Initial Climate Mood Analysis project
This commit is contained in:
Justin Fisher
@@ -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()
|
||||
Reference in New Issue
Block a user