIVE_POINT_SOURCE_TAG, rows["01001"]["source"])
self.assertEqual(rows["01003"]["clearSkyGhiReductionIndex"], "0.4444")
self.assertIn(REPRESENTATIVE_POINT_SOURCE_TAG, rows["01003"]["source"])
self.assertEqual(rows["01005"]["clearSkyGhiReductionIndex"], "")
if __name__ == "__main__":
unittest.main()