Knou/Climate-Mood-Analysis
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Initial Climate Mood Analysis project

Browse Source
This commit is contained in:
Justin Fisher
2026-06-11 14:50:33 -04:00
commit 18e099ce84
34 changed files with 18807 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/apply_diurnal_temperature_range_to_climate_data.py
+159
View File
@@ -0,0 +1,159 @@
#!/usr/bin/env python3
"""
Apply county diurnal temperature range to the app CSV.
This joins only the final app-facing metric into climate-data.csv. Detailed ETL
fields stay in data/noaa/county_diurnal_temperature_range.csv.
"""
from __future__ import annotations
import argparse
import csv
from pathlib import Path
from build_county_locally_extreme_data import OLD_APP_FIPS_TO_CURRENT_FIPS
REPO_ROOT = Path(__file__).resolve().parents[1]
DEFAULT_CLIMATE_DATA = REPO_ROOT / "data" / "climate-data.csv"
DEFAULT_DTR_CSV = REPO_ROOT / "data" / "noaa" / "county_diurnal_temperature_range.csv"
METRIC_FIELD = "avgDiurnalTempRangeF"
SOURCE_TAG_PREFIX = "diurnalTempRange="
SOURCE_TAG = "diurnalTempRange=noaa-nclimgrid-daily-1991-2020"
MISSING_SOURCE_TAG = "missing-noaa-diurnal-temperature-range"
def normalize_fips(value: object) -> str:
"""Return a 5-digit county FIPS string from mixed text or numeric input."""
digits = "".join(ch for ch in str(value).strip() if ch.isdigit())
return digits.zfill(5)[-5:] if digits else ""
def read_csv_rows(path: Path) -> tuple[list[str], list[dict]]:
"""Read a CSV while preserving the source field order."""
with path.open("r", encoding="utf-8-sig", newline="") as csv_file:
reader = csv.DictReader(csv_file)
if reader.fieldnames is None:
raise ValueError(f"{path} has no CSV header.")
return list(reader.fieldnames), list(reader)
def load_dtr_lookup(path: Path) -> dict[str, dict]:
"""Load DTR rows keyed by current county FIPS plus supported old app FIPS."""
fieldnames, rows = read_csv_rows(path)
required_fields = {"countyFips", METRIC_FIELD}
missing_fields = required_fields - set(fieldnames)
if missing_fields:
raise ValueError(f"{path} is missing required fields: {sorted(missing_fields)}")
current_lookup: dict[str, dict] = {}
for row in rows:
county_fips = normalize_fips(row.get("countyFips", ""))
metric_value = (row.get(METRIC_FIELD) or "").strip()
if not county_fips or not metric_value:
continue
float(metric_value)
current_lookup[county_fips] = row
lookup = dict(current_lookup)
for old_fips, (current_fips, reason) in OLD_APP_FIPS_TO_CURRENT_FIPS.items():
current_row = current_lookup.get(normalize_fips(current_fips))
if not current_row:
continue
proxy_row = dict(current_row)
proxy_row["fipsAdjustment"] = reason
lookup[normalize_fips(old_fips)] = proxy_row
return lookup
def fieldnames_with_metric(original_fields: list[str]) -> list[str]:
"""Insert the DTR metric near the other temperature field."""
fields = [field for field in original_fields if field != METRIC_FIELD]
if "avgTempF" in fields:
insert_at = fields.index("avgTempF") + 1
else:
insert_at = len(fields)
fields.insert(insert_at, METRIC_FIELD)
return fields
def replace_dtr_source_tag(source: str, has_value: bool) -> str:
"""Replace previous DTR provenance with the active one."""
parts = [
part.strip()
for part in (source.strip() or "unknown-source").split("+")
if part.strip()
]
kept_parts = [
part
for part in parts
if not part.startswith(SOURCE_TAG_PREFIX) and part != MISSING_SOURCE_TAG
]
kept_parts.append(SOURCE_TAG if has_value else MISSING_SOURCE_TAG)
return " + ".join(kept_parts)
def apply_diurnal_temperature_range(
*,
climate_data: Path,
dtr_csv: Path,
out: Path,
) -> None:
"""Join DTR values into climate-data.csv."""
original_fields, climate_rows = read_csv_rows(climate_data)
dtr_lookup = load_dtr_lookup(dtr_csv)
fieldnames = fieldnames_with_metric(original_fields)
updated_count = 0
missing_count = 0
adjusted_count = 0
for row in climate_rows:
county_fips = normalize_fips(row.get("countyFips", ""))
dtr_row = dtr_lookup.get(county_fips)
if dtr_row:
row[METRIC_FIELD] = dtr_row.get(METRIC_FIELD, "")
row["source"] = replace_dtr_source_tag(row.get("source", ""), has_value=True)
updated_count += 1
if dtr_row.get("fipsAdjustment"):
adjusted_count += 1
else:
row[METRIC_FIELD] = ""
row["source"] = replace_dtr_source_tag(row.get("source", ""), has_value=False)
missing_count += 1
with out.open("w", encoding="utf-8", newline="") as csv_file:
writer = csv.DictWriter(csv_file, fieldnames=fieldnames, extrasaction="ignore")
writer.writeheader()
writer.writerows(climate_rows)
print(f"Wrote {len(climate_rows)} rows to {out}")
print(f"Updated {METRIC_FIELD} for {updated_count} rows.")
print(f"Used supported county-vintage FIPS adjustments for {adjusted_count} rows.")
print(f"Left {METRIC_FIELD} blank for {missing_count} rows without DTR data.")
def parse_args() -> argparse.Namespace:
"""Parse command-line paths."""
parser = argparse.ArgumentParser(
description="Apply average diurnal temperature range to climate-data.csv."
)
parser.add_argument("--climate-data", type=Path, default=DEFAULT_CLIMATE_DATA)
parser.add_argument("--dtr-csv", type=Path, default=DEFAULT_DTR_CSV)
parser.add_argument("--out", type=Path, default=DEFAULT_CLIMATE_DATA)
return parser.parse_args()
def main() -> None:
"""Run the climate-data update."""
args = parse_args()
apply_diurnal_temperature_range(
climate_data=args.climate_data,
dtr_csv=args.dtr_csv,
out=args.out,
)
if __name__ == "__main__":
main()
scripts/apply_gridmet_humidity_metric_to_climate_data.py
+119
View File
@@ -0,0 +1,119 @@
#!/usr/bin/env python3
"""
Merge selected gridMET humidity and heat metrics into climate-data.csv.
Currently adds:
- avgSummerSpecificHumidityGKg
- humidHeatDays
- humidHeatSourceFips
- humidHeatFipsAdjustment
"""
from __future__ import annotations
import argparse
import csv
from pathlib import Path
DEFAULT_CLIMATE_DATA = Path("data/climate-data.csv")
DEFAULT_GRIDMET_HUMIDITY = Path("data/gridmet/county_gridmet_humidity.csv")
METRIC_FIELDS = [
"avgSummerSpecificHumidityGKg",
"humidHeatDays",
"humidHeatSourceFips",
"humidHeatFipsAdjustment",
]
SOURCE_TAGS_BY_FIELD = {
"avgSummerSpecificHumidityGKg": "gridmet-specific-humidity-1991-2020",
"humidHeatDays": "heat-index-noaa-tmax-gridmet-rmin-1991-2020",
}
def load_gridmet_values(path: Path) -> dict[str, dict[str, str]]:
values: dict[str, dict[str, str]] = {}
with path.open("r", encoding="utf-8", newline="") as handle:
reader = csv.DictReader(handle)
fieldnames = reader.fieldnames or []
missing_fields = [field for field in METRIC_FIELDS if field not in fieldnames]
if missing_fields:
raise ValueError(f"{path} is missing fields: {', '.join(missing_fields)}")
for row in reader:
county_fips = (row.get("countyFips") or "").strip().zfill(5)
if county_fips:
values[county_fips] = {
field: (row.get(field) or "").strip() for field in METRIC_FIELDS
}
return values
def append_source_tag(source: str, tag: str) -> str:
clean_source = source.strip()
if tag in clean_source:
return clean_source
return f"{clean_source} + {tag}".strip(" +")
def ensure_field_after(fieldnames: list[str], field: str, after_field: str | None = None) -> None:
if field in fieldnames:
return
if after_field and after_field in fieldnames:
fieldnames.insert(fieldnames.index(after_field) + 1, field)
return
insert_at = fieldnames.index("source") if "source" in fieldnames else len(fieldnames)
fieldnames.insert(insert_at, field)
def merge_metrics(climate_data: Path, humidity_csv: Path) -> tuple[int, dict[str, int]]:
gridmet_by_fips = load_gridmet_values(humidity_csv)
with climate_data.open("r", encoding="utf-8", newline="") as handle:
reader = csv.DictReader(handle)
fieldnames = list(reader.fieldnames or [])
rows = list(reader)
if "countyFips" not in fieldnames:
raise ValueError(f"{climate_data} is missing countyFips")
ensure_field_after(fieldnames, "avgSummerSpecificHumidityGKg")
ensure_field_after(fieldnames, "humidHeatDays", "avgSummerSpecificHumidityGKg")
ensure_field_after(fieldnames, "humidHeatSourceFips", "humidHeatDays")
ensure_field_after(fieldnames, "humidHeatFipsAdjustment", "humidHeatSourceFips")
missing_counts = {field: 0 for field in METRIC_FIELDS}
for row in rows:
county_fips = (row.get("countyFips") or "").strip().zfill(5)
gridmet_values = gridmet_by_fips.get(county_fips, {})
for field in METRIC_FIELDS:
value = gridmet_values.get(field, "")
row[field] = value
if not value:
missing_counts[field] += 1
for field, tag in SOURCE_TAGS_BY_FIELD.items():
if row.get(field):
row["source"] = append_source_tag(row.get("source", ""), tag)
with climate_data.open("w", encoding="utf-8", newline="") as handle:
writer = csv.DictWriter(handle, fieldnames=fieldnames)
writer.writeheader()
writer.writerows(rows)
return len(rows), missing_counts
def main() -> int:
parser = argparse.ArgumentParser(description="Merge gridMET humidity and Heat Index metrics into climate-data.csv.")
parser.add_argument("--climate-data", type=Path, default=DEFAULT_CLIMATE_DATA)
parser.add_argument("--humidity-csv", type=Path, default=DEFAULT_GRIDMET_HUMIDITY)
args = parser.parse_args()
row_count, missing_counts = merge_metrics(args.climate_data, args.humidity_csv)
print(f"Updated {args.climate_data} with {', '.join(METRIC_FIELDS)}")
print(f"Rows: {row_count}")
for field, missing_count in missing_counts.items():
print(f"Missing {field}: {missing_count}")
return 0
if __name__ == "__main__":
raise SystemExit(main())
scripts/apply_locally_extreme_metric_to_climate_data.py
+290
View File
@@ -0,0 +1,290 @@
#!/usr/bin/env python3
"""
Apply NOAA daily extreme-day and polygon solar metrics to the app CSV.
The browser app already reads the `extremeDays` column, so this script updates
that column to the average locally extreme days/year while preserving the older
proxy value in `oldExtremeDays`. It also writes an absolute daily heat/cold
bucket metric from the same NOAA nClimGrid-Daily county data.
When an NSRDB polygon archive summary is available, this also replaces the
older representative-point solar GHI value with the county polygon value. Rows
without a polygon summary keep the representative-point fallback when present.
"""
from __future__ import annotations
import argparse
import csv
from pathlib import Path
REPO_ROOT = Path(__file__).resolve().parents[1]
DEFAULT_CLIMATE_DATA = REPO_ROOT / "data" / "climate-data.csv"
DEFAULT_COMPARISON = REPO_ROOT / "data" / "noaa" / "county_locally_extreme_days_comparison.csv"
DEFAULT_POLYGON_SOLAR_GHI = REPO_ROOT / "data" / "nrel" / "county_polygon_ghi_summary.csv"
DEFAULT_REPRESENTATIVE_POINT_SOLAR_GHI = REPO_ROOT / "data" / "nrel" / "county_representative_point_ghi_summary.csv"
BASE_FIELDS = [
"countyFips",
"countyName",
"state",
"koppenZone",
"avgTempF",
"annualPrecipIn",
"seasonalityIndex",
"wettestPrecipMonth",
"driestPrecipMonth",
"extremeDays",
"locallyExtremeDays",
"locallyExtremeHotDays",
"locallyExtremeColdDays",
"absoluteExtremeDays",
"oldExtremeDays",
"locallyExtremeAnalysisYears",
"locallyExtremeSourceFips",
"locallyExtremeFipsAdjustment",
"avgSolarGhiKwhM2Day",
"source",
]
LEGACY_FIELDS = {
"absoluteExtremeHeatDays",
"absoluteExtremeColdDays",
}
SOLAR_SOURCE_TAGS = {
"solar-ghi-centroid-preview",
"solar-ghi-representative-point",
"solar-ghi-polygon-area-weighted",
"solar-ghi-polygon-archive-area-weighted",
"no-solar-ghi-source",
"missing-solar-ghi",
}
def normalize_fips(value: object) -> str:
"""Return a 5-digit county FIPS string from mixed text or numeric input."""
digits = "".join(ch for ch in str(value).strip() if ch.isdigit())
return digits.zfill(5)[-5:] if digits else ""
def read_csv_rows(path: Path) -> tuple[list[str], list[dict]]:
"""Read a CSV while preserving the source field order."""
with path.open("r", encoding="utf-8-sig", newline="") as csv_file:
reader = csv.DictReader(csv_file)
if reader.fieldnames is None:
raise ValueError(f"{path} has no CSV header.")
return list(reader.fieldnames), list(reader)
def load_locally_extreme_lookup(comparison_csv: Path) -> dict[str, dict]:
"""Map current and supported old app FIPS codes to locally extreme rows."""
_, rows = read_csv_rows(comparison_csv)
lookup: dict[str, dict] = {}
for row in rows:
if row.get("hasLocallyExtremeData") != "yes":
continue
current_fips = normalize_fips(row.get("countyFips", ""))
if current_fips:
lookup[current_fips] = row
for old_fips in (row.get("oldSourceFips") or "").split(";"):
normalized_old_fips = normalize_fips(old_fips)
if normalized_old_fips:
lookup[normalized_old_fips] = row
return lookup
def load_solar_ghi_lookup(solar_ghi_csv: Path) -> dict[str, str]:
"""Map county FIPS codes to average daily GHI values from a county CSV."""
if not solar_ghi_csv.exists():
return {}
fieldnames, rows = read_csv_rows(solar_ghi_csv)
if "avgSolarGhiKwhM2Day" not in fieldnames:
raise ValueError(f"{solar_ghi_csv} must include avgSolarGhiKwhM2Day.")
if "county_fips" in fieldnames:
fips_field = "county_fips"
elif "countyFips" in fieldnames:
fips_field = "countyFips"
else:
raise ValueError(f"{solar_ghi_csv} must include county_fips or countyFips.")
lookup: dict[str, str] = {}
for row in rows:
county_fips = normalize_fips(row.get(fips_field, ""))
raw_value = (row.get("avgSolarGhiKwhM2Day") or "").strip()
if not county_fips or not raw_value:
continue
try:
float(raw_value)
except ValueError as error:
raise ValueError(
f"Invalid avgSolarGhiKwhM2Day value for county {county_fips}: {raw_value}"
) from error
lookup[county_fips] = raw_value
return lookup
def append_source_tag(source: str, has_local_value: bool) -> str:
"""Add the locally extreme provenance tags without duplicating old tags."""
old_source = source.strip() or "unknown-source"
old_source = old_source.replace(" + absoluteExtremeHeatDays=tmax-gte-95f", "")
old_source = old_source.replace(" + absoluteExtremeColdDays=tmin-lte-0f", "")
if not has_local_value:
return f"{old_source} + missing-noaa-locally-extreme-days"
has_local_tag = "extremeDays=locally-extreme-noaa-nclimgrid-daily-1991-2025" in old_source
has_absolute_tag = "absoluteExtremeDays=tmax-gte-95f-or-tmin-lte-0f" in old_source
if has_local_tag and has_absolute_tag:
return old_source
if has_local_tag:
return f"{old_source} + absoluteExtremeDays=tmax-gte-95f-or-tmin-lte-0f"
return (
f"{old_source} + extremeDays=locally-extreme-noaa-nclimgrid-daily-1991-2025 "
"+ absoluteExtremeDays=tmax-gte-95f-or-tmin-lte-0f "
"+ oldExtremeDays=previous-monthly-proxy"
)
def replace_solar_source_tag(source: str, solar_source_tag: str) -> str:
"""Replace any previous solar provenance tag with the active one."""
parts = [part.strip() for part in (source.strip() or "unknown-source").split("+")]
kept_parts = [
part
for part in parts
if part and part not in SOLAR_SOURCE_TAGS
]
if solar_source_tag not in kept_parts:
kept_parts.append(solar_source_tag)
return " + ".join(kept_parts)
def apply_locally_extreme_metric(
*,
climate_data: Path,
comparison_csv: Path,
polygon_solar_ghi_csv: Path,
representative_point_solar_ghi_csv: Path,
out: Path,
) -> None:
"""Replace app extreme-day fields and solar GHI with improved metrics."""
original_fields, climate_rows = read_csv_rows(climate_data)
local_lookup = load_locally_extreme_lookup(comparison_csv)
polygon_solar_lookup = load_solar_ghi_lookup(polygon_solar_ghi_csv)
representative_solar_lookup = load_solar_ghi_lookup(representative_point_solar_ghi_csv)
extra_fields = [
field
for field in original_fields
if field not in BASE_FIELDS and field not in LEGACY_FIELDS
]
fieldnames = BASE_FIELDS + extra_fields
updated_count = 0
missing_count = 0
polygon_solar_count = 0
representative_solar_count = 0
missing_solar_count = 0
for row in climate_rows:
county_fips = normalize_fips(row.get("countyFips", ""))
local_row = local_lookup.get(county_fips)
old_extreme_days = (row.get("oldExtremeDays") or row.get("extremeDays") or "").strip()
row["oldExtremeDays"] = old_extreme_days
if local_row:
row["extremeDays"] = local_row.get("avgLocallyExtremeDays", "")
row["locallyExtremeDays"] = local_row.get("avgLocallyExtremeDays", "")
row["locallyExtremeHotDays"] = local_row.get("avgHotExtremeDays", "")
row["locallyExtremeColdDays"] = local_row.get("avgColdExtremeDays", "")
row["absoluteExtremeDays"] = local_row.get("avgAbsoluteExtremeDays", "")
row["locallyExtremeAnalysisYears"] = local_row.get("analysisYears", "")
row["locallyExtremeSourceFips"] = local_row.get("countyFips", "")
row["locallyExtremeFipsAdjustment"] = local_row.get("fipsAdjustment", "")
row["source"] = append_source_tag(row.get("source", ""), has_local_value=True)
updated_count += 1
else:
row["extremeDays"] = ""
row["locallyExtremeDays"] = ""
row["locallyExtremeHotDays"] = ""
row["locallyExtremeColdDays"] = ""
row["absoluteExtremeDays"] = ""
row["locallyExtremeAnalysisYears"] = ""
row["locallyExtremeSourceFips"] = ""
row["locallyExtremeFipsAdjustment"] = ""
row["source"] = append_source_tag(row.get("source", ""), has_local_value=False)
missing_count += 1
polygon_solar_value = polygon_solar_lookup.get(county_fips)
representative_solar_value = representative_solar_lookup.get(county_fips)
current_solar_value = (row.get("avgSolarGhiKwhM2Day") or "").strip()
if polygon_solar_value:
row["avgSolarGhiKwhM2Day"] = polygon_solar_value
row["source"] = replace_solar_source_tag(
row.get("source", ""),
"solar-ghi-polygon-archive-area-weighted",
)
polygon_solar_count += 1
elif representative_solar_value or current_solar_value:
row["avgSolarGhiKwhM2Day"] = representative_solar_value or current_solar_value
row["source"] = replace_solar_source_tag(
row.get("source", ""),
"solar-ghi-representative-point",
)
representative_solar_count += 1
else:
row["avgSolarGhiKwhM2Day"] = ""
row["source"] = replace_solar_source_tag(row.get("source", ""), "missing-solar-ghi")
missing_solar_count += 1
with out.open("w", encoding="utf-8", newline="") as csv_file:
writer = csv.DictWriter(csv_file, fieldnames=fieldnames, extrasaction="ignore")
writer.writeheader()
writer.writerows(climate_rows)
print(f"Wrote {len(climate_rows)} rows to {out}")
print(f"Updated active extremeDays from locally extreme data for {updated_count} rows.")
print(f"Left active extremeDays blank for {missing_count} rows without locally extreme data.")
print(f"Updated avgSolarGhiKwhM2Day from polygon archives for {polygon_solar_count} rows.")
print(f"Kept representative-point solar fallback for {representative_solar_count} rows.")
print(f"Left avgSolarGhiKwhM2Day blank for {missing_solar_count} rows without solar data.")
def parse_args() -> argparse.Namespace:
"""Parse command-line paths for the climate-data update."""
parser = argparse.ArgumentParser(
description="Apply locally extreme days/year and polygon solar GHI to climate-data.csv."
)
parser.add_argument("--climate-data", type=Path, default=DEFAULT_CLIMATE_DATA)
parser.add_argument("--comparison-csv", type=Path, default=DEFAULT_COMPARISON)
parser.add_argument("--polygon-solar-ghi-csv", type=Path, default=DEFAULT_POLYGON_SOLAR_GHI)
parser.add_argument(
"--representative-point-solar-ghi-csv",
type=Path,
default=DEFAULT_REPRESENTATIVE_POINT_SOLAR_GHI,
)
parser.add_argument("--out", type=Path, default=DEFAULT_CLIMATE_DATA)
return parser.parse_args()
def main() -> None:
"""Run the CSV update from parsed command-line arguments."""
args = parse_args()
apply_locally_extreme_metric(
climate_data=args.climate_data,
comparison_csv=args.comparison_csv,
polygon_solar_ghi_csv=args.polygon_solar_ghi_csv,
representative_point_solar_ghi_csv=args.representative_point_solar_ghi_csv,
out=args.out,
)
if __name__ == "__main__":
main()
scripts/apply_nsrdb_cloud_metric_to_climate_data.py
+147
View File
@@ -0,0 +1,147 @@
#!/usr/bin/env python3
"""
Merge NSRDB cloudiness metrics into climate-data.csv.
Adds:
- cloudinessIndexPct
Polygon area-weighted values are used first when available; representative-point
values remain the fallback.
"""
from __future__ import annotations
import argparse
import csv
from pathlib import Path
DEFAULT_CLIMATE_DATA = Path("data/climate-data.csv")
DEFAULT_POLYGON_CLOUD_SUMMARY = Path("data/nrel/county_polygon_cloud_summary.csv")
DEFAULT_REPRESENTATIVE_POINT_CLOUD_SUMMARY = Path("data/nrel/county_representative_point_cloud_summary.csv")
METRIC_FIELD = "cloudinessIndexPct"
POLYGON_SOURCE_TAG = "nsrdb-polygon-area-weighted-cloudiness-tmy"
REPRESENTATIVE_POINT_SOURCE_TAG = "nsrdb-representative-point-cloudiness-tmy"
CLOUD_SOURCE_TAGS = {
POLYGON_SOURCE_TAG,
REPRESENTATIVE_POINT_SOURCE_TAG,
}
def load_cloud_values(path: Path) -> dict[str, str]:
"""Read cloudiness values keyed by county FIPS."""
values: dict[str, str] = {}
with path.open("r", encoding="utf-8-sig", newline="") as handle:
reader = csv.DictReader(handle)
fieldnames = reader.fieldnames or []
required_fields = {"county_fips", METRIC_FIELD}
missing_fields = sorted(required_fields - set(fieldnames))
if missing_fields:
raise ValueError(f"{path} is missing fields: {', '.join(missing_fields)}")
for row in reader:
county_fips = (row.get("county_fips") or "").strip().zfill(5)
value = (row.get(METRIC_FIELD) or "").strip()
if county_fips and value:
values[county_fips] = value
return values
def append_source_tag(source: str, tag: str) -> str:
"""Append a source tag if it is not already present."""
parts = [
part.strip()
for part in source.split("+")
if part.strip() and part.strip() not in CLOUD_SOURCE_TAGS
]
if tag not in parts:
parts.append(tag)
return " + ".join(parts)
def ensure_field_after(fieldnames: list[str], field: str, after_field: str | None = None) -> None:
"""Insert a field into CSV field order if it is missing."""
if field in fieldnames:
return
if after_field and after_field in fieldnames:
fieldnames.insert(fieldnames.index(after_field) + 1, field)
return
insert_at = fieldnames.index("source") if "source" in fieldnames else len(fieldnames)
fieldnames.insert(insert_at, field)
def merge_metric(
climate_data: Path,
polygon_cloud_summary: Path,
representative_point_cloud_summary: Path,
) -> tuple[int, int, int, int]:
"""Merge cloudiness values into the app climate CSV."""
polygon_cloudiness_by_fips = (
load_cloud_values(polygon_cloud_summary)
if polygon_cloud_summary.exists()
else {}
)
representative_cloudiness_by_fips = load_cloud_values(representative_point_cloud_summary)
with climate_data.open("r", encoding="utf-8", newline="") as handle:
reader = csv.DictReader(handle)
fieldnames = list(reader.fieldnames or [])
rows = list(reader)
if "countyFips" not in fieldnames:
raise ValueError(f"{climate_data} is missing countyFips")
ensure_field_after(fieldnames, METRIC_FIELD, "avgSolarGhiKwhM2Day")
polygon_count = 0
representative_count = 0
missing_count = 0
for row in rows:
county_fips = (row.get("countyFips") or "").strip().zfill(5)
polygon_value = polygon_cloudiness_by_fips.get(county_fips, "")
representative_value = representative_cloudiness_by_fips.get(county_fips, "")
value = polygon_value or representative_value
row[METRIC_FIELD] = value
if polygon_value:
row["source"] = append_source_tag(row.get("source", ""), POLYGON_SOURCE_TAG)
polygon_count += 1
elif representative_value:
row["source"] = append_source_tag(row.get("source", ""), REPRESENTATIVE_POINT_SOURCE_TAG)
representative_count += 1
else:
missing_count += 1
with climate_data.open("w", encoding="utf-8", newline="") as handle:
writer = csv.DictWriter(handle, fieldnames=fieldnames)
writer.writeheader()
writer.writerows(rows)
return len(rows), polygon_count, representative_count, missing_count
def main() -> int:
parser = argparse.ArgumentParser(description="Merge NSRDB cloudiness metric into climate-data.csv.")
parser.add_argument("--climate-data", type=Path, default=DEFAULT_CLIMATE_DATA)
parser.add_argument("--polygon-cloud-summary", type=Path, default=DEFAULT_POLYGON_CLOUD_SUMMARY)
parser.add_argument(
"--representative-point-cloud-summary",
type=Path,
default=DEFAULT_REPRESENTATIVE_POINT_CLOUD_SUMMARY,
)
args = parser.parse_args()
row_count, polygon_count, representative_count, missing_count = merge_metric(
args.climate_data,
args.polygon_cloud_summary,
args.representative_point_cloud_summary,
)
print(f"Updated {args.climate_data} with {METRIC_FIELD}")
print(f"Rows: {row_count}")
print(f"Polygon area-weighted rows: {polygon_count}")
print(f"Representative-point fallback rows: {representative_count}")
print(f"Missing {METRIC_FIELD}: {missing_count}")
return 0
if __name__ == "__main__":
raise SystemExit(main())
scripts/apply_precipitation_month_metrics_to_climate_data.py
+172
View File
@@ -0,0 +1,172 @@
#!/usr/bin/env python3
"""
Add wettest/driest precipitation month metrics to data/climate-data.csv.
The metrics use the existing monthly NOAA nClimGrid precipitation file. They
are categorical month labels derived from 1991-2020 county-area means.
"""
from __future__ import annotations
import argparse
import csv
from pathlib import Path
import numpy as np
import xarray as xr
from build_county_climate_data import (
MONTH_NAMES,
_as_monthly_climatology,
_extract_grid_2d,
_load_counties,
_select_data_var,
_zonal_mean,
)
REPO_ROOT = Path(__file__).resolve().parents[1]
DEFAULT_CLIMATE_DATA = REPO_ROOT / "data" / "climate-data.csv"
DEFAULT_COUNTIES_GEOJSON = REPO_ROOT / "data" / "geojson-counties-fips.json"
DEFAULT_MONTHLY_PRCP_NC = REPO_ROOT / "data" / "noaa" / "nclimgrid" / "nclimgrid_prcp.nc"
PRECIP_MONTH_FIELDS = ["wettestPrecipMonth", "driestPrecipMonth"]
def normalize_fips(value: object) -> str:
"""Return a 5-digit county FIPS string from mixed text or numeric input."""
digits = "".join(ch for ch in str(value).strip() if ch.isdigit())
return digits.zfill(5)[-5:] if digits else ""
def read_csv_rows(path: Path) -> tuple[list[str], list[dict]]:
"""Read a CSV while preserving the source field order."""
with path.open("r", encoding="utf-8-sig", newline="") as csv_file:
reader = csv.DictReader(csv_file)
if reader.fieldnames is None:
raise ValueError(f"{path} has no CSV header.")
return list(reader.fieldnames), list(reader)
def fieldnames_with_precip_months(original_fields: list[str]) -> list[str]:
"""Place the new fields next to the existing precipitation metrics."""
fields = [field for field in original_fields if field not in PRECIP_MONTH_FIELDS]
insert_after = "seasonalityIndex"
insert_at = fields.index(insert_after) + 1 if insert_after in fields else len(fields)
return fields[:insert_at] + PRECIP_MONTH_FIELDS + fields[insert_at:]
def build_precip_month_lookup(
*,
counties_geojson: Path,
monthly_prcp_nc: Path,
climatology_start_year: int,
climatology_end_year: int,
) -> dict[str, tuple[str, str]]:
"""Calculate wettest and driest precipitation month for each county."""
counties = _load_counties(counties_geojson)
monthly_prcp = xr.open_dataset(monthly_prcp_nc, decode_times=True)
try:
prcp_var = _select_data_var(monthly_prcp, "mlyprcp_norm")
prcp_monthly = _as_monthly_climatology(
monthly_prcp[prcp_var],
start_year=climatology_start_year,
end_year=climatology_end_year,
)
prcp_by_month: list[list[float]] = []
for month in range(12):
prcp_arr, prcp_transform = _extract_grid_2d(prcp_monthly.isel(time=month))
prcp_by_month.append(_zonal_mean(prcp_arr, prcp_transform, counties))
finally:
monthly_prcp.close()
lookup: dict[str, tuple[str, str]] = {}
for idx, row in counties.iterrows():
county_fips = str(row["county_fips"])
prcp_months_mm = np.array([prcp_by_month[m][idx] for m in range(12)], dtype=np.float64)
if not np.any(np.isfinite(prcp_months_mm)):
continue
wettest_month = MONTH_NAMES[int(np.nanargmax(prcp_months_mm))]
driest_month = MONTH_NAMES[int(np.nanargmin(prcp_months_mm))]
lookup[county_fips] = (wettest_month, driest_month)
return lookup
def apply_precipitation_month_metrics(
*,
climate_data: Path,
counties_geojson: Path,
monthly_prcp_nc: Path,
out: Path,
climatology_start_year: int,
climatology_end_year: int,
) -> None:
"""Merge precipitation month categories into the app climate CSV."""
original_fields, rows = read_csv_rows(climate_data)
lookup = build_precip_month_lookup(
counties_geojson=counties_geojson,
monthly_prcp_nc=monthly_prcp_nc,
climatology_start_year=climatology_start_year,
climatology_end_year=climatology_end_year,
)
updated_count = 0
missing_count = 0
for row in rows:
county_fips = normalize_fips(row.get("countyFips", ""))
values = lookup.get(county_fips)
if values:
row["wettestPrecipMonth"], row["driestPrecipMonth"] = values
updated_count += 1
else:
row["wettestPrecipMonth"] = ""
row["driestPrecipMonth"] = ""
missing_count += 1
source = (row.get("source") or "").strip() or "unknown-source"
tag = f"precip-month-extremes=noaa-nclimgrid-monthly-{climatology_start_year}-{climatology_end_year}"
if tag not in source:
row["source"] = f"{source} + {tag}"
fieldnames = fieldnames_with_precip_months(original_fields)
with out.open("w", encoding="utf-8", newline="") as csv_file:
writer = csv.DictWriter(csv_file, fieldnames=fieldnames, extrasaction="ignore")
writer.writeheader()
writer.writerows(rows)
print(f"Wrote {len(rows)} rows to {out}")
print(f"Updated precipitation month metrics for {updated_count} rows.")
print(f"Left precipitation month metrics blank for {missing_count} rows.")
def parse_args() -> argparse.Namespace:
"""Parse command-line paths for the precipitation month update."""
parser = argparse.ArgumentParser(
description="Add wettestPrecipMonth and driestPrecipMonth to climate-data.csv."
)
parser.add_argument("--climate-data", type=Path, default=DEFAULT_CLIMATE_DATA)
parser.add_argument("--counties-geojson", type=Path, default=DEFAULT_COUNTIES_GEOJSON)
parser.add_argument("--monthly-prcp-nc", type=Path, default=DEFAULT_MONTHLY_PRCP_NC)
parser.add_argument("--out", type=Path, default=DEFAULT_CLIMATE_DATA)
parser.add_argument("--climatology-start-year", type=int, default=1991)
parser.add_argument("--climatology-end-year", type=int, default=2020)
return parser.parse_args()
def main() -> None:
"""Run the CSV update."""
args = parse_args()
apply_precipitation_month_metrics(
climate_data=args.climate_data,
counties_geojson=args.counties_geojson,
monthly_prcp_nc=args.monthly_prcp_nc,
out=args.out,
climatology_start_year=args.climatology_start_year,
climatology_end_year=args.climatology_end_year,
)
if __name__ == "__main__":
main()
scripts/build_county_climate_data.py
+861
View File
@@ -0,0 +1,861 @@
#!/usr/bin/env python3
"""
Build county-level climate records for the web app filters.
Outputs a CSV file compatible with the browser app:
climate-data.csv
Metrics produced per county:
- koppenZone: majority Koppen-Geiger class
- avgTempF: annual mean temperature from NOAA 1991-2020 gridded normals
- annualPrecipIn: annual total precipitation from NOAA 1991-2020 gridded normals
- seasonalityIndex: precipitation seasonality, coefficient of variation of monthly totals (%)
- wettestPrecipMonth: month with the highest 1991-2020 county mean precipitation
- driestPrecipMonth: month with the lowest 1991-2020 county mean precipitation
- extremeDays: count of normal-days with Tmax >= hot threshold or Tmin <= freeze threshold
- avgSolarGhiKwhM2Day: annual average daily global horizontal irradiance (GHI), when a solar raster or representative-point CSV is provided
This script is intended for offline generation of complete county records.
"""
from __future__ import annotations
import argparse
import csv
import json
from pathlib import Path
from typing import Dict, List, Tuple
import geopandas as gpd
import numpy as np
import rasterio
from rasterio.features import geometry_mask
import xarray as xr
DEFAULT_COUNTIES_GEOJSON_URL = "https://raw.githubusercontent.com/plotly/datasets/master/geojson-counties-fips.json"
STATE_FIPS_TO_ABBR = {
"01": "AL",
"02": "AK",
"04": "AZ",
"05": "AR",
"06": "CA",
"08": "CO",
"09": "CT",
"10": "DE",
"11": "DC",
"12": "FL",
"13": "GA",
"15": "HI",
"16": "ID",
"17": "IL",
"18": "IN",
"19": "IA",
"20": "KS",
"21": "KY",
"22": "LA",
"23": "ME",
"24": "MD",
"25": "MA",
"26": "MI",
"27": "MN",
"28": "MS",
"29": "MO",
"30": "MT",
"31": "NE",
"32": "NV",
"33": "NH",
"34": "NJ",
"35": "NM",
"36": "NY",
"37": "NC",
"38": "ND",
"39": "OH",
"40": "OK",
"41": "OR",
"42": "PA",
"44": "RI",
"45": "SC",
"46": "SD",
"47": "TN",
"48": "TX",
"49": "UT",
"50": "VT",
"51": "VA",
"53": "WA",
"54": "WV",
"55": "WI",
"56": "WY",
"60": "AS",
"66": "GU",
"69": "MP",
"72": "PR",
"78": "VI",
}
# Beck et al legend key is expected as text file, but this default handles common codes.
DEFAULT_KOPPEN_CODE_MAP = {
1: "Af",
2: "Am",
3: "Aw",
4: "BWh",
5: "BWk",
6: "BSh",
7: "BSk",
8: "Csa",
9: "Csb",
10: "Csc",
11: "Cwa",
12: "Cwb",
13: "Cwc",
14: "Cfa",
15: "Cfb",
16: "Cfc",
17: "Dsa",
18: "Dsb",
19: "Dsc",
20: "Dsd",
21: "Dwa",
22: "Dwb",
23: "Dwc",
24: "Dwd",
25: "Dfa",
26: "Dfb",
27: "Dfc",
28: "Dfd",
29: "ET",
30: "EF",
}
MONTH_NAMES = [
"January",
"February",
"March",
"April",
"May",
"June",
"July",
"August",
"September",
"October",
"November",
"December",
]
def _normalize_fips(value: object, width: int) -> str:
"""Return a zero-padded FIPS code with the requested width."""
text = str(value).strip()
digits = "".join(ch for ch in text if ch.isdigit())
if not digits:
return ""
return digits.zfill(width)[-width:]
def _load_counties(counties_geojson: Path) -> gpd.GeoDataFrame:
"""Load county polygons and normalize fields used downstream."""
if not counties_geojson.exists():
try:
print(
f"County GeoJSON not found at {counties_geojson}. "
f"Attempting download from {DEFAULT_COUNTIES_GEOJSON_URL}..."
)
gdf = gpd.read_file(DEFAULT_COUNTIES_GEOJSON_URL)
counties_geojson.parent.mkdir(parents=True, exist_ok=True)
# Cache the downloaded file for subsequent runs.
gdf.to_file(counties_geojson, driver="GeoJSON")
print(f"Downloaded and cached county GeoJSON to {counties_geojson}")
except Exception as exc:
raise FileNotFoundError(
f"County GeoJSON not found at {counties_geojson}, and download from "
f"{DEFAULT_COUNTIES_GEOJSON_URL} failed. Download the file manually "
"and rerun with --counties-geojson pointing to it."
) from exc
gdf = gpd.read_file(counties_geojson)
if gdf.crs is None:
gdf = gdf.set_crs("EPSG:4326")
else:
gdf = gdf.to_crs("EPSG:4326")
feature_id = None
if "id" in gdf.columns:
feature_id = gdf["id"]
elif "GEOID" in gdf.columns:
feature_id = gdf["GEOID"]
elif "GEOID10" in gdf.columns:
feature_id = gdf["GEOID10"]
elif "fips" in gdf.columns:
feature_id = gdf["fips"]
else:
raise ValueError("Unable to locate county FIPS identifier column in county polygons.")
gdf["county_fips"] = feature_id.map(lambda value: _normalize_fips(value, 5))
gdf = gdf[gdf["county_fips"] != ""].copy()
if "NAME" in gdf.columns:
gdf["county_name"] = gdf["NAME"].fillna("").astype(str).str.strip()
elif "name" in gdf.columns:
gdf["county_name"] = gdf["name"].fillna("").astype(str).str.strip()
else:
gdf["county_name"] = gdf["county_fips"].map(lambda value: f"County {value}")
gdf["state_fips"] = gdf["county_fips"].str.slice(0, 2)
gdf["state"] = gdf["state_fips"].map(lambda code: STATE_FIPS_TO_ABBR.get(code, f"S{code}"))
gdf = gdf.sort_values("county_fips").reset_index(drop=True)
return gdf
def _load_koppen_legend(legend_path: Path | None) -> Dict[int, str]:
"""Load Koppen raster codes, using defaults when no legend exists."""
if legend_path is None:
return DEFAULT_KOPPEN_CODE_MAP
mapping: Dict[int, str] = {}
for line in legend_path.read_text(encoding="utf-8").splitlines():
text = line.strip()
if not text or text.startswith("#"):
continue
# Handles patterns like:
# "1: Af ..." or "1 = Af" or "1 Af"
import re
match = re.match(r"^(\d+)\s*[:=]?\s*([A-Za-z]{2,3})\b", text)
if not match:
continue
key = int(match.group(1))
value = match.group(2)
mapping[key] = value
return mapping if mapping else DEFAULT_KOPPEN_CODE_MAP
def _select_data_var(dataset: xr.Dataset, preferred: str) -> str:
"""Choose the best matching climate variable from a dataset."""
if preferred in dataset.data_vars:
return preferred
alias_map = {
"mlytavg_norm": ["tavg", "tavg_norm"],
"mlyprcp_norm": ["prcp", "prcp_norm"],
"dlytmax_norm": ["tmax", "tmax_norm"],
"dlytmin_norm": ["tmin", "tmin_norm"],
}
for alias in alias_map.get(preferred, []):
if alias in dataset.data_vars:
return alias
for candidate in dataset.data_vars:
if candidate.endswith("_norm"):
return candidate
# If the dataset only has one variable, use it as a final fallback.
if len(dataset.data_vars) == 1:
return next(iter(dataset.data_vars))
raise ValueError(
f"Unable to select a climate variable. Preferred='{preferred}', available={list(dataset.data_vars)}"
)
def _load_solar_ghi_csv(solar_ghi_csv: Path, counties: gpd.GeoDataFrame) -> List[float]:
"""Load county-keyed average daily GHI values from a representative-point or area-average CSV."""
with solar_ghi_csv.open(newline="", encoding="utf-8") as handle:
reader = csv.DictReader(handle)
if reader.fieldnames is None:
raise ValueError(f"Solar GHI CSV at {solar_ghi_csv} has no header row.")
if "county_fips" in reader.fieldnames:
fips_field = "county_fips"
elif "countyFips" in reader.fieldnames:
fips_field = "countyFips"
else:
raise ValueError(
f"Solar GHI CSV at {solar_ghi_csv} must include county_fips or countyFips."
)
if "avgSolarGhiKwhM2Day" not in reader.fieldnames:
raise ValueError(
f"Solar GHI CSV at {solar_ghi_csv} must include avgSolarGhiKwhM2Day."
)
solar_by_fips: Dict[str, float] = {}
for row in reader:
county_fips = _normalize_fips(row.get(fips_field, ""), 5)
raw_value = str(row.get("avgSolarGhiKwhM2Day", "")).strip()
if not county_fips or not raw_value:
continue
try:
solar_by_fips[county_fips] = float(raw_value)
except ValueError as exc:
raise ValueError(
f"Invalid avgSolarGhiKwhM2Day value for county {county_fips}: {raw_value}"
) from exc
return [
solar_by_fips.get(str(row["county_fips"]), float("nan"))
for _, row in counties.iterrows()
]
def _as_monthly_climatology(data_array: xr.DataArray, start_year: int, end_year: int) -> xr.DataArray:
"""Return 12 monthly normals from slices or a time series."""
if "time" not in data_array.dims:
raise ValueError(f"Expected a time dimension, got dims={data_array.dims}")
time_size = int(data_array.sizes.get("time", 0))
if time_size == 12:
return data_array
time_index = data_array["time"]
if not hasattr(time_index, "dt"):
# Attempt CF decoding when time is numeric with units/calendar attrs.
try:
decoded = xr.decode_cf(xr.Dataset({"_v": data_array}))
data_array = decoded["_v"]
time_index = data_array["time"]
except Exception as exc:
raise ValueError(
"Time coordinate does not support datetime access for monthly climatology grouping, "
"and CF decoding failed."
) from exc
if not hasattr(time_index, "dt"):
raise ValueError("Time coordinate does not support datetime access for monthly climatology grouping.")
period = data_array.where(
(time_index.dt.year >= start_year) & (time_index.dt.year <= end_year),
drop=True,
)
if int(period.sizes.get("time", 0)) == 0:
raise ValueError(f"No monthly data found between {start_year} and {end_year}.")
monthly = period.groupby("time.month").mean("time", skipna=True)
if int(monthly.sizes.get("month", 0)) != 12:
raise ValueError(
f"Monthly climatology for {start_year}-{end_year} has {monthly.sizes.get('month', 0)} months; expected 12."
)
# Standardize to a `time` dimension so downstream code can reuse .isel(time=month_idx).
monthly = monthly.rename({"month": "time"})
monthly = monthly.assign_coords(time=np.arange(1, 13))
return monthly
def _infer_time_resolution_days(data_array: xr.DataArray) -> float:
"""Estimate the median spacing between time steps in days."""
time_values = np.asarray(data_array["time"].values)
if time_values.size < 2:
return float("inf")
deltas = np.diff(time_values).astype("timedelta64[D]").astype(np.int64)
deltas = deltas[deltas > 0]
if deltas.size == 0:
return float("inf")
return float(np.median(deltas))
def _extract_grid_2d(data_array: xr.DataArray) -> Tuple[np.ndarray, "Affine"]:
"""Convert a lat/lon slice to a raster array and transform."""
# Expected shape for 2D arrays: lat, lon
# Build affine from center coordinates.
lon = np.asarray(data_array["lon"].values, dtype=np.float64)
lat = np.asarray(data_array["lat"].values, dtype=np.float64)
arr = np.asarray(data_array.values, dtype=np.float64)
if arr.shape != (lat.size, lon.size):
raise ValueError(f"Unexpected grid shape {arr.shape}; expected {(lat.size, lon.size)}")
# Make sure the first row is northernmost to match affine from top-left.
if lat[0] < lat[-1]:
lat = lat[::-1]
arr = arr[::-1, :]
x_res = abs(lon[1] - lon[0])
y_res = abs(lat[0] - lat[1])
from affine import Affine
top_left_x = lon.min() - (x_res / 2.0)
top_left_y = lat.max() + (y_res / 2.0)
transform = Affine.translation(top_left_x, top_left_y) * Affine.scale(x_res, -y_res)
return arr, transform
def _zonal_mean(arr: np.ndarray, transform, counties: gpd.GeoDataFrame) -> List[float]:
"""Calculate the mean raster value inside each county polygon."""
values = np.asarray(arr, dtype=np.float64)
means: List[float] = []
for geometry in counties.geometry:
mask = geometry_mask(
[geometry.__geo_interface__],
out_shape=values.shape,
transform=transform,
invert=True,
all_touched=True,
)
selected = values[mask]
selected = selected[np.isfinite(selected)]
means.append(float(selected.mean()) if selected.size else float("nan"))
return means
def _zonal_mean_raster(raster_path: Path, counties: gpd.GeoDataFrame) -> List[float]:
"""Calculate the mean raster-file value for each county."""
with rasterio.open(raster_path) as source:
raster_counties = counties
if source.crs is not None and counties.crs is not None and counties.crs != source.crs:
raster_counties = counties.to_crs(source.crs)
data = source.read(1, masked=True)
values = np.asarray(data.filled(np.nan), dtype=np.float64)
if source.nodata is not None:
values = np.where(values == source.nodata, np.nan, values)
return _zonal_mean(values, source.transform, raster_counties)
def _zonal_majority_class(koppen_raster: Path, counties: gpd.GeoDataFrame, code_map: Dict[int, str]) -> List[str]:
"""Assign each county its most common Koppen-Geiger class."""
classes: List[str] = []
with rasterio.open(koppen_raster) as source:
raster_counties = counties
if source.crs is not None and counties.crs is not None and counties.crs != source.crs:
raster_counties = counties.to_crs(source.crs)
data = source.read(1, masked=True)
values = np.asarray(data.filled(0))
if source.nodata is not None:
values = np.where(values == source.nodata, 0, values)
for geometry in raster_counties.geometry:
mask = geometry_mask(
[geometry.__geo_interface__],
out_shape=values.shape,
transform=source.transform,
invert=True,
all_touched=True,
)
selected = values[mask]
selected = selected[selected != 0]
if selected.size == 0:
classes.append("Cfa")
continue
codes, counts = np.unique(selected.astype(np.int64), return_counts=True)
code_int = int(codes[int(np.argmax(counts))])
classes.append(code_map.get(code_int, "Cfa"))
return classes
def _compute_extreme_days(
tmax_daily: xr.Dataset,
tmin_daily: xr.Dataset,
counties: gpd.GeoDataFrame,
hot_threshold_c: float,
freeze_threshold_c: float,
) -> List[float]:
"""Count daily hot or freezing days for each county."""
tmax_var = _select_data_var(tmax_daily, "dlytmax_norm")
tmin_var = _select_data_var(tmin_daily, "dlytmin_norm")
tmax = tmax_daily[tmax_var]
tmin = tmin_daily[tmin_var]
# If datasets differ slightly in day count, use the overlapping day count.
day_count = int(min(tmax.sizes["time"], tmin.sizes["time"]))
totals = np.zeros(len(counties), dtype=np.float64)
for day in range(day_count):
tmax_arr, tmax_transform = _extract_grid_2d(tmax.isel(time=day))
tmin_arr, tmin_transform = _extract_grid_2d(tmin.isel(time=day))
if tmax_transform != tmin_transform:
raise ValueError("Daily tmax/tmin grids do not share the same transform.")
day_tmax = _zonal_mean(tmax_arr, tmax_transform, counties)
day_tmin = _zonal_mean(tmin_arr, tmin_transform, counties)
for idx, (mx, mn) in enumerate(zip(day_tmax, day_tmin)):
if np.isnan(mx) or np.isnan(mn):
continue
if mx >= hot_threshold_c or mn <= freeze_threshold_c:
totals[idx] += 1.0
return totals.tolist()
def _compute_extreme_days_monthly_proxy(
tmax_monthly: xr.DataArray,
tmin_monthly: xr.DataArray,
counties: gpd.GeoDataFrame,
hot_threshold_c: float,
freeze_threshold_c: float,
) -> List[float]:
"""Estimate extreme days from monthly tmax and tmin means."""
if int(tmax_monthly.sizes.get("time", 0)) != 12 or int(tmin_monthly.sizes.get("time", 0)) != 12:
raise ValueError("Monthly proxy for extremeDays requires 12 monthly slices for tmax and tmin.")
month_days = np.array([31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31], dtype=np.float64)
totals = np.zeros(len(counties), dtype=np.float64)
for month in range(12):
tmax_arr, tmax_transform = _extract_grid_2d(tmax_monthly.isel(time=month))
tmin_arr, tmin_transform = _extract_grid_2d(tmin_monthly.isel(time=month))
if tmax_transform != tmin_transform:
raise ValueError("Monthly proxy tmax/tmin grids do not share the same transform.")
month_tmax = _zonal_mean(tmax_arr, tmax_transform, counties)
month_tmin = _zonal_mean(tmin_arr, tmin_transform, counties)
for idx, (mx, mn) in enumerate(zip(month_tmax, month_tmin)):
if np.isnan(mx) or np.isnan(mn):
continue
if mx >= hot_threshold_c or mn <= freeze_threshold_c:
totals[idx] += month_days[month]
return totals.tolist()
def _precip_month_extremes(prcp_months_mm: np.ndarray) -> tuple[str | None, str | None]:
"""Return wettest and driest month names from 12 monthly precipitation totals."""
valid_mask = np.isfinite(prcp_months_mm)
if not np.any(valid_mask):
return None, None
comparable = np.where(valid_mask, prcp_months_mm, np.nan)
wettest_month = MONTH_NAMES[int(np.nanargmax(comparable))]
driest_month = MONTH_NAMES[int(np.nanargmin(comparable))]
return wettest_month, driest_month
def build_county_records(
counties_geojson: Path,
koppen_raster: Path,
koppen_legend: Path | None,
monthly_tavg_nc: Path,
monthly_prcp_nc: Path,
daily_tmax_nc: Path,
daily_tmin_nc: Path,
hot_threshold_f: float,
freeze_threshold_f: float,
climatology_start_year: int,
climatology_end_year: int,
extreme_days_mode: str,
solar_ghi_raster: Path | None,
solar_ghi_csv: Path | None,
) -> Dict[str, dict]:
"""Build county climate records consumed by the web app."""
counties = _load_counties(counties_geojson)
koppen_classes = _zonal_majority_class(koppen_raster, counties, _load_koppen_legend(koppen_legend))
monthly_tavg = xr.open_dataset(monthly_tavg_nc, decode_times=True)
monthly_prcp = xr.open_dataset(monthly_prcp_nc, decode_times=True)
daily_tmax = xr.open_dataset(daily_tmax_nc, decode_times=True)
daily_tmin = xr.open_dataset(daily_tmin_nc, decode_times=True)
tavg_var = _select_data_var(monthly_tavg, "mlytavg_norm")
prcp_var = _select_data_var(monthly_prcp, "mlyprcp_norm")
tavg_monthly = _as_monthly_climatology(
monthly_tavg[tavg_var],
start_year=climatology_start_year,
end_year=climatology_end_year,
)
prcp_monthly = _as_monthly_climatology(
monthly_prcp[prcp_var],
start_year=climatology_start_year,
end_year=climatology_end_year,
)
tavg_by_month: List[List[float]] = []
prcp_by_month_mm: List[List[float]] = []
for month in range(12):
tavg_arr, tavg_transform = _extract_grid_2d(tavg_monthly.isel(time=month))
prcp_arr, prcp_transform = _extract_grid_2d(prcp_monthly.isel(time=month))
if tavg_transform != prcp_transform:
raise ValueError("Monthly tavg/prcp grids do not share the same transform.")
tavg_by_month.append(_zonal_mean(tavg_arr, tavg_transform, counties))
prcp_by_month_mm.append(_zonal_mean(prcp_arr, prcp_transform, counties))
hot_threshold_c = (hot_threshold_f - 32.0) * (5.0 / 9.0)
freeze_threshold_c = (freeze_threshold_f - 32.0) * (5.0 / 9.0)
tmax_var = _select_data_var(daily_tmax, "dlytmax_norm")
tmin_var = _select_data_var(daily_tmin, "dlytmin_norm")
tmax_da = daily_tmax[tmax_var]
tmin_da = daily_tmin[tmin_var]
resolution_days = min(_infer_time_resolution_days(tmax_da), _infer_time_resolution_days(tmin_da))
# Daily-like input (true daily normals or daily grids).
if resolution_days <= 2.0:
extreme_days = _compute_extreme_days(
daily_tmax=daily_tmax,
daily_tmin=daily_tmin,
counties=counties,
hot_threshold_c=hot_threshold_c,
freeze_threshold_c=freeze_threshold_c,
)
extreme_days_source_tag = "daily"
else:
if extreme_days_mode == "require-daily":
raise ValueError(
"Extreme-days inputs appear to be monthly series, but --extreme-days-mode=require-daily was set."
)
tmax_monthly = _as_monthly_climatology(
tmax_da,
start_year=climatology_start_year,
end_year=climatology_end_year,
)
tmin_monthly = _as_monthly_climatology(
tmin_da,
start_year=climatology_start_year,
end_year=climatology_end_year,
)
extreme_days = _compute_extreme_days_monthly_proxy(
tmax_monthly=tmax_monthly,
tmin_monthly=tmin_monthly,
counties=counties,
hot_threshold_c=hot_threshold_c,
freeze_threshold_c=freeze_threshold_c,
)
extreme_days_source_tag = "monthly-proxy"
if solar_ghi_raster is not None and solar_ghi_raster.exists():
solar_ghi_kwh_m2_day = _zonal_mean_raster(solar_ghi_raster, counties)
solar_source_tag = "solar-ghi-raster"
elif solar_ghi_csv is not None and solar_ghi_csv.exists():
solar_ghi_kwh_m2_day = _load_solar_ghi_csv(solar_ghi_csv, counties)
solar_source_tag = "solar-ghi-representative-point"
else:
if solar_ghi_raster is not None:
print(f"Solar GHI raster not found at {solar_ghi_raster}; leaving avgSolarGhiKwhM2Day blank.")
if solar_ghi_csv is not None:
print(f"Solar GHI CSV not found at {solar_ghi_csv}; leaving avgSolarGhiKwhM2Day blank.")
solar_ghi_kwh_m2_day = [float("nan")] * len(counties)
solar_source_tag = "no-solar-ghi-source"
records: Dict[str, dict] = {}
missing_numeric_count = 0
for idx, row in counties.iterrows():
county_fips = row["county_fips"]
county_name = row["county_name"]
state = row["state"]
koppen_zone = koppen_classes[idx]
temp_months_c = np.array([tavg_by_month[m][idx] for m in range(12)], dtype=np.float64)
prcp_months_mm = np.array([prcp_by_month_mm[m][idx] for m in range(12)], dtype=np.float64)
# Guard against nodata counties (outside CONUS grids, islands, etc.).
valid_temp = temp_months_c[np.isfinite(temp_months_c)]
valid_prcp = prcp_months_mm[np.isfinite(prcp_months_mm)]
avg_temp_c = np.nanmean(valid_temp) if valid_temp.size else np.nan
annual_prcp_mm = np.nansum(valid_prcp) if valid_prcp.size else np.nan
# Precipitation seasonality as coefficient of variation, capped 0-100.
if valid_prcp.size:
mean_prcp = float(np.nanmean(valid_prcp))
std_prcp = float(np.nanstd(valid_prcp))
seasonality = 0.0 if mean_prcp <= 0 else max(0.0, min(100.0, (std_prcp / mean_prcp) * 100.0))
else:
seasonality = np.nan
wettest_precip_month, driest_precip_month = _precip_month_extremes(prcp_months_mm)
use_missing_temp = not np.isfinite(avg_temp_c)
use_missing_prcp = not np.isfinite(annual_prcp_mm)
use_missing_seasonality = not np.isfinite(seasonality)
use_missing_base_noaa = use_missing_temp or use_missing_prcp or use_missing_seasonality
use_missing_extreme = use_missing_base_noaa or not np.isfinite(extreme_days[idx])
used_any_missing_numeric = (
use_missing_temp or use_missing_prcp or use_missing_seasonality or use_missing_extreme
)
if used_any_missing_numeric:
missing_numeric_count += 1
avg_temp_f = (
round((float(avg_temp_c) * 9.0 / 5.0) + 32.0, 1)
if not use_missing_temp
else None
)
annual_prcp_in = (
round(float(annual_prcp_mm) / 25.4, 1)
if not use_missing_prcp
else None
)
seasonality_idx = (
int(round(float(seasonality)))
if not use_missing_seasonality
else None
)
extreme_days_value = (
int(round(float(extreme_days[idx])))
if not use_missing_extreme
else None
)
avg_solar_ghi_value = (
round(float(solar_ghi_kwh_m2_day[idx]), 2)
if np.isfinite(solar_ghi_kwh_m2_day[idx])
else None
)
source_suffix = " + missing-noaa-numeric" if used_any_missing_numeric else ""
solar_source_suffix = "" if avg_solar_ghi_value is not None else " + missing-solar-ghi"
record = {
"countyName": county_name,
"state": state,
"koppenZone": koppen_zone,
"avgTempF": avg_temp_f,
"annualPrecipIn": annual_prcp_in,
"seasonalityIndex": seasonality_idx,
"wettestPrecipMonth": wettest_precip_month,
"driestPrecipMonth": driest_precip_month,
"extremeDays": extreme_days_value,
"avgSolarGhiKwhM2Day": avg_solar_ghi_value,
"source": (
"kg-beck2023 + noaa-nclimgrid-1991-2020 "
f"({extreme_days_source_tag}) + {solar_source_tag}{source_suffix}{solar_source_suffix}"
)
}
records[county_fips] = record
monthly_tavg.close()
monthly_prcp.close()
daily_tmax.close()
daily_tmin.close()
if missing_numeric_count:
print(
f"Marked missing numeric NOAA values for {missing_numeric_count} counties "
"(likely outside NOAA grid coverage)."
)
return records
def write_csv(records: Dict[str, dict], out_file: Path) -> None:
"""Write county records to the browser-loaded CSV payload."""
fields = [
"countyFips",
"countyName",
"state",
"koppenZone",
"avgTempF",
"annualPrecipIn",
"seasonalityIndex",
"wettestPrecipMonth",
"driestPrecipMonth",
"extremeDays",
"avgSolarGhiKwhM2Day",
"source",
]
with out_file.open("w", encoding="utf-8", newline="") as csv_file:
writer = csv.DictWriter(csv_file, fieldnames=fields, extrasaction="ignore")
writer.writeheader()
for county_fips in sorted(records):
row = {"countyFips": county_fips}
row.update(records[county_fips])
writer.writerow(row)
def parse_args() -> argparse.Namespace:
"""Define and parse command-line options for this generator."""
parser = argparse.ArgumentParser(description="Generate county climate records for the web app.")
parser.add_argument("--counties-geojson", type=Path, required=True, help="County polygon GeoJSON path.")
parser.add_argument("--koppen-raster", type=Path, required=True, help="Koppen-Geiger raster TIFF path.")
parser.add_argument("--koppen-legend", type=Path, default=None, help="Optional legend.txt mapping integer codes.")
parser.add_argument(
"--monthly-tavg-nc",
type=Path,
required=True,
help="NOAA monthly tavg netCDF (12-slice normals or monthly time-series).",
)
parser.add_argument(
"--monthly-prcp-nc",
type=Path,
required=True,
help="NOAA monthly prcp netCDF (12-slice normals or monthly time-series).",
)
parser.add_argument(
"--daily-tmax-nc",
type=Path,
required=True,
help="NOAA tmax netCDF (daily normals/grids preferred; monthly time-series allowed in proxy mode).",
)
parser.add_argument(
"--daily-tmin-nc",
type=Path,
required=True,
help="NOAA tmin netCDF (daily normals/grids preferred; monthly time-series allowed in proxy mode).",
)
parser.add_argument("--hot-threshold-f", type=float, default=95.0, help="Hot day threshold in Fahrenheit.")
parser.add_argument("--freeze-threshold-f", type=float, default=32.0, help="Freeze day threshold in Fahrenheit.")
parser.add_argument(
"--climatology-start-year",
type=int,
default=1991,
help="Start year (inclusive) for monthly climatology calculation when time series files are provided.",
)
parser.add_argument(
"--climatology-end-year",
type=int,
default=2020,
help="End year (inclusive) for monthly climatology calculation when time series files are provided.",
)
parser.add_argument(
"--extreme-days-mode",
choices=["auto", "require-daily"],
default="auto",
help="`auto` allows monthly-proxy extremeDays if daily grids are not provided; `require-daily` enforces daily input.",
)
parser.add_argument(
"--solar-ghi-raster",
type=Path,
default=None,
help="Optional raster of annual average daily GHI in kWh/m2/day for avgSolarGhiKwhM2Day.",
)
parser.add_argument(
"--solar-ghi-csv",
type=Path,
default=None,
help=(
"Optional county CSV with avgSolarGhiKwhM2Day. Used as a representative-point fallback "
"when --solar-ghi-raster is not supplied."
),
)
parser.add_argument("--out", type=Path, default=Path("data/climate-data.csv"), help="Output CSV file path.")
return parser.parse_args()
def main() -> None:
"""Run the ETL flow and write the final CSV file."""
args = parse_args()
records = build_county_records(
counties_geojson=args.counties_geojson,
koppen_raster=args.koppen_raster,
koppen_legend=args.koppen_legend,
monthly_tavg_nc=args.monthly_tavg_nc,
monthly_prcp_nc=args.monthly_prcp_nc,
daily_tmax_nc=args.daily_tmax_nc,
daily_tmin_nc=args.daily_tmin_nc,
hot_threshold_f=args.hot_threshold_f,
freeze_threshold_f=args.freeze_threshold_f,
climatology_start_year=args.climatology_start_year,
climatology_end_year=args.climatology_end_year,
extreme_days_mode=args.extreme_days_mode,
solar_ghi_raster=args.solar_ghi_raster,
solar_ghi_csv=args.solar_ghi_csv,
)
write_csv(records=records, out_file=args.out)
print(f"Wrote {len(records)} county records to {args.out}")
if __name__ == "__main__":
main()
scripts/build_county_diurnal_temperature_range.py
+191
View File
@@ -0,0 +1,191 @@
#!/usr/bin/env python3
"""
Build county-level average diurnal temperature range from NOAA nClimGrid-Daily.
The output is an ETL artifact used to keep climate-data.csv lean:
data/noaa/county_diurnal_temperature_range.csv
Metric definition:
- avgDiurnalTempRangeF: mean daily county Tmax - Tmin, expressed as a
Fahrenheit temperature difference, over the selected analysis period.
"""
from __future__ import annotations
import argparse
import csv
from dataclasses import dataclass
from pathlib import Path
from build_county_locally_extreme_data import (
DEFAULT_STATE_CROSSWALK,
DEFAULT_TMAX_DIR,
DEFAULT_TMIN_DIR,
load_state_crosswalk,
require_monthly_file,
rows_by_fips,
)
REPO_ROOT = Path(__file__).resolve().parents[1]
DEFAULT_OUT = REPO_ROOT / "data" / "noaa" / "county_diurnal_temperature_range.csv"
SOURCE_TAG = "noaa-nclimgrid-daily-county-area-averages-scaled"
@dataclass
class DiurnalRangeTotals:
"""Running total for one county's daily Tmax-Tmin differences."""
noaa_region_code: str = ""
county_name: str = ""
total_range_c: float = 0.0
valid_days: int = 0
skipped_negative_days: int = 0
def c_delta_to_f_delta(value_c: float) -> float:
"""Convert a Celsius temperature difference to a Fahrenheit difference."""
return value_c * 9.0 / 5.0
def build_diurnal_temperature_range(
*,
start_year: int,
end_year: int,
tmax_dir: Path,
tmin_dir: Path,
state_crosswalk_path: Path,
) -> dict[str, DiurnalRangeTotals]:
"""Average daily county Tmax-Tmin over the requested analysis years."""
state_crosswalk = load_state_crosswalk(state_crosswalk_path)
totals: dict[str, DiurnalRangeTotals] = {}
for year in range(start_year, end_year + 1):
print(f"Reading daily Tmax/Tmin for {year}...")
for month in range(1, 13):
tmax_path = require_monthly_file(tmax_dir, "tmax", year, month)
tmin_path = require_monthly_file(tmin_dir, "tmin", year, month)
tmax_rows = rows_by_fips(
tmax_path,
year=year,
month=month,
state_crosswalk=state_crosswalk,
)
tmin_rows = rows_by_fips(
tmin_path,
year=year,
month=month,
state_crosswalk=state_crosswalk,
)
for county_fips in sorted(set(tmax_rows) & set(tmin_rows)):
tmax_record = tmax_rows[county_fips]
tmin_record = tmin_rows[county_fips]
county_totals = totals.setdefault(
county_fips,
DiurnalRangeTotals(
noaa_region_code=tmax_record.region_code,
county_name=tmax_record.county_name,
),
)
for tmax_value, tmin_value in zip(tmax_record.values, tmin_record.values):
if tmax_value is None or tmin_value is None:
continue
daily_range_c = tmax_value - tmin_value
if daily_range_c < 0:
county_totals.skipped_negative_days += 1
continue
county_totals.total_range_c += daily_range_c
county_totals.valid_days += 1
return totals
def write_diurnal_temperature_range_csv(
*,
path: Path,
totals: dict[str, DiurnalRangeTotals],
start_year: int,
end_year: int,
) -> None:
"""Write county DTR summary rows."""
path.parent.mkdir(parents=True, exist_ok=True)
fieldnames = [
"countyFips",
"noaaRegionCode",
"countyName",
"avgDiurnalTempRangeC",
"avgDiurnalTempRangeF",
"validDays",
"skippedNegativeDays",
"analysisStartYear",
"analysisEndYear",
"source",
]
with path.open("w", encoding="utf-8", newline="") as csv_file:
writer = csv.DictWriter(csv_file, fieldnames=fieldnames)
writer.writeheader()
for county_fips in sorted(totals):
county_totals = totals[county_fips]
avg_range_c = (
county_totals.total_range_c / county_totals.valid_days
if county_totals.valid_days
else None
)
writer.writerow(
{
"countyFips": county_fips,
"noaaRegionCode": county_totals.noaa_region_code,
"countyName": county_totals.county_name,
"avgDiurnalTempRangeC": f"{avg_range_c:.2f}" if avg_range_c is not None else "",
"avgDiurnalTempRangeF": (
f"{c_delta_to_f_delta(avg_range_c):.2f}" if avg_range_c is not None else ""
),
"validDays": county_totals.valid_days,
"skippedNegativeDays": county_totals.skipped_negative_days,
"analysisStartYear": start_year,
"analysisEndYear": end_year,
"source": SOURCE_TAG,
}
)
print(f"Wrote {len(totals)} county DTR rows to {path}")
def parse_args() -> argparse.Namespace:
"""Parse command-line arguments."""
parser = argparse.ArgumentParser(
description="Build county average diurnal temperature range from cached NOAA Tmax/Tmin files."
)
parser.add_argument("--start-year", type=int, default=1991)
parser.add_argument("--end-year", type=int, default=2020)
parser.add_argument("--tmax-dir", type=Path, default=DEFAULT_TMAX_DIR)
parser.add_argument("--tmin-dir", type=Path, default=DEFAULT_TMIN_DIR)
parser.add_argument("--state-crosswalk", type=Path, default=DEFAULT_STATE_CROSSWALK)
parser.add_argument("--out", type=Path, default=DEFAULT_OUT)
return parser.parse_args()
def main() -> None:
"""Run the DTR ETL."""
args = parse_args()
totals = build_diurnal_temperature_range(
start_year=args.start_year,
end_year=args.end_year,
tmax_dir=args.tmax_dir,
tmin_dir=args.tmin_dir,
state_crosswalk_path=args.state_crosswalk,
)
write_diurnal_temperature_range_csv(
path=args.out,
totals=totals,
start_year=args.start_year,
end_year=args.end_year,
)
if __name__ == "__main__":
main()
scripts/build_county_locally_extreme_data.py
+1002
View File
File diff suppressed because it is too large Load Diff
scripts/build_county_representative_points.py
+150
View File
@@ -0,0 +1,150 @@
#!/usr/bin/env python3
"""
Build representative county points for NSRDB point-based solar sampling.
The output CSV is intended as input to fetch_nsrdb_representative_point_ghi.py.
"""
from __future__ import annotations
import argparse
import csv
from pathlib import Path
import geopandas as gpd
DEFAULT_COUNTIES_GEOJSON = Path("data/geojson-counties-fips.json")
DEFAULT_OUTPUT_CSV = Path("data/nrel/county_representative_points.csv")
STATE_FIPS_TO_ABBR = {
"01": "AL",
"02": "AK",
"04": "AZ",
"05": "AR",
"06": "CA",
"08": "CO",
"09": "CT",
"10": "DE",
"11": "DC",
"12": "FL",
"13": "GA",
"15": "HI",
"16": "ID",
"17": "IL",
"18": "IN",
"19": "IA",
"20": "KS",
"21": "KY",
"22": "LA",
"23": "ME",
"24": "MD",
"25": "MA",
"26": "MI",
"27": "MN",
"28": "MS",
"29": "MO",
"30": "MT",
"31": "NE",
"32": "NV",
"33": "NH",
"34": "NJ",
"35": "NM",
"36": "NY",
"37": "NC",
"38": "ND",
"39": "OH",
"40": "OK",
"41": "OR",
"42": "PA",
"44": "RI",
"45": "SC",
"46": "SD",
"47": "TN",
"48": "TX",
"49": "UT",
"50": "VT",
"51": "VA",
"53": "WA",
"54": "WV",
"55": "WI",
"56": "WY",
"60": "AS",
"66": "GU",
"69": "MP",
"72": "PR",
"78": "VI",
}
def normalize_fips(value: object, width: int) -> str:
"""Return a zero-padded FIPS string from a mixed text or numeric value."""
digits = "".join(character for character in str(value).strip() if character.isdigit())
return digits.zfill(width)[-width:] if digits else ""
def build_county_points(input_geojson: Path, include_puerto_rico: bool) -> list[dict[str, str]]:
"""Load county polygons and return one interior representative point per county."""
counties = gpd.read_file(input_geojson)
rows: list[dict[str, str]] = []
for _, county in counties.iterrows():
state_fips = normalize_fips(county.get("STATE"), 2)
county_code = normalize_fips(county.get("COUNTY"), 3)
county_fips = normalize_fips(county.get("id") or f"{state_fips}{county_code}", 5)
if not county_fips or (state_fips == "72" and not include_puerto_rico):
continue
point = county.geometry.representative_point()
county_name = str(county.get("NAME") or f"County {county_fips}").strip()
rows.append(
{
"county_fips": county_fips,
"county_name": county_name,
"state_fips": state_fips,
"state_abbr": STATE_FIPS_TO_ABBR.get(state_fips, state_fips),
"lat": f"{point.y:.6f}",
"lon": f"{point.x:.6f}",
}
)
return sorted(rows, key=lambda row: row["county_fips"])
def write_points_csv(rows: list[dict[str, str]], output_csv: Path) -> None:
"""Write county representative points to CSV."""
output_csv.parent.mkdir(parents=True, exist_ok=True)
with output_csv.open("w", newline="", encoding="utf-8") as handle:
writer = csv.DictWriter(
handle,
fieldnames=["county_fips", "county_name", "state_fips", "state_abbr", "lat", "lon"],
)
writer.writeheader()
writer.writerows(rows)
def parse_args() -> argparse.Namespace:
"""Parse command-line arguments."""
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("--input-geojson", type=Path, default=DEFAULT_COUNTIES_GEOJSON)
parser.add_argument("--output-csv", type=Path, default=DEFAULT_OUTPUT_CSV)
parser.add_argument(
"--include-puerto-rico",
action="store_true",
help="Include Puerto Rico counties. The current web app excludes Puerto Rico polygons.",
)
return parser.parse_args()
def main() -> None:
"""Build and write the county representative-point CSV."""
args = parse_args()
rows = build_county_points(args.input_geojson, args.include_puerto_rico)
write_points_csv(rows, args.output_csv)
print(f"Wrote {len(rows)} county representative points to {args.output_csv}")
if __name__ == "__main__":
main()
scripts/county_data_sources.md
+363
View File
@@ -0,0 +1,363 @@
# County Climate Data Sources and Mapping
This project now supports county polygons and county-level filter records keyed by 5-digit county FIPS.
## Launching the app
The browser blocks `fetch("data/climate-data.csv")` when `index.html` is opened directly as a `file://` URL, so run the site through a local HTTP server:
```powershell
.\serve.ps1
```
Then open [http://localhost:8000/](http://localhost:8000/). This keeps the app CSV-only while allowing the map and filters to load normally.
## Source 1: Koppen-Geiger classes (`koppenZone`)
- Dataset: Beck et al. updated 1-km Koppen-Geiger climate classes (historical + future windows)
- Landing page: [https://www.gloh2o.org/koppen/](https://www.gloh2o.org/koppen/)
- Primary paper for updated release: [https://www.nature.com/articles/s41597-023-02549-6](https://www.nature.com/articles/s41597-023-02549-6)
- Coverage: 1901-2099 (use historical 1991-2020 layer for this project to align with NOAA baselines)
- License shown on dataset page: CC BY 4.0
## Source 2: NOAA 1991-2020 gridded normals (`avgTempF`, `annualPrecipIn`, `seasonalityIndex`, previous `extremeDays`)
- Main product page: [https://www.ncei.noaa.gov/products/land-based-station/us-climate-normals](https://www.ncei.noaa.gov/products/land-based-station/us-climate-normals)
- Monthly gridded normals readme: [https://www.ncei.noaa.gov/sites/default/files/2022-04/Readme_Monthly_Gridded_Normals.pdf](https://www.ncei.noaa.gov/sites/default/files/2022-04/Readme_Monthly_Gridded_Normals.pdf)
- Daily gridded normals readme: [https://www.ncei.noaa.gov/sites/default/files/2022-09/Readme%20for%20Daily%20Gridded%20Normals%201991-2020.pdf](https://www.ncei.noaa.gov/sites/default/files/2022-09/Readme%20for%20Daily%20Gridded%20Normals%201991-2020.pdf)
- Daily gridded normals documentation (includes units in C/mm): [https://www.ncei.noaa.gov/sites/default/files/2022-09/Documentation_Daily_Gridded_Normals%20V1.0.pdf](https://www.ncei.noaa.gov/sites/default/files/2022-09/Documentation_Daily_Gridded_Normals%20V1.0.pdf)
The ETL script uses:
- Monthly `tavg` normals (C)
- Monthly `prcp` normals (mm)
- Daily `tmax` normals (C)
- Daily `tmin` normals (C)
If you have monthly nClimGrid history files (for example `nclimgrid_tavg.nc`) rather than 12-slice normals files:
- The script now computes a 1991-2020 monthly climatology from the time series automatically.
- `extremeDays` can run in `auto` mode, which uses a documented monthly proxy when daily grids are not provided.
## Source 3: County polygons / FIPS join geometry
- Current app geometry file: `data/geojson-counties-fips.json`
- Original Plotly county geometry source: [https://raw.githubusercontent.com/plotly/datasets/master/geojson-counties-fips.json](https://raw.githubusercontent.com/plotly/datasets/master/geojson-counties-fips.json)
- Official county geometry reference (Census TIGER/Line): [https://www.census.gov/geographies/mapping-files/time-series/geo/tiger-line-file.html](https://www.census.gov/geographies/mapping-files/time-series/geo/tiger-line-file.html)
## Source 4: Solar resource (`avgSolarGhiKwhM2Day`)
- Recommended dataset: NREL National Solar Radiation Database (NSRDB)
- Data/API page: [https://developer.nrel.gov/docs/solar/nsrdb/](https://developer.nrel.gov/docs/solar/nsrdb/)
- Maps/geospatial data page: [https://www.nrel.gov/gis/solar-resource-maps](https://www.nrel.gov/gis/solar-resource-maps)
- Fallback point API option: NASA POWER `ALLSKY_SFC_SW_DWN` (surface shortwave downwelling radiation), [https://power.larc.nasa.gov/docs/tutorials/service-data-request/api/](https://power.larc.nasa.gov/docs/tutorials/service-data-request/api/)
The app metric is designed for annual average daily global horizontal irradiance (GHI), in `kWh/m2/day`.
For county means, use a gridded annual GHI raster and pass it to the generator with `--solar-ghi-raster`.
### First test: NSRDB county representative points
For a lightweight first pass, sample each county at one interior representative point instead of requesting full county polygons.
This creates a point CSV:
```powershell
.venv\Scripts\python.exe scripts\build_county_representative_points.py
```
Then fetch a small NSRDB GOES TMY test batch.
If `--email` or `--api-key` are omitted, the script prompts you for them:
```powershell
.venv\Scripts\python.exe scripts\fetch_nsrdb_representative_point_ghi.py --limit 10
```
The fetch script uses GOES TMY first.
For high-latitude points, it can automatically retry the NSRDB Polar TMY endpoint when GOES reports no data.
If a county FIPS appears in `data/nrel/county_representative_point_ghi_error_log.csv` from an earlier run, that county tries the Polar endpoint first on the next run.
Disable this behavior with `--no-polar-fallback`.
Outputs:
- `data/nrel/county_representative_points.csv`: county FIPS, name, state, latitude, and longitude.
- `data/nrel/representative_point_csv/`: cached raw NSRDB CSV responses by county FIPS.
- `data/nrel/county_representative_point_ghi_summary.csv`: summarized `avgSolarGhiKwhM2Day` values.
The calculation is:
```text
avgSolarGhiKwhM2Day = sum(hourly GHI) / 1000 / 365
```
If the raw cache is complete but the summary CSV only contains the last fetched batch, rebuild the summary from cached files without calling the API:
```powershell
.venv\Scripts\python.exe scripts\rebuild_nsrdb_representative_point_ghi_summary.py
```
This point-based workflow is easier to validate and resume than full polygon downloads, but it is an approximation of county sunlight rather than an area-weighted county mean.
### First cloud-cover pass: NSRDB representative points
For a fast cloud-cover input layer, fetch representative-point NSRDB CSVs with observed GHI, Clearsky GHI, and Cloud Type:
```powershell
.venv\Scripts\python.exe scripts\fetch_nsrdb_representative_point_cloud_metrics.py --limit 10
```
Once the first batch looks right, fetch every county:
```powershell
.venv\Scripts\python.exe scripts\fetch_nsrdb_representative_point_cloud_metrics.py --all
```
Outputs:
- `data/nrel/representative_point_cloud_csv/`: cached raw NSRDB CSV responses with `ghi,clearsky_ghi,cloud_type`.
- `data/nrel/county_representative_point_cloud_summary.csv`: summarized cloud-cover proxy fields.
- `data/nrel/county_representative_point_cloud_error_log.csv`: failed county requests with redacted API context.
The primary calculation uses daylight rows where Clearsky GHI is at least 50 W/m2:
```text
cloudinessIndexPct = 1 - mean(clamped(GHI / Clearsky GHI, 0, 1))
```
The same summary also stores daylight row counts, observed-to-clear-sky ratio, and broad Cloud Type frequency buckets. This is faster than the polygon archive workflow, but it remains a representative-point county approximation.
Apply the representative-point cloudiness metric to the browser app CSV:
```powershell
.venv\Scripts\python.exe scripts\apply_nsrdb_cloud_metric_to_climate_data.py
```
The current cloud summary covers the 3,143 county representative points and leaves Puerto Rico rows blank in `data/climate-data.csv`.
### County-average target: NSRDB polygon cloud archive requests
For a less noisy county-level cloudiness layer, submit county polygons to the NSRDB archive workflow with `ghi,clearsky_ghi,cloud_type`. This uses the same polygon tiling and pacing logic as the GHI archive workflow, but writes separate cloud manifests, response JSON files, archives, and summaries.
Start with a dry run:
```powershell
.venv\Scripts\python.exe scripts\request_nsrdb_county_polygon_cloud_archives.py `
--dry-run `
--skip-site-count `
--limit 5
```
Then submit a small real batch:
```powershell
.venv\Scripts\python.exe scripts\request_nsrdb_county_polygon_cloud_archives.py `
--limit 5
```
Continue in resumable chunks:
```powershell
.venv\Scripts\python.exe scripts\request_nsrdb_county_polygon_cloud_archives.py `
--start 5 `
--limit 100
```
Download completed archives:
```powershell
.venv\Scripts\python.exe scripts\download_nsrdb_county_polygon_cloud_archives.py
```
Summarize downloaded archives into area-weighted county cloudiness:
```powershell
.venv\Scripts\python.exe scripts\summarize_nsrdb_county_polygon_cloud_archives.py --reuse-existing-output
```
Outputs:
- `data/nrel/county_polygon_cloud_request_manifest.csv`: submitted cloud archive requests.
- `data/nrel/county_polygon_cloud_error_log.csv`: cloud archive request errors.
- `data/nrel/polygon_cloud_request_responses/`: raw NSRDB cloud acknowledgement JSON files.
- `data/nrel/polygon_cloud_archives/`: downloaded cloud ZIP archives.
- `data/nrel/county_polygon_cloud_summary.csv`: area-weighted county cloudiness summaries.
Then update the browser app CSV. Polygon area-weighted values are used first when `data/nrel/county_polygon_cloud_summary.csv` exists; representative-point values remain the fallback:
```powershell
.venv\Scripts\python.exe scripts\apply_nsrdb_cloud_metric_to_climate_data.py
```
### County-average target: NSRDB polygon archive requests
For the final county-average solar layer, submit county polygons to the NSRDB archive workflow instead of sampling one representative point.
The polygon request returns a generated archive URL per county. Download those archives, then summarize them into a county polygon GHI CSV that can replace the representative-point solar values where available.
Start with a small dry run that does not touch the API:
```powershell
.venv\Scripts\python.exe scripts\request_nsrdb_county_polygon_ghi_archives.py `
--dry-run `
--skip-site-count `
--limit 5
```
Then submit a small real batch:
```powershell
.venv\Scripts\python.exe scripts\request_nsrdb_county_polygon_ghi_archives.py `
--limit 5
```
Once the first batch looks right, continue in resumable chunks:
```powershell
.venv\Scripts\python.exe scripts\request_nsrdb_county_polygon_ghi_archives.py `
--start 5 `
--limit 100
```
Or request every county from the current start point:
```powershell
.venv\Scripts\python.exe scripts\request_nsrdb_county_polygon_ghi_archives.py `
--all
```
Outputs:
- `data/nrel/county_polygon_ghi_request_manifest.csv`: one row per submitted county, including NSRDB profile, site count, request weight, response JSON path, and `download_url`.
- `data/nrel/county_polygon_ghi_error_log.csv`: counties that need retrying or tiling.
- `data/nrel/polygon_request_responses/`: raw API acknowledgement JSON files.
- `data/nrel/polygon_archives/`: downloaded county or tiled county ZIP archives.
- `data/nrel/county_polygon_ghi_summary.csv`: summarized polygon archive GHI, including `avgSolarGhiKwhM2Day`.
Download completed GHI archives:
```powershell
.venv\Scripts\python.exe scripts\download_nsrdb_county_polygon_ghi_archives.py
```
The script uses POST requests because county polygon WKT can be long.
It checks NSRDB site count by default and skips counties whose estimated request weight exceeds the API maximum.
Default pacing is one request every 2.1 seconds, matching the NSRDB archive limit.
Use `--include-puerto-rico` if you want to test Puerto Rico polygons too.
After the archives are downloaded, rebuild or resume the polygon summary:
```powershell
.venv\Scripts\python.exe scripts\summarize_nsrdb_county_polygon_archives.py --reuse-existing-output
```
Then update the app CSV. Polygon archive GHI is used first; representative-point GHI remains as a fallback for counties without polygon archive data:
```powershell
.venv\Scripts\python.exe scripts\apply_locally_extreme_metric_to_climate_data.py
```
## Metric definitions in generated output
- `koppenZone`: majority class within county polygon from Koppen raster.
- `avgTempF`: mean of 12 monthly county mean temperatures, converted C -> F.
- `annualPrecipIn`: sum of 12 monthly county mean precipitation totals, converted mm -> inches.
- `seasonalityIndex`: coefficient of variation of monthly precipitation totals, scaled to 0-100.
- `wettestPrecipMonth`: month with the highest 1991-2020 county mean precipitation total.
- `driestPrecipMonth`: month with the lowest 1991-2020 county mean precipitation total.
- previous `extremeDays` / `oldExtremeDays`: count of daily-normal or monthly-proxy days where county mean `tmax >= 95F` or `tmin <= 32F` (thresholds configurable in script). This is preserved only as an audit column after the NOAA nClimGrid-Daily metrics are applied.
- `avgSolarGhiKwhM2Day`: county mean annual average daily GHI, in `kWh/m2/day`. The current app CSV uses NSRDB polygon archive area-weighted values where available, with representative-point values kept as fallback.
- `cloudinessIndexPct`: representative-point NSRDB daylight cloudiness proxy derived from observed GHI divided by Clearsky GHI. Higher values mean observed irradiance is lower relative to modeled clear-sky irradiance. Despite the legacy field name, values are stored on a 0-1 scale.
## Run the generator
Install dependencies:
```powershell
pip install -r scripts/requirements_county_etl.txt
```
Run:
```powershell
python scripts/build_county_climate_data.py `
--counties-geojson data/geojson-counties-fips.json `
--koppen-raster data/koppen_geiger_tif/1991_2020/koppen_geiger_0p00833333.tif `
--koppen-legend data/koppen_geiger_tif/legend.txt `
--monthly-tavg-nc data/noaa/nclimgrid/nclimgrid_tavg.nc `
--monthly-prcp-nc data/noaa/nclimgrid/nclimgrid_prcp.nc `
--daily-tmax-nc data/noaa/nclimgrid/nclimgrid_tmax.nc `
--daily-tmin-nc data/noaa/nclimgrid/nclimgrid_tmin.nc `
--climatology-start-year 1991 `
--climatology-end-year 2020 `
--extreme-days-mode auto `
--solar-ghi-csv data/nrel/county_polygon_ghi_summary.csv `
--out data/climate-data.csv
```
Notes:
- This computes all counties in your geometry file, not just the sample records.
- For counties outside CONUS coverage in NOAA gridded files, fallback values are applied by the script when no valid grid values intersect.
- For physically-based daily `extremeDays`, provide true daily grids and set `--extreme-days-mode require-daily`.
- If `--counties-geojson` does not exist locally, the script will try to download the county GeoJSON automatically from the Plotly URL above and cache it at that path.
- `--solar-ghi-csv` is optional and can load county-keyed solar summaries into `avgSolarGhiKwhM2Day`.
- `--solar-ghi-raster` is optional and takes precedence over `--solar-ghi-csv`. If you have a gridded annual GHI raster, add `--solar-ghi-raster path/to/annual_ghi_kwh_m2_day.tif` for a true county-area raster mean.
## Source 5: NOAA nClimGrid-Daily county area averages (`locallyExtremeDays`)
- Main product page: [https://www.ncei.noaa.gov/products/land-based-station/nclimgrid-daily](https://www.ncei.noaa.gov/products/land-based-station/nclimgrid-daily)
- County/monthly area averages root: [https://www.ncei.noaa.gov/data/nclimgrid-daily/access/averages/](https://www.ncei.noaa.gov/data/nclimgrid-daily/access/averages/)
- User guide: [https://www.ncei.noaa.gov/data/nclimgrid-daily/doc/nclimgrid-daily_v1-0-0_user-guide.pdf](https://www.ncei.noaa.gov/data/nclimgrid-daily/doc/nclimgrid-daily_v1-0-0_user-guide.pdf)
- NCEI state-code to FIPS crosswalk: [https://www.ncei.noaa.gov/data/nclimgrid-daily/doc/us-state-codes_ncei-to-fips.csv](https://www.ncei.noaa.gov/data/nclimgrid-daily/doc/us-state-codes_ncei-to-fips.csv)
- Census boundary change notes: [https://www.census.gov/programs-surveys/geography/technical-documentation/boundary-change-notes.html](https://www.census.gov/programs-surveys/geography/technical-documentation/boundary-change-notes.html)
- Census county changes: [https://www.census.gov/programs-surveys/geography/technical-documentation/county-changes.html](https://www.census.gov/programs-surveys/geography/technical-documentation/county-changes.html)
The locally extreme metric uses county-specific 1991-2020 thresholds:
```text
p95_tmax_c = 95th percentile of county-average daily Tmax
p05_tmin_c = 5th percentile of county-average daily Tmin
locallyExtremeDays = count(Tmax >= p95_tmax_c OR Tmin <= p05_tmin_c)
```
The same daily county Tmax/Tmin records now also produce an absolute climate-bucket metric:
```text
absoluteExtremeDays = count(Tmax >= 95F OR Tmin <= 0F)
```
The heat threshold follows the EPA extreme-heat example of days at or above 95F.
The cold threshold is intentionally stricter than the older 32F freeze bucket because NWS cold guidance treats freezing as a freeze-warning/crop threshold and describes human extreme cold as region-dependent and often wind-chill based. The current NOAA cache does not include wind, so `Tmin <= 0F` is used as a configurable air-temperature proxy.
Run from the local NOAA CSV cache:
```powershell
.venv\Scripts\python.exe scripts\build_county_locally_extreme_data.py --skip-download
```
Outputs:
- `data/noaa/county_locally_extreme_thresholds.csv`
- `data/noaa/county_locally_extreme_days.csv`
- `data/noaa/county_locally_extreme_days_comparison.csv`
Apply the locally extreme average to the browser app CSV:
```powershell
.venv\Scripts\python.exe scripts\apply_locally_extreme_metric_to_climate_data.py
```
This keeps `data/climate-data.csv` compatible with the existing app by writing the locally extreme average into the active `extremeDays` column, while preserving the earlier proxy metric in `oldExtremeDays`. It also adds detail/audit columns:
- `locallyExtremeDays`
- `locallyExtremeHotDays`
- `locallyExtremeColdDays`
- `absoluteExtremeDays`
- `oldExtremeDays`
- `locallyExtremeAnalysisYears`
- `locallyExtremeSourceFips`
- `locallyExtremeFipsAdjustment`
FIPS/geography-vintage policy:
- Use current NOAA/Census county-equivalent FIPS for the locally extreme outputs.
- Correct NOAA's District of Columbia county row from source region code `18511` to Census FIPS `11001`.
- Apply only one-to-one old app comparison concordances, currently `46113 -> 46102` for Shannon/Oglala Lakota and `51515 -> 51019` for Bedford city/Bedford County.
- Do not guess split or many-to-one geography changes without a Census relationship file; leave those rows flagged in the comparison output.
scripts/download_gridmet_data.py
+143
View File
@@ -0,0 +1,143 @@
#!/usr/bin/env python3
"""
Download gridMET daily NetCDF files into year-based folders.
Default layout:
data/gridmet/1991/sph.nc
data/gridmet/1991/rmax.nc
data/gridmet/1991/rmin.nc
gridMET source:
https://www.northwestknowledge.net/metdata/data/{variable}_{year}.nc
"""
from __future__ import annotations
import argparse
import sys
import tempfile
import urllib.error
import urllib.request
from pathlib import Path
DEFAULT_BASE_URL = "https://www.northwestknowledge.net/metdata/data"
DEFAULT_VARIABLES = ("sph", "rmax", "rmin")
def _parse_years(text: str) -> list[int]:
years: set[int] = set()
for part in text.split(","):
token = part.strip()
if not token:
continue
if "-" in token:
start_text, end_text = token.split("-", 1)
start = int(start_text)
end = int(end_text)
if start > end:
raise argparse.ArgumentTypeError(f"Invalid descending year range: {token}")
years.update(range(start, end + 1))
else:
years.add(int(token))
if not years:
raise argparse.ArgumentTypeError("At least one year is required.")
return sorted(years)
def _parse_variables(text: str) -> list[str]:
variables = [part.strip() for part in text.split(",") if part.strip()]
if not variables:
raise argparse.ArgumentTypeError("At least one variable is required.")
return variables
def _download_file(url: str, destination: Path, overwrite: bool) -> bool:
if destination.exists() and not overwrite:
print(f"skip existing {destination}")
return False
destination.parent.mkdir(parents=True, exist_ok=True)
with tempfile.NamedTemporaryFile(
prefix=destination.stem + ".",
suffix=".download",
dir=destination.parent,
delete=False,
) as handle:
temp_path = Path(handle.name)
try:
print(f"download {url}")
with urllib.request.urlopen(url) as response, temp_path.open("wb") as output:
total_text = response.headers.get("Content-Length")
total = int(total_text) if total_text and total_text.isdigit() else None
copied = 0
while True:
chunk = response.read(1024 * 1024)
if not chunk:
break
output.write(chunk)
copied += len(chunk)
if total:
percent = copied / total * 100
print(f"\r {copied / 1024 / 1024:,.1f} MiB / {total / 1024 / 1024:,.1f} MiB ({percent:5.1f}%)", end="")
if total:
print()
temp_path.replace(destination)
print(f"saved {destination}")
return True
except (urllib.error.URLError, urllib.error.HTTPError, OSError) as exc:
temp_path.unlink(missing_ok=True)
print(f"failed {url}: {exc}", file=sys.stderr)
raise
def main() -> int:
parser = argparse.ArgumentParser(
description="Download gridMET NetCDF files into data/gridmet/<year>/<variable>.nc."
)
parser.add_argument(
"--years",
type=_parse_years,
default=_parse_years("1991-2020"),
help="Comma-separated years/ranges. Default: 1991-2020.",
)
parser.add_argument(
"--variables",
type=_parse_variables,
default=list(DEFAULT_VARIABLES),
help="Comma-separated gridMET variables. Default: sph,rmax,rmin.",
)
parser.add_argument(
"--output-dir",
type=Path,
default=Path("data/gridmet"),
help="Root folder for downloaded files. Default: data/gridmet.",
)
parser.add_argument(
"--base-url",
default=DEFAULT_BASE_URL,
help=f"Base gridMET download URL. Default: {DEFAULT_BASE_URL}.",
)
parser.add_argument(
"--overwrite",
action="store_true",
help="Redownload files that already exist.",
)
args = parser.parse_args()
downloaded = 0
for year in args.years:
for variable in args.variables:
url = f"{args.base_url.rstrip('/')}/{variable}_{year}.nc"
destination = args.output_dir / str(year) / f"{variable}.nc"
if _download_file(url, destination, args.overwrite):
downloaded += 1
print(f"done; downloaded {downloaded} file(s)")
return 0
if __name__ == "__main__":
raise SystemExit(main())
scripts/download_nsrdb_county_polygon_archives.py
+325
View File
@@ -0,0 +1,325 @@
#!/usr/bin/env python3
"""
Download completed NSRDB county polygon archive ZIP files.
This shared engine reads JSON acknowledgements produced by the polygon request
workflow and downloads each outputs.downloadUrl. Metric-specific wrappers
supply the response and archive directories.
"""
from __future__ import annotations
import argparse
import json
import time
import urllib.error
import urllib.parse
import urllib.request
from dataclasses import dataclass, field
from enum import Enum
from pathlib import Path
from typing import Any
DEFAULT_TIMEOUT = 300
DEFAULT_CHUNK_SIZE = 1024 * 1024
class ArchiveDownloadState(Enum):
"""Distinct lifecycle phases for one NSRDB archive download."""
QUEUED = "queued"
CHECKING = "checking"
DOWNLOADING = "downloading"
SKIPPED = "skipped"
PENDING = "pending"
DOWNLOADED = "downloaded"
FAILED = "failed"
class ArchiveDownloadEvent(Enum):
"""Events that may move an archive download to another lifecycle phase."""
START = "start"
EXISTING_FILE_FOUND = "existing_file_found"
DOWNLOAD_STARTED = "download_started"
ARCHIVE_NOT_READY = "archive_not_ready"
DOWNLOAD_SUCCEEDED = "download_succeeded"
DOWNLOAD_FAILED = "download_failed"
ARCHIVE_DOWNLOAD_TRANSITIONS = {
(ArchiveDownloadState.QUEUED, ArchiveDownloadEvent.START): ArchiveDownloadState.CHECKING,
(
ArchiveDownloadState.CHECKING,
ArchiveDownloadEvent.EXISTING_FILE_FOUND,
): ArchiveDownloadState.SKIPPED,
(
ArchiveDownloadState.CHECKING,
ArchiveDownloadEvent.DOWNLOAD_STARTED,
): ArchiveDownloadState.DOWNLOADING,
(
ArchiveDownloadState.DOWNLOADING,
ArchiveDownloadEvent.ARCHIVE_NOT_READY,
): ArchiveDownloadState.PENDING,
(
ArchiveDownloadState.DOWNLOADING,
ArchiveDownloadEvent.DOWNLOAD_SUCCEEDED,
): ArchiveDownloadState.DOWNLOADED,
(
ArchiveDownloadState.QUEUED,
ArchiveDownloadEvent.DOWNLOAD_FAILED,
): ArchiveDownloadState.FAILED,
(
ArchiveDownloadState.CHECKING,
ArchiveDownloadEvent.DOWNLOAD_FAILED,
): ArchiveDownloadState.FAILED,
(
ArchiveDownloadState.DOWNLOADING,
ArchiveDownloadEvent.DOWNLOAD_FAILED,
): ArchiveDownloadState.FAILED,
}
class InvalidArchiveDownloadTransition(RuntimeError):
"""Reject an event that is not valid for the current download state."""
@dataclass
class ArchiveDownloadStateMachine:
"""Track and validate the lifecycle of one archive download."""
label: str
state: ArchiveDownloadState = ArchiveDownloadState.QUEUED
history: list[ArchiveDownloadState] = field(
default_factory=lambda: [ArchiveDownloadState.QUEUED]
)
def transition(self, event: ArchiveDownloadEvent) -> ArchiveDownloadState:
"""Apply one event and return the resulting state."""
next_state = ARCHIVE_DOWNLOAD_TRANSITIONS.get((self.state, event))
if next_state is None:
raise InvalidArchiveDownloadTransition(
f"Invalid archive download transition for {self.label}: "
f"{event.value} while {self.state.value}."
)
self.state = next_state
self.history.append(next_state)
return next_state
class PolygonArchiveDownloadError(RuntimeError):
"""Store a failed archive download with useful context."""
def __init__(self, message: str, status_code: int | None = None) -> None:
super().__init__(message)
self.status_code = status_code
def is_pending_s3_archive_response(url: str, status_code: int) -> bool:
"""Return whether an S3 HTTP response likely means the archive is pending."""
if status_code != 403:
return False
host = urllib.parse.urlsplit(url).netloc.lower()
return host == "s3.amazonaws.com" or host.endswith(".amazonaws.com")
def read_response(response_path: Path) -> dict[str, Any]:
"""Read a saved NSRDB archive response JSON file."""
with response_path.open(encoding="utf-8") as handle:
response = json.load(handle)
if not isinstance(response, dict):
raise ValueError("Response JSON must contain an object.")
return response
def download_url_from_response(response: dict[str, Any]) -> str:
"""Return the download URL from a saved NSRDB archive response."""
outputs = response.get("outputs")
if not isinstance(outputs, dict):
raise ValueError("Response JSON is missing an outputs object.")
download_url = outputs.get("downloadUrl")
if not isinstance(download_url, str) or not download_url.strip():
raise ValueError("Response JSON is missing outputs.downloadUrl.")
return download_url.strip()
def output_name_for_response(response_path: Path) -> str:
"""Convert a response JSON filename into the corresponding ZIP filename."""
stem = response_path.stem
if stem.endswith("_response"):
stem = stem[: -len("_response")]
return f"{stem}.zip"
def download_file(
url: str,
output_path: Path,
timeout: int,
overwrite: bool,
machine: ArchiveDownloadStateMachine,
) -> ArchiveDownloadState:
"""Download a URL to disk and return the terminal download state."""
output_path.parent.mkdir(parents=True, exist_ok=True)
if output_path.exists() and not overwrite:
return machine.transition(ArchiveDownloadEvent.EXISTING_FILE_FOUND)
machine.transition(ArchiveDownloadEvent.DOWNLOAD_STARTED)
temp_path = output_path.with_suffix(f"{output_path.suffix}.part")
if temp_path.exists():
temp_path.unlink()
request = urllib.request.Request(url, headers={"User-Agent": "county-climate-explorer/0.1"})
try:
with urllib.request.urlopen(request, timeout=timeout) as response:
with temp_path.open("wb") as handle:
while True:
chunk = response.read(DEFAULT_CHUNK_SIZE)
if not chunk:
break
handle.write(chunk)
except urllib.error.HTTPError as error:
if temp_path.exists():
temp_path.unlink()
if is_pending_s3_archive_response(url, error.code):
return machine.transition(ArchiveDownloadEvent.ARCHIVE_NOT_READY)
machine.transition(ArchiveDownloadEvent.DOWNLOAD_FAILED)
raise PolygonArchiveDownloadError(f"HTTP {error.code} {error.reason}", error.code) from error
except urllib.error.URLError as error:
if temp_path.exists():
temp_path.unlink()
machine.transition(ArchiveDownloadEvent.DOWNLOAD_FAILED)
raise PolygonArchiveDownloadError(str(error.reason)) from error
temp_path.replace(output_path)
return machine.transition(ArchiveDownloadEvent.DOWNLOAD_SUCCEEDED)
def response_paths(response_dir: Path, start: int, limit: int | None) -> list[Path]:
"""Return saved response JSON files in deterministic order."""
paths = sorted(response_dir.glob("*.json"))
if start < 0:
raise ValueError("--start must be 0 or greater.")
if limit is not None and limit < 1:
raise ValueError("--limit must be 1 or greater.")
if limit is None:
return paths[start:]
return paths[start : start + limit]
def run(args: argparse.Namespace) -> None:
"""Download all requested NSRDB polygon archives."""
paths = response_paths(args.response_dir, args.start, args.limit)
if not paths:
print(f"No response JSON files found in {args.response_dir}")
return
counts = {
ArchiveDownloadState.DOWNLOADED: 0,
ArchiveDownloadState.SKIPPED: 0,
ArchiveDownloadState.PENDING: 0,
ArchiveDownloadState.FAILED: 0,
}
total = len(paths)
for index, response_path in enumerate(paths, start=1):
output_path = args.output_dir / output_name_for_response(response_path)
label = response_path.name
machine = ArchiveDownloadStateMachine(label)
machine.transition(ArchiveDownloadEvent.START)
try:
response = read_response(response_path)
download_url = download_url_from_response(response)
state = download_file(
download_url,
output_path,
args.timeout,
args.overwrite,
machine,
)
except (OSError, ValueError, PolygonArchiveDownloadError) as error:
if machine.state not in {
ArchiveDownloadState.FAILED,
ArchiveDownloadState.SKIPPED,
ArchiveDownloadState.PENDING,
ArchiveDownloadState.DOWNLOADED,
}:
machine.transition(ArchiveDownloadEvent.DOWNLOAD_FAILED)
counts[machine.state] += 1
print(f"[{index}/{total}] Failed {label}: {error}")
continue
counts[state] += 1
if state is ArchiveDownloadState.SKIPPED:
print(f"[{index}/{total}] Skipped existing {output_path}")
elif state is ArchiveDownloadState.PENDING:
print(
f"[{index}/{total}] Pending {label}: archive URL returned "
"S3 HTTP 403; retry after NSRDB finishes generating it."
)
else:
print(f"[{index}/{total}] Downloaded {output_path}")
if args.delay > 0 and index < total:
time.sleep(args.delay)
print(
f"Finished: downloaded={counts[ArchiveDownloadState.DOWNLOADED]}, "
f"skipped={counts[ArchiveDownloadState.SKIPPED]}, "
f"pending={counts[ArchiveDownloadState.PENDING]}, "
f"failed={counts[ArchiveDownloadState.FAILED]}, output_dir={args.output_dir}"
)
def parse_args(
argv: list[str] | None = None,
description: str | None = None,
) -> argparse.Namespace:
"""Parse command-line arguments."""
parser = argparse.ArgumentParser(description=description or __doc__)
parser.add_argument("--response-dir", type=Path)
parser.add_argument("--output-dir", type=Path)
parser.add_argument("--start", type=int, default=0, help="Zero-based response file offset.")
parser.add_argument("--limit", type=int, help="Number of response files to download.")
parser.add_argument("--timeout", type=int, default=DEFAULT_TIMEOUT, help="Download timeout in seconds.")
parser.add_argument("--delay", type=float, default=0.0, help="Seconds to wait between downloads.")
parser.add_argument("--overwrite", action="store_true", help="Download even when the ZIP already exists.")
args = parser.parse_args(argv)
missing = [
option
for option, value in {
"--response-dir": args.response_dir,
"--output-dir": args.output_dir,
}.items()
if not value
]
if missing:
parser.error(f"the following arguments are required: {', '.join(missing)}")
if args.timeout <= 0:
parser.error("--timeout must be greater than 0.")
if args.delay < 0:
parser.error("--delay must be 0 or greater.")
return args
def main(
argv: list[str] | None = None,
description: str | None = None,
) -> None:
"""Run the archive downloader."""
run(parse_args(argv, description))
if __name__ == "__main__":
main()
scripts/download_nsrdb_county_polygon_cloud_archives.py
+33
View File
@@ -0,0 +1,33 @@
#!/usr/bin/env python3
"""
Download completed NSRDB county polygon cloud archive ZIP files.
This is a cloud-specific wrapper around download_nsrdb_county_polygon_archives.py
that reads cloud request responses and writes archives into a separate folder.
"""
from __future__ import annotations
import sys
import download_nsrdb_county_polygon_archives as polygon_download
DEFAULT_ARGS = [
"--response-dir",
"data/nrel/polygon_cloud_request_responses",
"--output-dir",
"data/nrel/polygon_cloud_archives",
]
def main() -> None:
"""Run the existing polygon archive downloader with cloud-specific defaults."""
polygon_download.main(
[*DEFAULT_ARGS, *sys.argv[1:]],
description=__doc__,
)
if __name__ == "__main__":
main()
scripts/download_nsrdb_county_polygon_ghi_archives.py
+34
View File
@@ -0,0 +1,34 @@
#!/usr/bin/env python3
"""
Download completed NSRDB county polygon GHI archive ZIP files.
This is a GHI-specific wrapper around download_nsrdb_county_polygon_archives.py.
It reuses the shared download state machine with GHI-specific response and
archive directories.
"""
from __future__ import annotations
import sys
import download_nsrdb_county_polygon_archives as polygon_download
DEFAULT_ARGS = [
"--response-dir",
"data/nrel/polygon_request_responses",
"--output-dir",
"data/nrel/polygon_archives",
]
def main() -> None:
"""Run the shared polygon archive downloader with GHI-specific defaults."""
polygon_download.main(
[*DEFAULT_ARGS, *sys.argv[1:]],
description=__doc__,
)
if __name__ == "__main__":
main()
scripts/fetch_nsrdb_representative_point_cloud_metrics.py
+832
View File
@@ -0,0 +1,832 @@
#!/usr/bin/env python3
"""
Fetch NSRDB representative-point inputs for a county cloud-cover metric.
This uses the direct single-point NSRDB CSV endpoint rather than polygon archive
requests. It is faster for first-pass cloud metrics because it downloads one CSV
per county point and can run multiple county requests concurrently.
Default requested attributes:
ghi,clearsky_ghi,cloud_type
The summary metric is based on daylight rows with valid GHI and Clearsky GHI:
cloudinessIndexPct = 1 - mean(clamped(GHI / Clearsky GHI))
where the ratio is clamped to [0, 1] so occasional above-clear-sky modeled GHI
does not create negative cloudiness.
"""
from __future__ import annotations
import argparse
import concurrent.futures
import csv
import getpass
import math
import re
import threading
import time
import urllib.error
import urllib.parse
import urllib.request
from pathlib import Path
DEFAULT_POINTS_CSV = Path("data/nrel/county_representative_points.csv")
DEFAULT_OUTPUT_CSV = Path("data/nrel/county_representative_point_cloud_summary.csv")
DEFAULT_ERROR_CSV = Path("data/nrel/county_representative_point_cloud_error_log.csv")
DEFAULT_CACHE_DIR = Path("data/nrel/representative_point_cloud_csv")
DEFAULT_ENDPOINT = "https://developer.nlr.gov/api/nsrdb/v2/solar/nsrdb-GOES-tmy-v4-0-0-download.csv"
DEFAULT_POLAR_ENDPOINT = "https://developer.nlr.gov/api/nsrdb/v2/solar/nsrdb-polar-tmy-v4-0-0-download.csv"
DEFAULT_TMY_NAME = "tmy-2024"
DEFAULT_POLAR_TMY_NAME = "tmy"
DEFAULT_ATTRIBUTES = "ghi,clearsky_ghi,cloud_type"
DEFAULT_INTERVAL = 60
DEFAULT_POLAR_MIN_LATITUDE = 60.0
DEFAULT_MIN_CLEARSKY_GHI = 50.0
EMAIL_PATTERN = re.compile(r"[\w.!#$%&'*+/=?^`{|}~-]+@[\w-]+(?:\.[\w-]+)+")
SENSITIVE_QUERY_PATTERN = re.compile(r"((?:api_key|email)=)([^&\s,\"']+)", re.IGNORECASE)
CLOUD_TYPE_LABELS = {
"-15": "na",
"0": "clear",
"1": "probably_clear",
"2": "fog",
"3": "water",
"4": "super_cooled_water",
"5": "mixed",
"6": "opaque_ice",
"7": "cirrus",
"8": "overlapping",
"9": "overshooting",
"10": "unknown",
"11": "dust",
"12": "smoke",
}
CLOUD_SUMMARY_FIELDS = [
"county_fips",
"county_name",
"state_fips",
"state_abbr",
"lat",
"lon",
"cloudinessIndexPct",
"avgObservedToClearskyRatio",
"daylightRows",
"allRows",
"clearOrProbablyClearPct",
"cloudyOrObscuredPct",
"fogPct",
"waterCloudPct",
"iceCloudPct",
"cirrusPct",
"unknownCloudTypePct",
"ghi_min",
"ghi_max",
"clearsky_ghi_min",
"clearsky_ghi_max",
"source",
"raw_csv",
]
def prompt_for_secret(prompt: str, current_value: str | None) -> str:
"""Prompt for a sensitive value only when it was not supplied."""
if current_value:
return current_value
return getpass.getpass(prompt).strip()
def prompt_for_text(prompt: str, current_value: str | None) -> str:
"""Prompt for normal text only when it was not supplied."""
if current_value:
return current_value
return input(prompt).strip()
def read_county_points(points_csv: Path) -> list[dict[str, str]]:
"""Read the county point CSV."""
with points_csv.open(newline="", encoding="utf-8") as handle:
return list(csv.DictReader(handle))
def select_county_points(
rows: list[dict[str, str]],
start: int,
limit: int | None,
completed_fips: set[str],
overwrite: bool,
) -> list[dict[str, str]]:
"""Return the requested batch, skipping completed counties unless overwriting."""
if start < 0:
raise ValueError("--start must be 0 or greater.")
if limit is not None and limit < 1:
raise ValueError("--limit must be 1 or greater.")
candidates = rows[start:]
if not overwrite:
candidates = [
row
for row in candidates
if row.get("county_fips") not in completed_fips
]
if limit is None:
return candidates
return candidates[:limit]
def read_existing_summary_rows(output_csv: Path) -> dict[str, dict[str, str]]:
"""Read already summarized county cloud rows keyed by FIPS."""
if not output_csv.exists():
return {}
with output_csv.open(newline="", encoding="utf-8-sig") as handle:
return {
row["county_fips"]: row
for row in csv.DictReader(handle)
if row.get("county_fips")
}
def read_previous_error_fips(error_csv: Path) -> set[str]:
"""Read county FIPS values from a previous error log."""
if not error_csv.exists():
return set()
with error_csv.open(newline="", encoding="utf-8") as handle:
return {
row["county_fips"]
for row in csv.DictReader(handle)
if row.get("county_fips")
}
def is_polar_candidate(point: dict[str, str], min_latitude: float) -> bool:
"""Return whether a point is in the latitude range for the Polar endpoint."""
try:
return float(point["lat"]) >= min_latitude
except (KeyError, ValueError):
return False
def build_nsrdb_url(
endpoint: str,
api_key: str,
email: str,
point: dict[str, str],
name: str,
attributes: str,
interval: int,
) -> str:
"""Build a single-point NSRDB CSV request URL."""
wkt = f"POINT({point['lon']} {point['lat']})"
query = {
"api_key": api_key,
"wkt": wkt,
"attributes": attributes,
"names": name,
"utc": "false",
"leap_day": "false",
"interval": str(interval),
"email": email,
}
return f"{endpoint}?{urllib.parse.urlencode(query)}"
def redact_url(url: str) -> str:
"""Return a request URL with sensitive query values removed."""
parsed_url = urllib.parse.urlsplit(url)
query = urllib.parse.parse_qsl(parsed_url.query, keep_blank_values=True)
redacted_query = [
(key, "<redacted>" if key in {"api_key", "email"} else value)
for key, value in query
]
return urllib.parse.urlunsplit(
parsed_url._replace(query=urllib.parse.urlencode(redacted_query))
)
def redact_sensitive_text(text: str) -> str:
"""Remove likely credentials and email addresses from log text."""
without_query_values = SENSITIVE_QUERY_PATTERN.sub(r"\1<redacted>", text)
return EMAIL_PATTERN.sub("<redacted>", without_query_values)
class NsrdDataRequestError(RuntimeError):
"""Store a failed NSRDB request with sanitized context for logging."""
def __init__(
self,
message: str,
status_code: int | None = None,
url: str | None = None,
response: str = "",
) -> None:
super().__init__(message)
self.status_code = status_code
self.url = url
self.response = response
class RequestRateLimiter:
"""Coordinate network request starts across worker threads."""
def __init__(self, delay: float) -> None:
self.delay = max(0.0, delay)
self._lock = threading.Lock()
self._next_request_at = 0.0
def wait(self) -> None:
"""Wait until the next request can start."""
if self.delay <= 0:
return
with self._lock:
now = time.monotonic()
wait_seconds = max(0.0, self._next_request_at - now)
self._next_request_at = max(now, self._next_request_at) + self.delay
if wait_seconds:
time.sleep(wait_seconds)
def build_http_request_error(error: urllib.error.HTTPError, url: str) -> NsrdDataRequestError:
"""Create a structured NSRDB request error from an HTTPError."""
body = error.read().decode("utf-8-sig", errors="replace").strip()
body_excerpt = redact_sensitive_text(body[:1000]) if body else "No response body returned."
redacted_url = redact_url(url)
retry_after = error.headers.get("Retry-After") if error.headers else None
retry_message = f"\n Retry-After: {retry_after}" if retry_after else ""
message = f"HTTP {error.code} {error.reason}\n URL: {redacted_url}{retry_message}\n Response: {body_excerpt}"
return NsrdDataRequestError(
message=message,
status_code=error.code,
url=redacted_url,
response=body_excerpt,
)
def download_text(url: str, timeout: int, rate_limiter: RequestRateLimiter | None = None) -> str:
"""Download text from a URL and return its decoded body."""
request = urllib.request.Request(url, headers={"User-Agent": "county-climate-explorer/0.1"})
try:
if rate_limiter is not None:
rate_limiter.wait()
with urllib.request.urlopen(request, timeout=timeout) as response:
return response.read().decode("utf-8-sig")
except urllib.error.HTTPError as error:
raise build_http_request_error(error, url) from error
def cache_suffix(attributes: str) -> str:
"""Return a stable, readable suffix for the cached CSV filename."""
normalized = re.sub(r"[^a-z0-9]+", "-", attributes.lower()).strip("-")
return normalized or "cloud"
def read_or_download_county_csv(
point: dict[str, str],
endpoint: str,
api_key: str,
email: str,
name: str,
source_key: str,
attributes: str,
interval: int,
cache_dir: Path,
timeout: int,
overwrite: bool,
rate_limiter: RequestRateLimiter | None = None,
) -> tuple[str, Path]:
"""Return cached NSRDB CSV text, downloading it first when needed."""
cache_dir.mkdir(parents=True, exist_ok=True)
cache_path = cache_dir / f"{point['county_fips']}_{source_key}_{name}_{cache_suffix(attributes)}.csv"
if cache_path.exists() and not overwrite:
return cache_path.read_text(encoding="utf-8-sig"), cache_path
url = build_nsrdb_url(endpoint, api_key, email, point, name, attributes, interval)
csv_text = download_text(url, timeout, rate_limiter)
cache_path.write_text(csv_text, encoding="utf-8")
return csv_text, cache_path
def normalized_header(value: str) -> str:
"""Normalize a CSV header to make NSRDB spelling variations easier to match."""
return re.sub(r"[^a-z0-9]+", "", value.lower())
def find_column(header: list[str], candidates: set[str]) -> int | None:
"""Return the first header index whose normalized name matches a candidate."""
normalized_candidates = {normalized_header(candidate) for candidate in candidates}
for index, value in enumerate(header):
if normalized_header(value) in normalized_candidates:
return index
return None
def find_data_header(rows: list[list[str]]) -> int | None:
"""Return the NSRDB hourly data header row index."""
required = {"Year", "Month", "Day", "Hour", "Minute"}
for index, row in enumerate(rows):
if required.issubset(set(row)):
return index
return None
def parse_optional_float(row: list[str], index: int | None) -> float | None:
"""Parse an optional float field from a CSV row."""
if index is None or len(row) <= index:
return None
value = row[index].strip()
if not value:
return None
try:
parsed = float(value)
except ValueError:
return None
if not math.isfinite(parsed):
return None
return parsed
def parse_cloud_type(row: list[str], index: int | None) -> str:
"""Parse an optional cloud type code as a string."""
if index is None or len(row) <= index:
return ""
value = row[index].strip()
if not value:
return ""
try:
return str(int(float(value)))
except ValueError:
return value
def pct(count: int, total: int) -> float:
"""Return a percentage or NaN when there is no denominator."""
return count / total * 100 if total else math.nan
def fmt(value: float | None, places: int = 3) -> str:
"""Format an optional float for CSV output."""
if value is None or not math.isfinite(value):
return ""
return f"{value:.{places}f}"
def summarize_cloud_metrics(
point: dict[str, str],
csv_text: str,
source_file: Path,
source_label: str,
min_clearsky_ghi: float,
) -> dict[str, str]:
"""Convert hourly GHI/Clearsky GHI/Cloud Type rows into county metrics."""
rows = list(csv.reader(csv_text.splitlines()))
header_index = find_data_header(rows)
if header_index is None:
raise ValueError("Could not find the NSRDB data header row.")
header = rows[header_index]
ghi_index = find_column(header, {"GHI", "ghi"})
clearsky_ghi_index = find_column(
header,
{
"Clearsky GHI",
"Clear Sky GHI",
"Clear-sky GHI",
"clearsky_ghi",
"clear_sky_ghi",
},
)
cloud_type_index = find_column(header, {"Cloud Type", "cloud_type", "cloudtype"})
if ghi_index is None:
raise ValueError("Could not find a GHI column in the NSRDB response.")
if clearsky_ghi_index is None:
raise ValueError("Could not find a Clearsky GHI column in the NSRDB response.")
if cloud_type_index is None:
raise ValueError("Could not find a Cloud Type column in the NSRDB response.")
all_rows = 0
daylight_rows = 0
ratio_sum = 0.0
ghi_values: list[float] = []
clearsky_values: list[float] = []
daylight_cloud_type_counts: dict[str, int] = {}
for row in rows[header_index + 1 :]:
if not row:
continue
all_rows += 1
ghi = parse_optional_float(row, ghi_index)
clearsky_ghi = parse_optional_float(row, clearsky_ghi_index)
cloud_type = parse_cloud_type(row, cloud_type_index)
if ghi is None or clearsky_ghi is None:
continue
ghi_values.append(ghi)
clearsky_values.append(clearsky_ghi)
if clearsky_ghi < min_clearsky_ghi:
continue
ratio_sum += min(1.0, max(0.0, ghi / clearsky_ghi))
daylight_rows += 1
if cloud_type:
daylight_cloud_type_counts[cloud_type] = daylight_cloud_type_counts.get(cloud_type, 0) + 1
if daylight_rows == 0:
raise ValueError("No daylight rows with valid GHI and Clearsky GHI were found.")
avg_ratio = ratio_sum / daylight_rows
cloudiness_pct = 1 - avg_ratio
clear_or_probably_clear = daylight_cloud_type_counts.get("0", 0) + daylight_cloud_type_counts.get("1", 0)
cloudy_or_obscured = sum(
daylight_cloud_type_counts.get(code, 0)
for code in ["2", "3", "4", "5", "6", "7", "8", "9", "11", "12"]
)
water_cloud = (
daylight_cloud_type_counts.get("3", 0)
+ daylight_cloud_type_counts.get("4", 0)
+ daylight_cloud_type_counts.get("5", 0)
)
ice_cloud = (
daylight_cloud_type_counts.get("6", 0)
+ daylight_cloud_type_counts.get("8", 0)
+ daylight_cloud_type_counts.get("9", 0)
)
unknown_cloud_type = daylight_cloud_type_counts.get("10", 0) + daylight_cloud_type_counts.get("-15", 0)
return {
"county_fips": point["county_fips"],
"county_name": point["county_name"],
"state_fips": point["state_fips"],
"state_abbr": point["state_abbr"],
"lat": point["lat"],
"lon": point["lon"],
"cloudinessIndexPct": fmt(cloudiness_pct, 4),
"avgObservedToClearskyRatio": fmt(avg_ratio, 4),
"daylightRows": str(daylight_rows),
"allRows": str(all_rows),
"clearOrProbablyClearPct": fmt(pct(clear_or_probably_clear, daylight_rows), 2),
"cloudyOrObscuredPct": fmt(pct(cloudy_or_obscured, daylight_rows), 2),
"fogPct": fmt(pct(daylight_cloud_type_counts.get("2", 0), daylight_rows), 2),
"waterCloudPct": fmt(pct(water_cloud, daylight_rows), 2),
"iceCloudPct": fmt(pct(ice_cloud, daylight_rows), 2),
"cirrusPct": fmt(pct(daylight_cloud_type_counts.get("7", 0), daylight_rows), 2),
"unknownCloudTypePct": fmt(pct(unknown_cloud_type, daylight_rows), 2),
"ghi_min": fmt(min(ghi_values), 1) if ghi_values else "",
"ghi_max": fmt(max(ghi_values), 1) if ghi_values else "",
"clearsky_ghi_min": fmt(min(clearsky_values), 1) if clearsky_values else "",
"clearsky_ghi_max": fmt(max(clearsky_values), 1) if clearsky_values else "",
"source": f"{source_label} representative point",
"raw_csv": str(source_file),
}
def write_summary_csv(rows: list[dict[str, str]], output_csv: Path) -> None:
"""Write fetched county cloud summaries to CSV."""
output_csv.parent.mkdir(parents=True, exist_ok=True)
with output_csv.open("w", newline="", encoding="utf-8") as handle:
writer = csv.DictWriter(handle, fieldnames=CLOUD_SUMMARY_FIELDS)
writer.writeheader()
writer.writerows(rows)
def merged_summary_rows(
all_points: list[dict[str, str]],
existing_rows_by_fips: dict[str, dict[str, str]],
new_rows: list[dict[str, str]],
) -> list[dict[str, str]]:
"""Return existing and newly fetched rows in county point order."""
rows_by_fips = dict(existing_rows_by_fips)
for row in new_rows:
rows_by_fips[row["county_fips"]] = row
ordered_rows: list[dict[str, str]] = []
seen_fips: set[str] = set()
for point in all_points:
county_fips = point.get("county_fips", "")
row = rows_by_fips.get(county_fips)
if row is not None:
ordered_rows.append(row)
seen_fips.add(county_fips)
extra_rows = [
row
for county_fips, row in sorted(rows_by_fips.items())
if county_fips not in seen_fips
]
return ordered_rows + extra_rows
def write_error_csv(rows: list[dict[str, str]], error_csv: Path) -> None:
"""Write failed county cloud fetches to CSV."""
error_csv.parent.mkdir(parents=True, exist_ok=True)
with error_csv.open("w", newline="", encoding="utf-8") as handle:
writer = csv.DictWriter(
handle,
fieldnames=[
"county_fips",
"county_name",
"state_fips",
"state_abbr",
"lat",
"lon",
"error_type",
"status_code",
"request_url",
"response",
"message",
],
)
writer.writeheader()
writer.writerows(rows)
def build_error_row(point: dict[str, str], error: Exception) -> dict[str, str]:
"""Convert a failed county fetch into a structured CSV row."""
status_code = ""
request_url = ""
response = ""
if isinstance(error, NsrdDataRequestError):
status_code = str(error.status_code or "")
request_url = error.url or ""
response = error.response
return {
"county_fips": point["county_fips"],
"county_name": point["county_name"],
"state_fips": point["state_fips"],
"state_abbr": point["state_abbr"],
"lat": point["lat"],
"lon": point["lon"],
"error_type": type(error).__name__,
"status_code": status_code,
"request_url": request_url,
"response": redact_sensitive_text(response),
"message": redact_sensitive_text(str(error)),
}
def build_request_profiles(
args: argparse.Namespace,
point: dict[str, str],
previous_error_fips: set[str],
) -> list[dict[str, str]]:
"""Build the ordered list of NSRDB endpoints to try for a county point."""
goes_profile = {
"source_key": "goes-tmy",
"source_label": "NSRDB GOES TMY PSM v4",
"endpoint": args.endpoint,
"name": args.name,
}
polar_profile = {
"source_key": "polar-tmy",
"source_label": "NSRDB Polar TMY PSM v4",
"endpoint": args.polar_endpoint,
"name": args.polar_name,
}
if not args.polar_fallback or not is_polar_candidate(point, args.polar_min_latitude):
return [goes_profile]
if point["county_fips"] in previous_error_fips:
return [polar_profile, goes_profile]
return [goes_profile, polar_profile]
def should_try_next_profile(error: Exception, profile_index: int, profiles: list[dict[str, str]]) -> bool:
"""Return whether another configured endpoint should be tried after this error."""
if profile_index >= len(profiles) - 1:
return False
if not isinstance(error, NsrdDataRequestError):
return False
return error.status_code == 400 and "No data available at the provided location" in error.response
def fetch_county_summary(
args: argparse.Namespace,
point: dict[str, str],
previous_error_fips: set[str],
api_key: str,
email: str,
rate_limiter: RequestRateLimiter,
) -> tuple[dict[str, str] | None, dict[str, str] | None, list[str]]:
"""Fetch and summarize one county point."""
profiles = build_request_profiles(args, point, previous_error_fips)
final_error: Exception | None = None
messages: list[str] = []
for profile_index, profile in enumerate(profiles):
try:
messages.append(f"Trying {profile['source_label']} ({profile['name']})")
csv_text, source_file = read_or_download_county_csv(
point=point,
endpoint=profile["endpoint"],
api_key=api_key,
email=email,
name=profile["name"],
source_key=profile["source_key"],
attributes=args.attributes,
interval=args.interval,
cache_dir=args.cache_dir,
timeout=args.timeout,
overwrite=args.overwrite,
rate_limiter=rate_limiter,
)
summary = summarize_cloud_metrics(
point=point,
csv_text=csv_text,
source_file=source_file,
source_label=profile["source_label"],
min_clearsky_ghi=args.min_clearsky_ghi,
)
return summary, None, messages
except (OSError, urllib.error.URLError, RuntimeError, ValueError) as error:
final_error = error
if should_try_next_profile(error, profile_index, profiles):
messages.append(f"{profile['source_label']} had no data; trying fallback.")
continue
break
if final_error is None:
final_error = RuntimeError("No NSRDB profiles were available for this county.")
return None, build_error_row(point, final_error), messages
def log_county_result(
index: int,
total: int,
point: dict[str, str],
summary: dict[str, str] | None,
error: dict[str, str] | None,
messages: list[str],
) -> None:
"""Print progress for one completed county."""
label = f"{point['county_fips']} {point['county_name']}, {point['state_abbr']}"
status = "Fetched" if summary is not None else "Skipped"
print(f"[{index}/{total}] {status} {label}")
for message in messages:
print(f" {message}")
if summary is not None:
print(
" "
f"cloudiness={summary['cloudinessIndexPct']}, "
f"clear_ratio={summary['avgObservedToClearskyRatio']}, "
f"daylight_rows={summary['daylightRows']}"
)
if error is not None:
print(f" Error: {error['message']}")
def fetch_batch(
args: argparse.Namespace,
all_points: list[dict[str, str]],
existing_rows_by_fips: dict[str, dict[str, str]],
) -> list[dict[str, str]]:
"""Fetch and summarize the requested county point batch."""
points = select_county_points(
rows=all_points,
start=args.start,
limit=args.limit,
completed_fips=set(existing_rows_by_fips),
overwrite=args.overwrite,
)
skipped_count = len(all_points[args.start :]) - len(
select_county_points(
rows=all_points,
start=args.start,
limit=None,
completed_fips=set(existing_rows_by_fips),
overwrite=args.overwrite,
)
)
if skipped_count and not args.overwrite:
print(f"Skipping {skipped_count} counties already present in {args.output_csv}.")
if not points:
write_error_csv([], args.error_csv)
print("No missing counties selected for fetch.")
return []
email = prompt_for_text("NLR/NREL API email: ", args.email)
api_key = prompt_for_secret("NLR/NREL API key: ", args.api_key)
previous_error_fips = read_previous_error_fips(args.error_csv)
rate_limiter = RequestRateLimiter(args.delay)
summaries_by_index: dict[int, dict[str, str]] = {}
errors_by_index: dict[int, dict[str, str]] = {}
total = len(points)
if args.workers == 1:
for index, point in enumerate(points, start=1):
summary, error, messages = fetch_county_summary(
args=args,
point=point,
previous_error_fips=previous_error_fips,
api_key=api_key,
email=email,
rate_limiter=rate_limiter,
)
if summary is not None:
summaries_by_index[index] = summary
if error is not None:
errors_by_index[index] = error
log_county_result(index, total, point, summary, error, messages)
else:
with concurrent.futures.ThreadPoolExecutor(max_workers=args.workers) as executor:
future_to_context = {
executor.submit(
fetch_county_summary,
args,
point,
previous_error_fips,
api_key,
email,
rate_limiter,
): (index, point)
for index, point in enumerate(points, start=1)
}
for future in concurrent.futures.as_completed(future_to_context):
index, point = future_to_context[future]
summary, error, messages = future.result()
if summary is not None:
summaries_by_index[index] = summary
if error is not None:
errors_by_index[index] = error
log_county_result(index, total, point, summary, error, messages)
errors = [errors_by_index[index] for index in sorted(errors_by_index)]
write_error_csv(errors, args.error_csv)
return [summaries_by_index[index] for index in sorted(summaries_by_index)]
def parse_args() -> argparse.Namespace:
"""Parse command-line arguments."""
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("--points-csv", type=Path, default=DEFAULT_POINTS_CSV)
parser.add_argument("--output-csv", type=Path, default=DEFAULT_OUTPUT_CSV)
parser.add_argument("--error-csv", type=Path, default=DEFAULT_ERROR_CSV)
parser.add_argument("--cache-dir", type=Path, default=DEFAULT_CACHE_DIR)
parser.add_argument("--endpoint", default=DEFAULT_ENDPOINT)
parser.add_argument("--polar-endpoint", default=DEFAULT_POLAR_ENDPOINT)
parser.add_argument("--name", default=DEFAULT_TMY_NAME, help="NSRDB GOES TMY name, such as tmy or tmy-2024.")
parser.add_argument("--polar-name", default=DEFAULT_POLAR_TMY_NAME, help="NSRDB Polar TMY name, usually tmy.")
parser.add_argument("--attributes", default=DEFAULT_ATTRIBUTES, help="Comma-delimited NSRDB attributes to request.")
parser.add_argument("--interval", type=int, default=DEFAULT_INTERVAL, help="NSRDB interval in minutes.")
parser.add_argument("--polar-min-latitude", type=float, default=DEFAULT_POLAR_MIN_LATITUDE)
parser.add_argument(
"--min-clearsky-ghi",
type=float,
default=DEFAULT_MIN_CLEARSKY_GHI,
help="Minimum Clearsky GHI W/m2 for daylight cloudiness ratio rows.",
)
parser.add_argument(
"--no-polar-fallback",
action="store_false",
dest="polar_fallback",
help="Disable retrying failed high-latitude GOES requests against the NSRDB Polar endpoint.",
)
parser.add_argument("--email", help="Email address registered with the NLR/NREL API.")
parser.add_argument("--api-key", help="API key. If omitted, the script prompts securely.")
parser.add_argument("--start", type=int, default=0, help="Zero-based row offset in the points CSV.")
parser.add_argument("--limit", type=int, default=10, help="Number of counties to fetch. Use --all for all counties.")
parser.add_argument("--all", action="store_true", help="Fetch all counties from --start onward.")
parser.add_argument("--delay", type=float, default=1.0, help="Minimum seconds between new API requests.")
parser.add_argument("--workers", type=int, default=4, help="Number of county jobs to run at once.")
parser.add_argument("--timeout", type=int, default=120, help="Request timeout in seconds.")
parser.add_argument("--overwrite", action="store_true", help="Re-download cached county CSV files.")
args = parser.parse_args()
if args.all:
args.limit = None
if args.delay < 0:
parser.error("--delay must be 0 or greater.")
if args.workers < 1:
parser.error("--workers must be 1 or greater.")
if args.interval <= 0:
parser.error("--interval must be greater than 0.")
if args.min_clearsky_ghi < 0:
parser.error("--min-clearsky-ghi must be 0 or greater.")
return args
def main() -> None:
"""Run the NSRDB representative-point cloud metric fetch."""
args = parse_args()
all_points = read_county_points(args.points_csv)
existing_rows_by_fips = read_existing_summary_rows(args.output_csv)
summaries = fetch_batch(args, all_points, existing_rows_by_fips)
output_rows = merged_summary_rows(all_points, existing_rows_by_fips, summaries)
write_summary_csv(output_rows, args.output_csv)
print(
f"Wrote {len(output_rows)} county cloud summaries to {args.output_csv} "
f"({len(summaries)} newly fetched)."
)
if __name__ == "__main__":
main()
scripts/fetch_nsrdb_representative_point_ghi.py
+543
View File
@@ -0,0 +1,543 @@
#!/usr/bin/env python3
"""
Fetch NSRDB GOES TMY GHI data for county representative points.
This is designed for a small first test batch. It prompts for email and API key
when those values are not passed as command-line arguments.
"""
from __future__ import annotations
import argparse
import concurrent.futures
import csv
import getpass
import re
import threading
import time
import urllib.error
import urllib.parse
import urllib.request
from pathlib import Path
DEFAULT_POINTS_CSV = Path("data/nrel/county_representative_points.csv")
DEFAULT_OUTPUT_CSV = Path("data/nrel/county_representative_point_ghi_summary.csv")
DEFAULT_ERROR_CSV = Path("data/nrel/county_representative_point_ghi_error_log.csv")
DEFAULT_CACHE_DIR = Path("data/nrel/representative_point_csv")
DEFAULT_ENDPOINT = "https://developer.nlr.gov/api/nsrdb/v2/solar/nsrdb-GOES-tmy-v4-0-0-download.csv"
DEFAULT_POLAR_ENDPOINT = "https://developer.nlr.gov/api/nsrdb/v2/solar/nsrdb-polar-tmy-v4-0-0-download.csv"
DEFAULT_TMY_NAME = "tmy-2024"
DEFAULT_POLAR_TMY_NAME = "tmy"
DEFAULT_POLAR_MIN_LATITUDE = 60.0
EMAIL_PATTERN = re.compile(r"[\w.!#$%&'*+/=?^`{|}~-]+@[\w-]+(?:\.[\w-]+)+")
SENSITIVE_QUERY_PATTERN = re.compile(r"((?:api_key|email)=)([^&\s,\"']+)", re.IGNORECASE)
def prompt_for_secret(prompt: str, current_value: str | None) -> str:
"""Prompt for a sensitive value only when it was not supplied."""
if current_value:
return current_value
return getpass.getpass(prompt).strip()
def prompt_for_text(prompt: str, current_value: str | None) -> str:
"""Prompt for a normal text value only when it was not supplied."""
if current_value:
return current_value
return input(prompt).strip()
def read_county_points(points_csv: Path, start: int, limit: int | None) -> list[dict[str, str]]:
"""Read the county point CSV and return the requested batch."""
with points_csv.open(newline="", encoding="utf-8") as handle:
rows = list(csv.DictReader(handle))
if start < 0:
raise ValueError("--start must be 0 or greater.")
if limit is None:
return rows[start:]
if limit < 1:
raise ValueError("--limit must be 1 or greater.")
return rows[start : start + limit]
def read_previous_error_fips(error_csv: Path) -> set[str]:
"""Read county FIPS values from a previous error log."""
if not error_csv.exists():
return set()
with error_csv.open(newline="", encoding="utf-8") as handle:
return {
row["county_fips"]
for row in csv.DictReader(handle)
if row.get("county_fips")
}
def is_polar_candidate(point: dict[str, str], min_latitude: float) -> bool:
"""Return whether a point is in the latitude range for the Polar NSRDB endpoint."""
try:
return float(point["lat"]) >= min_latitude
except (KeyError, ValueError):
return False
def build_nsrdb_url(endpoint: str, api_key: str, email: str, point: dict[str, str], name: str) -> str:
"""Build a single-point NSRDB CSV request URL."""
wkt = f"POINT({point['lon']} {point['lat']})"
query = {
"api_key": api_key,
"wkt": wkt,
"attributes": "ghi",
"names": name,
"utc": "false",
"leap_day": "false",
"interval": "60",
"email": email,
}
return f"{endpoint}?{urllib.parse.urlencode(query)}"
def redact_url(url: str) -> str:
"""Return a request URL with sensitive query values removed."""
parsed_url = urllib.parse.urlsplit(url)
query = urllib.parse.parse_qsl(parsed_url.query, keep_blank_values=True)
redacted_query = [
(key, "<redacted>" if key in {"api_key", "email"} else value)
for key, value in query
]
return urllib.parse.urlunsplit(
parsed_url._replace(query=urllib.parse.urlencode(redacted_query))
)
def redact_sensitive_text(text: str) -> str:
"""Remove likely credentials and email addresses from log text."""
without_query_values = SENSITIVE_QUERY_PATTERN.sub(r"\1<redacted>", text)
return EMAIL_PATTERN.sub("<redacted>", without_query_values)
class NsrdDataRequestError(RuntimeError):
"""Store a failed NSRDB request with sanitized context for logging."""
def __init__(self, message: str, status_code: int | None = None, url: str | None = None, response: str = "") -> None:
super().__init__(message)
self.status_code = status_code
self.url = url
self.response = response
class RequestRateLimiter:
"""Coordinate network request starts across worker threads."""
def __init__(self, delay: float) -> None:
self.delay = max(0.0, delay)
self._lock = threading.Lock()
self._next_request_at = 0.0
def wait(self) -> None:
"""Wait until the next request can start."""
if self.delay <= 0:
return
with self._lock:
now = time.monotonic()
wait_seconds = max(0.0, self._next_request_at - now)
self._next_request_at = max(now, self._next_request_at) + self.delay
if wait_seconds:
time.sleep(wait_seconds)
def build_http_request_error(error: urllib.error.HTTPError, url: str) -> NsrdDataRequestError:
"""Create a structured NSRDB request error from an HTTPError."""
body = error.read().decode("utf-8-sig", errors="replace").strip()
body_excerpt = redact_sensitive_text(body[:1000]) if body else "No response body returned."
redacted_url = redact_url(url)
retry_after = error.headers.get("Retry-After") if error.headers else None
retry_message = f"\n Retry-After: {retry_after}" if retry_after else ""
message = f"HTTP {error.code} {error.reason}\n URL: {redacted_url}{retry_message}\n Response: {body_excerpt}"
return NsrdDataRequestError(
message=message,
status_code=error.code,
url=redacted_url,
response=body_excerpt,
)
def download_text(url: str, timeout: int, rate_limiter: RequestRateLimiter | None = None) -> str:
"""Download text from a URL and return its decoded body."""
request = urllib.request.Request(url, headers={"User-Agent": "county-climate-explorer/0.1"})
try:
if rate_limiter is not None:
rate_limiter.wait()
with urllib.request.urlopen(request, timeout=timeout) as response:
return response.read().decode("utf-8-sig")
except urllib.error.HTTPError as error:
raise build_http_request_error(error, url) from error
def read_or_download_county_csv(
point: dict[str, str],
endpoint: str,
api_key: str,
email: str,
name: str,
source_key: str,
cache_dir: Path,
timeout: int,
overwrite: bool,
rate_limiter: RequestRateLimiter | None = None,
) -> tuple[str, Path]:
"""Return cached NSRDB CSV text, downloading it first when needed."""
cache_dir.mkdir(parents=True, exist_ok=True)
cache_path = cache_dir / f"{point['county_fips']}_{source_key}_{name}_ghi.csv"
if cache_path.exists() and not overwrite:
return cache_path.read_text(encoding="utf-8-sig"), cache_path
url = build_nsrdb_url(endpoint, api_key, email, point, name)
csv_text = download_text(url, timeout, rate_limiter)
cache_path.write_text(csv_text, encoding="utf-8")
return csv_text, cache_path
def extract_ghi_values(csv_text: str) -> list[float]:
"""Extract numeric GHI values from an NSRDB CSV response."""
rows = list(csv.reader(csv_text.splitlines()))
header_index = next(
(
index
for index, row in enumerate(rows)
if {"Year", "Month", "Day", "Hour", "Minute", "GHI"}.issubset(set(row))
),
None,
)
if header_index is None:
raise ValueError("Could not find the NSRDB data header row with a GHI column.")
ghi_index = rows[header_index].index("GHI")
ghi_values: list[float] = []
for row in rows[header_index + 1 :]:
if len(row) <= ghi_index or not row[ghi_index].strip():
continue
ghi_values.append(float(row[ghi_index]))
if not ghi_values:
raise ValueError("No GHI values were found in the NSRDB response.")
return ghi_values
def summarize_ghi(point: dict[str, str], csv_text: str, source_file: Path, source_label: str) -> dict[str, str]:
"""Convert hourly GHI values into average daily kWh/m2/day."""
ghi_values = extract_ghi_values(csv_text)
ghi_sum = sum(ghi_values)
avg_daily_ghi = ghi_sum / 1000 / 365
return {
"county_fips": point["county_fips"],
"county_name": point["county_name"],
"state_fips": point["state_fips"],
"state_abbr": point["state_abbr"],
"lat": point["lat"],
"lon": point["lon"],
"avgSolarGhiKwhM2Day": f"{avg_daily_ghi:.3f}",
"ghi_rows": str(len(ghi_values)),
"ghi_min": f"{min(ghi_values):.1f}",
"ghi_max": f"{max(ghi_values):.1f}",
"source": f"{source_label} representative point",
"raw_csv": str(source_file),
}
def write_summary_csv(rows: list[dict[str, str]], output_csv: Path) -> None:
"""Write fetched county solar summaries to CSV."""
output_csv.parent.mkdir(parents=True, exist_ok=True)
with output_csv.open("w", newline="", encoding="utf-8") as handle:
writer = csv.DictWriter(
handle,
fieldnames=[
"county_fips",
"county_name",
"state_fips",
"state_abbr",
"lat",
"lon",
"avgSolarGhiKwhM2Day",
"ghi_rows",
"ghi_min",
"ghi_max",
"source",
"raw_csv",
],
)
writer.writeheader()
writer.writerows(rows)
def write_error_csv(rows: list[dict[str, str]], error_csv: Path) -> None:
"""Write failed county solar fetches to CSV."""
error_csv.parent.mkdir(parents=True, exist_ok=True)
with error_csv.open("w", newline="", encoding="utf-8") as handle:
writer = csv.DictWriter(
handle,
fieldnames=[
"county_fips",
"county_name",
"state_fips",
"state_abbr",
"lat",
"lon",
"error_type",
"status_code",
"request_url",
"response",
"message",
],
)
writer.writeheader()
writer.writerows(rows)
def build_error_row(point: dict[str, str], error: Exception) -> dict[str, str]:
"""Convert a failed county fetch into a structured CSV row."""
status_code = ""
request_url = ""
response = ""
if isinstance(error, NsrdDataRequestError):
status_code = str(error.status_code or "")
request_url = error.url or ""
response = error.response
return {
"county_fips": point["county_fips"],
"county_name": point["county_name"],
"state_fips": point["state_fips"],
"state_abbr": point["state_abbr"],
"lat": point["lat"],
"lon": point["lon"],
"error_type": type(error).__name__,
"status_code": status_code,
"request_url": request_url,
"response": redact_sensitive_text(response),
"message": redact_sensitive_text(str(error)),
}
def build_request_profiles(
args: argparse.Namespace,
point: dict[str, str],
previous_error_fips: set[str],
) -> list[dict[str, str]]:
"""Build the ordered list of NSRDB endpoints to try for a county point."""
goes_profile = {
"source_key": "goes-tmy",
"source_label": "NSRDB GOES TMY PSM v4",
"endpoint": args.endpoint,
"name": args.name,
}
polar_profile = {
"source_key": "polar-tmy",
"source_label": "NSRDB Polar TMY PSM v4",
"endpoint": args.polar_endpoint,
"name": args.polar_name,
}
if not args.polar_fallback or not is_polar_candidate(point, args.polar_min_latitude):
return [goes_profile]
if point["county_fips"] in previous_error_fips:
return [polar_profile, goes_profile]
return [goes_profile, polar_profile]
def should_try_next_profile(error: Exception, profile_index: int, profiles: list[dict[str, str]]) -> bool:
"""Return whether another configured endpoint should be tried after this error."""
if profile_index >= len(profiles) - 1:
return False
if not isinstance(error, NsrdDataRequestError):
return False
return error.status_code == 400 and "No data available at the provided location" in error.response
def fetch_county_summary(
args: argparse.Namespace,
point: dict[str, str],
previous_error_fips: set[str],
api_key: str,
email: str,
rate_limiter: RequestRateLimiter,
) -> tuple[dict[str, str] | None, dict[str, str] | None, list[str]]:
"""Fetch and summarize one county point."""
profiles = build_request_profiles(args, point, previous_error_fips)
final_error: Exception | None = None
messages: list[str] = []
for profile_index, profile in enumerate(profiles):
try:
messages.append(f"Trying {profile['source_label']} ({profile['name']})")
csv_text, source_file = read_or_download_county_csv(
point=point,
endpoint=profile["endpoint"],
api_key=api_key,
email=email,
name=profile["name"],
source_key=profile["source_key"],
cache_dir=args.cache_dir,
timeout=args.timeout,
overwrite=args.overwrite,
rate_limiter=rate_limiter,
)
summary = summarize_ghi(point, csv_text, source_file, profile["source_label"])
return summary, None, messages
except (OSError, urllib.error.URLError, RuntimeError, ValueError) as error:
final_error = error
if should_try_next_profile(error, profile_index, profiles):
messages.append(f"{profile['source_label']} had no data; trying fallback.")
continue
break
if final_error is None:
final_error = RuntimeError("No NSRDB profiles were available for this county.")
return None, build_error_row(point, final_error), messages
def log_county_result(
index: int,
total: int,
point: dict[str, str],
summary: dict[str, str] | None,
error: dict[str, str] | None,
messages: list[str],
) -> None:
"""Print progress for one completed county."""
label = f"{point['county_fips']} {point['county_name']}, {point['state_abbr']}"
status = "Fetched" if summary is not None else "Skipped"
print(f"[{index}/{total}] {status} {label}")
for message in messages:
print(f" {message}")
if error is not None:
print(f" Error: {error['message']}")
def fetch_batch(args: argparse.Namespace) -> list[dict[str, str]]:
"""Fetch and summarize the requested county point batch."""
email = prompt_for_text("NLR/NREL API email: ", args.email)
api_key = prompt_for_secret("NLR/NREL API key: ", args.api_key)
points = read_county_points(args.points_csv, args.start, args.limit)
previous_error_fips = read_previous_error_fips(args.error_csv)
rate_limiter = RequestRateLimiter(args.delay)
summaries_by_index: dict[int, dict[str, str]] = {}
errors_by_index: dict[int, dict[str, str]] = {}
total = len(points)
if args.workers == 1:
for index, point in enumerate(points, start=1):
summary, error, messages = fetch_county_summary(
args=args,
point=point,
previous_error_fips=previous_error_fips,
api_key=api_key,
email=email,
rate_limiter=rate_limiter,
)
if summary is not None:
summaries_by_index[index] = summary
if error is not None:
errors_by_index[index] = error
log_county_result(index, total, point, summary, error, messages)
else:
with concurrent.futures.ThreadPoolExecutor(max_workers=args.workers) as executor:
future_to_context = {
executor.submit(
fetch_county_summary,
args,
point,
previous_error_fips,
api_key,
email,
rate_limiter,
): (index, point)
for index, point in enumerate(points, start=1)
}
for future in concurrent.futures.as_completed(future_to_context):
index, point = future_to_context[future]
summary, error, messages = future.result()
if summary is not None:
summaries_by_index[index] = summary
if error is not None:
errors_by_index[index] = error
log_county_result(index, total, point, summary, error, messages)
errors = [errors_by_index[index] for index in sorted(errors_by_index)]
write_error_csv(errors, args.error_csv)
return [summaries_by_index[index] for index in sorted(summaries_by_index)]
def parse_args() -> argparse.Namespace:
"""Parse command-line arguments."""
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("--points-csv", type=Path, default=DEFAULT_POINTS_CSV)
parser.add_argument("--output-csv", type=Path, default=DEFAULT_OUTPUT_CSV)
parser.add_argument("--error-csv", type=Path, default=DEFAULT_ERROR_CSV)
parser.add_argument("--representative-point-csv-dir", "--cache-dir", dest="cache_dir", type=Path, default=DEFAULT_CACHE_DIR)
parser.add_argument("--endpoint", default=DEFAULT_ENDPOINT)
parser.add_argument("--polar-endpoint", default=DEFAULT_POLAR_ENDPOINT)
parser.add_argument("--name", default=DEFAULT_TMY_NAME, help="NSRDB TMY name, such as tmy or tmy-2024.")
parser.add_argument("--polar-name", default=DEFAULT_POLAR_TMY_NAME, help="NSRDB Polar TMY name, usually tmy.")
parser.add_argument("--polar-min-latitude", type=float, default=DEFAULT_POLAR_MIN_LATITUDE)
parser.add_argument(
"--no-polar-fallback",
action="store_false",
dest="polar_fallback",
help="Disable retrying failed high-latitude GOES requests against the NSRDB Polar endpoint.",
)
parser.add_argument("--email", help="Email address registered with the NLR/NREL API.")
parser.add_argument("--api-key", help="API key. If omitted, the script prompts securely.")
parser.add_argument("--start", type=int, default=0, help="Zero-based row offset in the points CSV.")
parser.add_argument("--limit", type=int, default=10, help="Number of counties to fetch for the test batch.")
parser.add_argument(
"--delay",
type=float,
default=1.0,
help="Minimum seconds between new API requests. Cached files do not wait.",
)
parser.add_argument(
"--workers",
type=int,
default=4,
help="Number of county jobs to run at once. Set to 1 for the old sequential behavior.",
)
parser.add_argument("--timeout", type=int, default=120, help="Request timeout in seconds.")
parser.add_argument("--overwrite", action="store_true", help="Re-download cached county CSV files.")
args = parser.parse_args()
if args.delay < 0:
parser.error("--delay must be 0 or greater.")
if args.workers < 1:
parser.error("--workers must be 1 or greater.")
return args
def main() -> None:
"""Run the NSRDB point-fetch test batch."""
args = parse_args()
summaries = fetch_batch(args)
write_summary_csv(summaries, args.output_csv)
print(f"Wrote {len(summaries)} solar summaries to {args.output_csv}")
if __name__ == "__main__":
main()
scripts/rebuild_nsrdb_representative_point_ghi_summary.py
+163
View File
@@ -0,0 +1,163 @@
#!/usr/bin/env python3
"""
Rebuild county representative-point GHI summaries from cached NSRDB raw CSV responses.
This does not call the NSRDB API. It reads data/nrel/representative_point_csv/*.csv, computes:
avgSolarGhiKwhM2Day = sum(hourly GHI) / 1000 / 365
and writes a county-keyed CSV compatible with build_county_climate_data.py.
"""
from __future__ import annotations
import argparse
import csv
from pathlib import Path
DEFAULT_POINTS_CSV = Path("data/nrel/county_representative_points.csv")
DEFAULT_REPRESENTATIVE_POINT_CSV_DIR = Path("data/nrel/representative_point_csv")
DEFAULT_OUTPUT_CSV = Path("data/nrel/county_representative_point_ghi_summary.csv")
def read_county_points(points_csv: Path) -> list[dict[str, str]]:
"""Read county representative points keyed by county FIPS."""
with points_csv.open(newline="", encoding="utf-8") as handle:
return list(csv.DictReader(handle))
def extract_ghi_values(csv_path: Path) -> list[float]:
"""Extract numeric hourly GHI values from a cached NSRDB CSV response."""
with csv_path.open(newline="", encoding="utf-8-sig") as handle:
reader = csv.reader(handle)
ghi_index: int | None = None
values: list[float] = []
for row in reader:
if ghi_index is None:
if {"Year", "Month", "Day", "Hour", "Minute", "GHI"}.issubset(set(row)):
ghi_index = row.index("GHI")
continue
if len(row) <= ghi_index or not row[ghi_index].strip():
continue
values.append(float(row[ghi_index]))
if ghi_index is None:
raise ValueError(f"Could not find NSRDB data header with a GHI column in {csv_path}.")
if not values:
raise ValueError(f"No GHI values were found in {csv_path}.")
return values
def select_raw_csv(representative_point_csv_dir: Path, county_fips: str) -> Path | None:
"""Return the cached raw CSV for a county, preferring polar data when both exist."""
matches = sorted(representative_point_csv_dir.glob(f"{county_fips}_*_ghi.csv"))
if not matches:
return None
polar_matches = [path for path in matches if "_polar-tmy_" in path.name]
return polar_matches[0] if polar_matches else matches[0]
def source_label(raw_csv: Path) -> str:
"""Return a readable source label from the cached filename."""
if "_polar-tmy_" in raw_csv.name:
return "NSRDB Polar TMY PSM v4 representative point"
if "_goes-tmy_" in raw_csv.name:
return "NSRDB GOES TMY PSM v4 representative point"
return "NSRDB TMY representative point"
def summarize_county(point: dict[str, str], raw_csv: Path) -> dict[str, str]:
"""Summarize one county raw CSV into the app solar metric."""
ghi_values = extract_ghi_values(raw_csv)
avg_daily_ghi = sum(ghi_values) / 1000 / 365
return {
"county_fips": point["county_fips"],
"county_name": point["county_name"],
"state_fips": point["state_fips"],
"state_abbr": point["state_abbr"],
"lat": point["lat"],
"lon": point["lon"],
"avgSolarGhiKwhM2Day": f"{avg_daily_ghi:.3f}",
"ghi_rows": str(len(ghi_values)),
"ghi_min": f"{min(ghi_values):.1f}",
"ghi_max": f"{max(ghi_values):.1f}",
"source": source_label(raw_csv),
"raw_csv": str(raw_csv),
}
def write_summary_csv(rows: list[dict[str, str]], output_csv: Path) -> None:
"""Write rebuilt county solar summaries."""
output_csv.parent.mkdir(parents=True, exist_ok=True)
with output_csv.open("w", newline="", encoding="utf-8") as handle:
writer = csv.DictWriter(
handle,
fieldnames=[
"county_fips",
"county_name",
"state_fips",
"state_abbr",
"lat",
"lon",
"avgSolarGhiKwhM2Day",
"ghi_rows",
"ghi_min",
"ghi_max",
"source",
"raw_csv",
],
)
writer.writeheader()
writer.writerows(rows)
def parse_args() -> argparse.Namespace:
"""Parse command-line arguments."""
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("--points-csv", type=Path, default=DEFAULT_POINTS_CSV)
parser.add_argument(
"--representative-point-csv-dir",
dest="representative_point_csv_dir",
type=Path,
default=DEFAULT_REPRESENTATIVE_POINT_CSV_DIR,
)
parser.add_argument("--output-csv", type=Path, default=DEFAULT_OUTPUT_CSV)
return parser.parse_args()
def main() -> None:
"""Run the cached raw CSV summarizer."""
args = parse_args()
rows: list[dict[str, str]] = []
missing: list[str] = []
failed: list[str] = []
for point in read_county_points(args.points_csv):
county_fips = point["county_fips"]
raw_csv = select_raw_csv(args.representative_point_csv_dir, county_fips)
if raw_csv is None:
missing.append(county_fips)
continue
try:
rows.append(summarize_county(point, raw_csv))
except (OSError, ValueError) as exc:
failed.append(f"{county_fips}: {exc}")
write_summary_csv(rows, args.output_csv)
print(f"Wrote {len(rows)} county representative-point solar summaries to {args.output_csv}")
if missing:
print(f"Missing raw CSVs for {len(missing)} counties: {', '.join(missing[:20])}")
if failed:
print(f"Failed to summarize {len(failed)} counties:")
for message in failed[:20]:
print(f" {message}")
if __name__ == "__main__":
main()
scripts/request_nsrdb_county_polygon_archives.py
+1696
View File
File diff suppressed because it is too large Load Diff
scripts/request_nsrdb_county_polygon_cloud_archives.py
+44
View File
@@ -0,0 +1,44 @@
#!/usr/bin/env python3
"""
Submit NSRDB polygon archive requests for county-average cloudiness inputs.
This is a cloud-specific wrapper around request_nsrdb_county_polygon_archives.py.
It reuses the existing polygon tiling, site-count, Polar fallback, pacing, and
manifest logic, but writes to separate cloud request/response files and requests:
ghi,clearsky_ghi,cloud_type
"""
from __future__ import annotations
import sys
import request_nsrdb_county_polygon_archives as polygon_request
DEFAULT_ARGS = [
"--requests-csv",
"data/nrel/county_polygon_cloud_request_manifest.csv",
"--error-csv",
"data/nrel/county_polygon_cloud_error_log.csv",
"--response-dir",
"data/nrel/polygon_cloud_request_responses",
"--artifact-label",
"cloud",
"--legacy-artifact-label",
"ghi",
"--attributes",
"ghi,clearsky_ghi,cloud_type",
]
def main() -> None:
"""Run the existing polygon requester with cloud-specific defaults."""
polygon_request.main(
[*DEFAULT_ARGS, *sys.argv[1:]],
description=__doc__,
)
if __name__ == "__main__":
main()
scripts/request_nsrdb_county_polygon_ghi_archives.py
+40
View File
@@ -0,0 +1,40 @@
#!/usr/bin/env python3
"""
Submit NSRDB polygon archive requests for county-average GHI.
This is a GHI-specific wrapper around request_nsrdb_county_polygon_archives.py.
It reuses the shared state machine, polygon tiling, site-count, Polar fallback,
pacing, and manifest logic with GHI-specific defaults.
"""
from __future__ import annotations
import sys
import request_nsrdb_county_polygon_archives as polygon_request
DEFAULT_ARGS = [
"--requests-csv",
"data/nrel/county_polygon_ghi_request_manifest.csv",
"--error-csv",
"data/nrel/county_polygon_ghi_error_log.csv",
"--response-dir",
"data/nrel/polygon_request_responses",
"--artifact-label",
"ghi",
"--attributes",
"ghi",
]
def main() -> None:
"""Run the shared polygon requester with GHI-specific defaults."""
polygon_request.main(
[*DEFAULT_ARGS, *sys.argv[1:]],
description=__doc__,
)
if __name__ == "__main__":
main()
scripts/requirements_county_etl.txt
+9
View File
@@ -0,0 +1,9 @@
geopandas>=0.14
numpy>=1.26
pandas>=2.2
xarray>=2024.2.0
affine>=2.4
rasterio>=1.5
netcdf4>=1.7
h5netcdf>=1.6
h5py>=3.12
scripts/summarize_county_gridmet_humidity.py
+690
View File
@@ -0,0 +1,690 @@
#!/usr/bin/env python3
"""
Aggregate downloaded gridMET humidity/heat files to county-level metrics.
Expected input layout:
data/gridmet/<year>/sph.nc
data/gridmet/<year>/rmax.nc
data/gridmet/<year>/rmin.nc
Default output:
data/gridmet/county_gridmet_humidity.csv
"""
from __future__ import annotations
import argparse
import csv
import math
from collections.abc import Sequence
from dataclasses import dataclass
from pathlib import Path
import geopandas as gpd
import numpy as np
import pandas as pd
import xarray as xr
STATE_FIPS_TO_ABBR = {
"01": "AL",
"04": "AZ",
"05": "AR",
"06": "CA",
"08": "CO",
"09": "CT",
"10": "DE",
"11": "DC",
"12": "FL",
"13": "GA",
"16": "ID",
"17": "IL",
"18": "IN",
"19": "IA",
"20": "KS",
"21": "KY",
"22": "LA",
"23": "ME",
"24": "MD",
"25": "MA",
"26": "MI",
"27": "MN",
"28": "MS",
"29": "MO",
"30": "MT",
"31": "NE",
"32": "NV",
"33": "NH",
"34": "NJ",
"35": "NM",
"36": "NY",
"37": "NC",
"38": "ND",
"39": "OH",
"40": "OK",
"41": "OR",
"42": "PA",
"44": "RI",
"45": "SC",
"46": "SD",
"47": "TN",
"48": "TX",
"49": "UT",
"50": "VT",
"51": "VA",
"53": "WA",
"54": "WV",
"55": "WI",
"56": "WY",
}
CONUS_STATE_FIPS = set(STATE_FIPS_TO_ABBR)
REQUIRED_VARIABLES = ("sph", "rmax", "rmin")
SUMMER_MONTHS = {6, 7, 8}
NOAA_REGION_CODE_TO_FIPS_OVERRIDES = {
"18511": "11001",
}
NOAA_TMAX_SOURCE_FIPS_OVERRIDES = {
"46113": (
"46102",
"Shannon County, SD changed name/code to Oglala Lakota County, SD effective 2015-05-01.",
),
"51515": (
"51019",
"Bedford independent city, VA changed to town status and was added to Bedford County effective 2013-07-01.",
),
"51678": (
"51163",
"Lexington independent city, VA uses surrounding Rockbridge County, VA as NOAA tmax proxy because NOAA county daily files do not include Lexington city.",
),
}
@dataclass(frozen=True)
class CountyGridMap:
counties: gpd.GeoDataFrame
pixel_indices: np.ndarray
county_indices: np.ndarray
weights: np.ndarray
sorted_pixel_indices: np.ndarray
sorted_county_indices: np.ndarray
sorted_weights: np.ndarray
group_starts: np.ndarray
group_county_indices: np.ndarray
lat_dim: str
lon_dim: str
@dataclass
class YearData:
datasets: list[xr.Dataset]
arrays: dict[str, xr.DataArray]
def _normalize_fips(value: object, width: int = 5) -> str:
text = str(value).strip()
digits = "".join(ch for ch in text if ch.isdigit())
return digits.zfill(width)[-width:] if digits else ""
def _load_state_crosswalk(path: Path) -> dict[str, str]:
if not path.exists():
print(
f"State crosswalk not found at {path}. Falling back to the first two "
"NOAA region-code digits as state FIPS."
)
return {}
rows = list(csv.reader(path.open("r", encoding="utf-8-sig", newline="")))
if not rows:
return {}
header = [cell.strip().lower() for cell in rows[0]]
ncei_idx = next((idx for idx, cell in enumerate(header) if "ncei" in cell and "code" in cell), None)
fips_idx = next((idx for idx, cell in enumerate(header) if "fips" in cell and "code" in cell), None)
data_rows = rows[1:] if ncei_idx is not None and fips_idx is not None else rows
mapping: dict[str, str] = {}
for row in data_rows:
if ncei_idx is not None and fips_idx is not None:
if len(row) <= max(ncei_idx, fips_idx):
continue
ncei = _normalize_fips(row[ncei_idx], 2)
fips = _normalize_fips(row[fips_idx], 2)
else:
codes = [_normalize_fips(cell, 2) for cell in row]
codes = [code for code in codes if code]
if len(codes) < 2:
continue
ncei, fips = codes[0], codes[1]
if ncei and fips:
mapping[ncei] = fips
return mapping
def _county_fips_from_noaa_region(region_code: object, state_crosswalk: dict[str, str]) -> str:
code = _normalize_fips(region_code, 5)
if code in NOAA_REGION_CODE_TO_FIPS_OVERRIDES:
return NOAA_REGION_CODE_TO_FIPS_OVERRIDES[code]
state_fips = state_crosswalk.get(code[:2], code[:2])
return f"{state_fips}{code[-3:]}" if state_fips else ""
def _load_counties(path: Path) -> gpd.GeoDataFrame:
counties = gpd.read_file(path)
if counties.crs is None:
counties = counties.set_crs("EPSG:4326")
else:
counties = counties.to_crs("EPSG:4326")
if "id" in counties.columns:
fips = counties["id"]
elif "GEOID" in counties.columns:
fips = counties["GEOID"]
elif "GEOID10" in counties.columns:
fips = counties["GEOID10"]
else:
raise ValueError("County GeoJSON needs an id, GEOID, or GEOID10 column.")
counties["countyFips"] = fips.map(_normalize_fips)
counties["stateFips"] = counties["countyFips"].str.slice(0, 2)
counties = counties[counties["stateFips"].isin(CONUS_STATE_FIPS)].copy()
counties["countyName"] = counties.get("NAME", counties["countyFips"]).astype(str)
counties["state"] = counties["stateFips"].map(STATE_FIPS_TO_ABBR)
counties = counties.sort_values("countyFips").reset_index(drop=True)
counties["countyIndex"] = np.arange(len(counties), dtype=np.int32)
return counties
def _find_dimension(dataset: xr.Dataset, candidates: tuple[str, ...]) -> str:
for candidate in candidates:
if candidate in dataset.dims or candidate in dataset.coords:
return candidate
lower_lookup = {name.lower(): name for name in set(dataset.dims) | set(dataset.coords)}
for candidate in candidates:
if candidate.lower() in lower_lookup:
return lower_lookup[candidate.lower()]
raise ValueError(f"Unable to find one of these dimensions: {', '.join(candidates)}")
def _select_variable(dataset: xr.Dataset, preferred: str) -> str:
if preferred in dataset.data_vars:
return preferred
for name in dataset.data_vars:
if name.lower() == preferred.lower():
return name
if len(dataset.data_vars) == 1:
return next(iter(dataset.data_vars))
raise ValueError(f"Unable to select variable {preferred}; found {list(dataset.data_vars)}")
def _year_folder(path: Path) -> int | None:
try:
return int(path.name)
except ValueError:
return None
def _discover_complete_years(gridmet_dir: Path) -> list[int]:
years: list[int] = []
for child in sorted(gridmet_dir.iterdir()):
if not child.is_dir():
continue
year = _year_folder(child)
if year is None:
continue
if all((child / f"{variable}.nc").exists() for variable in REQUIRED_VARIABLES):
years.append(year)
return years
def _load_noaa_tmax_month(
noaa_tmax_dir: Path,
year: int,
month: int,
state_crosswalk: dict[str, str],
) -> dict[str, list[float]]:
path = noaa_tmax_dir / str(year) / f"tmax-{year}{month:02d}-cty-scaled.csv"
if not path.exists():
return {}
values: dict[str, list[float]] = {}
with path.open("r", encoding="utf-8-sig", newline="") as handle:
reader = csv.reader(handle)
for row in reader:
if len(row) < 7 or row[0].strip().lower() != "cty":
continue
county_fips = _county_fips_from_noaa_region(row[1], state_crosswalk)
day_values: list[float] = []
for raw_value in row[6:]:
try:
value = float(raw_value)
except ValueError:
day_values.append(math.nan)
continue
day_values.append(value if value > -999 else math.nan)
values[county_fips] = day_values
return values
def _noaa_tmax_for_date(
*,
date: pd.Timestamp,
county_fips: Sequence[str],
noaa_tmax_dir: Path,
state_crosswalk: dict[str, str],
month_cache: dict[tuple[int, int], dict[str, list[float]]],
) -> np.ndarray:
cache_key = (int(date.year), int(date.month))
if cache_key not in month_cache:
month_cache[cache_key] = _load_noaa_tmax_month(
noaa_tmax_dir,
int(date.year),
int(date.month),
state_crosswalk,
)
month_values = month_cache[cache_key]
result = np.full(len(county_fips), np.nan, dtype=np.float64)
day_offset = int(date.day) - 1
for index, fips in enumerate(county_fips):
source_fips = NOAA_TMAX_SOURCE_FIPS_OVERRIDES.get(fips, (fips, ""))[0]
values = month_values.get(source_fips)
if values is not None and day_offset < len(values):
result[index] = values[day_offset]
return result
def _build_county_grid_map(counties: gpd.GeoDataFrame, sample_file: Path) -> CountyGridMap:
with xr.open_dataset(sample_file) as dataset:
lat_dim = _find_dimension(dataset, ("lat", "latitude", "y"))
lon_dim = _find_dimension(dataset, ("lon", "longitude", "x"))
lat_values = np.asarray(dataset[lat_dim].values)
lon_values = np.asarray(dataset[lon_dim].values)
if lat_values.ndim != 1 or lon_values.ndim != 1:
raise ValueError("This script expects 1D latitude and longitude coordinates.")
lon_grid, lat_grid = np.meshgrid(lon_values, lat_values)
flat_lats = lat_grid.ravel()
flat_lons = lon_grid.ravel()
flat_indices = np.arange(flat_lats.size, dtype=np.int64)
bounds = counties.total_bounds
in_bounds = (
(flat_lons >= bounds[0] - 0.25)
& (flat_lats >= bounds[1] - 0.25)
& (flat_lons <= bounds[2] + 0.25)
& (flat_lats <= bounds[3] + 0.25)
)
point_frame = gpd.GeoDataFrame(
{
"pixelIndex": flat_indices[in_bounds],
"lat": flat_lats[in_bounds],
},
geometry=gpd.points_from_xy(flat_lons[in_bounds], flat_lats[in_bounds]),
crs="EPSG:4326",
)
joined = gpd.sjoin(
point_frame,
counties[["countyIndex", "geometry"]],
how="inner",
predicate="within",
)
joined = joined.drop_duplicates(subset=["pixelIndex", "countyIndex"])
pixel_indices = joined["pixelIndex"].to_numpy(dtype=np.int64)
county_indices = joined["countyIndex"].to_numpy(dtype=np.int32)
weights = np.cos(np.deg2rad(joined["lat"].to_numpy(dtype=np.float64)))
mapped_counties = set(county_indices.tolist())
fallback_pixels: list[int] = []
fallback_counties: list[int] = []
fallback_weights: list[float] = []
for county_index, geometry in enumerate(counties.geometry):
if county_index in mapped_counties or geometry.is_empty:
continue
point = geometry.representative_point()
lon_position = int(np.argmin(np.abs(lon_values - point.x)))
lat_position = int(np.argmin(np.abs(lat_values - point.y)))
flat_index = lat_position * len(lon_values) + lon_position
fallback_pixels.append(flat_index)
fallback_counties.append(county_index)
fallback_weights.append(float(math.cos(math.radians(float(lat_values[lat_position])))))
if fallback_pixels:
pixel_indices = np.concatenate([pixel_indices, np.asarray(fallback_pixels, dtype=np.int64)])
county_indices = np.concatenate([county_indices, np.asarray(fallback_counties, dtype=np.int32)])
weights = np.concatenate([weights, np.asarray(fallback_weights, dtype=np.float64)])
print(
f"mapped {len(np.unique(county_indices)):,} counties to {len(pixel_indices):,} grid cells "
f"({len(fallback_pixels):,} nearest-cell fallback counties)"
)
sort_order = np.argsort(county_indices, kind="stable")
sorted_county_indices = county_indices[sort_order]
group_starts = np.r_[0, np.flatnonzero(np.diff(sorted_county_indices)) + 1]
group_county_indices = sorted_county_indices[group_starts]
return CountyGridMap(
counties=counties,
pixel_indices=pixel_indices,
county_indices=county_indices,
weights=weights,
sorted_pixel_indices=pixel_indices[sort_order],
sorted_county_indices=sorted_county_indices,
sorted_weights=weights[sort_order],
group_starts=group_starts,
group_county_indices=group_county_indices,
lat_dim=lat_dim,
lon_dim=lon_dim,
)
def _county_means(
data_array: xr.DataArray,
time_index: int,
time_dim: str,
county_map: CountyGridMap,
) -> np.ndarray:
data = data_array.isel({time_dim: time_index}).transpose(county_map.lat_dim, county_map.lon_dim)
flat = np.asarray(data.values, dtype=np.float64).ravel()
values = flat[county_map.pixel_indices]
valid = np.isfinite(values)
county_count = len(county_map.counties)
sums = np.bincount(
county_map.county_indices[valid],
weights=values[valid] * county_map.weights[valid],
minlength=county_count,
)
weight_sums = np.bincount(
county_map.county_indices[valid],
weights=county_map.weights[valid],
minlength=county_count,
)
means = np.full(county_count, np.nan, dtype=np.float64)
np.divide(sums, weight_sums, out=means, where=weight_sums > 0)
return means
def _county_means_chunk(
data_array: xr.DataArray,
start_index: int,
end_index: int,
time_dim: str,
county_map: CountyGridMap,
) -> np.ndarray:
data = data_array.isel({time_dim: slice(start_index, end_index)}).transpose(
time_dim,
county_map.lat_dim,
county_map.lon_dim,
)
raw = np.asarray(data.values, dtype=np.float64)
selected = raw.reshape(raw.shape[0], -1)[:, county_map.sorted_pixel_indices]
valid = np.isfinite(selected)
weighted_values = np.where(valid, selected * county_map.sorted_weights, 0.0)
weight_values = np.where(valid, county_map.sorted_weights, 0.0)
sums = np.add.reduceat(weighted_values, county_map.group_starts, axis=1)
weight_sums = np.add.reduceat(weight_values, county_map.group_starts, axis=1)
grouped_means = np.full_like(sums, np.nan, dtype=np.float64)
np.divide(sums, weight_sums, out=grouped_means, where=weight_sums > 0)
means = np.full((raw.shape[0], len(county_map.counties)), np.nan, dtype=np.float64)
means[:, county_map.group_county_indices] = grouped_means
return means
def _heat_index_f(t_f: np.ndarray, rh_pct: np.ndarray) -> np.ndarray:
rh = np.clip(rh_pct, 0, 100)
heat_index = (
-42.379
+ 2.04901523 * t_f
+ 10.14333127 * rh
- 0.22475541 * t_f * rh
- 0.00683783 * t_f * t_f
- 0.05481717 * rh * rh
+ 0.00122874 * t_f * t_f * rh
+ 0.00085282 * t_f * rh * rh
- 0.00000199 * t_f * t_f * rh * rh
)
low_rh_adjustment = ((13 - rh) / 4) * np.sqrt(np.maximum((17 - np.abs(t_f - 95)) / 17, 0))
high_rh_adjustment = ((rh - 85) / 10) * ((87 - t_f) / 5)
heat_index = np.where((rh < 13) & (80 <= t_f) & (t_f <= 112), heat_index - low_rh_adjustment, heat_index)
heat_index = np.where((rh > 85) & (80 <= t_f) & (t_f <= 87), heat_index + high_rh_adjustment, heat_index)
return np.where(t_f >= 80, heat_index, t_f)
def _time_dimension(data_array: xr.DataArray, lat_dim: str, lon_dim: str) -> str:
candidates = [dim for dim in data_array.dims if dim not in {lat_dim, lon_dim}]
if not candidates:
raise ValueError(f"No time dimension found for {data_array.name}.")
return candidates[0]
def _open_year_datasets(gridmet_dir: Path, year: int) -> YearData:
datasets: list[xr.Dataset] = []
arrays: dict[str, xr.DataArray] = {}
for variable in REQUIRED_VARIABLES:
dataset = xr.open_dataset(gridmet_dir / str(year) / f"{variable}.nc")
datasets.append(dataset)
variable_name = _select_variable(dataset, variable)
arrays[variable] = dataset[variable_name]
return YearData(datasets=datasets, arrays=arrays)
def _close_year_datasets(year_data: YearData) -> None:
for dataset in year_data.datasets:
try:
dataset.close()
except Exception:
pass
def _round_or_blank(value: float, digits: int) -> str:
if not np.isfinite(value):
return ""
return str(round(float(value), digits))
def summarize(args: argparse.Namespace) -> None:
years = args.years or _discover_complete_years(args.gridmet_dir)
if not years:
raise FileNotFoundError(
f"No complete gridMET years found in {args.gridmet_dir}. "
"Run scripts/download_gridmet_data.py first."
)
if args.years is None:
start = args.start_year if args.start_year is not None else 1991
end = args.end_year if args.end_year is not None else 2020
years = [year for year in years if start <= year <= end]
elif args.start_year is not None or args.end_year is not None:
start = args.start_year if args.start_year is not None else min(years)
end = args.end_year if args.end_year is not None else max(years)
years = [year for year in years if start <= year <= end]
if not years:
raise FileNotFoundError("No complete gridMET years matched the requested year filters.")
sample_file = args.gridmet_dir / str(years[0]) / "sph.nc"
counties = _load_counties(args.counties_geojson)
county_map = _build_county_grid_map(counties, sample_file)
county_count = len(county_map.counties)
county_fips = county_map.counties["countyFips"].astype(str).tolist()
state_crosswalk = _load_state_crosswalk(args.state_crosswalk)
noaa_month_cache: dict[tuple[int, int], dict[str, list[float]]] = {}
annual_sph_sum = np.zeros(county_count, dtype=np.float64)
annual_sph_count = np.zeros(county_count, dtype=np.float64)
summer_sph_sum = np.zeros(county_count, dtype=np.float64)
summer_sph_count = np.zeros(county_count, dtype=np.float64)
annual_rh_sum = np.zeros(county_count, dtype=np.float64)
annual_rh_count = np.zeros(county_count, dtype=np.float64)
summer_rh_sum = np.zeros(county_count, dtype=np.float64)
summer_rh_count = np.zeros(county_count, dtype=np.float64)
heat_day_sum = np.zeros(county_count, dtype=np.float64)
years_with_heat_data = np.zeros(county_count, dtype=np.float64)
for year in years:
print(f"process {year}")
year_data = _open_year_datasets(args.gridmet_dir, year)
arrays = year_data.arrays
try:
time_dim = _time_dimension(arrays["sph"], county_map.lat_dim, county_map.lon_dim)
dates = pd.to_datetime(arrays["sph"][time_dim].values)
yearly_heat_days = np.zeros(county_count, dtype=np.float64)
yearly_heat_valid_days = np.zeros(county_count, dtype=np.float64)
for chunk_start in range(0, len(dates), args.chunk_days):
chunk_end = min(chunk_start + args.chunk_days, len(dates))
chunk_dates = dates[chunk_start:chunk_end]
sph_chunk = _county_means_chunk(arrays["sph"], chunk_start, chunk_end, time_dim, county_map) * 1000
rmax_chunk = _county_means_chunk(arrays["rmax"], chunk_start, chunk_end, time_dim, county_map)
rmin_chunk = _county_means_chunk(arrays["rmin"], chunk_start, chunk_end, time_dim, county_map)
for offset, date in enumerate(chunk_dates):
sph = sph_chunk[offset]
rmax = rmax_chunk[offset]
rmin = rmin_chunk[offset]
tmax_f = _noaa_tmax_for_date(
date=date,
county_fips=county_fips,
noaa_tmax_dir=args.noaa_tmax_dir,
state_crosswalk=state_crosswalk,
month_cache=noaa_month_cache,
) * 9 / 5 + 32
rh_mean = (rmax + rmin) / 2
annual_sph_valid = np.isfinite(sph)
annual_rh_valid = np.isfinite(rh_mean)
annual_sph_sum[annual_sph_valid] += sph[annual_sph_valid]
annual_sph_count[annual_sph_valid] += 1
annual_rh_sum[annual_rh_valid] += rh_mean[annual_rh_valid]
annual_rh_count[annual_rh_valid] += 1
if int(date.month) in SUMMER_MONTHS:
summer_sph_sum[annual_sph_valid] += sph[annual_sph_valid]
summer_sph_count[annual_sph_valid] += 1
summer_rh_sum[annual_rh_valid] += rh_mean[annual_rh_valid]
summer_rh_count[annual_rh_valid] += 1
heat_valid = np.isfinite(tmax_f) & np.isfinite(rmin)
heat_index = _heat_index_f(tmax_f, rmin)
yearly_heat_days[heat_valid] += heat_index[heat_valid] >= args.heat_index_threshold_f
yearly_heat_valid_days[heat_valid] += 1
has_heat_year = yearly_heat_valid_days > 0
heat_day_sum[has_heat_year] += yearly_heat_days[has_heat_year]
years_with_heat_data[has_heat_year] += 1
finally:
_close_year_datasets(year_data)
avg_sph = np.divide(annual_sph_sum, annual_sph_count, out=np.full(county_count, np.nan), where=annual_sph_count > 0)
avg_summer_sph = np.divide(
summer_sph_sum,
summer_sph_count,
out=np.full(county_count, np.nan),
where=summer_sph_count > 0,
)
avg_rh = np.divide(annual_rh_sum, annual_rh_count, out=np.full(county_count, np.nan), where=annual_rh_count > 0)
avg_summer_rh = np.divide(
summer_rh_sum,
summer_rh_count,
out=np.full(county_count, np.nan),
where=summer_rh_count > 0,
)
humid_heat_days = np.divide(
heat_day_sum,
years_with_heat_data,
out=np.full(county_count, np.nan),
where=years_with_heat_data > 0,
)
source_period = f"{min(years)}-{max(years)}" if len(years) > 1 else str(years[0])
args.output.parent.mkdir(parents=True, exist_ok=True)
with args.output.open("w", newline="", encoding="utf-8") as handle:
writer = csv.DictWriter(
handle,
fieldnames=[
"countyFips",
"countyName",
"state",
"avgSpecificHumidityGKg",
"avgSummerSpecificHumidityGKg",
"avgRelHumidityPct",
"avgSummerRelHumidityPct",
"humidHeatDays",
"humidHeatSourceFips",
"humidHeatFipsAdjustment",
"gridmetAnalysisYears",
"gridmetSource",
],
)
writer.writeheader()
for index, county in county_map.counties.iterrows():
writer.writerow(
{
"countyFips": county["countyFips"],
"countyName": county["countyName"],
"state": county["state"],
"avgSpecificHumidityGKg": _round_or_blank(avg_sph[index], 3),
"avgSummerSpecificHumidityGKg": _round_or_blank(avg_summer_sph[index], 3),
"avgRelHumidityPct": _round_or_blank(avg_rh[index], 2),
"avgSummerRelHumidityPct": _round_or_blank(avg_summer_rh[index], 2),
"humidHeatDays": _round_or_blank(humid_heat_days[index], 2),
"humidHeatSourceFips": NOAA_TMAX_SOURCE_FIPS_OVERRIDES.get(
county["countyFips"],
(county["countyFips"], ""),
)[0],
"humidHeatFipsAdjustment": NOAA_TMAX_SOURCE_FIPS_OVERRIDES.get(
county["countyFips"],
("", ""),
)[1],
"gridmetAnalysisYears": len(years),
"gridmetSource": (
f"gridmet-{source_period} county-cell-weighted; "
"relative-humidity=(rmax+rmin)/2; "
"humidHeatDays=noaa-nclimgrid-tmax+gridmet-rmin heat-index-gte-90f"
),
}
)
print(f"wrote {args.output}")
def _parse_years(text: str) -> list[int]:
years: set[int] = set()
for part in text.split(","):
token = part.strip()
if not token:
continue
if "-" in token:
start_text, end_text = token.split("-", 1)
years.update(range(int(start_text), int(end_text) + 1))
else:
years.add(int(token))
return sorted(years)
def main() -> int:
parser = argparse.ArgumentParser(
description="Summarize downloaded gridMET humidity files into county-level CSV metrics."
)
parser.add_argument("--gridmet-dir", type=Path, default=Path("data/gridmet"))
parser.add_argument("--noaa-tmax-dir", type=Path, default=Path("data/noaa/tmax_cty_scaled"))
parser.add_argument("--state-crosswalk", type=Path, default=Path("data/noaa/nclimgrid/us-state-codes_ncei-to-fips.csv"))
parser.add_argument("--counties-geojson", type=Path, default=Path("data/geojson-counties-fips.json"))
parser.add_argument("--output", type=Path, default=Path("data/gridmet/county_gridmet_humidity.csv"))
parser.add_argument("--years", type=_parse_years, default=None, help="Optional comma/range years, e.g. 1991-2020.")
parser.add_argument("--start-year", type=int, default=None)
parser.add_argument("--end-year", type=int, default=None)
parser.add_argument("--heat-index-threshold-f", type=float, default=90.0)
parser.add_argument("--chunk-days", type=int, default=31)
summarize(parser.parse_args())
return 0
if __name__ == "__main__":
raise SystemExit(main())
scripts/summarize_nsrdb_county_polygon_archives.py
+614
View File
@@ -0,0 +1,614 @@
#!/usr/bin/env python3
"""
Summarize downloaded NSRDB county polygon GHI archives.
Each downloaded polygon archive contains one CSV per NSRDB site that intersects
the county polygon or tile. This script computes area-weighted county-level
average daily GHI values across those site CSVs, combining multiple tile
archives back into one county summary when present.
"""
from __future__ import annotations
import argparse
import csv
import json
import math
import statistics
import zipfile
from pathlib import Path
DEFAULT_ARCHIVE_DIR = Path("data/nrel/polygon_archives")
DEFAULT_COUNTIES_GEOJSON = Path("data/geojson-counties-fips.json")
DEFAULT_REQUESTS_CSV = Path("data/nrel/county_polygon_ghi_request_manifest.csv")
DEFAULT_REPRESENTATIVE_POINT_CSV = Path("data/nrel/county_representative_point_ghi_summary.csv")
DEFAULT_OUTPUT_CSV = Path("data/nrel/county_polygon_ghi_summary.csv")
DEFAULT_CELL_SIZE_M = 4000.0
DEFAULT_ARCHIVE_GLOB = "*_ghi.zip"
EARTH_RADIUS_M = 6_371_008.8
SUMMARY_FIELDS = [
"county_fips",
"county_name",
"state_abbr",
"archive_zip",
"polygon_sites",
"request_site_count",
"ghi_rows_per_site_min",
"ghi_rows_per_site_max",
"avgSolarGhiKwhM2Day",
"areaWeightedAvgSolarGhiKwhM2Day",
"areaWeightedSites",
"weightedCellAreaKm2",
"countyAreaKm2",
"site_avg_min",
"site_avg_max",
"site_avg_stddev",
"representativePointAvgSolarGhiKwhM2Day",
"areaWeightedMinusRepresentativePoint",
"areaWeightedPctDiffFromRepresentativePoint",
]
def read_lookup(csv_path: Path, key_field: str) -> dict[str, dict[str, str]]:
"""Read a CSV into a dictionary keyed by one field."""
if not csv_path.exists():
return {}
with csv_path.open(newline="", encoding="utf-8-sig") as handle:
return {
row[key_field]: row
for row in csv.DictReader(handle)
if row.get(key_field)
}
def read_grouped_lookup(csv_path: Path, key_field: str) -> dict[str, list[dict[str, str]]]:
"""Read a CSV into lists of rows keyed by one field."""
rows_by_key: dict[str, list[dict[str, str]]] = {}
if not csv_path.exists():
return rows_by_key
with csv_path.open(newline="", encoding="utf-8-sig") as handle:
for row in csv.DictReader(handle):
key = row.get(key_field)
if key:
rows_by_key.setdefault(key, []).append(row)
return rows_by_key
def county_fips_from_archive(path: Path) -> str:
"""Extract the county FIPS prefix from an archive filename."""
return path.name.split("_", 1)[0]
def archive_groups_by_county(archives: list[Path]) -> dict[str, list[Path]]:
"""Group archive ZIP paths by county FIPS."""
grouped: dict[str, list[Path]] = {}
for archive in archives:
grouped.setdefault(county_fips_from_archive(archive), []).append(archive)
return grouped
def normalize_fips(value: object, width: int) -> str:
"""Return a zero-padded FIPS string from a mixed text or numeric value."""
digits = "".join(character for character in str(value).strip() if character.isdigit())
return digits.zfill(width)[-width:] if digits else ""
def load_county_geometries(counties_geojson: Path) -> dict[str, list[list[list[tuple[float, float]]]]]:
"""Load county polygon rings from GeoJSON without third-party GIS dependencies."""
with counties_geojson.open(encoding="utf-8") as handle:
geojson = json.load(handle)
county_geometries: dict[str, list[list[list[tuple[float, float]]]]] = {}
for feature in geojson.get("features", []):
properties = feature.get("properties", {})
county_fips = normalize_fips(properties.get("id"), 5)
if not county_fips:
county_fips = normalize_fips(properties.get("STATE"), 2) + normalize_fips(properties.get("COUNTY"), 3)
geometry = feature.get("geometry") or {}
polygons = geometry_polygons(geometry)
if county_fips and polygons:
county_geometries[county_fips] = polygons
return county_geometries
def geometry_polygons(geometry: dict[str, object]) -> list[list[list[tuple[float, float]]]]:
"""Return GeoJSON Polygon/MultiPolygon coordinates as polygon rings."""
geometry_type = geometry.get("type")
coordinates = geometry.get("coordinates")
if not isinstance(coordinates, list):
return []
if geometry_type == "Polygon":
return [coordinates_to_polygon(coordinates)]
if geometry_type == "MultiPolygon":
return [coordinates_to_polygon(polygon) for polygon in coordinates]
return []
def coordinates_to_polygon(coordinates: list[object]) -> list[list[tuple[float, float]]]:
"""Convert raw GeoJSON polygon coordinates to typed rings."""
polygon: list[list[tuple[float, float]]] = []
for ring in coordinates:
polygon.append([(float(point[0]), float(point[1])) for point in ring])
return polygon
def extract_site_lon_lat(csv_text: str) -> tuple[float, float]:
"""Extract the NSRDB site longitude and latitude from CSV metadata rows."""
rows = list(csv.reader(csv_text.splitlines()))
if len(rows) < 2:
raise ValueError("Could not read NSRDB metadata rows.")
metadata = {key.strip().lower(): value.strip() for key, value in zip(rows[0], rows[1])}
try:
lon = float(metadata["longitude"])
lat = float(metadata["latitude"])
except KeyError as error:
raise ValueError("Could not find Longitude/Latitude metadata in NSRDB CSV.") from error
except ValueError as error:
raise ValueError("NSRDB Longitude/Latitude metadata is not numeric.") from error
return lon, lat
def extract_ghi_values(csv_text: str) -> list[float]:
"""Extract numeric GHI values from an NSRDB CSV response."""
rows = list(csv.reader(csv_text.splitlines()))
header_index = next(
(
index
for index, row in enumerate(rows)
if {"Year", "Month", "Day", "Hour", "Minute", "GHI"}.issubset(set(row))
),
None,
)
if header_index is None:
raise ValueError("Could not find the NSRDB data header row with a GHI column.")
ghi_index = rows[header_index].index("GHI")
ghi_values: list[float] = []
for row in rows[header_index + 1 :]:
if len(row) <= ghi_index or not row[ghi_index].strip():
continue
ghi_values.append(float(row[ghi_index]))
if not ghi_values:
raise ValueError("No GHI values were found in the NSRDB response.")
return ghi_values
def site_average_daily_ghi(csv_text: str) -> tuple[float, int]:
"""Return average daily GHI in kWh/m2/day and number of GHI rows."""
ghi_values = extract_ghi_values(csv_text)
return sum(ghi_values) / 1000 / 365, len(ghi_values)
def average_geometry_latitude(county_geometry: list[list[list[tuple[float, float]]]]) -> float:
"""Return a representative latitude for local meter projection."""
latitudes = [
lat
for polygon in county_geometry
for ring in polygon[:1]
for _lon, lat in ring
]
if not latitudes:
return 0.0
return statistics.fmean(latitudes)
def project_lon_lat(lon: float, lat: float, reference_lat: float) -> tuple[float, float]:
"""Project lon/lat to local meters with an equirectangular approximation."""
reference_lat_radians = math.radians(reference_lat)
x = EARTH_RADIUS_M * math.radians(lon) * math.cos(reference_lat_radians)
y = EARTH_RADIUS_M * math.radians(lat)
return x, y
def project_county_geometry(
county_geometry: list[list[list[tuple[float, float]]]],
reference_lat: float,
) -> list[list[list[tuple[float, float]]]]:
"""Project county polygon rings to local meter coordinates."""
return [
[
[project_lon_lat(lon, lat, reference_lat) for lon, lat in ring]
for ring in polygon
]
for polygon in county_geometry
]
def polygon_area(points: list[tuple[float, float]]) -> float:
"""Return absolute polygon area using the shoelace formula."""
if len(points) < 3:
return 0.0
area = 0.0
for index, (x1, y1) in enumerate(points):
x2, y2 = points[(index + 1) % len(points)]
area += x1 * y2 - x2 * y1
return abs(area) / 2
def remove_closing_point(points: list[tuple[float, float]]) -> list[tuple[float, float]]:
"""Remove duplicate final point before polygon clipping."""
if len(points) > 1 and points[0] == points[-1]:
return points[:-1]
return points
def clip_ring_to_rectangle(
ring: list[tuple[float, float]],
min_x: float,
min_y: float,
max_x: float,
max_y: float,
) -> list[tuple[float, float]]:
"""Clip a polygon ring to an axis-aligned rectangle."""
points = remove_closing_point(ring)
def clip_edge(
input_points: list[tuple[float, float]],
inside: object,
intersect: object,
) -> list[tuple[float, float]]:
if not input_points:
return []
output_points: list[tuple[float, float]] = []
previous = input_points[-1]
previous_inside = inside(previous)
for current in input_points:
current_inside = inside(current)
if current_inside:
if not previous_inside:
output_points.append(intersect(previous, current))
output_points.append(current)
elif previous_inside:
output_points.append(intersect(previous, current))
previous = current
previous_inside = current_inside
return output_points
def vertical_intersection(x_value: float, start: tuple[float, float], end: tuple[float, float]) -> tuple[float, float]:
x1, y1 = start
x2, y2 = end
if x2 == x1:
return x_value, y1
ratio = (x_value - x1) / (x2 - x1)
return x_value, y1 + ratio * (y2 - y1)
def horizontal_intersection(y_value: float, start: tuple[float, float], end: tuple[float, float]) -> tuple[float, float]:
x1, y1 = start
x2, y2 = end
if y2 == y1:
return x1, y_value
ratio = (y_value - y1) / (y2 - y1)
return x1 + ratio * (x2 - x1), y_value
points = clip_edge(points, lambda point: point[0] >= min_x, lambda start, end: vertical_intersection(min_x, start, end))
points = clip_edge(points, lambda point: point[0] <= max_x, lambda start, end: vertical_intersection(max_x, start, end))
points = clip_edge(points, lambda point: point[1] >= min_y, lambda start, end: horizontal_intersection(min_y, start, end))
points = clip_edge(points, lambda point: point[1] <= max_y, lambda start, end: horizontal_intersection(max_y, start, end))
return points
def projected_polygon_area(polygon: list[list[tuple[float, float]]]) -> float:
"""Return projected polygon area, subtracting interior rings."""
if not polygon:
return 0.0
area = polygon_area(polygon[0])
for hole in polygon[1:]:
area -= polygon_area(hole)
return max(0.0, area)
def clipped_projected_polygon_area(
polygon: list[list[tuple[float, float]]],
min_x: float,
min_y: float,
max_x: float,
max_y: float,
) -> float:
"""Return projected polygon area inside a rectangle, subtracting holes."""
if not polygon:
return 0.0
clipped_exterior = clip_ring_to_rectangle(polygon[0], min_x, min_y, max_x, max_y)
area = polygon_area(clipped_exterior)
for hole in polygon[1:]:
clipped_hole = clip_ring_to_rectangle(hole, min_x, min_y, max_x, max_y)
area -= polygon_area(clipped_hole)
return max(0.0, area)
def area_weighted_average(
site_averages: list[float],
site_lon_lats: list[tuple[float, float]],
county_geometry: list[list[list[tuple[float, float]]]] | None,
cell_size_m: float,
) -> dict[str, float | int]:
"""Compute a county average weighted by estimated grid-cell overlap area."""
if county_geometry is None:
return {
"area_weighted_avg": math.nan,
"area_weighted_sites": 0,
"weighted_cell_area_km2": math.nan,
"county_area_km2": math.nan,
}
reference_lat = average_geometry_latitude(county_geometry)
projected_county = project_county_geometry(county_geometry, reference_lat)
half_cell = cell_size_m / 2
weighted_sum = 0.0
total_weight = 0.0
weighted_sites = 0
county_area = sum(projected_polygon_area(polygon) for polygon in projected_county)
for site_average, (lon, lat) in zip(site_averages, site_lon_lats):
x, y = project_lon_lat(lon, lat, reference_lat)
min_x = x - half_cell
min_y = y - half_cell
max_x = x + half_cell
max_y = y + half_cell
overlap_area = sum(
clipped_projected_polygon_area(polygon, min_x, min_y, max_x, max_y)
for polygon in projected_county
)
if overlap_area <= 0:
continue
weighted_sum += site_average * overlap_area
total_weight += overlap_area
weighted_sites += 1
area_weighted_avg = weighted_sum / total_weight if total_weight else math.nan
return {
"area_weighted_avg": area_weighted_avg,
"area_weighted_sites": weighted_sites,
"weighted_cell_area_km2": total_weight / 1_000_000,
"county_area_km2": county_area / 1_000_000,
}
def summarize_archives(
paths: list[Path],
county_geometry: list[list[list[tuple[float, float]]]] | None,
cell_size_m: float,
) -> dict[str, float | int | str]:
"""Summarize all NSRDB site CSVs in one or more ZIP archives."""
site_averages: list[float] = []
site_lon_lats: list[tuple[float, float]] = []
row_counts: list[int] = []
for path in paths:
with zipfile.ZipFile(path) as archive:
csv_names = sorted(name for name in archive.namelist() if name.lower().endswith(".csv"))
for csv_name in csv_names:
csv_text = archive.read(csv_name).decode("utf-8-sig")
site_average, row_count = site_average_daily_ghi(csv_text)
site_lon_lat = extract_site_lon_lat(csv_text)
site_averages.append(site_average)
site_lon_lats.append(site_lon_lat)
row_counts.append(row_count)
if not site_averages:
raise ValueError(f"No CSV files found in {', '.join(str(path) for path in paths)}")
weighted = area_weighted_average(site_averages, site_lon_lats, county_geometry, cell_size_m)
return {
"polygon_sites": len(site_averages),
"ghi_rows_per_site_min": min(row_counts),
"ghi_rows_per_site_max": max(row_counts),
"avgSolarGhiKwhM2Day": weighted["area_weighted_avg"],
"area_weighted_avg": weighted["area_weighted_avg"],
"area_weighted_sites": weighted["area_weighted_sites"],
"weighted_cell_area_km2": weighted["weighted_cell_area_km2"],
"county_area_km2": weighted["county_area_km2"],
"site_avg_min": min(site_averages),
"site_avg_max": max(site_averages),
"site_avg_stddev": statistics.pstdev(site_averages) if len(site_averages) > 1 else 0.0,
}
def summarize_archive(
path: Path,
county_geometry: list[list[list[tuple[float, float]]]] | None,
cell_size_m: float,
) -> dict[str, float | int | str]:
"""Summarize all NSRDB site CSVs in one ZIP archive."""
return summarize_archives([path], county_geometry, cell_size_m)
def format_float(value: float | None, places: int = 3) -> str:
"""Format an optional float for CSV output."""
if value is None or math.isnan(value):
return ""
return f"{value:.{places}f}"
def build_summary_row(
archive_paths: list[Path],
polygon_summary: dict[str, float | int | str],
request_rows: list[dict[str, str]],
representative_point_row: dict[str, str],
) -> dict[str, str]:
"""Build one output row from polygon and optional representative-point summaries."""
county_fips = county_fips_from_archive(archive_paths[0])
request_row = request_rows[0] if request_rows else {}
request_site_counts = [
int(row["site_count"])
for row in request_rows
if str(row.get("site_count", "")).strip().isdigit()
]
archive_zip = ";".join(str(path) for path in archive_paths)
final_avg = float(polygon_summary["avgSolarGhiKwhM2Day"])
area_weighted_avg = float(polygon_summary["area_weighted_avg"])
representative_point_avg = (
float(representative_point_row["avgSolarGhiKwhM2Day"])
if representative_point_row.get("avgSolarGhiKwhM2Day")
else None
)
weighted_minus_representative_point = (
area_weighted_avg - representative_point_avg if representative_point_avg is not None else None
)
weighted_pct_diff_representative_point = (
weighted_minus_representative_point / representative_point_avg * 100
if representative_point_avg not in (None, 0)
else None
)
return {
"county_fips": county_fips,
"county_name": request_row.get("county_name") or representative_point_row.get("county_name", ""),
"state_abbr": request_row.get("state_abbr") or representative_point_row.get("state_abbr", ""),
"archive_zip": archive_zip,
"polygon_sites": str(polygon_summary["polygon_sites"]),
"request_site_count": str(sum(request_site_counts)) if request_site_counts else request_row.get("site_count", ""),
"ghi_rows_per_site_min": str(polygon_summary["ghi_rows_per_site_min"]),
"ghi_rows_per_site_max": str(polygon_summary["ghi_rows_per_site_max"]),
"avgSolarGhiKwhM2Day": format_float(final_avg),
"areaWeightedAvgSolarGhiKwhM2Day": format_float(area_weighted_avg),
"areaWeightedSites": str(polygon_summary["area_weighted_sites"]),
"weightedCellAreaKm2": format_float(float(polygon_summary["weighted_cell_area_km2"]), 1),
"countyAreaKm2": format_float(float(polygon_summary["county_area_km2"]), 1),
"site_avg_min": format_float(float(polygon_summary["site_avg_min"])),
"site_avg_max": format_float(float(polygon_summary["site_avg_max"])),
"site_avg_stddev": format_float(float(polygon_summary["site_avg_stddev"])),
"representativePointAvgSolarGhiKwhM2Day": format_float(representative_point_avg),
"areaWeightedMinusRepresentativePoint": format_float(weighted_minus_representative_point),
"areaWeightedPctDiffFromRepresentativePoint": format_float(weighted_pct_diff_representative_point),
}
def archive_signature(paths: list[Path]) -> set[str]:
"""Return archive filenames for comparing existing summary rows."""
return {path.name for path in paths}
def existing_archive_signature(row: dict[str, str]) -> set[str]:
"""Return archive filenames recorded in an existing summary row."""
return {
Path(path_text).name
for path_text in row.get("archive_zip", "").split(";")
if path_text.strip()
}
def write_summary(rows: list[dict[str, str]], output_csv: Path) -> None:
"""Write polygon GHI summary rows to disk."""
output_csv.parent.mkdir(parents=True, exist_ok=True)
with output_csv.open("w", newline="", encoding="utf-8") as handle:
writer = csv.DictWriter(handle, fieldnames=SUMMARY_FIELDS)
writer.writeheader()
writer.writerows(rows)
def run(args: argparse.Namespace) -> None:
"""Summarize downloaded polygon archives."""
county_geometries = load_county_geometries(args.counties_geojson)
request_rows = read_grouped_lookup(args.requests_csv, "county_fips")
representative_point_rows = read_lookup(args.representative_point_csv, "county_fips")
existing_rows = (
read_lookup(args.output_csv, "county_fips")
if args.reuse_existing_output
else {}
)
archives = sorted(args.archive_dir.glob(args.archive_glob))
if not archives:
print(f"No archives matched {args.archive_dir / args.archive_glob}")
return
rows: list[dict[str, str]] = []
archive_groups = archive_groups_by_county(archives)
total = len(archive_groups)
reused_count = 0
for index, county_fips in enumerate(sorted(archive_groups), start=1):
archive_paths = sorted(archive_groups[county_fips])
existing_row = existing_rows.get(county_fips)
if existing_row and existing_archive_signature(existing_row) == archive_signature(archive_paths):
rows.append({field: existing_row.get(field, "") for field in SUMMARY_FIELDS})
reused_count += 1
continue
try:
polygon_summary = summarize_archives(
archive_paths,
county_geometries.get(county_fips),
args.cell_size_m,
)
row = build_summary_row(
archive_paths,
polygon_summary,
request_rows.get(county_fips, []),
representative_point_rows.get(county_fips, {}),
)
rows.append(row)
except (OSError, ValueError, zipfile.BadZipFile) as error:
print(f"[{index}/{total}] Failed {county_fips}: {error}")
continue
tile_note = f", archives={len(archive_paths)}" if len(archive_paths) > 1 else ""
print(
f"[{index}/{total}] {county_fips}: "
f"sites={row['polygon_sites']}, weighted={row['areaWeightedAvgSolarGhiKwhM2Day']}, "
f"representative_point={row['representativePointAvgSolarGhiKwhM2Day'] or 'n/a'}"
f"{tile_note}"
)
write_summary(rows, args.output_csv)
if reused_count:
print(f"Reused {reused_count} existing rows whose archive sets still match.")
print(f"Wrote {len(rows)} rows to {args.output_csv}")
def parse_args() -> argparse.Namespace:
"""Parse command-line arguments."""
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("--archive-dir", type=Path, default=DEFAULT_ARCHIVE_DIR)
parser.add_argument("--archive-glob", default=DEFAULT_ARCHIVE_GLOB)
parser.add_argument("--counties-geojson", type=Path, default=DEFAULT_COUNTIES_GEOJSON)
parser.add_argument("--requests-csv", type=Path, default=DEFAULT_REQUESTS_CSV)
parser.add_argument(
"--representative-point-csv",
type=Path,
default=DEFAULT_REPRESENTATIVE_POINT_CSV,
help="County representative-point GHI summary CSV.",
)
parser.add_argument("--output-csv", type=Path, default=DEFAULT_OUTPUT_CSV)
parser.add_argument(
"--cell-size-m",
type=float,
default=DEFAULT_CELL_SIZE_M,
help="Estimated NSRDB grid-cell side length in meters. GOES TMY is 4 km.",
)
parser.add_argument(
"--reuse-existing-output",
action="store_true",
help=(
"Reuse rows already present in --output-csv when the recorded archive filenames "
"match the current archive directory, and summarize only missing or changed counties."
),
)
args = parser.parse_args()
if args.cell_size_m <= 0:
parser.error("--cell-size-m must be greater than 0.")
return args
def main() -> None:
"""Run the polygon GHI summarizer."""
run(parse_args())
if __name__ == "__main__":
main()
scripts/summarize_nsrdb_county_polygon_cloud_archives.py
+527
View File
@@ -0,0 +1,527 @@
#!/usr/bin/env python3
"""
Summarize downloaded NSRDB county polygon cloud archives.
Each downloaded polygon archive contains one CSV per NSRDB grid site that
intersects the county polygon or tile. This script computes area-weighted
county-level cloudiness metrics across those site CSVs, combining multiple tile
archives back into one county summary when present.
Primary metric:
cloudinessIndexPct = 1 - mean(clamped(GHI / Clearsky GHI, 0, 1))
Despite the legacy "Pct" field name, the primary index is stored on a 0-1 scale.
Cloud Type bucket fields are stored as percentages.
"""
from __future__ import annotations
import argparse
import csv
import math
import re
import statistics
import zipfile
from pathlib import Path
from summarize_nsrdb_county_polygon_archives import (
area_weighted_average,
archive_groups_by_county,
archive_signature,
county_fips_from_archive,
existing_archive_signature,
extract_site_lon_lat,
format_float,
load_county_geometries,
read_grouped_lookup,
read_lookup,
)
DEFAULT_ARCHIVE_DIR = Path("data/nrel/polygon_cloud_archives")
DEFAULT_COUNTIES_GEOJSON = Path("data/geojson-counties-fips.json")
DEFAULT_REQUESTS_CSV = Path("data/nrel/county_polygon_cloud_request_manifest.csv")
DEFAULT_REPRESENTATIVE_POINT_CSV = Path("data/nrel/county_representative_point_cloud_summary.csv")
DEFAULT_OUTPUT_CSV = Path("data/nrel/county_polygon_cloud_summary.csv")
DEFAULT_CELL_SIZE_M = 4000.0
DEFAULT_ARCHIVE_GLOB = "*.zip"
DEFAULT_MIN_CLEARSKY_GHI = 50.0
SUMMARY_FIELDS = [
"county_fips",
"county_name",
"state_abbr",
"archive_zip",
"polygon_sites",
"request_site_count",
"rows_per_site_min",
"rows_per_site_max",
"daylight_rows_per_site_min",
"daylight_rows_per_site_max",
"cloudinessIndexPct",
"areaWeightedCloudinessIndexPct",
"areaWeightedAvgObservedToClearskyRatio",
"areaWeightedSites",
"weightedCellAreaKm2",
"countyAreaKm2",
"site_cloudiness_min",
"site_cloudiness_max",
"site_cloudiness_stddev",
"clearOrProbablyClearPct",
"cloudyOrObscuredPct",
"fogPct",
"waterCloudPct",
"iceCloudPct",
"cirrusPct",
"unknownCloudTypePct",
"representativePointCloudinessIndexPct",
"areaWeightedMinusRepresentativePoint",
"areaWeightedPctDiffFromRepresentativePoint",
]
def normalized_header(value: str) -> str:
"""Normalize a CSV header to make NSRDB spelling variations easier to match."""
return re.sub(r"[^a-z0-9]+", "", value.lower())
def find_column(header: list[str], candidates: set[str]) -> int | None:
"""Return the first header index whose normalized name matches a candidate."""
normalized_candidates = {normalized_header(candidate) for candidate in candidates}
for index, value in enumerate(header):
if normalized_header(value) in normalized_candidates:
return index
return None
def find_data_header(rows: list[list[str]]) -> int | None:
"""Return the NSRDB hourly data header row index."""
required = {"Year", "Month", "Day", "Hour", "Minute"}
for index, row in enumerate(rows):
if required.issubset(set(row)):
return index
return None
def parse_optional_float(row: list[str], index: int | None) -> float | None:
"""Parse an optional float field from a CSV row."""
if index is None or len(row) <= index:
return None
value = row[index].strip()
if not value:
return None
try:
parsed = float(value)
except ValueError:
return None
return parsed if math.isfinite(parsed) else None
def parse_cloud_type(row: list[str], index: int | None) -> str:
"""Parse an optional Cloud Type code as a stable string."""
if index is None or len(row) <= index:
return ""
value = row[index].strip()
if not value:
return ""
try:
return str(int(float(value)))
except ValueError:
return value
def pct(count: int, total: int) -> float:
"""Return a percentage or NaN when there is no denominator."""
return count / total * 100 if total else math.nan
def site_cloud_metrics(csv_text: str, min_clearsky_ghi: float) -> dict[str, float | int]:
"""Return site-level cloudiness metrics from one NSRDB CSV response."""
rows = list(csv.reader(csv_text.splitlines()))
header_index = find_data_header(rows)
if header_index is None:
raise ValueError("Could not find the NSRDB data header row.")
header = rows[header_index]
ghi_index = find_column(header, {"GHI", "ghi"})
clearsky_ghi_index = find_column(
header,
{
"Clearsky GHI",
"Clear Sky GHI",
"Clear-sky GHI",
"clearsky_ghi",
"clear_sky_ghi",
},
)
cloud_type_index = find_column(header, {"Cloud Type", "cloud_type", "cloudtype"})
if ghi_index is None:
raise ValueError("Could not find a GHI column in the NSRDB response.")
if clearsky_ghi_index is None:
raise ValueError("Could not find a Clearsky GHI column in the NSRDB response.")
if cloud_type_index is None:
raise ValueError("Could not find a Cloud Type column in the NSRDB response.")
all_rows = 0
daylight_rows = 0
ratio_sum = 0.0
daylight_cloud_type_counts: dict[str, int] = {}
for row in rows[header_index + 1 :]:
if not row:
continue
all_rows += 1
ghi = parse_optional_float(row, ghi_index)
clearsky_ghi = parse_optional_float(row, clearsky_ghi_index)
cloud_type = parse_cloud_type(row, cloud_type_index)
if ghi is None or clearsky_ghi is None or clearsky_ghi < min_clearsky_ghi:
continue
ratio_sum += min(1.0, max(0.0, ghi / clearsky_ghi))
daylight_rows += 1
if cloud_type:
daylight_cloud_type_counts[cloud_type] = daylight_cloud_type_counts.get(cloud_type, 0) + 1
if daylight_rows == 0:
raise ValueError("No daylight rows with valid GHI and Clearsky GHI were found.")
avg_ratio = ratio_sum / daylight_rows
cloudiness = 1 - avg_ratio
clear_or_probably_clear = daylight_cloud_type_counts.get("0", 0) + daylight_cloud_type_counts.get("1", 0)
cloudy_or_obscured = sum(
daylight_cloud_type_counts.get(code, 0)
for code in ["2", "3", "4", "5", "6", "7", "8", "9", "11", "12"]
)
water_cloud = (
daylight_cloud_type_counts.get("3", 0)
+ daylight_cloud_type_counts.get("4", 0)
+ daylight_cloud_type_counts.get("5", 0)
)
ice_cloud = (
daylight_cloud_type_counts.get("6", 0)
+ daylight_cloud_type_counts.get("8", 0)
+ daylight_cloud_type_counts.get("9", 0)
)
unknown_cloud_type = daylight_cloud_type_counts.get("10", 0) + daylight_cloud_type_counts.get("-15", 0)
return {
"cloudiness": cloudiness,
"avg_ratio": avg_ratio,
"all_rows": all_rows,
"daylight_rows": daylight_rows,
"clear_or_probably_clear_pct": pct(clear_or_probably_clear, daylight_rows),
"cloudy_or_obscured_pct": pct(cloudy_or_obscured, daylight_rows),
"fog_pct": pct(daylight_cloud_type_counts.get("2", 0), daylight_rows),
"water_cloud_pct": pct(water_cloud, daylight_rows),
"ice_cloud_pct": pct(ice_cloud, daylight_rows),
"cirrus_pct": pct(daylight_cloud_type_counts.get("7", 0), daylight_rows),
"unknown_cloud_type_pct": pct(unknown_cloud_type, daylight_rows),
}
def weighted_metric(
site_metrics: list[dict[str, float | int]],
metric_key: str,
site_lon_lats: list[tuple[float, float]],
county_geometry: list[list[list[tuple[float, float]]]] | None,
cell_size_m: float,
) -> dict[str, float | int]:
"""Area-weight one metric across sites using estimated grid-cell overlap."""
values = [float(metrics[metric_key]) for metrics in site_metrics]
return area_weighted_average(values, site_lon_lats, county_geometry, cell_size_m)
def summarize_archives(
paths: list[Path],
county_geometry: list[list[list[tuple[float, float]]]] | None,
cell_size_m: float,
min_clearsky_ghi: float,
) -> dict[str, float | int]:
"""Summarize all NSRDB site CSVs in one or more ZIP archives."""
site_metrics: list[dict[str, float | int]] = []
site_lon_lats: list[tuple[float, float]] = []
empty_csv_members: list[str] = []
for path in paths:
with zipfile.ZipFile(path) as archive:
bad_member = archive.testzip()
if bad_member:
raise zipfile.BadZipFile(
f"CRC check failed for {bad_member} in {path.name}"
)
csv_names = sorted(name for name in archive.namelist() if name.lower().endswith(".csv"))
for csv_name in csv_names:
csv_text = archive.read(csv_name).decode("utf-8-sig")
if not csv_text.strip():
empty_csv_members.append(f"{path.name}:{csv_name}")
continue
site_metrics.append(site_cloud_metrics(csv_text, min_clearsky_ghi))
site_lon_lats.append(extract_site_lon_lat(csv_text))
if not site_metrics:
raise ValueError(f"No CSV files found in {', '.join(str(path) for path in paths)}")
cloudiness_values = [float(metrics["cloudiness"]) for metrics in site_metrics]
row_counts = [int(metrics["all_rows"]) for metrics in site_metrics]
daylight_row_counts = [int(metrics["daylight_rows"]) for metrics in site_metrics]
weighted_cloudiness = weighted_metric(site_metrics, "cloudiness", site_lon_lats, county_geometry, cell_size_m)
weighted_avg_ratio = weighted_metric(site_metrics, "avg_ratio", site_lon_lats, county_geometry, cell_size_m)
return {
"polygon_sites": len(site_metrics),
"rows_per_site_min": min(row_counts),
"rows_per_site_max": max(row_counts),
"daylight_rows_per_site_min": min(daylight_row_counts),
"daylight_rows_per_site_max": max(daylight_row_counts),
"area_weighted_cloudiness": weighted_cloudiness["area_weighted_avg"],
"area_weighted_avg_ratio": weighted_avg_ratio["area_weighted_avg"],
"area_weighted_sites": weighted_cloudiness["area_weighted_sites"],
"weighted_cell_area_km2": weighted_cloudiness["weighted_cell_area_km2"],
"county_area_km2": weighted_cloudiness["county_area_km2"],
"site_cloudiness_min": min(cloudiness_values),
"site_cloudiness_max": max(cloudiness_values),
"site_cloudiness_stddev": statistics.pstdev(cloudiness_values) if len(cloudiness_values) > 1 else 0.0,
"clear_or_probably_clear_pct": weighted_metric(
site_metrics, "clear_or_probably_clear_pct", site_lon_lats, county_geometry, cell_size_m
)["area_weighted_avg"],
"cloudy_or_obscured_pct": weighted_metric(
site_metrics, "cloudy_or_obscured_pct", site_lon_lats, county_geometry, cell_size_m
)["area_weighted_avg"],
"fog_pct": weighted_metric(site_metrics, "fog_pct", site_lon_lats, county_geometry, cell_size_m)[
"area_weighted_avg"
],
"water_cloud_pct": weighted_metric(
site_metrics, "water_cloud_pct", site_lon_lats, county_geometry, cell_size_m
)["area_weighted_avg"],
"ice_cloud_pct": weighted_metric(site_metrics, "ice_cloud_pct", site_lon_lats, county_geometry, cell_size_m)[
"area_weighted_avg"
],
"cirrus_pct": weighted_metric(site_metrics, "cirrus_pct", site_lon_lats, county_geometry, cell_size_m)[
"area_weighted_avg"
],
"unknown_cloud_type_pct": weighted_metric(
site_metrics, "unknown_cloud_type_pct", site_lon_lats, county_geometry, cell_size_m
)["area_weighted_avg"],
"empty_csv_members": len(empty_csv_members),
}
def archive_part_id(path: Path) -> str:
"""Return county or tileNNN for one downloaded archive filename."""
parts = path.stem.split("_")
return parts[1] if len(parts) > 1 and parts[1].startswith("tile") else "county"
def missing_archive_parts(
archive_paths: list[Path],
request_rows: list[dict[str, str]],
) -> list[str]:
"""Return requested county/tile archive parts that are not downloaded."""
expected = {
row.get("tile_id", "").strip() or "county"
for row in request_rows
if row.get("download_url", "").strip()
}
actual = {archive_part_id(path) for path in archive_paths}
return sorted(expected - actual)
def build_summary_row(
archive_paths: list[Path],
polygon_summary: dict[str, float | int],
request_rows: list[dict[str, str]],
representative_point_row: dict[str, str],
) -> dict[str, str]:
"""Build one output row from polygon and optional representative-point summaries."""
county_fips = county_fips_from_archive(archive_paths[0])
request_row = request_rows[0] if request_rows else {}
request_site_counts = [
int(row["site_count"])
for row in request_rows
if str(row.get("site_count", "")).strip().isdigit()
]
archive_zip = ";".join(str(path) for path in archive_paths)
area_weighted_cloudiness = float(polygon_summary["area_weighted_cloudiness"])
representative_point_cloudiness = (
float(representative_point_row["cloudinessIndexPct"])
if representative_point_row.get("cloudinessIndexPct")
else None
)
weighted_minus_representative_point = (
area_weighted_cloudiness - representative_point_cloudiness
if representative_point_cloudiness is not None
else None
)
weighted_pct_diff_representative_point = (
weighted_minus_representative_point / representative_point_cloudiness * 100
if representative_point_cloudiness not in (None, 0)
else None
)
return {
"county_fips": county_fips,
"county_name": request_row.get("county_name") or representative_point_row.get("county_name", ""),
"state_abbr": request_row.get("state_abbr") or representative_point_row.get("state_abbr", ""),
"archive_zip": archive_zip,
"polygon_sites": str(polygon_summary["polygon_sites"]),
"request_site_count": str(sum(request_site_counts)) if request_site_counts else request_row.get("site_count", ""),
"rows_per_site_min": str(polygon_summary["rows_per_site_min"]),
"rows_per_site_max": str(polygon_summary["rows_per_site_max"]),
"daylight_rows_per_site_min": str(polygon_summary["daylight_rows_per_site_min"]),
"daylight_rows_per_site_max": str(polygon_summary["daylight_rows_per_site_max"]),
"cloudinessIndexPct": format_float(area_weighted_cloudiness, 4),
"areaWeightedCloudinessIndexPct": format_float(area_weighted_cloudiness, 4),
"areaWeightedAvgObservedToClearskyRatio": format_float(float(polygon_summary["area_weighted_avg_ratio"]), 4),
"areaWeightedSites": str(polygon_summary["area_weighted_sites"]),
"weightedCellAreaKm2": format_float(float(polygon_summary["weighted_cell_area_km2"]), 1),
"countyAreaKm2": format_float(float(polygon_summary["county_area_km2"]), 1),
"site_cloudiness_min": format_float(float(polygon_summary["site_cloudiness_min"]), 4),
"site_cloudiness_max": format_float(float(polygon_summary["site_cloudiness_max"]), 4),
"site_cloudiness_stddev": format_float(float(polygon_summary["site_cloudiness_stddev"]), 4),
"clearOrProbablyClearPct": format_float(float(polygon_summary["clear_or_probably_clear_pct"]), 2),
"cloudyOrObscuredPct": format_float(float(polygon_summary["cloudy_or_obscured_pct"]), 2),
"fogPct": format_float(float(polygon_summary["fog_pct"]), 2),
"waterCloudPct": format_float(float(polygon_summary["water_cloud_pct"]), 2),
"iceCloudPct": format_float(float(polygon_summary["ice_cloud_pct"]), 2),
"cirrusPct": format_float(float(polygon_summary["cirrus_pct"]), 2),
"unknownCloudTypePct": format_float(float(polygon_summary["unknown_cloud_type_pct"]), 2),
"representativePointCloudinessIndexPct": format_float(representative_point_cloudiness, 4),
"areaWeightedMinusRepresentativePoint": format_float(weighted_minus_representative_point, 4),
"areaWeightedPctDiffFromRepresentativePoint": format_float(weighted_pct_diff_representative_point),
}
def write_summary(rows: list[dict[str, str]], output_csv: Path) -> None:
"""Write polygon cloud summary rows to disk."""
output_csv.parent.mkdir(parents=True, exist_ok=True)
with output_csv.open("w", newline="", encoding="utf-8") as handle:
writer = csv.DictWriter(handle, fieldnames=SUMMARY_FIELDS)
writer.writeheader()
writer.writerows(rows)
def run(args: argparse.Namespace) -> None:
"""Summarize downloaded polygon cloud archives."""
county_geometries = load_county_geometries(args.counties_geojson)
request_rows = read_grouped_lookup(args.requests_csv, "county_fips")
representative_point_rows = read_lookup(args.representative_point_csv, "county_fips")
existing_rows = (
read_lookup(args.output_csv, "county_fips")
if args.reuse_existing_output
else {}
)
archives = sorted(args.archive_dir.glob(args.archive_glob))
if not archives:
print(f"No archives matched {args.archive_dir / args.archive_glob}")
return
rows: list[dict[str, str]] = []
archive_groups = archive_groups_by_county(archives)
total = len(archive_groups)
reused_count = 0
for index, county_fips in enumerate(sorted(archive_groups), start=1):
archive_paths = sorted(archive_groups[county_fips])
county_request_rows = request_rows.get(county_fips, [])
missing_parts = missing_archive_parts(archive_paths, county_request_rows)
if missing_parts:
print(
f"[{index}/{total}] Skipped {county_fips}: incomplete archive set; "
f"missing {', '.join(missing_parts)}."
)
continue
existing_row = existing_rows.get(county_fips)
if existing_row and existing_archive_signature(existing_row) == archive_signature(archive_paths):
rows.append({field: existing_row.get(field, "") for field in SUMMARY_FIELDS})
reused_count += 1
continue
try:
polygon_summary = summarize_archives(
archive_paths,
county_geometries.get(county_fips),
args.cell_size_m,
args.min_clearsky_ghi,
)
row = build_summary_row(
archive_paths,
polygon_summary,
county_request_rows,
representative_point_rows.get(county_fips, {}),
)
rows.append(row)
except (OSError, ValueError, zipfile.BadZipFile) as error:
print(f"[{index}/{total}] Failed {county_fips}: {error}")
continue
tile_note = f", archives={len(archive_paths)}" if len(archive_paths) > 1 else ""
empty_note = (
f", skipped_empty_csvs={polygon_summary['empty_csv_members']}"
if polygon_summary["empty_csv_members"]
else ""
)
print(
f"[{index}/{total}] {county_fips}: "
f"sites={row['polygon_sites']}, weighted={row['areaWeightedCloudinessIndexPct']}, "
f"representative_point={row['representativePointCloudinessIndexPct'] or 'n/a'}"
f"{tile_note}{empty_note}"
)
write_summary(rows, args.output_csv)
if reused_count:
print(f"Reused {reused_count} existing rows whose archive sets still match.")
print(f"Wrote {len(rows)} rows to {args.output_csv}")
def parse_args() -> argparse.Namespace:
"""Parse command-line arguments."""
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("--archive-dir", type=Path, default=DEFAULT_ARCHIVE_DIR)
parser.add_argument("--archive-glob", default=DEFAULT_ARCHIVE_GLOB)
parser.add_argument("--counties-geojson", type=Path, default=DEFAULT_COUNTIES_GEOJSON)
parser.add_argument("--requests-csv", type=Path, default=DEFAULT_REQUESTS_CSV)
parser.add_argument(
"--representative-point-csv",
type=Path,
default=DEFAULT_REPRESENTATIVE_POINT_CSV,
help="County representative-point cloud summary CSV.",
)
parser.add_argument("--output-csv", type=Path, default=DEFAULT_OUTPUT_CSV)
parser.add_argument(
"--cell-size-m",
type=float,
default=DEFAULT_CELL_SIZE_M,
help="Estimated NSRDB grid-cell side length in meters. GOES TMY is 4 km.",
)
parser.add_argument(
"--min-clearsky-ghi",
type=float,
default=DEFAULT_MIN_CLEARSKY_GHI,
help="Minimum Clearsky GHI W/m2 for daylight cloudiness ratio rows.",
)
parser.add_argument(
"--reuse-existing-output",
action="store_true",
help=(
"Reuse rows already present in --output-csv when the recorded archive filenames "
"match the current archive directory, and summarize only missing or changed counties."
),
)
args = parser.parse_args()
if args.cell_size_m <= 0:
parser.error("--cell-size-m must be greater than 0.")
if args.min_clearsky_ghi < 0:
parser.error("--min-clearsky-ghi must be 0 or greater.")
return args
def main() -> None:
"""Run the polygon cloud summarizer."""
run(parse_args())
if __name__ == "__main__":
main()