dataforge/fn_registry
1
0
Fork 0
Code Issues Pull Requests 5 Actions Packages Projects Releases Wiki Activity

merge: capitulo AutomaticEDA geospatial (verificado met) + detect_latlon_columns/analyze_geo_extent/build_geo_scatter

Browse Source
This commit is contained in:
Egutierrez
2026-06-30 15:36:22 +02:00
parent 81b57f9acd 00cd5274bc
commit 864430e988
12 changed files with 1891 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/functions/datascience/automatic_eda/chapters/geospatial.py
+477
View File
@@ -0,0 +1,477 @@
"""Geospatial chapter (GEOSPATIAL) for AutomaticEDA.
When the dataset carries a coordinate pair (latitude/longitude), this chapter
draws the points on a **geographic scatter** in an equirectangular projection
(scaled so degrees of longitude are not stretched at the data's latitude) and
analyses the **zone / country** the points fall in: bounding box, centroid,
geographic span, and a per-region count. When there is **no** coordinate pair the
chapter returns ``None`` — exactly the user requirement.
Detection and the heavy lifting are delegated to pure ``eda``-group registry
functions, never reimplemented here:
- ``detect_latlon_columns`` — finds the (lat, lon) column pair by name + value
range from the ``profile['columns']`` metadata.
- ``analyze_geo_extent`` — bbox, centroid, haversine span, per-region counts and
hemisphere from the raw coordinate arrays.
- ``build_geo_scatter`` — deterministically down-sampled points + bbox + the
aspect ratio for the equirectangular projection. This chapter only draws the
matplotlib figure from that prepared data (same split as ``num_distr`` does
with ``build_boxplot_stats``).
The raw coordinate arrays are **not** in a standard TableProfile (it stores only
per-column aggregates), so — exactly like ``modelos`` reads ``raw_numeric`` from
``ctx`` — this chapter looks for the coordinates in ``ctx`` (or ``profile``) and
degrades honestly when they are absent: it still detects the columns and shows an
approximate bounding box derived from the per-column ``numeric.min/max``, with a
note that the raw points are needed for the map.
ctx keys this chapter consumes (all optional):
geo_points : dict — ``{"lats": [...], "lons": [...]}`` raw coordinate arrays.
Used directly when present (forward-compatible with a calculation phase
that samples them from the table).
raw_numeric : dict — ``{col: [values]}`` raw numeric columns; when present
and ``geo_points`` is not, the detected lat/lon columns are read from it.
run_geo_llm : bool — when True, call ``ask_llm`` for a one-line narrative of
where the points concentrate (otherwise a derived note is used).
geo_llm_model : str — model id for the optional live LLM call.
Contract: build_<id>(profile, ctx) -> Chapter | None ; CHAPTER_VERSION = "x.y.z".
Reads everything defensively (``.get``) and never raises.
"""
from __future__ import annotations
import math
from .. import model
# Pure registry functions (group ``eda``) delegated to. Imported defensively so
# the chapter stays importable (degrading gracefully) if one is unavailable.
try:
from datascience.detect_latlon_columns import detect_latlon_columns
except Exception: # noqa: BLE001 — keep the chapter importable no matter what.
detect_latlon_columns = None # type: ignore[assignment]
try:
from datascience.analyze_geo_extent import analyze_geo_extent
except Exception: # noqa: BLE001
analyze_geo_extent = None # type: ignore[assignment]
try:
from datascience.build_geo_scatter import build_geo_scatter
except Exception: # noqa: BLE001
build_geo_scatter = None # type: ignore[assignment]
CHAPTER_VERSION = "1.0.0"
CHAPTER_ID = "geospatial"
CHAPTER_TITLE = "Análisis geoespacial"
# --------------------------------------------------------------------------- #
# Formatting helpers (mirror the other chapters' defensive style).
# --------------------------------------------------------------------------- #
def _fmt_num(value, decimals: int = 4) -> str:
if value is None:
return "—"
if isinstance(value, bool):
return "sí" if value else "no"
if isinstance(value, int):
return f"{value:,}".replace(",", ".")
if isinstance(value, float):
if value != value: # NaN
return "NaN"
if value in (float("inf"), float("-inf")):
return str(value)
text = f"{value:.{decimals}f}".rstrip("0").rstrip(".")
return text if text else "0"
return model._safe_str(value)
def _fmt_coord(value, decimals: int = 4) -> str:
"""Format a coordinate degree value, defensively."""
try:
return f"{float(value):.{decimals}f}°"
except (TypeError, ValueError):
return model._safe_str(value)
def _fmt_km(value) -> str:
if value is None:
return "—"
try:
v = float(value)
except (TypeError, ValueError):
return model._safe_str(value)
if v >= 100:
return f"{v:,.0f} km".replace(",", ".")
return f"{v:.1f} km"
def _is_dict(v) -> bool:
return isinstance(v, dict)
def _clean_floats(seq) -> list:
"""Return a list of floats from an arbitrary sequence (drop None/NaN)."""
out = []
if not isinstance(seq, (list, tuple)):
return out
for v in seq:
try:
f = float(v)
except (TypeError, ValueError):
out.append(None)
continue
out.append(f if f == f else None) # NaN -> None
return out
# --------------------------------------------------------------------------- #
# Resolve the (lat, lon) columns and the raw coordinate arrays.
# --------------------------------------------------------------------------- #
def _detect_columns(profile: dict) -> dict:
"""Detect the lat/lon column pair from the profile metadata, or {}."""
cols = profile.get("columns")
if not isinstance(cols, list) or not cols or detect_latlon_columns is None:
return {}
try:
det = detect_latlon_columns(cols)
except Exception: # noqa: BLE001 — never break the chapter.
return {}
return det if _is_dict(det) else {}
def _resolve_coords(profile: dict, ctx: dict, detected: dict):
"""Return (lats, lons, source_label).
Order: ctx/profile['geo_points'] (explicit arrays) → ctx/profile
['raw_numeric'] keyed by the detected lat/lon column names → (None, None).
"""
gp = ctx.get("geo_points") or profile.get("geo_points")
if _is_dict(gp):
lats = gp.get("lats")
if lats is None:
lats = gp.get("lat")
lons = gp.get("lons")
if lons is None:
lons = gp.get("lon")
if lats and lons:
return list(lats), list(lons), "geo_points"
lat_col = (detected or {}).get("lat_col")
lon_col = (detected or {}).get("lon_col")
if lat_col and lon_col:
raw = ctx.get("raw_numeric") or profile.get("raw_numeric")
if _is_dict(raw):
lats = raw.get(lat_col)
lons = raw.get(lon_col)
if lats and lons:
return list(lats), list(lons), "raw_numeric"
return None, None, "none"
def _column_by_name(profile: dict, name):
if not name:
return None
for col in profile.get("columns") or []:
if isinstance(col, dict) and col.get("name") == name:
return col
return None
def _bbox_from_profile(profile: dict, detected: dict):
"""Approximate bbox from the per-column numeric.min/max (no raw points)."""
lat_c = _column_by_name(profile, (detected or {}).get("lat_col"))
lon_c = _column_by_name(profile, (detected or {}).get("lon_col"))
lat_n = lat_c.get("numeric") if _is_dict(lat_c) else None
lon_n = lon_c.get("numeric") if _is_dict(lon_c) else None
if not _is_dict(lat_n) or not _is_dict(lon_n):
return None
try:
return {
"lat_min": float(lat_n.get("min")),
"lat_max": float(lat_n.get("max")),
"lon_min": float(lon_n.get("min")),
"lon_max": float(lon_n.get("max")),
}
except (TypeError, ValueError):
return None
# --------------------------------------------------------------------------- #
# Figure builder (lazy: matplotlib only imported when the renderer draws it).
# --------------------------------------------------------------------------- #
def _make_geo_scatter(scatter: dict, lat_col: str, lon_col: str):
"""Return a zero-arg callable drawing the geographic scatter, or None."""
points = scatter.get("points") or []
if not points:
return None
bbox = scatter.get("bbox") if _is_dict(scatter.get("bbox")) else {}
aspect = scatter.get("aspect") or 1.0
pad = scatter.get("pad") if _is_dict(scatter.get("pad")) else {}
n_total = scatter.get("n_total")
n_shown = scatter.get("n_shown")
def _draw():
import matplotlib
matplotlib.use("Agg")
import matplotlib.pyplot as plt
xs = [p[0] for p in points if isinstance(p, (list, tuple)) and len(p) >= 2]
ys = [p[1] for p in points if isinstance(p, (list, tuple)) and len(p) >= 2]
fig, ax = plt.subplots(figsize=(6.6, 5.0))
# More points -> smaller markers + lower alpha so dense clouds read as
# density without saturating the page with ink (Tufte).
n = max(len(xs), 1)
size = 18 if n <= 200 else (8 if n <= 1000 else 4)
alpha = 0.75 if n <= 200 else (0.5 if n <= 1000 else 0.35)
ax.scatter(xs, ys, s=size, c="#2a6f97", alpha=alpha, linewidths=0,
zorder=3)
# Bounding box rectangle for orientation.
if bbox:
try:
lo_x, hi_x = float(bbox["lon_min"]), float(bbox["lon_max"])
lo_y, hi_y = float(bbox["lat_min"]), float(bbox["lat_max"])
ax.plot([lo_x, hi_x, hi_x, lo_x, lo_x],
[lo_y, lo_y, hi_y, hi_y, lo_y],
color="#e15759", linewidth=1.0, linestyle="--",
alpha=0.8, zorder=4, label="Bounding box")
px = float(pad.get("lon", 0.0) or 0.0)
py = float(pad.get("lat", 0.0) or 0.0)
ax.set_xlim(lo_x - px, hi_x + px)
ax.set_ylim(lo_y - py, hi_y + py)
except (TypeError, ValueError, KeyError):
pass
# Equirectangular: scale Y/X so longitude is not stretched at this
# latitude (integridad de proyección, Tufte). aspect = 1/cos(lat).
try:
ax.set_aspect(float(aspect))
except (TypeError, ValueError):
pass
ax.set_xlabel(f"Longitud ({lon_col})", fontsize=8)
ax.set_ylabel(f"Latitud ({lat_col})", fontsize=8)
ax.tick_params(labelsize=7)
ax.grid(color="#e6e6e6", linewidth=0.5, zorder=0)
title = "Distribución geográfica de las coordenadas"
if n_shown is not None and n_total is not None and n_shown < n_total:
title += f"\n(mostrando {n_shown:,} de {n_total:,} puntos)".replace(",", ".")
ax.set_title(title, fontsize=10)
ax.legend(loc="best", fontsize=7, frameon=True, framealpha=0.9)
fig.tight_layout()
return fig
return _draw
# --------------------------------------------------------------------------- #
# Section builders.
# --------------------------------------------------------------------------- #
def _intro_block(detected: dict, lat_col: str, lon_col: str) -> list:
conf = (detected or {}).get("confidence")
reason = model._safe_str((detected or {}).get("reason"))
conf_txt = ""
if conf is not None:
try:
conf_txt = f" (confianza {float(conf) * 100:.0f}%)"
except (TypeError, ValueError):
conf_txt = ""
text = (
"Este dataset contiene **coordenadas geográficas**: se identificó el par "
f"**latitud = «{lat_col}»** y **longitud = «{lon_col}»**{conf_txt}. La "
"detección combina el nombre de la columna y el rango de sus valores "
"(latitud en [−90, 90], longitud en [−180, 180])."
)
if reason:
text += f"\n\n*Criterio de detección:* {reason}."
return [model.Heading(text=CHAPTER_TITLE, level=1),
model.Markdown(text=text)]
def _extent_blocks(extent: dict) -> list:
"""KVTable with bbox/centroid/span + DataTable with the per-region counts."""
if not _is_dict(extent) or not extent.get("n_points"):
return []
blocks = []
bbox = extent.get("bbox") if _is_dict(extent.get("bbox")) else {}
centroid = extent.get("centroid") if _is_dict(extent.get("centroid")) else {}
hemi = extent.get("hemisphere") if _is_dict(extent.get("hemisphere")) else {}
rows = [("Puntos con coordenadas", _fmt_num(extent.get("n_points")))]
if bbox:
rows.append(("Latitud (mín. / máx.)",
f"{_fmt_coord(bbox.get('lat_min'))} a "
f"{_fmt_coord(bbox.get('lat_max'))}"))
rows.append(("Longitud (mín. / máx.)",
f"{_fmt_coord(bbox.get('lon_min'))} a "
f"{_fmt_coord(bbox.get('lon_max'))}"))
if centroid:
rows.append(("Centroide",
f"{_fmt_coord(centroid.get('lat'))}, "
f"{_fmt_coord(centroid.get('lon'))}"))
if extent.get("span_km") is not None:
rows.append(("Extensión (diagonal)", _fmt_km(extent.get("span_km"))))
if hemi:
n, s = hemi.get("north"), hemi.get("south")
e, w = hemi.get("east"), hemi.get("west")
rows.append(("Hemisferios",
f"N {_fmt_num(n)} / S {_fmt_num(s)} · "
f"E {_fmt_num(e)} / O {_fmt_num(w)}"))
blocks.append(model.KVTable(rows=rows, title="Extensión geográfica"))
by_region = extent.get("by_region")
if isinstance(by_region, list) and by_region:
total = sum(r.get("count", 0) for r in by_region if _is_dict(r)) or 0
rrows = []
for r in by_region:
if not _is_dict(r):
continue
cnt = r.get("count", 0)
pct = (cnt / total) if total else None
pct_txt = f"{pct * 100:.1f}%" if pct is not None else "—"
rrows.append([model._safe_str(r.get("region")), _fmt_num(cnt),
pct_txt])
if rrows:
blocks.append(model.DataTable(
header=["Zona / país", "Puntos", "% del total"], rows=rrows,
title="Distribución por zona",
note="Asignación aproximada por bounding box de cada región "
"(no es reverse-geocoding exacto de fronteras)."))
return blocks
def _narrative_block(profile: dict, ctx: dict, extent: dict) -> list:
"""A one-line narrative of where the points concentrate.
Uses the derived ``note`` from analyze_geo_extent by default; optionally
calls an LLM (ctx['run_geo_llm']) for a richer one-liner.
"""
note = model._safe_str((extent or {}).get("note"))
if ctx.get("run_geo_llm"):
by_region = (extent or {}).get("by_region") or []
bbox = (extent or {}).get("bbox") or {}
try:
from core.ask_llm import ask_llm
prompt = (
"Eres un analista de datos. En UNA frase en español, describe "
"dónde se concentran geográficamente estos puntos. Sé concreto "
"y no inventes precisión que los datos no tienen.\n"
f"Conteo por zona: {by_region}\nBounding box: {bbox}."
)
out = ask_llm(prompt,
model=ctx.get("geo_llm_model",
"claude-haiku-4-5-20251001"),
echo=False)
if out and isinstance(out, str) and out.strip():
note = out.strip()
except Exception: # noqa: BLE001 — degrade to the derived note.
pass
if not note:
return []
return [model.Markdown(text=f"**Interpretación.** {note}")]
def _no_points_block(profile: dict, detected: dict) -> list:
"""Degrade honestly when the raw coordinate arrays are not available."""
blocks = []
bbox = _bbox_from_profile(profile, detected)
if bbox:
rows = [
("Latitud (mín. / máx.)",
f"{_fmt_coord(bbox.get('lat_min'))} a "
f"{_fmt_coord(bbox.get('lat_max'))}"),
("Longitud (mín. / máx.)",
f"{_fmt_coord(bbox.get('lon_min'))} a "
f"{_fmt_coord(bbox.get('lon_max'))}"),
]
blocks.append(model.KVTable(
rows=rows, title="Extensión geográfica (aproximada)"))
blocks.append(model.Note(
"No se incluyeron las coordenadas crudas en el contexto, por lo que el "
"mapa y el análisis por zona no se han dibujado. El bounding box "
"mostrado se deriva de los mínimos y máximos por columna. Para el "
"scatter geográfico completo, pasa los arrays en "
"ctx['geo_points'] = {'lats': [...], 'lons': [...]} o las columnas en "
"ctx['raw_numeric']."))
return blocks
# --------------------------------------------------------------------------- #
# Entry point.
# --------------------------------------------------------------------------- #
def build_geospatial(profile: dict, ctx: dict):
"""Build the GEOSPATIAL Chapter, or None if the dataset has no coordinates.
Args:
profile: the ``eda`` group TableProfile dict.
ctx: presentation context; may carry ``geo_points``/``raw_numeric`` with
the raw coordinate arrays and the ``run_geo_llm`` flag.
Returns:
A ``model.Chapter`` with the geographic scatter + zone/country analysis,
or ``None`` when no latitude/longitude column pair is detected.
"""
profile = profile or {}
ctx = ctx or {}
if not isinstance(profile, dict):
return None
detected = _detect_columns(profile)
lats, lons, source = _resolve_coords(profile, ctx, detected)
has_detection = bool((detected or {}).get("lat_col") and
(detected or {}).get("lon_col"))
has_points = bool(lats and lons)
if not has_detection and not has_points:
return None # chapter does not apply: no coordinates in this dataset.
# Labels for axes / intro. When only raw arrays were given (no detection),
# fall back to generic names.
lat_col = (detected or {}).get("lat_col") or "lat"
lon_col = (detected or {}).get("lon_col") or "lon"
blocks = _intro_block(detected, lat_col, lon_col)
if has_points:
clean_lats = _clean_floats(lats)
clean_lons = _clean_floats(lons)
# Zone / country analysis.
extent = {}
if analyze_geo_extent is not None:
try:
extent = analyze_geo_extent(clean_lats, clean_lons) or {}
except Exception: # noqa: BLE001
extent = {}
# The geographic scatter figure (its own page/slide).
scatter = {}
if build_geo_scatter is not None:
try:
scatter = build_geo_scatter(clean_lats, clean_lons) or {}
except Exception: # noqa: BLE001
scatter = {}
maker = _make_geo_scatter(scatter, lat_col, lon_col) if scatter else None
if maker is not None:
blocks.append(model.Figure(
make=maker,
caption="Cada punto es una observación situada por sus "
"coordenadas; el recuadro rojo es el bounding box. La "
"escala respeta la latitud (proyección equirectangular)."))
else:
blocks.append(model.Note(
"No se pudo construir el scatter geográfico a partir de las "
"coordenadas proporcionadas."))
blocks += _extent_blocks(extent)
blocks += _narrative_block(profile, ctx, extent)
else:
# Columns detected but no raw points available — degrade honestly.
blocks += _no_points_block(profile, detected)
if not blocks:
return None
return model.Chapter(id=CHAPTER_ID, title=CHAPTER_TITLE,
version=CHAPTER_VERSION, blocks=blocks)
python/functions/datascience/automatic_eda/chapters/geospatial_test.py
+245
View File
@@ -0,0 +1,245 @@
"""Tests for the GEOSPATIAL chapter — DoD: golden + edges + anti-cut.
Self-contained: builds synthetic TableProfiles (no DuckDB) so the suite is fast
and deterministic. The raw coordinate arrays are passed through ``ctx`` exactly
as the chapter's contract documents (``ctx['geo_points']`` / ``ctx['raw_numeric']``).
Verifies that the chapter detects the lat/lon pair, draws the geographic scatter
figure, analyses the zone/country (bounding box + per-region counts), returns
None when there are no coordinates, degrades honestly when the raw points are
absent, and that a profile with long column names + many points + several
regions renders to PDF and PPTX without cutting any text (long content wraps, it
is never truncated).
"""
import os
import re
import tempfile
from pypdf import PdfReader
from pptx import Presentation
from datascience.automatic_eda.chapters.geospatial import (
build_geospatial,
CHAPTER_VERSION,
)
from datascience.automatic_eda import build_document, render_pdf, render_pptx
# --------------------------------------------------------------------------- #
# Synthetic data helpers
# --------------------------------------------------------------------------- #
def _grid(lat0: float, lon0: float, n: int, spread: float = 1.0):
"""A small deterministic cloud of n points around (lat0, lon0)."""
lats, lons = [], []
for i in range(n):
# deterministic pseudo-spread, no randomness.
f = (i % 11) / 11.0 - 0.5
g = (i % 7) / 7.0 - 0.5
lats.append(lat0 + f * spread)
lons.append(lon0 + g * spread)
return lats, lons
def _profile_with_coords(lat_name="lat", lon_name="lon", lats=None, lons=None):
"""A profile carrying a lat/lon column pair with valid ranges."""
lats = lats if lats is not None else [40.4, 41.0, 39.8, 40.1]
lons = lons if lons is not None else [-3.7, -3.6, -4.0, -3.9]
return {
"table": "lugares",
"columns": [
{"name": lat_name, "inferred_type": "numeric",
"numeric": {"min": min(lats), "max": max(lats),
"mean": sum(lats) / len(lats)}},
{"name": lon_name, "inferred_type": "numeric",
"numeric": {"min": min(lons), "max": max(lons),
"mean": sum(lons) / len(lons)}},
{"name": "valor", "inferred_type": "numeric",
"numeric": {"min": 0, "max": 100, "mean": 50}},
],
}
def _ctx_points(lats, lons):
return {"geo_points": {"lats": lats, "lons": lons}}
def _kinds(chapter):
return [getattr(b, "kind", None) for b in chapter.blocks]
def _tables(chapter):
return [b for b in chapter.blocks if getattr(b, "kind", None) == "data_table"]
def _figures(chapter):
return [b for b in chapter.blocks if getattr(b, "kind", None) == "figure"]
# --------------------------------------------------------------------------- #
# Golden
# --------------------------------------------------------------------------- #
def test_golden_estructura_y_version():
lats, lons = [40.4, 41.0, 39.8, 40.1], [-3.7, -3.6, -4.0, -3.9]
ch = build_geospatial(_profile_with_coords(lats=lats, lons=lons),
_ctx_points(lats, lons))
assert ch is not None
assert ch.id == "geospatial"
assert ch.version == CHAPTER_VERSION
kinds = _kinds(ch)
# intro heading + markdown + scatter figure + extent kv + per-region table.
assert "heading" in kinds
assert "markdown" in kinds
assert "figure" in kinds, "falta el scatter geográfico"
assert "kv_table" in kinds, "falta la tabla de extensión"
def test_golden_detecta_columnas_y_nombra_ejes():
lats, lons = _grid(40.4, -3.7, 30, spread=0.8)
prof = _profile_with_coords("latitude", "longitude", lats, lons)
ch = build_geospatial(prof, _ctx_points(lats, lons))
intro = [b for b in ch.blocks if b.kind == "markdown"][0].text
assert "latitude" in intro and "longitude" in intro
def test_golden_figura_es_perezosa_y_dibujable():
lats, lons = _grid(40.4, -3.7, 50, spread=0.6)
ch = build_geospatial(_profile_with_coords(lats=lats, lons=lons),
_ctx_points(lats, lons))
fig_block = _figures(ch)[0]
assert fig_block.make is not None and fig_block.fig is None # lazy
fig = fig_block.make() # must draw without raising
assert fig is not None
import matplotlib.pyplot as plt
plt.close(fig)
def test_golden_analisis_por_zona_espana():
lats, lons = _grid(40.4, -3.7, 40, spread=0.5) # Madrid area
ch = build_geospatial(_profile_with_coords(lats=lats, lons=lons),
_ctx_points(lats, lons))
tables = _tables(ch)
region_tbl = [t for t in tables if "zona" in (t.title or "").lower()]
assert region_tbl, "falta la tabla por zona/país"
flat = " ".join(" ".join(str(c) for c in r) for r in region_tbl[0].rows)
# Spain-area points must resolve to a Spain/European region, not empty.
assert region_tbl[0].rows
assert any(c for c in (region_tbl[0].rows[0]))
def test_golden_raw_numeric_source():
"""Coordinates can also come from ctx['raw_numeric'] keyed by detected cols."""
lats, lons = _grid(48.85, 2.35, 25, spread=0.4) # Paris area
prof = _profile_with_coords("lat", "lon", lats, lons)
ctx = {"raw_numeric": {"lat": lats, "lon": lons}}
ch = build_geospatial(prof, ctx)
assert ch is not None
assert _figures(ch), "el scatter debe construirse desde raw_numeric"
# --------------------------------------------------------------------------- #
# Edges
# --------------------------------------------------------------------------- #
def test_edge_sin_coordenadas_devuelve_none():
prof = {
"table": "ventas",
"columns": [
{"name": "precio", "inferred_type": "numeric",
"numeric": {"min": 0, "max": 1000}},
{"name": "categoria", "inferred_type": "text"},
],
}
assert build_geospatial(prof, {}) is None
def test_edge_none_y_vacio_no_rompen():
assert build_geospatial(None, None) is None
assert build_geospatial({}, {}) is None
assert build_geospatial({"columns": []}, {}) is None
assert build_geospatial("not a dict", {}) is None
def test_edge_nombre_lat_pero_rango_invalido_no_aplica():
"""A column named 'lat' whose values are out of [-90,90] is NOT a coordinate."""
prof = {
"table": "x",
"columns": [
{"name": "lat", "inferred_type": "numeric",
"numeric": {"min": 1000, "max": 9999}},
{"name": "lon", "inferred_type": "numeric",
"numeric": {"min": 1000, "max": 9999}},
],
}
assert build_geospatial(prof, {}) is None
def test_edge_columnas_detectadas_sin_puntos_degrada():
"""Detected lat/lon but no raw arrays -> honest note + approx bbox, no crash."""
prof = _profile_with_coords(lats=[40.0, 41.0], lons=[-3.0, -4.0])
ch = build_geospatial(prof, {}) # no geo_points / raw_numeric
assert ch is not None
assert not _figures(ch), "sin puntos no debe dibujarse el scatter"
notes = [b for b in ch.blocks if b.kind == "note"]
assert notes and "coordenadas crudas" in notes[0].text
def test_edge_coordenadas_con_nan_se_filtran():
lats = [40.4, float("nan"), 41.0, None, 39.8]
lons = [-3.7, -3.6, float("nan"), -3.9, -4.0]
ch = build_geospatial(_profile_with_coords(lats=[39.8, 41.0],
lons=[-4.0, -3.6]),
_ctx_points(lats, lons))
assert ch is not None # must not raise on NaN/None
# --------------------------------------------------------------------------- #
# Anti-cut: long names + many points + several regions render without truncation
# --------------------------------------------------------------------------- #
def _multiregion_points(per: int = 700):
"""Points spread across Spain, France and the USA to fill the region table."""
lats, lons = [], []
for (la, lo) in ((40.4, -3.7), (48.85, 2.35), (39.0, -98.0)):
gl, gn = _grid(la, lo, per, spread=2.0)
lats += gl
lons += gn
return lats, lons
def test_anticut_pdf_y_pptx_no_truncan():
lat_name = "latitud_geografica_del_punto_de_observacion_registrado"
lon_name = "longitud_geografica_del_punto_de_observacion_registrado"
lats, lons = _multiregion_points(700)
prof = _profile_with_coords(lat_name, lon_name, lats, lons)
ctx = {"geo_points": {"lats": lats, "lons": lons}}
full = build_document(prof, ctx)
assert any(c.id == "geospatial" for c in full)
chapters = [c for c in full if c.id == "geospatial"]
with tempfile.TemporaryDirectory() as d:
pdf = os.path.join(d, "g.pdf")
pptx = os.path.join(d, "g.pptx")
rp = render_pdf(chapters, pdf, {"title": "EDA"})
rx = render_pptx(chapters, pptx, {"title": "EDA"})
assert os.path.exists(pdf) and os.path.exists(pptx)
assert (rp or {}).get("n_pages", 0) >= 1
# PDF: the long lat column name survives whole (wraps, not cut) and there
# is no truncation marker in this chapter.
pdf_txt = "".join((pg.extract_text() or "") for pg in PdfReader(pdf).pages)
assert "…" not in pdf_txt and "..." not in pdf_txt
norm = re.sub(r"\s+", "", pdf_txt)
assert lat_name in norm, "el nombre largo de la columna se cortó en el PDF"
# PPTX: long name present in some shape/cell, untruncated.
allt = []
for s in Presentation(pptx).slides:
for sh in s.shapes:
if sh.has_text_frame:
allt.append(sh.text_frame.text)
if sh.has_table:
for row in sh.table.rows:
for c in row.cells:
allt.append(c.text)
joined = re.sub(r"\s+", "", "\n".join(allt))
assert lat_name in joined, "el nombre largo de la columna se cortó en el PPTX"