egutierrez
dabc945eda
Extrae al registry funciones del proyecto interno footprint_aurgi: - core (6): slugify_ascii, normalize_for_join, cp_provincia_es, infer_provincia_from_cp, safe_read_csv_fallback, csv_to_parquet_duckdb - geo puras (7): haversine_km, point_in_ring, point_in_polygon, point_in_polygons_bbox, polygon_bbox, extent_with_padding, distance_bucket - geo I/O (4): load_geojson_polygons, load_boundary_gdf, add_basemap_osm, add_basemap_with_timeout - valhalla client (4): valhalla_route, valhalla_isochrone, valhalla_isochrones_async, valhalla_matrix_1_to_n - datascience stats (7): trimmed_mean, geometric_mean, detect_distribution_type, best_central_tendency, summary_stats, kde_density_levels, alpha_shape_concave_hull - datascience fuzzy (3): fuzzy_merge_adaptive (rapidfuzz), words_to_dataset, remove_words_from_column - datascience viz (2): plot_kde_2d, plot_heatmap_log - infra (4): compress_pdf_ghostscript, render_table_page_pdfpages, add_header_logo, osm2pgsql_ingest - pipelines (4): setup_geo_stack_docker, compute_centers_reachability, generate_isochrones_by_zone, count_points_per_zone - types geo (4): LonLat, BBox, IsochroneRequest, Centro Incluye: - apps/footprint_geo_stack/ (PostGIS + Martin + Valhalla via docker-compose) - 131/132 tests pasan (1 skip esperado: osm2pgsql en PATH) - Issue tracker dev/issues/0052-footprint-aurgi-extraction.md - Atribucion uniforme: source_repo internal:footprint_aurgi, source_license internal-aurgi - Build con 9 agentes en paralelo (8 wave 1 + 1 wave 2 pipelines) Tambien commitea trabajo previo no commiteado: aggregate_extraction_results, chunk_with_overlap, clean_pdf_text, merge_entity_aliases, extract_graph_gliner2, extract_relations_mrebel, extract_triples_spacy_es, gliner2/mrebel/marianmt/rebel/spacy_es load_model, parse_rebel_output, translate_es_to_en, issue 0050/0051. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
66 lines
2.2 KiB
Python
66 lines
2.2 KiB
Python
"""kde_density_levels — Compute density levels via KDE or histogram fallback."""
|
|
|
|
import math
|
|
import numpy as np
|
|
|
|
|
|
def kde_density_levels(
|
|
xs: list[float],
|
|
ys: list[float],
|
|
bw_adjust: float = 0.6,
|
|
abs_quantile: float = 0.1,
|
|
dense_quantile: float = 0.85,
|
|
bins: int = 80,
|
|
) -> dict | None:
|
|
"""Estimate 2-D density and compute absolute and dense threshold levels.
|
|
|
|
Uses scipy.stats.gaussian_kde when available; falls back to
|
|
numpy.histogram2d if scipy is not installed.
|
|
|
|
Args:
|
|
xs: X-coordinates of points.
|
|
ys: Y-coordinates of points.
|
|
bw_adjust: Bandwidth adjustment factor for KDE (ignored for histogram fallback).
|
|
abs_quantile: Quantile of density values used as the absolute threshold.
|
|
dense_quantile: Quantile of density values used as the dense threshold.
|
|
bins: Number of bins per axis for the histogram fallback.
|
|
|
|
Returns:
|
|
Dict with keys:
|
|
"method" (str): "kde" or "hist".
|
|
"densities" (np.ndarray): 1-D array of per-point density estimates.
|
|
"abs_level" (float): density at abs_quantile.
|
|
"dense_level" (float): density at dense_quantile.
|
|
Returns None if len(xs) < 5 or xs and ys have different lengths.
|
|
"""
|
|
if len(xs) < 5 or len(xs) != len(ys):
|
|
return None
|
|
|
|
xs_arr = np.array(xs, dtype=float)
|
|
ys_arr = np.array(ys, dtype=float)
|
|
points = np.vstack([xs_arr, ys_arr])
|
|
|
|
try:
|
|
from scipy.stats import gaussian_kde # type: ignore
|
|
|
|
kde = gaussian_kde(points, bw_method=bw_adjust)
|
|
densities = kde(points)
|
|
method = "kde"
|
|
except ImportError:
|
|
# Histogram fallback
|
|
h, xedges, yedges = np.histogram2d(xs_arr, ys_arr, bins=bins)
|
|
xi = np.clip(np.searchsorted(xedges, xs_arr) - 1, 0, bins - 1)
|
|
yi = np.clip(np.searchsorted(yedges, ys_arr) - 1, 0, bins - 1)
|
|
densities = h[xi, yi].astype(float)
|
|
method = "hist"
|
|
|
|
abs_level = float(np.quantile(densities, abs_quantile))
|
|
dense_level = float(np.quantile(densities, dense_quantile))
|
|
|
|
return {
|
|
"method": method,
|
|
"densities": densities,
|
|
"abs_level": abs_level,
|
|
"dense_level": dense_level,
|
|
}
|