merge(eda): scatters de pares correlacionados + tipo de relacion en cap CORRELACION
This commit is contained in:
@@ -31,7 +31,7 @@ import math
|
||||
|
||||
from .. import model
|
||||
|
||||
CHAPTER_VERSION = "1.0.0"
|
||||
CHAPTER_VERSION = "1.1.0"
|
||||
CHAPTER_ID = "correlacion"
|
||||
CHAPTER_TITLE = "Correlación"
|
||||
|
||||
@@ -47,6 +47,13 @@ _MAX_MATRIX_LABELS = 16
|
||||
# How many pairs to show in each of the top-positive / top-negative tables.
|
||||
_TOP_N = 10
|
||||
|
||||
# How many of the strongest numeric-numeric pairs to draw as scatter plots on
|
||||
# each sign (positive / negative). A scatter per pair carries a fitted line/curve
|
||||
# and a relationship-type label; keeping the count small keeps the chapter
|
||||
# readable on a phone / a slide. Only signed (Pearson/Spearman) pairs qualify —
|
||||
# Cramér's V / correlation ratio pairs are not numeric-numeric, so no scatter.
|
||||
_SCATTER_TOP_N = 3
|
||||
|
||||
# Glossary terms this chapter explains. Each is registered in the shared
|
||||
# collector (ctx['glossary']) and marked clickable on its first appearance in the
|
||||
# body — the canonical two-step pattern (see ``cat_distr`` for the reference
|
||||
@@ -314,6 +321,139 @@ def _fdr_text(corr: dict, mark_term: bool = False) -> str | None:
|
||||
return " ".join(parts)
|
||||
|
||||
|
||||
def _is_seq(values) -> bool:
|
||||
"""True for a non-empty list/tuple of values (a raw numeric column)."""
|
||||
return isinstance(values, (list, tuple)) and len(values) > 0
|
||||
|
||||
|
||||
def _select_scatter_pairs(pairs: list, top_n: int = _SCATTER_TOP_N):
|
||||
"""Pick the strongest numeric-numeric pairs to draw as scatters.
|
||||
|
||||
Only signed (Pearson/Spearman) pairs are numeric-numeric and thus eligible
|
||||
for a scatter with a fitted curve. Returns up to ``top_n`` of the strongest
|
||||
positive pairs followed by up to ``top_n`` of the strongest negative ones,
|
||||
each ranked by magnitude. Mixed-type metrics (Cramér's V, correlation ratio,
|
||||
mutual information) are excluded — they have no x/y scatter interpretation.
|
||||
"""
|
||||
positive = []
|
||||
negative = []
|
||||
for pair in pairs:
|
||||
if not isinstance(pair, dict) or not _is_signed(pair):
|
||||
continue
|
||||
value = pair.get("value")
|
||||
if not _is_num(value):
|
||||
continue
|
||||
if value > 0:
|
||||
positive.append(pair)
|
||||
elif value < 0:
|
||||
negative.append(pair)
|
||||
positive.sort(key=lambda p: abs(float(p.get("value", 0.0))), reverse=True)
|
||||
negative.sort(key=lambda p: abs(float(p.get("value", 0.0))), reverse=True)
|
||||
return positive[:top_n] + negative[:top_n]
|
||||
|
||||
|
||||
def _classification_note(a: str, b: str, cls: dict) -> str:
|
||||
"""Human-readable sentence describing the relationship of a pair.
|
||||
|
||||
Plain text (not baked into the figure image) so the type label is selectable
|
||||
in the PDF / extractable by pdftotext, and sits right next to its scatter
|
||||
inside the keep-together Group.
|
||||
"""
|
||||
tipo = model._safe_str(cls.get("tipo")) or "sin forma clara"
|
||||
bits = []
|
||||
pearson = cls.get("pearson")
|
||||
spearman = cls.get("spearman")
|
||||
r2_lin = cls.get("r2_linear")
|
||||
r2_poly = None
|
||||
for key in ("r2_poly2", "r2_poly3"):
|
||||
v = cls.get(key)
|
||||
if _is_num(v) and (r2_poly is None or float(v) > r2_poly):
|
||||
r2_poly = float(v)
|
||||
if _is_num(pearson):
|
||||
bits.append(f"Pearson r={float(pearson):+.2f}")
|
||||
if _is_num(spearman):
|
||||
bits.append(f"Spearman ρ={float(spearman):+.2f}")
|
||||
if _is_num(r2_lin):
|
||||
bits.append(f"R² lineal={float(r2_lin):.2f}")
|
||||
if r2_poly is not None:
|
||||
bits.append(f"R² polinómico={r2_poly:.2f}")
|
||||
metrics = "; ".join(bits)
|
||||
text = (f"Relación **{tipo}** entre «{a}» y «{b}»."
|
||||
+ (f" {metrics}." if metrics else ""))
|
||||
return text
|
||||
|
||||
|
||||
def _scatter_blocks(pairs: list, raw_numeric):
|
||||
"""Build keep-together scatter Groups for the strongest num-num pairs.
|
||||
|
||||
Returns a list of blocks (a Heading plus one Group per pair), or an empty
|
||||
list when there is no raw numeric data (e.g. the lite profile drops
|
||||
``ctx['raw_numeric']`` to skip live recomputation) or the relationship
|
||||
helpers are unavailable. Never raises: any failure degrades to no scatters,
|
||||
leaving the matrix + tables intact.
|
||||
"""
|
||||
if not isinstance(raw_numeric, dict) or not raw_numeric:
|
||||
return []
|
||||
selected = _select_scatter_pairs(pairs)
|
||||
if not selected:
|
||||
return []
|
||||
|
||||
# The relationship helpers live in the datascience package. Import lazily so
|
||||
# the chapter still builds (matrix + tables) when they are absent.
|
||||
try:
|
||||
from datascience.classify_relationship_type import (
|
||||
classify_relationship_type,
|
||||
)
|
||||
from datascience.relationship_scatter_figure import (
|
||||
relationship_scatter_figure,
|
||||
)
|
||||
except Exception: # noqa: BLE001 — degrade, never break the chapter.
|
||||
return []
|
||||
|
||||
groups = []
|
||||
for pair in selected:
|
||||
a = pair.get("a")
|
||||
b = pair.get("b")
|
||||
xs = raw_numeric.get(a)
|
||||
ys = raw_numeric.get(b)
|
||||
# Edge: a selected pair has no raw column (aggregated profile, renamed
|
||||
# column, …) — skip just that pair, keep the rest.
|
||||
if not _is_seq(xs) or not _is_seq(ys):
|
||||
continue
|
||||
try:
|
||||
cls = classify_relationship_type(list(xs), list(ys)) or {}
|
||||
except Exception: # noqa: BLE001
|
||||
continue
|
||||
a_lbl = model._safe_str(a)
|
||||
b_lbl = model._safe_str(b)
|
||||
|
||||
def _make(xs=xs, ys=ys, a_lbl=a_lbl, b_lbl=b_lbl, cls=cls):
|
||||
return relationship_scatter_figure(
|
||||
list(xs), list(ys), x_label=a_lbl, y_label=b_lbl,
|
||||
classification=cls)
|
||||
|
||||
groups.append(model.Group(blocks=[
|
||||
model.Heading(text=f"{a_lbl} ↔ {b_lbl}", level=2),
|
||||
model.Figure(
|
||||
make=_make,
|
||||
caption=(f"Dispersión de «{a_lbl}» frente a «{b_lbl}» con la "
|
||||
"curva de ajuste del mejor modelo.")),
|
||||
model.Markdown(text=_classification_note(a_lbl, b_lbl, cls)),
|
||||
]))
|
||||
|
||||
if not groups:
|
||||
return []
|
||||
intro = model.Markdown(text=(
|
||||
"Para los pares numéricos más fuertes (positivos y negativos) se dibuja "
|
||||
"la nube de puntos con su ajuste y se clasifica el **tipo de relación**: "
|
||||
"**lineal** (una recta basta), **polinómica** (curva de grado 2/3 que "
|
||||
"mejora claramente el ajuste lineal), **monótona no-lineal** (crece o "
|
||||
"decrece siempre pero no en línea recta; Spearman ≫ Pearson) o "
|
||||
"**débil/sin forma**."))
|
||||
return [model.Heading(text="Relaciones más fuertes (scatter)", level=2),
|
||||
intro] + groups
|
||||
|
||||
|
||||
def build_correlacion(profile: dict, ctx: dict):
|
||||
"""Build the Correlation Chapter, or None if there are no pairs to show.
|
||||
|
||||
@@ -392,6 +532,18 @@ def build_correlacion(profile: dict, ctx: dict):
|
||||
"No se han hallado correlaciones negativas significativas entre "
|
||||
"columnas numéricas.")))
|
||||
|
||||
# 2.5) Scatter plots of the strongest numeric-numeric pairs, each with its
|
||||
# fitted curve and a relationship-type label (lineal / polinómica / monótona
|
||||
# / débil). Needs the raw numeric sample (ctx['raw_numeric'], row-aligned);
|
||||
# when it is absent (aggregated/lite profile) the scatters are simply omitted
|
||||
# and the matrix + tables above stand on their own.
|
||||
raw_numeric = None
|
||||
if isinstance(ctx, dict):
|
||||
raw_numeric = ctx.get("raw_numeric") or profile.get("raw_numeric")
|
||||
else:
|
||||
raw_numeric = profile.get("raw_numeric")
|
||||
blocks.extend(_scatter_blocks(pairs, raw_numeric))
|
||||
|
||||
# 3) Spuriousness caveat for level-based correlations (Granger–Newbold).
|
||||
caveat = corr.get("levels_caveat")
|
||||
if isinstance(caveat, str) and caveat.strip():
|
||||
|
||||
@@ -175,6 +175,105 @@ def test_anticorte_matriz_ancha_y_etiquetas_largas_no_se_cortan():
|
||||
assert "azufre" in _pdf_text(pdf)
|
||||
|
||||
|
||||
def _raw_numeric_for_profile(n: int = 80) -> dict:
|
||||
"""Row-aligned raw numeric sample matching the signed pairs of _profile().
|
||||
|
||||
Builds columns with a clear, deterministic shape so the relationship-type
|
||||
classifier has something unambiguous to label:
|
||||
- density vs alcohol: strong negative linear (the top-negative pair).
|
||||
- alcohol vs quality: positive linear.
|
||||
- ph, fixed_acidity, sulphates: filler columns for the remaining pairs.
|
||||
"""
|
||||
import math as _m
|
||||
|
||||
alcohol = [8.0 + 0.05 * i for i in range(n)]
|
||||
density = [1.0 - 0.002 * a for a in alcohol] # neg linear vs alcohol
|
||||
quality = [3.0 + 0.4 * a + (0.1 if i % 2 else -0.1) # pos linear vs alcohol
|
||||
for i, a in enumerate(alcohol)]
|
||||
ph = [3.0 + 0.3 * _m.sin(i / 5.0) for i in range(n)]
|
||||
fixed_acidity = [7.0 - 0.5 * p for p in ph] # neg linear vs ph
|
||||
sulphates = [0.5 + 0.01 * (i % 7) for i in range(n)]
|
||||
return {
|
||||
"alcohol": alcohol, "density": density, "quality": quality,
|
||||
"ph": ph, "fixed_acidity": fixed_acidity, "sulphates": sulphates,
|
||||
}
|
||||
|
||||
|
||||
def test_golden_scatters_de_pares_num_num_con_tipo_de_relacion():
|
||||
"""Con ctx['raw_numeric'], el capítulo añade scatters (Figure dentro de Group)
|
||||
de los pares num-num más fuertes, cada uno con su etiqueta de tipo en texto."""
|
||||
from datascience.automatic_eda.model import Group
|
||||
|
||||
ctx = {"raw_numeric": _raw_numeric_for_profile()}
|
||||
ch = build_correlacion(_profile(), ctx)
|
||||
assert ch is not None
|
||||
groups = [b for b in ch.blocks if isinstance(b, Group)]
|
||||
assert groups, "debe emitir al menos un Group con scatter"
|
||||
# Cada Group lleva su figura (lazy) y una nota de texto con el tipo.
|
||||
for g in groups:
|
||||
gkinds = [b.kind for b in g.blocks]
|
||||
assert "figure" in gkinds and "markdown" in gkinds
|
||||
# La sección y la etiqueta de tipo aparecen como texto plano (extraíble).
|
||||
headings = " ".join(b.text for b in ch.blocks if b.kind == "heading")
|
||||
assert "Relaciones más fuertes" in headings
|
||||
body = " ".join(b.text for g in groups for b in g.blocks
|
||||
if b.kind == "markdown")
|
||||
assert any(t in body for t in
|
||||
("lineal", "polinómica", "monótona", "sin forma"))
|
||||
# El par num-num más fuerte (density ↔ alcohol) tiene scatter; el par cat-cat
|
||||
# (region ↔ type) NO — no es numérico.
|
||||
assert "density" in body or "alcohol" in body
|
||||
assert "region" not in body and "type" not in body
|
||||
|
||||
|
||||
def test_golden_pdf_muestra_scatters_con_etiqueta_de_tipo():
|
||||
"""En el PDF, el capítulo Correlación incluye los scatters y su etiqueta de
|
||||
tipo en texto seleccionable (pdftotext la encuentra)."""
|
||||
prof = _profile()
|
||||
ctx = {"raw_numeric": _raw_numeric_for_profile()}
|
||||
with tempfile.TemporaryDirectory() as d:
|
||||
pdf = os.path.join(d, "corr_scatter.pdf")
|
||||
rp = render_automatic_eda_pdf(prof, pdf, {"title": "EDA — wine",
|
||||
"ctx": ctx})
|
||||
assert rp["path"] == pdf and rp["n_pages"] >= 1
|
||||
txt = _pdf_text(pdf)
|
||||
assert "Relaciones" in txt and "scatter" in txt.lower()
|
||||
# Alguna etiqueta de tipo de relación, en texto.
|
||||
assert any(t in txt for t in
|
||||
("lineal", "polin", "monóton", "monoton", "sin forma"))
|
||||
|
||||
|
||||
def test_edge_sin_raw_numeric_omite_scatters_sin_lanzar():
|
||||
"""profile lite / ctx None: sin raw_numeric el capítulo omite los scatters
|
||||
pero sigue emitiendo matriz + tablas (no lanza)."""
|
||||
from datascience.automatic_eda.model import Group
|
||||
|
||||
for ctx in (None, {}, {"raw_numeric": None}, {"raw_numeric": {}}):
|
||||
ch = build_correlacion(_profile(), ctx)
|
||||
assert ch is not None
|
||||
assert not [b for b in ch.blocks if isinstance(b, Group)]
|
||||
# La matriz y al menos una tabla top siguen presentes.
|
||||
assert any(b.kind == "figure" for b in ch.blocks)
|
||||
assert any(b.kind == "data_table" for b in ch.blocks)
|
||||
|
||||
|
||||
def test_edge_par_sin_columna_cruda_se_omite_sin_lanzar():
|
||||
"""Si un par seleccionado no tiene su columna en raw_numeric, se omite ese
|
||||
par (no lanza); los demás scatters se construyen igual."""
|
||||
from datascience.automatic_eda.model import Group
|
||||
|
||||
raw = _raw_numeric_for_profile()
|
||||
raw.pop("density", None) # rompe el par density ↔ alcohol
|
||||
ch = build_correlacion(_profile(), {"raw_numeric": raw})
|
||||
assert ch is not None
|
||||
groups = [b for b in ch.blocks if isinstance(b, Group)]
|
||||
body = " ".join(b.text for g in groups for b in g.blocks
|
||||
if b.kind == "markdown")
|
||||
# density desaparece de los scatters; otros pares (p.ej. ph↔fixed_acidity,
|
||||
# alcohol↔quality) pueden seguir presentes sin error.
|
||||
assert "density" not in body
|
||||
|
||||
|
||||
def test_glosario_engancha_metodos_y_fdr():
|
||||
"""Mejora 4b: los métodos de correlación (Pearson, Spearman, Cramér's V,
|
||||
razón de correlación) y la corrección por comparaciones múltiples (FDR) se
|
||||
|
||||
@@ -0,0 +1,68 @@
|
||||
---
|
||||
name: classify_relationship_type
|
||||
kind: function
|
||||
lang: py
|
||||
domain: datascience
|
||||
version: "1.0.0"
|
||||
purity: pure
|
||||
signature: "def classify_relationship_type(xs: list, ys: list) -> dict"
|
||||
description: "Clasifica el TIPO de relacion entre dos variables numericas pareadas por indice para el EDA automatico del grupo eda. Limpia los pares de forma defensiva (descarta None/bool/NaN/inf), reusa pearson y spearman_corr del registry y ajusta polinomios de grado 2 y 3 con numpy.polyfit (R^2 manual), y a partir de esas senales etiqueta la forma: 'lineal', 'polinomica (grado 2/3)', 'monotona no-lineal' o 'debil/sin forma'. Orden de decision: debil -> monotona -> polinomica -> lineal (la primera que matchea gana), con umbrales calibrados para datos reales discretos/ruidosos. Devuelve ademas los coeficientes del mejor modelo en orden de numpy.polyval para pintar la curva de ajuste sobre el scatter. Funcion pura no-throw: ante datos insuficientes (menos de 5 pares validos o varianza ~0) o cualquier fallo devuelve el dict canonico con tipo='debil/sin forma' y el resto a None."
|
||||
tags: [eda, correlation, relationship, classification, polyfit, datascience, pure]
|
||||
params:
|
||||
- name: xs
|
||||
desc: "Lista (o tupla) de valores numericos de la primera variable, pareada por indice con ys. Cada par xs[i],ys[i] se descarta si cualquiera de los dos es None, bool, NaN o inf. Lectura defensiva."
|
||||
- name: ys
|
||||
desc: "Lista (o tupla) de valores numericos de la segunda variable, pareada por indice con xs. Mismas reglas de limpieza que xs."
|
||||
output: "Dict con SIEMPRE las mismas 8 claves: tipo (str: 'lineal' | 'polinómica (grado 2)' | 'polinómica (grado 3)' | 'monótona no-lineal' | 'débil/sin forma'); pearson (float|None: coeficiente de Pearson r); r2_linear (float|None: r**2 del ajuste lineal); spearman (float|None: rho de Spearman); r2_poly2 (float|None: R^2 del ajuste polinomico de grado 2); r2_poly3 (float|None: R^2 del ajuste de grado 3); best_degree (int|None: grado del modelo elegido — 1 lineal, 2/3 polinomico, None si monotona/debil); coeffs (list|None: coeficientes del mejor modelo en orden de numpy.polyval para pintar la curva, o None). Ante datos insuficientes o error: tipo='débil/sin forma' y el resto de claves a None."
|
||||
uses_functions: [pearson_py_datascience, spearman_corr_py_datascience]
|
||||
uses_types: []
|
||||
returns: []
|
||||
returns_optional: false
|
||||
error_type: ""
|
||||
imports: [numpy]
|
||||
tested: true
|
||||
tests: ["test_lineal", "test_polinomica_cuadratica", "test_monotona_no_lineal", "test_monotona_exponencial", "test_debil_sin_forma", "test_lista_vacia_no_lanza", "test_longitudes_distintas_no_lanza", "test_todos_none_no_lanza", "test_entradas_none_no_lanza", "test_constante_no_lanza", "test_filtra_nan_inf_bool"]
|
||||
test_file_path: "python/functions/datascience/classify_relationship_type_test.py"
|
||||
file_path: "python/functions/datascience/classify_relationship_type.py"
|
||||
---
|
||||
|
||||
## Ejemplo
|
||||
|
||||
```python
|
||||
import sys, os
|
||||
sys.path.insert(0, os.path.join("python", "functions"))
|
||||
from datascience.classify_relationship_type import classify_relationship_type
|
||||
import numpy as np
|
||||
|
||||
# Relacion claramente cuadratica (forma de parabola) sobre dominio simetrico.
|
||||
x = list(np.linspace(-10, 10, 60))
|
||||
y = [v * v for v in x]
|
||||
|
||||
res = classify_relationship_type(x, y)
|
||||
print(res["tipo"]) # 'polinómica (grado 2)'
|
||||
print(res["best_degree"]) # 2
|
||||
print(res["r2_linear"]) # 0.0 -> el Pearson lineal no ve la parabola
|
||||
print(res["r2_poly2"]) # 1.0
|
||||
print(res["coeffs"]) # [1.0, -0.0, -0.0] -> numpy.polyval(coeffs, x) ~ x**2
|
||||
|
||||
# El capitulo pinta la curva de ajuste cuando coeffs no es None:
|
||||
# if res["coeffs"] is not None:
|
||||
# xs_fit = np.linspace(min(x), max(x), 200)
|
||||
# ys_fit = np.polyval(res["coeffs"], xs_fit)
|
||||
# ax.plot(xs_fit, ys_fit) # curva sobre el ax.scatter(x, y)
|
||||
```
|
||||
|
||||
## Cuando usarla
|
||||
|
||||
- Usala en el capitulo de relaciones/correlaciones del EDA automatico, despues de detectar dos columnas numericas con alguna asociacion, para decidir QUE curva de ajuste pintar sobre el scatter (recta, parabola, cubica o ninguna) y poner una etiqueta legible al tipo de relacion.
|
||||
- Cuando un Pearson bajo no signifique "sin relacion": esta funcion cruza Pearson con Spearman y con ajustes polinomicos para distinguir una relacion lineal debil de una monotona no-lineal (que el rango si capta) o de una curva polinomica.
|
||||
- Cuando necesites un punto de entrada determinista y no-throw que, con los mismos datos, devuelva siempre el mismo `tipo` y los mismos `coeffs` listos para `numpy.polyval` sin tener que ajustar modelos a mano en el capitulo.
|
||||
|
||||
## Gotchas
|
||||
|
||||
- Funcion pura, deterministica y no-throw: ante menos de 5 pares validos, varianza ~0 (xs o ys constante) o cualquier excepcion interna devuelve el dict canonico `tipo="débil/sin forma"` con el resto de claves a `None`. El dict SIEMPRE trae las 8 claves: nunca compruebes existencia, comprueba `None`.
|
||||
- El orden de decision importa: `débil -> monótona -> polinómica -> lineal` (la primera que matchee gana). La monotonia se evalua ANTES que el ajuste polinomico, asi que una curva monotona suave (exp, log, potencias) sale `monótona no-lineal` aunque un cubico tambien la ajuste — la dominancia del rango (Spearman >> Pearson) es la senal mas interpretable. Solo cae en `polinómica` una forma curva NO monotona (p.ej. una parabola, Spearman ~0 pero R^2 polinomico alto).
|
||||
- Umbrales fijos (calibrados para EDA con datos discretos/ruidosos, no para inferencia formal): `débil/sin forma` si las tres senales son bajas a la vez (`abs(pearson) < 0.3` y `abs(spearman) < 0.3` y `mejor_poly < 0.3`); `monótona no-lineal` si `abs(spearman) - abs(pearson) >= 0.1` y `abs(spearman) >= 0.4`; `polinómica (grado N)` si el mejor polinomico mejora `>= 0.1` sobre el lineal y su R^2 `>= 0.3`; en cualquier otro caso con senal (no debil) `lineal`. El suelo de 0.3 evita llamar "debil" a relaciones reales pero discretas (conteos, escalas ordinales) con R^2 bajo pero direccion clara.
|
||||
- `coeffs` va en orden de `numpy.polyval` (grado descendente). Para `lineal` es `[pendiente, intercepto]` (grado 1); para `polinómica` los del grado elegido; para `monótona no-lineal` y `débil/sin forma` es `None` (el scatter pintara una curva suavizada o nada — lo decide el capitulo, no esta funcion).
|
||||
- `best_degree` prefiere el grado 2 sobre el 3 cuando empatan dentro de 0.02 de R^2 (parsimonia): no esperes grado 3 salvo que mejore claramente.
|
||||
- Los pares con `None`, `bool`, `NaN` o `inf` se descartan por indice en silencio; `bool` cuenta como no-numerico (un `True` no es `1`). El dominio de los datos afecta al resultado: una parabola sobre un dominio simetrico da Pearson ~0 (sale `polinómica`), pero sobre un dominio asimetrico el Pearson sube y puede salir `lineal`.
|
||||
@@ -0,0 +1,187 @@
|
||||
"""Clasifica el TIPO de relacion entre dos variables numericas pareadas.
|
||||
|
||||
Funcion pura del grupo eda. Dadas dos listas numericas pareadas por indice,
|
||||
limpia los pares de forma defensiva, calcula correlaciones lineal (Pearson) y de
|
||||
rangos (Spearman) y ajustes polinomicos de grado 2 y 3, y a partir de esas
|
||||
senales etiqueta la forma de la relacion para el EDA automatico:
|
||||
|
||||
"lineal" | "polinómica (grado 2)" | "polinómica (grado 3)" |
|
||||
"monótona no-lineal" | "débil/sin forma"
|
||||
|
||||
Ademas devuelve los coeficientes del mejor modelo (en orden de numpy.polyval)
|
||||
para que el capitulo pinte la curva de ajuste sobre el scatter. Reusa las
|
||||
funciones del registry `pearson` y `spearman_corr` en vez de reimplementarlas.
|
||||
|
||||
NUNCA lanza: ante cualquier fallo o dato insuficiente devuelve el dict canonico
|
||||
con tipo="débil/sin forma" y el resto de claves a None.
|
||||
"""
|
||||
|
||||
import math
|
||||
import warnings
|
||||
|
||||
import numpy as np
|
||||
|
||||
from datascience.datascience import pearson
|
||||
from datascience.spearman_corr import spearman_corr
|
||||
|
||||
# Forma canonica de la respuesta cuando no se puede clasificar (datos
|
||||
# insuficientes, varianza nula o error interno). Siempre las mismas claves.
|
||||
_WEAK = {
|
||||
"tipo": "débil/sin forma",
|
||||
"pearson": None,
|
||||
"r2_linear": None,
|
||||
"spearman": None,
|
||||
"r2_poly2": None,
|
||||
"r2_poly3": None,
|
||||
"best_degree": None,
|
||||
"coeffs": None,
|
||||
}
|
||||
|
||||
|
||||
def _is_num(v) -> bool:
|
||||
"""True si v es un numero real finito (int/float, no bool, no NaN, no inf)."""
|
||||
return (
|
||||
isinstance(v, (int, float))
|
||||
and not isinstance(v, bool)
|
||||
and not (isinstance(v, float) and (math.isnan(v) or math.isinf(v)))
|
||||
)
|
||||
|
||||
|
||||
def _poly_r2(coeffs, x_arr, y_arr, ss_tot: float) -> float:
|
||||
"""R^2 de un ajuste polinomico: 1 - SS_res/SS_tot. 0 si SS_tot==0."""
|
||||
if ss_tot == 0.0:
|
||||
return 0.0
|
||||
pred = np.polyval(coeffs, x_arr)
|
||||
ss_res = float(np.sum((y_arr - pred) ** 2))
|
||||
return 1.0 - ss_res / ss_tot
|
||||
|
||||
|
||||
def classify_relationship_type(xs: list, ys: list) -> dict:
|
||||
"""Clasifica el tipo de relacion entre dos variables numericas pareadas.
|
||||
|
||||
Empareja xs[i],ys[i] por indice y descarta el par si cualquiera de los dos
|
||||
es None, bool, NaN o inf. Sobre los pares limpios calcula Pearson r
|
||||
(r2_linear = r**2), Spearman rho y los R^2 de ajustes polinomicos de grado 2
|
||||
y 3 (con numpy.polyfit + R^2 manual). Con esas senales decide la etiqueta.
|
||||
|
||||
Orden de evaluacion de la etiqueta (la primera que matchee gana). Los
|
||||
umbrales estan calibrados para datos reales, a menudo discretos y ruidosos
|
||||
(conteos, escalas ordinales): una relacion con |r| >= 0.3, |rho| >= 0.3 o un
|
||||
polinomio con R^2 >= 0.3 ya tiene FORMA y no debe etiquetarse como "debil".
|
||||
1. "débil/sin forma" — todas las senales bajas a la vez:
|
||||
abs(pearson) < 0.3 y abs(spearman) < 0.3 y mejor_poly < 0.3.
|
||||
2. "monótona no-lineal" — el rango (Spearman) capta una monotonia que el
|
||||
Pearson lineal no: abs(spearman) - abs(pearson) >= 0.1 y
|
||||
abs(spearman) >= 0.4. No se fuerza un polinomio (coeffs/best_degree =
|
||||
None); el capitulo dibuja la tendencia ordenada sobre el scatter.
|
||||
3. "polinómica (grado N)" — el mejor polinomico mejora claramente sobre
|
||||
el lineal (mejor_poly - r2_linear >= 0.1) y mejor_poly >= 0.3. N es el
|
||||
grado (2 o 3) con mejor R^2, prefiriendo el 2 si empatan dentro de 0.02
|
||||
(parsimonia).
|
||||
4. "lineal" — el resto: hay senal (no es debil) y la forma que existe es
|
||||
esencialmente lineal. best_degree=1, coeffs del ajuste de grado 1.
|
||||
|
||||
Si hay menos de 5 pares validos, o la varianza de xs o de ys es ~0
|
||||
(constante), devuelve directamente "débil/sin forma".
|
||||
|
||||
Args:
|
||||
xs: lista (o tupla) de valores numericos de la primera variable,
|
||||
pareada por indice con ys. Pares con None/bool/NaN/inf se descartan.
|
||||
ys: lista (o tupla) de valores numericos de la segunda variable,
|
||||
pareada por indice con xs.
|
||||
|
||||
Returns:
|
||||
dict con SIEMPRE las mismas claves:
|
||||
tipo (str), pearson (float|None), r2_linear (float|None),
|
||||
spearman (float|None), r2_poly2 (float|None), r2_poly3 (float|None),
|
||||
best_degree (int|None: 1, 2, 3 o None),
|
||||
coeffs (list|None: coeficientes en orden de numpy.polyval, o None).
|
||||
Nunca lanza: ante fallo o datos insuficientes devuelve el dict debil.
|
||||
"""
|
||||
try:
|
||||
if xs is None or ys is None:
|
||||
return dict(_WEAK)
|
||||
|
||||
pairs = [
|
||||
(float(x), float(y))
|
||||
for x, y in zip(xs, ys)
|
||||
if _is_num(x) and _is_num(y)
|
||||
]
|
||||
|
||||
# Datos insuficientes para hablar de forma de la relacion.
|
||||
if len(pairs) < 5:
|
||||
return dict(_WEAK)
|
||||
|
||||
clean_x = [p[0] for p in pairs]
|
||||
clean_y = [p[1] for p in pairs]
|
||||
|
||||
# Varianza ~0 en cualquiera de las series => relacion indefinida.
|
||||
if len(set(clean_x)) < 2 or len(set(clean_y)) < 2:
|
||||
return dict(_WEAK)
|
||||
x_arr = np.asarray(clean_x, dtype=float)
|
||||
y_arr = np.asarray(clean_y, dtype=float)
|
||||
if float(np.var(x_arr)) < 1e-15 or float(np.var(y_arr)) < 1e-15:
|
||||
return dict(_WEAK)
|
||||
|
||||
# Correlaciones reutilizando las funciones del registry.
|
||||
r = pearson(clean_x, clean_y)
|
||||
spearman = spearman_corr(clean_x, clean_y)
|
||||
r2_linear = r ** 2
|
||||
|
||||
# Ajustes polinomicos grado 2 y 3 con R^2 manual.
|
||||
ss_tot = float(np.sum((y_arr - float(np.mean(y_arr))) ** 2))
|
||||
with warnings.catch_warnings():
|
||||
warnings.simplefilter("ignore")
|
||||
c1 = np.polyfit(x_arr, y_arr, 1)
|
||||
c2 = np.polyfit(x_arr, y_arr, 2)
|
||||
c3 = np.polyfit(x_arr, y_arr, 3)
|
||||
r2_poly2 = _poly_r2(c2, x_arr, y_arr, ss_tot)
|
||||
r2_poly3 = _poly_r2(c3, x_arr, y_arr, ss_tot)
|
||||
|
||||
mejor_poly = max(r2_poly2, r2_poly3)
|
||||
# Grado del mejor polinomico, con preferencia por la parsimonia: solo se
|
||||
# elige el grado 3 si supera al grado 2 por mas de 0.02.
|
||||
best_poly_degree = 3 if (r2_poly3 - r2_poly2) > 0.02 else 2
|
||||
|
||||
abs_s = abs(spearman)
|
||||
abs_p = abs(r)
|
||||
|
||||
# Decision en orden: debil-temprano -> monotona -> polinomica -> lineal.
|
||||
if abs_p < 0.3 and abs_s < 0.3 and mejor_poly < 0.3:
|
||||
# Ninguna senal supera el suelo de forma: relacion debil/sin forma.
|
||||
tipo = "débil/sin forma"
|
||||
best_degree = None
|
||||
coeffs = None
|
||||
elif (abs_s - abs_p) >= 0.1 and abs_s >= 0.4:
|
||||
# Spearman (rango) capta una monotonia que el Pearson lineal no:
|
||||
# relacion monotona no-lineal. No se fuerza un polinomio que tal vez
|
||||
# no ajusta bien; el capitulo dibuja la tendencia ordenada.
|
||||
tipo = "monótona no-lineal"
|
||||
best_degree = None
|
||||
coeffs = None
|
||||
elif (mejor_poly - r2_linear) >= 0.1 and mejor_poly >= 0.3:
|
||||
tipo = "polinómica (grado {})".format(best_poly_degree)
|
||||
best_degree = best_poly_degree
|
||||
best_coeffs = c2 if best_poly_degree == 2 else c3
|
||||
coeffs = [float(c) for c in best_coeffs]
|
||||
else:
|
||||
# Hay senal (no es debil) y no es ni monotona-pura ni polinomica:
|
||||
# la correlacion que existe es esencialmente lineal.
|
||||
tipo = "lineal"
|
||||
best_degree = 1
|
||||
coeffs = [float(c) for c in c1]
|
||||
|
||||
return {
|
||||
"tipo": tipo,
|
||||
"pearson": round(float(r), 6),
|
||||
"r2_linear": round(float(r2_linear), 6),
|
||||
"spearman": round(float(spearman), 6),
|
||||
"r2_poly2": round(float(r2_poly2), 6),
|
||||
"r2_poly3": round(float(r2_poly3), 6),
|
||||
"best_degree": best_degree,
|
||||
"coeffs": (
|
||||
[round(c, 8) for c in coeffs] if coeffs is not None else None
|
||||
),
|
||||
}
|
||||
except Exception:
|
||||
return dict(_WEAK)
|
||||
@@ -0,0 +1,174 @@
|
||||
"""Tests para classify_relationship_type."""
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
import numpy as np
|
||||
|
||||
sys.path.insert(0, os.path.dirname(__file__))
|
||||
|
||||
from classify_relationship_type import classify_relationship_type
|
||||
|
||||
# Claves que el dict de salida debe contener SIEMPRE.
|
||||
_EXPECTED_KEYS = {
|
||||
"tipo", "pearson", "r2_linear", "spearman",
|
||||
"r2_poly2", "r2_poly3", "best_degree", "coeffs",
|
||||
}
|
||||
|
||||
|
||||
def _assert_shape(r):
|
||||
"""Toda salida tiene exactamente las 8 claves canonicas."""
|
||||
assert isinstance(r, dict)
|
||||
assert set(r.keys()) == _EXPECTED_KEYS
|
||||
|
||||
|
||||
def test_lineal():
|
||||
"""Golden: y = 2x + 1 con ruido pequeno -> 'lineal', best_degree=1."""
|
||||
rng = np.random.default_rng(42)
|
||||
x = np.linspace(0.0, 10.0, 50)
|
||||
y = 2.0 * x + 1.0 + rng.normal(0.0, 0.3, 50)
|
||||
|
||||
r = classify_relationship_type(list(x), list(y))
|
||||
_assert_shape(r)
|
||||
|
||||
assert r["tipo"] == "lineal"
|
||||
assert r["best_degree"] == 1
|
||||
assert r["r2_linear"] >= 0.5
|
||||
# coeffs ~ [pendiente, intercepto] del ajuste de grado 1.
|
||||
assert r["coeffs"] is not None and len(r["coeffs"]) == 2
|
||||
assert abs(r["coeffs"][0] - 2.0) < 0.1 # pendiente ~2
|
||||
assert abs(r["coeffs"][1] - 1.0) < 0.3 # intercepto ~1
|
||||
|
||||
|
||||
def test_polinomica_cuadratica():
|
||||
"""Golden: y = x**2 sobre [-10, 10] -> 'polinómica', best_degree in (2, 3)."""
|
||||
x = np.linspace(-10.0, 10.0, 60)
|
||||
y = x ** 2
|
||||
|
||||
r = classify_relationship_type(list(x), list(y))
|
||||
_assert_shape(r)
|
||||
|
||||
assert r["tipo"].startswith("polinómica")
|
||||
assert r["best_degree"] in (2, 3)
|
||||
# Una parabola perfecta queda capturada por el grado 2 (parsimonia).
|
||||
assert r["best_degree"] == 2
|
||||
assert r["r2_poly2"] > 0.99
|
||||
assert r["coeffs"] is not None and len(r["coeffs"]) == r["best_degree"] + 1
|
||||
|
||||
|
||||
def test_monotona_no_lineal():
|
||||
"""Golden: monotona convexa de cola pesada -> 'monótona no-lineal'.
|
||||
|
||||
y = 1/(N+1-i)**2 es estrictamente creciente (Spearman ~ 1) pero su cola
|
||||
explosiva hace que ni la recta ni un polinomio de grado 2/3 la ajusten
|
||||
(R^2 polinomico < 0.5), de modo que el Pearson lineal NO capta la relacion
|
||||
que el rango (Spearman) si ve. Construccion deterministica (sin azar).
|
||||
"""
|
||||
n = 200
|
||||
i = np.arange(n, dtype=float)
|
||||
y = 1.0 / (n + 1 - i) ** 2
|
||||
|
||||
r = classify_relationship_type(list(i), list(y))
|
||||
_assert_shape(r)
|
||||
|
||||
assert r["tipo"] == "monótona no-lineal"
|
||||
assert r["best_degree"] is None
|
||||
assert r["coeffs"] is None
|
||||
# Spearman fuerte y claramente por encima del Pearson.
|
||||
assert abs(r["spearman"]) >= 0.5
|
||||
assert abs(r["spearman"]) - abs(r["pearson"]) >= 0.15
|
||||
|
||||
|
||||
def test_monotona_exponencial():
|
||||
"""DoD literal: y = exp(x) (monotona no-lineal) -> 'monótona no-lineal'.
|
||||
|
||||
exp es estrictamente creciente (Spearman = 1) pero el Pearson lineal queda
|
||||
claramente por debajo (~0.86), así que la dominancia del rango la marca como
|
||||
monótona no-lineal en vez de lineal o polinómica.
|
||||
"""
|
||||
x = np.linspace(0.0, 5.0, 80)
|
||||
y = np.exp(x)
|
||||
|
||||
r = classify_relationship_type(list(x), list(y))
|
||||
_assert_shape(r)
|
||||
|
||||
assert r["tipo"] == "monótona no-lineal"
|
||||
assert r["best_degree"] is None and r["coeffs"] is None
|
||||
assert abs(r["spearman"]) >= 0.9
|
||||
assert abs(r["spearman"]) - abs(r["pearson"]) >= 0.1
|
||||
|
||||
|
||||
def test_debil_sin_forma():
|
||||
"""Golden: x e y independientes (semilla fija) -> 'débil/sin forma'."""
|
||||
rng = np.random.default_rng(0)
|
||||
x = rng.normal(0.0, 1.0, 200)
|
||||
y = rng.normal(0.0, 1.0, 200)
|
||||
|
||||
r = classify_relationship_type(list(x), list(y))
|
||||
_assert_shape(r)
|
||||
|
||||
assert r["tipo"] == "débil/sin forma"
|
||||
assert r["best_degree"] is None
|
||||
assert r["coeffs"] is None
|
||||
# Todas las senales son bajas.
|
||||
assert abs(r["pearson"]) < 0.3
|
||||
assert r["r2_linear"] < 0.1
|
||||
|
||||
|
||||
def test_lista_vacia_no_lanza():
|
||||
"""Edge: listas vacias -> dict debil canonico, sin lanzar."""
|
||||
r = classify_relationship_type([], [])
|
||||
_assert_shape(r)
|
||||
assert r["tipo"] == "débil/sin forma"
|
||||
assert r["pearson"] is None
|
||||
assert r["r2_linear"] is None
|
||||
assert r["spearman"] is None
|
||||
assert r["r2_poly2"] is None
|
||||
assert r["r2_poly3"] is None
|
||||
assert r["best_degree"] is None
|
||||
assert r["coeffs"] is None
|
||||
|
||||
|
||||
def test_longitudes_distintas_no_lanza():
|
||||
"""Edge: listas de distinta longitud -> empareja por indice, no lanza."""
|
||||
# zip trunca a la longitud minima: solo 3 pares (< 5) -> debil.
|
||||
r = classify_relationship_type([1, 2, 3, 4, 5, 6, 7, 8], [1.0, 2.0, 3.0])
|
||||
_assert_shape(r)
|
||||
assert r["tipo"] == "débil/sin forma"
|
||||
assert r["best_degree"] is None
|
||||
|
||||
|
||||
def test_todos_none_no_lanza():
|
||||
"""Edge: todos los valores None -> ningun par valido -> debil, no lanza."""
|
||||
r = classify_relationship_type([None, None, None, None, None, None],
|
||||
[None, None, None, None, None, None])
|
||||
_assert_shape(r)
|
||||
assert r["tipo"] == "débil/sin forma"
|
||||
assert r["coeffs"] is None
|
||||
|
||||
|
||||
def test_entradas_none_no_lanza():
|
||||
"""Edge: xs/ys None directamente -> debil, no lanza."""
|
||||
assert classify_relationship_type(None, None)["tipo"] == "débil/sin forma"
|
||||
assert classify_relationship_type([1.0, 2.0], None)["tipo"] == "débil/sin forma"
|
||||
|
||||
|
||||
def test_constante_no_lanza():
|
||||
"""Edge: ys constante (varianza ~0) -> debil, no lanza."""
|
||||
r = classify_relationship_type([1, 2, 3, 4, 5, 6, 7], [5, 5, 5, 5, 5, 5, 5])
|
||||
_assert_shape(r)
|
||||
assert r["tipo"] == "débil/sin forma"
|
||||
|
||||
|
||||
def test_filtra_nan_inf_bool():
|
||||
"""Edge: pares con NaN/inf/bool/None se descartan por indice."""
|
||||
nan = float("nan")
|
||||
inf = float("inf")
|
||||
# Solo i=0,1,2,3,4 quedan validos (5 pares) y forman una recta perfecta.
|
||||
xs = [0.0, 1.0, 2.0, 3.0, 4.0, nan, inf, True, None]
|
||||
ys = [1.0, 3.0, 5.0, 7.0, 9.0, 1.0, 2.0, 3.0, 4.0]
|
||||
r = classify_relationship_type(xs, ys)
|
||||
_assert_shape(r)
|
||||
# Los 5 pares validos son y = 2x + 1 exacto -> lineal.
|
||||
assert r["tipo"] == "lineal"
|
||||
assert r["best_degree"] == 1
|
||||
@@ -0,0 +1,122 @@
|
||||
---
|
||||
id: relationship_scatter_figure_py_datascience
|
||||
name: relationship_scatter_figure
|
||||
kind: function
|
||||
lang: py
|
||||
domain: datascience
|
||||
version: "1.0.0"
|
||||
purity: impure
|
||||
signature: "def relationship_scatter_figure(xs: list, ys: list, x_label: str = \"\", y_label: str = \"\", classification: dict = None, max_points: int = 2000) -> \"matplotlib.figure.Figure\""
|
||||
description: "Construye una figura matplotlib scatter de un par de variables numéricas con su curva/recta de ajuste y una anotación del tipo de relación (lineal, polinómica grado 2/3, monótona no-lineal, etc.) más sus métricas (r, ρ, R²lin, R²poly). Consume el dict de classify_relationship_type; si es None lo calcula internamente reusando esa función. Devuelve un matplotlib.figure.Figure listo para rasterizar por el renderer del informe EDA (PDF/PPTX). Backend Agg sin pyplot global; downsample determinista de los puntos dibujados; defensivo ante vacío/None."
|
||||
tags: [eda, correlation, scatter, relationship, matplotlib, figure, visualization, datascience, impure]
|
||||
uses_functions: [classify_relationship_type_py_datascience]
|
||||
uses_types: []
|
||||
returns: []
|
||||
returns_optional: false
|
||||
error_type: "error_go_core"
|
||||
imports: [matplotlib, numpy]
|
||||
example: |
|
||||
from relationship_scatter_figure import relationship_scatter_figure
|
||||
xs = [float(i) for i in range(100)]
|
||||
ys = [0.5 * x * x - x + 3 for x in xs]
|
||||
classification = {
|
||||
"tipo": "polinómica (grado 2)", "pearson": 0.97, "spearman": 0.99,
|
||||
"r2_linear": 0.92, "r2_poly2": 0.999, "r2_poly3": 0.999,
|
||||
"best_degree": 2, "coeffs": [0.5, -1.0, 3.0],
|
||||
}
|
||||
fig = relationship_scatter_figure(xs, ys, x_label="dosis", y_label="efecto", classification=classification)
|
||||
tested: true
|
||||
tests:
|
||||
- "test_returns_figure"
|
||||
- "test_downsample_determinista"
|
||||
- "test_empty_no_lanza"
|
||||
- "test_classification_none"
|
||||
test_file_path: "python/functions/datascience/relationship_scatter_figure_test.py"
|
||||
file_path: "python/functions/datascience/relationship_scatter_figure.py"
|
||||
params:
|
||||
- name: xs
|
||||
desc: "Lista (o tupla) de valores x. Se emparejan por índice con ys. Valores None, bool, NaN o inf descartan ese par (lectura defensiva)."
|
||||
- name: ys
|
||||
desc: "Lista (o tupla) de valores y, paralela a xs. Mismas reglas defensivas que xs."
|
||||
- name: x_label
|
||||
desc: "Etiqueta del eje/título para la variable x. Default \"\" (en el título cae a \"x\")."
|
||||
- name: y_label
|
||||
desc: "Etiqueta del eje/título para la variable y. Default \"\" (en el título cae a \"y\")."
|
||||
- name: classification
|
||||
desc: "Opcional. Dict de classify_relationship_type con claves tipo, pearson, r2_linear, spearman, r2_poly2, r2_poly3, best_degree, coeffs. Si es None se calcula internamente importando y llamando a classify_relationship_type sobre los pares limpios (self-contained). Si el módulo hermano no está disponible, se dibuja el scatter sin curva de ajuste ni anotación. Default None."
|
||||
- name: max_points
|
||||
desc: "Tope del nº de puntos DIBUJADOS. Si los pares limpios superan el tope, la nube se submuestrea por paso fijo ceil(n/max_points) tomando pairs[::step] — DETERMINISTA, no aleatorio, reproducible. La clasificación/ajuste usa SIEMPRE todos los pares limpios; el downsample solo adelgaza el dibujo. Valor no-positivo o no-int desactiva el downsample. Default 2000."
|
||||
output: "Un matplotlib.figure.Figure (figsize 6.4x4.0, dpi 150) con un Axes scatter (puntos semitransparentes alpha 0.5, color #4C72B0), la curva/recta de ajuste (numpy.polyval sobre coeffs, color #C44E52) cuando hay un ajuste polinómico disponible, título \"{x_label} ↔ {y_label}\", labels de ejes y una caja de anotación en la esquina superior izquierda con el tipo de relación y las métricas disponibles (r, ρ, R²lin, R²poly; se omiten las None). Si tras la limpieza hay menos de 2 pares válidos, devuelve igualmente una Figure con un texto centrado \"Sin datos suficientes para el scatter\" (nunca lanza). El caller rasteriza/cierra la figura; la función no la muestra ni la guarda."
|
||||
---
|
||||
|
||||
## Ejemplo
|
||||
|
||||
```python
|
||||
from relationship_scatter_figure import relationship_scatter_figure
|
||||
|
||||
# Par numérico con relación cuadrática y su clasificación (de
|
||||
# classify_relationship_type). Pasándola explícita evitas recomputarla.
|
||||
xs = [float(i) for i in range(100)]
|
||||
ys = [0.5 * x * x - x + 3 for x in xs]
|
||||
classification = {
|
||||
"tipo": "polinómica (grado 2)",
|
||||
"pearson": 0.97,
|
||||
"spearman": 0.99,
|
||||
"r2_linear": 0.92,
|
||||
"r2_poly2": 0.999,
|
||||
"r2_poly3": 0.999,
|
||||
"best_degree": 2,
|
||||
"coeffs": [0.5, -1.0, 3.0],
|
||||
}
|
||||
|
||||
fig = relationship_scatter_figure(
|
||||
xs, ys, x_label="dosis", y_label="efecto", classification=classification
|
||||
)
|
||||
|
||||
# El renderer del informe lo rasteriza; aquí solo persistimos para inspección.
|
||||
fig.savefig("/tmp/scatter_dosis_efecto.png")
|
||||
|
||||
# Con classification=None la función la calcula internamente (self-contained):
|
||||
fig2 = relationship_scatter_figure(xs, ys, x_label="dosis", y_label="efecto")
|
||||
```
|
||||
|
||||
## Cuando usarla
|
||||
|
||||
Úsala dentro del informe EDA automático cuando quieras visualizar de un vistazo
|
||||
la relación entre dos variables numéricas: la nube de puntos, la curva que mejor
|
||||
la ajusta y una etiqueta legible del tipo de relación con sus métricas. Es la
|
||||
pareja "vista humana" de `classify_relationship_type`: esa función decide el
|
||||
tipo y los coeficientes; esta los pinta en una `Figure` que el renderer del
|
||||
informe rasteriza a PDF/PPTX. Pásale el dict de clasificación si ya lo tienes
|
||||
calculado (evitas recomputar el ajuste); si no, déjalo en `None` y la función lo
|
||||
resuelve sola sobre los pares limpios. Pensada para móvil: anotación pequeña
|
||||
(fontsize 8) y nube adelgazada por `max_points` para que el PDF no pese.
|
||||
|
||||
## Gotchas
|
||||
|
||||
- **Impura por matplotlib.** Toca la maquinaria de render. Usa el backend `Agg`
|
||||
y la API orientada a objetos `Figure`/`add_subplot` — NUNCA `pyplot.*` aquí,
|
||||
para no tocar el estado global ni filtrar figuras entre llamadas. `pyplot` NO
|
||||
es thread-safe; esta función lo evita construyendo el `Figure` directamente,
|
||||
así que es segura de llamar en bucle desde el renderer.
|
||||
- **El caller cierra la figura.** Devuelve el `Figure` pero no lo muestra ni lo
|
||||
guarda. Quien la consume debe rasterizarla y luego liberarla
|
||||
(`matplotlib.pyplot.close(fig)`) para no acumular memoria en lotes grandes de
|
||||
pares de columnas.
|
||||
- **Downsample determinista, solo del dibujo.** Cuando los pares limpios superan
|
||||
`max_points`, la nube DIBUJADA se adelgaza por paso fijo `pairs[::step]`
|
||||
(reproducible, no aleatorio). La clasificación y el ajuste usan SIEMPRE todos
|
||||
los pares limpios; el downsample no altera las métricas ni la curva.
|
||||
- **`classification=None` ⇒ se calcula sola.** Importa y llama a
|
||||
`classify_relationship_type` sobre los pares limpios. Si ese módulo hermano no
|
||||
está disponible (entorno incompleto), NO lanza: dibuja el scatter sin curva de
|
||||
ajuste ni anotación. Pasar la clasificación explícita es más barato (no
|
||||
recomputa el ajuste).
|
||||
- **Sin curva para `monótona no-lineal`.** Cuando `coeffs` es `None` o
|
||||
`best_degree` es `None` (p.ej. tipo "monótona no-lineal"), no se pinta recta
|
||||
polinómica — solo la nube y la anotación. Tampoco se dibuja la curva si el
|
||||
rango de x es nulo (todos los x iguales). Nunca falla por esto.
|
||||
- **Defensiva, nunca lanza.** `xs=[]`, `ys=[]`, menos de 2 pares válidos, ends
|
||||
`None`/`bool`/`NaN`/`inf` o `coeffs` malformado se manejan sin error: en el
|
||||
peor caso devuelve una `Figure` con "Sin datos suficientes para el scatter".
|
||||
No envuelvas la llamada en try/except por miedo a un raise — no lo hay.
|
||||
@@ -0,0 +1,322 @@
|
||||
"""Impure EDA helper: scatter figure of a numeric pair with its fit (`eda` group).
|
||||
|
||||
Builds a matplotlib scatter of two numeric variables, overlays the fitted
|
||||
curve/line implied by the relationship classification (linear, polynomial of
|
||||
degree 2/3, etc.) and annotates the relationship type with its available
|
||||
metrics. Returns a ready-to-rasterize ``matplotlib.figure.Figure``; it never
|
||||
shows nor saves it.
|
||||
|
||||
Impure because it touches matplotlib's rendering machinery. It uses the headless
|
||||
Agg backend and the object-oriented ``Figure`` API (no ``pyplot``) so it leaks no
|
||||
global state and is safe to call repeatedly from a report renderer.
|
||||
|
||||
To keep the rendered PDF/PPTX light on phones, when the number of valid pairs
|
||||
exceeds ``max_points`` the *plotted* points are down-sampled DETERMINISTICALLY by
|
||||
a fixed step (``pairs[::step]``), never randomly, so the output is reproducible.
|
||||
The classification/fit always uses every clean pair; the down-sample only thins
|
||||
the drawn cloud.
|
||||
"""
|
||||
|
||||
import math
|
||||
|
||||
import matplotlib
|
||||
|
||||
matplotlib.use("Agg")
|
||||
|
||||
import numpy as np # noqa: E402
|
||||
from matplotlib.figure import Figure # noqa: E402
|
||||
|
||||
# Sober blue for the scatter cloud and red for the fitted curve (Tufte: the
|
||||
# data points are the primary ink, the fit is the secondary highlight).
|
||||
_POINT_COLOR = "#4C72B0"
|
||||
_FIT_COLOR = "#C44E52"
|
||||
# Muted gray for the no-data fallback message.
|
||||
_MUTED_TEXT = "#5f6b7a"
|
||||
|
||||
|
||||
def _finite(value):
|
||||
"""Coerce ``value`` to a finite float, or return None when not usable.
|
||||
|
||||
bool is a subclass of int, but a real numeric measurement is never a bool,
|
||||
so True/False are treated as missing instead of coercing to 1.0/0.0. NaN and
|
||||
+/-infinity are never valid either.
|
||||
"""
|
||||
if value is None or isinstance(value, bool):
|
||||
return None
|
||||
try:
|
||||
f = float(value)
|
||||
except (TypeError, ValueError):
|
||||
return None
|
||||
if math.isnan(f) or math.isinf(f):
|
||||
return None
|
||||
return f
|
||||
|
||||
|
||||
def _clean_pairs(xs, ys):
|
||||
"""Pair ``xs[i], ys[i]`` by index, dropping any pair with a non-finite end."""
|
||||
pairs = []
|
||||
if isinstance(xs, (list, tuple)) and isinstance(ys, (list, tuple)):
|
||||
n = min(len(xs), len(ys))
|
||||
for i in range(n):
|
||||
x = _finite(xs[i])
|
||||
y = _finite(ys[i])
|
||||
if x is None or y is None:
|
||||
continue
|
||||
pairs.append((x, y))
|
||||
return pairs
|
||||
|
||||
|
||||
def _ordered_trend(xs_clean, ys_clean, n_bins: int = 12):
|
||||
"""Return (x_trend, y_trend): the ordered trend of y over x for a monotonic
|
||||
relationship that has no polynomial fit.
|
||||
|
||||
When x has few distinct values (an ordinal/discrete scale) the trend is the
|
||||
mean of y per distinct x value. Otherwise x is split into ``n_bins`` ordered
|
||||
quantile bins and each point is (mean x, mean y) of the bin. Returns
|
||||
``(None, None)`` when there is nothing meaningful to draw.
|
||||
"""
|
||||
x_arr = np.asarray(xs_clean, dtype=float)
|
||||
y_arr = np.asarray(ys_clean, dtype=float)
|
||||
if x_arr.size < 2:
|
||||
return None, None
|
||||
uniq = np.unique(x_arr)
|
||||
if uniq.size <= max(2, n_bins):
|
||||
# Discrete x: one trend point per distinct value (mean y).
|
||||
xt = uniq
|
||||
yt = np.array([float(np.mean(y_arr[x_arr == ux])) for ux in uniq])
|
||||
return xt, yt
|
||||
# Continuous x: ordered quantile bins, (mean x, mean y) per bin.
|
||||
order = np.argsort(x_arr, kind="stable")
|
||||
x_sorted = x_arr[order]
|
||||
y_sorted = y_arr[order]
|
||||
chunks_x = np.array_split(x_sorted, n_bins)
|
||||
chunks_y = np.array_split(y_sorted, n_bins)
|
||||
xt = np.array([float(np.mean(cx)) for cx in chunks_x if cx.size])
|
||||
yt = np.array([float(np.mean(cy)) for cy in chunks_y if cy.size])
|
||||
return xt, yt
|
||||
|
||||
|
||||
def _no_data_figure(message: str) -> "matplotlib.figure.Figure":
|
||||
"""A bare Figure carrying a centered muted message (defensive fallback)."""
|
||||
fig = Figure(figsize=(6.4, 4.0), dpi=150)
|
||||
ax = fig.add_subplot(111)
|
||||
ax.axis("off")
|
||||
ax.text(
|
||||
0.5,
|
||||
0.5,
|
||||
message,
|
||||
ha="center",
|
||||
va="center",
|
||||
fontsize=12,
|
||||
color=_MUTED_TEXT,
|
||||
transform=ax.transAxes,
|
||||
)
|
||||
fig.tight_layout()
|
||||
return fig
|
||||
|
||||
|
||||
def _metrics_caption(classification: dict) -> str:
|
||||
"""Format the available metrics of a classification dict into one line.
|
||||
|
||||
Omits the metrics that are None. Keys consumed (any may be absent/None):
|
||||
``pearson`` (r), ``spearman`` (rho), ``r2_linear`` (R²lin) and the best
|
||||
polynomial R² (``r2_poly3`` if a cubic was the best fit, else ``r2_poly2``).
|
||||
"""
|
||||
parts = []
|
||||
r = _finite(classification.get("pearson"))
|
||||
if r is not None:
|
||||
parts.append(f"r={r:.2f}")
|
||||
rho = _finite(classification.get("spearman"))
|
||||
if rho is not None:
|
||||
parts.append(f"ρ={rho:.2f}")
|
||||
r2_lin = _finite(classification.get("r2_linear"))
|
||||
if r2_lin is not None:
|
||||
parts.append(f"R²lin={r2_lin:.2f}")
|
||||
# Prefer the R² of the best polynomial degree when it is a poly fit.
|
||||
best_degree = classification.get("best_degree")
|
||||
r2_poly = None
|
||||
if best_degree == 3:
|
||||
r2_poly = _finite(classification.get("r2_poly3"))
|
||||
elif best_degree == 2:
|
||||
r2_poly = _finite(classification.get("r2_poly2"))
|
||||
if r2_poly is None:
|
||||
# Fall back to whichever poly R² is present (cubic first).
|
||||
r2_poly = _finite(classification.get("r2_poly3"))
|
||||
if r2_poly is None:
|
||||
r2_poly = _finite(classification.get("r2_poly2"))
|
||||
if r2_poly is not None:
|
||||
parts.append(f"R²poly={r2_poly:.2f}")
|
||||
return " ".join(parts)
|
||||
|
||||
|
||||
def relationship_scatter_figure(
|
||||
xs: list,
|
||||
ys: list,
|
||||
x_label: str = "",
|
||||
y_label: str = "",
|
||||
classification: dict = None,
|
||||
max_points: int = 2000,
|
||||
) -> "matplotlib.figure.Figure":
|
||||
"""Build a scatter figure of a numeric pair with its fit and a type label.
|
||||
|
||||
Cleans the pairs defensively (drops any pair with a None/bool/NaN/inf end),
|
||||
plots a semi-transparent scatter cloud (down-sampled deterministically when
|
||||
it exceeds ``max_points``), overlays the polynomial fit implied by
|
||||
``classification`` and annotates the relationship type plus its available
|
||||
metrics in a corner box.
|
||||
|
||||
The fit and classification always use every clean pair; only the drawn cloud
|
||||
is thinned by the down-sample. When ``classification`` is None it is computed
|
||||
internally by reusing ``classify_relationship_type`` over the clean pairs, so
|
||||
the function is self-contained.
|
||||
|
||||
The function is fully defensive: empty input, fewer than 2 clean pairs, a
|
||||
missing/None ``coeffs`` or a missing sibling classifier never raise. When
|
||||
there is nothing valid to draw it still returns a ``Figure`` carrying a
|
||||
centered "Sin datos suficientes para el scatter" message.
|
||||
|
||||
Args:
|
||||
xs: List (or tuple) of x values. Paired by index with ``ys``. Values that
|
||||
are None, bool, NaN or infinite discard that pair. Read defensively.
|
||||
ys: List (or tuple) of y values, parallel to ``xs``. Same defensive rules.
|
||||
x_label: Axis/title label for the x variable. Default "" (falls back to
|
||||
"x" in the title).
|
||||
y_label: Axis/title label for the y variable. Default "" (falls back to
|
||||
"y" in the title).
|
||||
classification: Optional dict from ``classify_relationship_type`` with
|
||||
keys ``tipo, pearson, r2_linear, spearman, r2_poly2, r2_poly3,
|
||||
best_degree, coeffs``. When None, it is computed internally by
|
||||
importing and calling ``classify_relationship_type`` over the clean
|
||||
pairs. When that sibling module is unavailable, the scatter is still
|
||||
drawn (no fit curve, no annotation).
|
||||
max_points: Cap on the number of *plotted* points. When the number of
|
||||
clean pairs exceeds this cap, the drawn cloud is down-sampled by a
|
||||
fixed step ``ceil(n/max_points)`` taking ``pairs[::step]`` —
|
||||
DETERMINISTIC, not random, so the figure is reproducible. A
|
||||
non-positive or non-int value disables down-sampling. Default 2000.
|
||||
|
||||
Returns:
|
||||
A ``matplotlib.figure.Figure`` (figsize 6.4x4.0, dpi 150) with a single
|
||||
scatter Axes, the fitted curve (when a polynomial fit is available) and a
|
||||
corner annotation with the relationship type and metrics. When there are
|
||||
fewer than 2 clean pairs it returns a Figure with a centered "Sin datos
|
||||
suficientes para el scatter" message. The caller rasterizes/closes it.
|
||||
"""
|
||||
pairs = _clean_pairs(xs, ys)
|
||||
if len(pairs) < 2:
|
||||
return _no_data_figure("Sin datos suficientes para el scatter")
|
||||
|
||||
# Full clean coordinates feed the classification/fit; the plotted cloud is
|
||||
# what gets thinned.
|
||||
xs_clean = [p[0] for p in pairs]
|
||||
ys_clean = [p[1] for p in pairs]
|
||||
|
||||
# Resolve the classification. If not provided, reuse the sibling classifier
|
||||
# over ALL clean pairs (self-contained). Missing module => no fit/annotation.
|
||||
cls = classification
|
||||
if cls is None:
|
||||
try:
|
||||
from classify_relationship_type import classify_relationship_type
|
||||
|
||||
cls = classify_relationship_type(xs_clean, ys_clean)
|
||||
except Exception:
|
||||
cls = None
|
||||
if not isinstance(cls, dict):
|
||||
cls = {}
|
||||
|
||||
# --- Deterministic down-sampling of the DRAWN points only.
|
||||
n_total = len(pairs)
|
||||
if (
|
||||
isinstance(max_points, int)
|
||||
and not isinstance(max_points, bool)
|
||||
and max_points > 0
|
||||
and n_total > max_points
|
||||
):
|
||||
step = math.ceil(n_total / max_points)
|
||||
sampled = pairs[::step]
|
||||
else:
|
||||
sampled = pairs
|
||||
|
||||
x_plot = [p[0] for p in sampled]
|
||||
y_plot = [p[1] for p in sampled]
|
||||
|
||||
fig = Figure(figsize=(6.4, 4.0), dpi=150)
|
||||
ax = fig.add_subplot(111)
|
||||
|
||||
ax.scatter(
|
||||
x_plot,
|
||||
y_plot,
|
||||
s=12,
|
||||
alpha=0.5,
|
||||
color=_POINT_COLOR,
|
||||
edgecolors="none",
|
||||
rasterized=True,
|
||||
)
|
||||
|
||||
# --- Fitted curve/line over the full clean x range.
|
||||
coeffs = cls.get("coeffs")
|
||||
best_degree = cls.get("best_degree")
|
||||
tipo = cls.get("tipo")
|
||||
x_min, x_max = min(xs_clean), max(xs_clean)
|
||||
drew_fit = False
|
||||
if coeffs is not None and best_degree is not None and x_max > x_min:
|
||||
try:
|
||||
coeff_arr = np.asarray(coeffs, dtype=float)
|
||||
if coeff_arr.ndim == 1 and coeff_arr.size > 0 and np.all(np.isfinite(coeff_arr)):
|
||||
x_line = np.linspace(x_min, x_max, 200)
|
||||
y_line = np.polyval(coeff_arr, x_line)
|
||||
if np.all(np.isfinite(y_line)):
|
||||
ax.plot(x_line, y_line, color=_FIT_COLOR, linewidth=2)
|
||||
drew_fit = True
|
||||
except Exception:
|
||||
# Never fail the figure because of a malformed coeffs array.
|
||||
pass
|
||||
|
||||
# A monotonic non-linear relationship has no fitted polynomial (coeffs is
|
||||
# None by design — a low-degree polynomial would mislead). Draw instead the
|
||||
# ordered trend of y over x so the reader still sees the shape: y averaged
|
||||
# within ordered x-bins (or per distinct x value when x is discrete with few
|
||||
# levels, e.g. an ordinal scale). Defensive: any failure leaves the cloud.
|
||||
if (not drew_fit and isinstance(tipo, str) and "monóton" in tipo.lower()
|
||||
and x_max > x_min):
|
||||
try:
|
||||
xt, yt = _ordered_trend(xs_clean, ys_clean)
|
||||
if xt is not None and len(xt) >= 2:
|
||||
ax.plot(xt, yt, color=_FIT_COLOR, linewidth=2, marker="o",
|
||||
markersize=3)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# --- Labels and title.
|
||||
tx = x_label if x_label else "x"
|
||||
ty = y_label if y_label else "y"
|
||||
ax.set_title(f"{tx} ↔ {ty}", fontsize=12, loc="left", pad=8)
|
||||
ax.set_xlabel(x_label)
|
||||
ax.set_ylabel(y_label)
|
||||
|
||||
# --- Corner annotation: relationship type + available metrics.
|
||||
caption_lines = []
|
||||
if tipo:
|
||||
caption_lines.append(str(tipo))
|
||||
metrics_line = _metrics_caption(cls)
|
||||
if metrics_line:
|
||||
caption_lines.append(metrics_line)
|
||||
if caption_lines:
|
||||
ax.text(
|
||||
0.03,
|
||||
0.97,
|
||||
"\n".join(caption_lines),
|
||||
transform=ax.transAxes,
|
||||
ha="left",
|
||||
va="top",
|
||||
fontsize=8,
|
||||
bbox=dict(
|
||||
boxstyle="round,pad=0.35",
|
||||
facecolor="white",
|
||||
edgecolor="#cccccc",
|
||||
alpha=0.85,
|
||||
),
|
||||
)
|
||||
|
||||
fig.tight_layout()
|
||||
return fig
|
||||
@@ -0,0 +1,100 @@
|
||||
"""Tests para relationship_scatter_figure (scatter de un par numérico, grupo eda).
|
||||
|
||||
Usa el backend Agg sin pyplot global; no muestra ni guarda figuras. Cada test
|
||||
cierra explícitamente la Figure construida (matplotlib.pyplot.close) para no
|
||||
acumular estado entre tests.
|
||||
"""
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
sys.path.insert(0, os.path.dirname(__file__))
|
||||
|
||||
import matplotlib
|
||||
|
||||
matplotlib.use("Agg")
|
||||
|
||||
import matplotlib.pyplot as plt # noqa: E402
|
||||
from matplotlib.collections import PathCollection # noqa: E402
|
||||
from matplotlib.figure import Figure # noqa: E402
|
||||
|
||||
from relationship_scatter_figure import relationship_scatter_figure
|
||||
|
||||
|
||||
def _scatter_offsets(fig):
|
||||
"""Return the plotted points of the first PathCollection (scatter) found."""
|
||||
for ax in fig.axes:
|
||||
for coll in ax.collections:
|
||||
if isinstance(coll, PathCollection):
|
||||
return coll.get_offsets()
|
||||
return None
|
||||
|
||||
|
||||
def test_returns_figure():
|
||||
xs = [float(i) for i in range(20)]
|
||||
ys = [2.0 * x + 1.0 for x in xs] # y = 2x + 1
|
||||
classification = {
|
||||
"tipo": "lineal",
|
||||
"pearson": 1.0,
|
||||
"r2_linear": 1.0,
|
||||
"spearman": 1.0,
|
||||
"r2_poly2": 1.0,
|
||||
"r2_poly3": 1.0,
|
||||
"best_degree": 1,
|
||||
"coeffs": [2.0, 1.0],
|
||||
}
|
||||
fig = relationship_scatter_figure(
|
||||
xs, ys, x_label="a", y_label="b", classification=classification
|
||||
)
|
||||
assert hasattr(fig, "savefig")
|
||||
assert len(fig.axes) >= 1
|
||||
plt.close(fig)
|
||||
|
||||
|
||||
def test_downsample_determinista():
|
||||
n = 5000
|
||||
xs = [float(i) for i in range(n)]
|
||||
ys = [0.5 * x for x in xs]
|
||||
classification = {
|
||||
"tipo": "lineal",
|
||||
"pearson": 1.0,
|
||||
"r2_linear": 1.0,
|
||||
"spearman": 1.0,
|
||||
"r2_poly2": 1.0,
|
||||
"r2_poly3": 1.0,
|
||||
"best_degree": 1,
|
||||
"coeffs": [0.5, 0.0],
|
||||
}
|
||||
fig = relationship_scatter_figure(
|
||||
xs, ys, x_label="x", y_label="y", classification=classification, max_points=1000
|
||||
)
|
||||
assert isinstance(fig, Figure)
|
||||
offsets = _scatter_offsets(fig)
|
||||
assert offsets is not None
|
||||
# El nº de puntos dibujados no debe exceder el cap.
|
||||
assert len(offsets) <= 1000
|
||||
plt.close(fig)
|
||||
|
||||
|
||||
def test_empty_no_lanza():
|
||||
fig = relationship_scatter_figure([], [], x_label="x", y_label="y")
|
||||
assert isinstance(fig, Figure)
|
||||
plt.close(fig)
|
||||
|
||||
|
||||
def test_classification_none():
|
||||
# Solo se ejecuta si el módulo hermano classify_relationship_type existe.
|
||||
try:
|
||||
import classify_relationship_type # noqa: F401
|
||||
except Exception:
|
||||
import pytest
|
||||
|
||||
pytest.skip("classify_relationship_type aún no disponible")
|
||||
xs = [float(i) for i in range(30)]
|
||||
ys = [3.0 * x - 2.0 for x in xs]
|
||||
fig = relationship_scatter_figure(
|
||||
xs, ys, x_label="a", y_label="b", classification=None
|
||||
)
|
||||
assert isinstance(fig, Figure)
|
||||
assert len(fig.axes) >= 1
|
||||
plt.close(fig)
|
||||
Reference in New Issue
Block a user