larvit/fejkdata
3
0
Fork 0
Code Pull Requests 1 Actions Activity

Ship a tenth of each place's streets, at least ten, and a tenth of the US places owning a ZCTA, drawn by population

Browse Source
This commit is contained in:
Lilleman auf Larv
2026-10-11 16:18:32 +02:00
committed by Lillem4n
parent b64b73cb9a
commit 88cea644b6
8 changed files with 181569 additions and 9083 deletions
Download Patch File Download Diff File Expand all files Collapse all files
data-import/geo.py
+5 -5
View File
@@ -12,7 +12,7 @@ CACHE = Path(__file__).resolve().parent / "cache"
def parser(doc, country, **own):
"""A parser for the options every country's import takes, plus the script's own: each keyword names one option, with
"_" standing for "-"."""
options = {"cache": {"default": str(CACHE)}, "out": {"default": str(DATA / country)}, "streets_per_locality": {"type": int, "default": 10}, **own}
options = {"cache": {"default": str(CACHE)}, "out": {"default": str(DATA / country)}, "min_streets": {"type": int, "default": 10}, "street_share": {"type": float, "default": 0.1}, **own}
p = argparse.ArgumentParser(description=doc.splitlines()[0])
for name in sorted(options):
p.add_argument("--" + name.replace("_", "-"), **options[name])
@@ -63,13 +63,13 @@ class Nearest:
return best
def top_streets(count, per_locality, column):
"""count maps (locality, street name) to a count. Returns, per locality, rows for the per_locality names counted
most, ties broken by name; each row holds its count under column."""
def top_streets(count, share, minimum, column):
"""count maps (locality, street name) to a count. Returns, per locality, rows for the share of its names counted
most, at least minimum of them, ties broken by name; each row holds its count under column."""
of = collections.defaultdict(list)
for (locality, name), n in count.items():
of[locality].append((n, name))
return {locality: [{"name": name, "locality": locality, column: n} for n, name in sorted(named, key=lambda s: (-s[0], s[1]))[:per_locality]] for locality, named in of.items()}
return {locality: [{"name": name, "locality": locality, column: n} for n, name in sorted(named, key=lambda s: (-s[0], s[1]))[:max(minimum, math.ceil(len(named) * share))]] for locality, named in of.items()}
def fence(regions, municipalities, localities, streets, postal_codes):