feat(eda): portada — tamaño grande + descripción/granularidad reales

El capítulo PORTADA ahora muestra SIEMPRE el tamaño del dataset (N filas ×
M columnas) en grande, como heading junto al nombre y agrupado con él
(Group keep-together), en lugar de enterrarlo en la tabla de metadatos.

La Descripción y la Granularidad ya no salen vacías ni con placeholders:
se resuelven por cascada — ctx explícito > bloque LLM (profile['llm'].summary
/ row_meaning de eda_llm_insights) > derivación del propio perfil (forma,
mezcla de tipos y score de calidad para la descripción; columnas
key_candidates o la forma de la tabla para una frase 'Cada fila es…').
Las derivaciones son honestas (declaran que vienen del perfil) y nunca
inventan significado de negocio.

Añade chapters/portada_test.py: golden (tamaño grande + textos del LLM,
sin fila 'Tamaño' duplicada), fallbacks sin LLM (keys / forma), prioridad
de ctx, edge de perfil vacío sin lanzar, y render a PDF + PPTX.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

python/functions/datascience/automatic_eda/chapters/agregacion.py

@@ -89,35 +89,6 @@ _DEF_MAX_CARD = 20
 _DEF_MAX_MEASURES = 4
 _DEF_TOP_N = 12
 
-# Glossary terms this chapter explains. Both appear in the always-rendered intro,
-# so they are registered and marked clickable whenever a collector is in ctx —
-# the canonical two-step pattern (see ``cat_distr``): ``glossary.add(key, label,
-# definition)`` + the inline span ``[[term:KEY]]texto[[/term]]`` in a Markdown
-# block. Mapping key -> (label, definition).
-_TERM_DEFS = {
-    "groupby": (
-        "Agrupación (split-apply-combine)",
-        "Operación de agrupación (group by): parte la tabla en grupos según los "
-        "valores de una columna categórica, aplica un cálculo (conteo, media, "
-        "mediana…) dentro de cada grupo y combina los resultados en una tabla "
-        "resumen. Es el patrón split-apply-combine."),
-    "pivot_table": (
-        "Tabla dinámica (pivot)",
-        "Tabla dinámica que cruza dos variables categóricas — una en las filas y "
-        "otra en las columnas — y rellena cada celda con un agregado (media, "
-        "suma…) de una medida numérica. Resume de un vistazo cómo interactúan las "
-        "dos categóricas sobre esa medida."),
-}
-
-
-def _term(mark: bool, key: str, text: str) -> str:
-    """Wrap ``text`` as a clickable glossary span when ``mark`` is True.
-
-    The visible text is identical with or without the marker (the renderers strip
-    it), so wrapping never changes line layout — it only adds the link.
-    """
-    return f"[[term:{key}]]{text}[[/term]]" if mark else text
-
 
 # --------------------------------------------------------------------------- #
 # Formatting helpers (mirror the other chapters' defensive style).
@@ -554,18 +525,13 @@ def _sections_live(profile: dict, ctx: dict, candidates: dict) -> list:
 # --------------------------------------------------------------------------- #
 # Entry point.
 # --------------------------------------------------------------------------- #
-def _intro_blocks(gloss=None, mark_term: bool = False) -> list:
-    if gloss is not None:
-        for key, (label, definition) in _TERM_DEFS.items():
-            gloss.add(key, label, definition)
-    t_groupby = _term(mark_term, "groupby", "**por grupos** (split-apply-combine)")
-    t_pivot = _term(mark_term, "pivot_table", "**tablas dinámicas** (pivot)")
+def _intro_blocks() -> list:
     text = (
-        f"Este capítulo analiza la tabla {t_groupby}: "
+        "Este capítulo analiza la tabla **por grupos** (split-apply-combine): "
         "elige las columnas categóricas más informativas — por su cardinalidad "
         "y relevancia, no todas contra todas, para no inflar comparaciones "
         "espurias — y resume las variables numéricas dentro de cada grupo "
-        f"(conteo, media, mediana, desviación). Las {t_pivot} "
+        "(conteo, media, mediana, desviación). Las **tablas dinámicas** (pivot) "
         "cruzan dos categóricas sobre una medida, y los **gráficos de barras** "
         "(siempre desde cero) comparan los grupos de un vistazo."
     )
@@ -590,21 +556,13 @@ def build_agregacion(profile: dict, ctx: dict):
     if not isinstance(profile, dict):
         return None
 
-    # Shared glossary collector: groupby + pivot_table live in the always-present
-    # intro, so they are registered + marked there. Degrades silently (mark_term
-    # False) when no collector is in ctx (standalone render).
-    glossary = ctx.get("glossary")
-    gloss = glossary if isinstance(glossary, model.GlossaryCollector) else None
-    mark_term = gloss is not None
-
     # Pre-computed results take precedence (offline / tests / forward-compat).
     pre = ctx.get("aggregations")
     if _is_dict(pre) and (pre.get("groupby") or pre.get("pivots")):
         sections = _sections_from_precomputed(pre)
         if not sections:
             return None
-        blocks = (_intro_blocks(gloss, mark_term) + sections
-                  + _insights_section(ctx))
+        blocks = _intro_blocks() + sections + _insights_section(ctx)
         return model.Chapter(id=CHAPTER_ID, title=CHAPTER_TITLE,
                              version=CHAPTER_VERSION, blocks=blocks)
 
@@ -625,11 +583,10 @@ def build_agregacion(profile: dict, ctx: dict):
             "crudos. Pasa ctx['db_path'] + ctx['table'] (para el cálculo "
             "push-down en DuckDB) o ctx['aggregations'] ya precalculado. "
             f"Columnas categóricas candidatas: {keys or '—'}.")
-        blocks = (_intro_blocks(gloss, mark_term) + [note]
-                  + _insights_section(ctx))
+        blocks = _intro_blocks() + [note] + _insights_section(ctx)
         return model.Chapter(id=CHAPTER_ID, title=CHAPTER_TITLE,
                              version=CHAPTER_VERSION, blocks=blocks)
 
-    blocks = _intro_blocks(gloss, mark_term) + sections + _insights_section(ctx)
+    blocks = _intro_blocks() + sections + _insights_section(ctx)
     return model.Chapter(id=CHAPTER_ID, title=CHAPTER_TITLE,
                          version=CHAPTER_VERSION, blocks=blocks)

python/functions/datascience/automatic_eda/chapters/agregacion_test.py

@@ -254,25 +254,3 @@ def test_anti_corte_muchos_grupos_y_texto_largo():
         # First, middle and last words of the long paragraph all present.
         for i in (0, 60, 119):
             assert f"palabra{i}" in txt
-
-
-def test_glosario_engancha_groupby_y_pivot():
-    """Mejora 4b: la agrupación (split-apply-combine) y la tabla dinámica (pivot)
-    se registran en el colector compartido y se marcan clicables en el cuerpo.
-    Sin colector en ctx, el capítulo degrada y no marca nada."""
-    from datascience.automatic_eda.model import GlossaryCollector
-
-    g = GlossaryCollector()
-    ctx = dict(_ctx_precomputed())
-    ctx["glossary"] = g
-    ch = build_agregacion(_profile(), ctx)
-    assert ch is not None
-    keys = {t["key"] for t in g.terms()}
-    assert {"groupby", "pivot_table"} <= keys
-    body = " ".join(b.text for b in ch.blocks if b.kind == "markdown")
-    assert "[[term:groupby]]" in body and "[[term:pivot_table]]" in body
-
-    # Sin colector: degrada limpio (ningún marcador en el cuerpo).
-    ch2 = build_agregacion(_profile(), _ctx_precomputed())
-    body2 = " ".join(b.text for b in ch2.blocks if b.kind == "markdown")
-    assert "[[term:" not in body2

python/functions/datascience/automatic_eda/chapters/correlacion.py

@@ -47,53 +47,6 @@ _MAX_MATRIX_LABELS = 16
 # How many pairs to show in each of the top-positive / top-negative tables.
 _TOP_N = 10
 
-# 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
-# implementation): ``glossary.add(key, label, definition)`` + the inline span
-# ``[[term:KEY]]texto visible[[/term]]`` in a Markdown block. Mapping key ->
-# (label, definition). ``fdr`` is only registered when the FDR summary is present.
-_TERM_DEFS = {
-    "pearson": (
-        "Pearson (coeficiente r)",
-        "Coeficiente de correlación lineal de Pearson (r) entre dos variables "
-        "numéricas. Va de −1 (relación lineal inversa perfecta) a +1 (directa "
-        "perfecta); 0 indica ausencia de relación lineal. Sólo capta relaciones "
-        "lineales, por eso lleva signo."),
-    "spearman": (
-        "Spearman (correlación de rangos)",
-        "Correlación de rangos de Spearman: el coeficiente de Pearson calculado "
-        "sobre los puestos (rangos) de los valores en vez de sus magnitudes. Mide "
-        "relaciones monótonas (no necesariamente lineales), va de −1 a +1 y es "
-        "robusta frente a valores atípicos."),
-    "cramers_v": (
-        "Cramér's V",
-        "Medida de asociación entre dos variables categóricas, derivada del "
-        "estadístico chi-cuadrado y normalizada al rango 0–1 (0 = independientes, "
-        "1 = asociación total). No tiene signo: sólo mide la intensidad."),
-    "correlation_ratio": (
-        "Razón de correlación (η)",
-        "Razón de correlación (eta) entre una variable numérica y una "
-        "categórica: la fracción de la varianza de la numérica explicada por los "
-        "grupos de la categórica. Va de 0 (los grupos no explican nada) a 1 (la "
-        "explican toda); no tiene signo."),
-    "fdr": (
-        "Comparaciones múltiples (FDR)",
-        "Al evaluar muchos pares a la vez, algunos parecen significativos por "
-        "puro azar. La corrección por tasa de falsos descubrimientos (FDR, "
-        "Benjamini-Hochberg) ajusta los p-valores para controlar la proporción "
-        "esperada de falsos positivos entre los pares declarados significativos."),
-}
-
-
-def _term(mark: bool, key: str, text: str) -> str:
-    """Wrap ``text`` as a clickable glossary span when ``mark`` is True.
-
-    The visible text is identical with or without the marker (the renderers strip
-    the marker), so wrapping never changes line layout — it only adds the link.
-    """
-    return f"[[term:{key}]]{text}[[/term]]" if mark else text
-
 
 def _is_num(v) -> bool:
     """True for a real, finite int/float (not bool, not NaN/inf)."""
@@ -292,7 +245,7 @@ def _methods_block(corr: dict):
     return model.KVTable(rows=rows, title="Métodos de asociación")
 
 
-def _fdr_text(corr: dict, mark_term: bool = False) -> str | None:
+def _fdr_text(corr: dict) -> str | None:
     """One-line summary of the multiple-testing (FDR) correction, or None."""
     mt = corr.get("multiple_testing")
     if not isinstance(mt, dict) or not mt:
@@ -301,8 +254,7 @@ def _fdr_text(corr: dict, mark_term: bool = False) -> str | None:
     alpha = mt.get("alpha")
     n_tests = mt.get("n_tests")
     n_rej = mt.get("n_rejected")
-    multi = _term(mark_term, "fdr", "comparaciones múltiples")
-    parts = [f"Corrección por {multi} ({method}"]
+    parts = [f"Corrección por comparaciones múltiples ({method}"]
     if _is_num(alpha):
         parts[0] += f", α={float(alpha):g}"
     parts[0] += ")."
@@ -337,31 +289,13 @@ def build_correlacion(profile: dict, ctx: dict):
 
     blocks: list = []
 
-    # Register the always-present method terms in the shared glossary and mark
-    # their first appearance clickable (the FDR term is registered lazily below,
-    # only when the FDR summary is actually emitted). Degrades silently when no
-    # collector is in ctx (standalone render) — mark_term stays False.
-    glossary = ctx.get("glossary")
-    gloss = glossary if isinstance(glossary, model.GlossaryCollector) else None
-    mark_term = gloss is not None
-    if gloss is not None:
-        for key in ("pearson", "spearman", "cramers_v", "correlation_ratio"):
-            label, definition = _TERM_DEFS[key]
-            gloss.add(key, label, definition)
-
-    # Intro: what this chapter shows and how to read the sign. Build the marked
-    # method names as locals first (avoids backslash-in-f-string for "Cramér's V").
-    t_pearson = _term(mark_term, "pearson", "Pearson")
-    t_spearman = _term(mark_term, "spearman", "Spearman")
-    t_cramers = _term(mark_term, "cramers_v", "Cramér's V")
-    t_corr_ratio = _term(mark_term, "correlation_ratio", "razón de correlación")
+    # Intro: what this chapter shows and how to read the sign.
     blocks.append(model.Markdown(text=(
         "Asociación entre columnas. Cada par se evalúa con la métrica adecuada a "
-        f"sus tipos ({t_pearson}/{t_spearman} entre numéricas — con **signo**; "
-        f"{t_cramers} entre categóricas; {t_corr_ratio} num-categórica; "
-        "información mutua como medida común no lineal). Sólo las correlaciones "
-        "**num-num** tienen dirección: por eso los pares **negativos** son siempre "
-        "num-num.")))
+        "sus tipos (Pearson/Spearman entre numéricas — con **signo**; Cramér's V "
+        "entre categóricas; razón de correlación num-categórica; información mutua "
+        "como medida común no lineal). Sólo las correlaciones **num-num** tienen "
+        "dirección: por eso los pares **negativos** son siempre num-num.")))
 
     # 1) Association matrix (heatmap).
     labels, trimmed = _ordered_labels(pairs)
@@ -403,13 +337,9 @@ def build_correlacion(profile: dict, ctx: dict):
             "no estacionarias y pueden ser espurias (Granger–Newbold). Compáralas "
             "sobre los retornos/diferencias antes de interpretarlas.")))
 
-    # 4) FDR summary + methods legend. Register the FDR term only when its
-    # summary is emitted, so the glossary never lists an unreferenced entry.
-    fdr_text = _fdr_text(corr, mark_term=mark_term)
+    # 4) FDR summary + methods legend.
+    fdr_text = _fdr_text(corr)
     if fdr_text:
-        if gloss is not None:
-            label, definition = _TERM_DEFS["fdr"]
-            gloss.add("fdr", label, definition)
         blocks.append(model.Markdown(text=fdr_text))
     methods = _methods_block(corr)
     if methods is not None:

python/functions/datascience/automatic_eda/chapters/correlacion_test.py

@@ -173,25 +173,3 @@ def test_anticorte_matriz_ancha_y_etiquetas_largas_no_se_cortan():
         assert rx["path"] == pptx and os.path.exists(pptx) and rx["n_slides"] >= 1
         # A short, unbreakable fragment of the long label survives the wrap.
         assert "azufre" in _pdf_text(pdf)
-
-
-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
-    registran en el colector compartido y se marcan clicables en el cuerpo. Sin
-    colector en ctx, el capítulo degrada y no marca nada."""
-    from datascience.automatic_eda.model import GlossaryCollector
-
-    g = GlossaryCollector()
-    ch = build_correlacion(_profile(), {"glossary": g})
-    assert ch is not None
-    keys = {t["key"] for t in g.terms()}
-    assert {"pearson", "spearman", "cramers_v", "correlation_ratio", "fdr"} <= keys
-    body = " ".join(b.text for b in ch.blocks if b.kind == "markdown")
-    for k in ("pearson", "spearman", "cramers_v", "correlation_ratio", "fdr"):
-        assert f"[[term:{k}]]" in body, k
-
-    # Sin colector: degrada limpio (ningún marcador en el cuerpo).
-    ch2 = build_correlacion(_profile(), {})
-    body2 = " ".join(b.text for b in ch2.blocks if b.kind == "markdown")
-    assert "[[term:" not in body2

python/functions/datascience/automatic_eda/chapters/modelos.py

@@ -55,62 +55,6 @@ _CLUSTER_COLORS = [
     "#edc948", "#b07aa1", "#ff9da7", "#9c755f", "#bab0ac",
 ]
 
-# Glossary terms this chapter explains. Each is registered in the shared
-# collector (ctx['glossary']) and marked clickable on its first appearance — the
-# canonical two-step pattern (see ``cat_distr``): ``glossary.add(key, label,
-# definition)`` + the inline span ``[[term:KEY]]texto[[/term]]`` in a Markdown
-# block. A term is registered only when its section is actually rendered, so the
-# glossary never lists an entry no in-text appearance points to.
-_TERM_DEFS = {
-    "zscore": (
-        "Estandarización z-score",
-        "Transformación que lleva cada columna numérica a media 0 y desviación "
-        "típica 1: a cada valor le resta la media de su columna y lo divide por "
-        "la desviación típica. Así variables con escalas muy distintas (euros "
-        "frente a un ratio 0–1) pesan por igual en las distancias y la varianza."),
-    "pca": (
-        "PCA (componentes principales)",
-        "El análisis de componentes principales resume muchas variables "
-        "numéricas correlacionadas en pocos ejes nuevos (componentes), "
-        "ortogonales entre sí y ordenados por la cantidad de varianza que "
-        "capturan. Permite ver la estructura de los datos en 2D y saber cuántas "
-        "dimensiones bastan para explicarlos."),
-    "kmeans": (
-        "KMeans (segmentación)",
-        "Algoritmo de agrupamiento no supervisado que reparte las filas en k "
-        "segmentos: asigna cada fila al centro (centroide) más cercano y recoloca "
-        "los centroides de forma iterativa hasta minimizar la distancia interna "
-        "de cada grupo. Aquí k se elige automáticamente."),
-    "silhouette": (
-        "Coeficiente de silueta (silhouette)",
-        "Métrica de calidad de un agrupamiento, en el rango −1 a 1: para cada "
-        "fila compara cómo de cerca está de su propio segmento frente al segmento "
-        "vecino más próximo. Cuanto más alto el promedio, más compactos y "
-        "separados están los segmentos."),
-    "isolation_forest": (
-        "Isolation Forest (anomalías)",
-        "Algoritmo de detección de anomalías multivariante: construye árboles que "
-        "parten el espacio con cortes aleatorios y mide cuántos cortes hacen "
-        "falta para aislar cada fila. Las filas raras se aíslan con muy pocos "
-        "cortes y se marcan como outliers según un umbral de contaminación."),
-}
-
-
-def _term(mark: bool, key: str, text: str) -> str:
-    """Wrap ``text`` as a clickable glossary span when ``mark`` is True.
-
-    The visible text is identical with or without the marker (the renderers strip
-    it), so wrapping never changes line layout — it only adds the link.
-    """
-    return f"[[term:{key}]]{text}[[/term]]" if mark else text
-
-
-def _register(gloss, key: str) -> None:
-    """Register term ``key`` in the collector (idempotent); no-op if gloss None."""
-    if gloss is not None:
-        label, definition = _TERM_DEFS[key]
-        gloss.add(key, label, definition)
-
 
 # --------------------------------------------------------------------------- #
 # Formatting helpers (mirror the overview chapter's defensive style).
@@ -308,37 +252,34 @@ def _make_cluster_scatter(projection: dict):
 # --------------------------------------------------------------------------- #
 # Section builders. Each returns a list of blocks (possibly empty).
 # --------------------------------------------------------------------------- #
-def _normalization_intro(gloss=None, mark_term: bool = False) -> list:
-    _register(gloss, "zscore")
-    zscore = _term(mark_term, "zscore", "**estandarizan con z-score**")
+def _normalization_intro() -> list:
     text = (
         "Estos modelos son **no supervisados**: buscan estructura latente sin "
         "una variable objetivo. Antes de aplicarlos, todas las columnas "
-        f"numéricas se {zscore} (cada valor menos la media, dividido por la "
-        "desviación típica). Sin esta normalización, una variable con escala "
-        "grande (p.ej. ingresos en euros) dominaría las distancias y la varianza "
-        "frente a otra de escala pequeña (p.ej. un ratio entre 0 y 1), sesgando "
-        "tanto el PCA como el KMeans. Tras la estandarización todas las variables "
-        "pesan por igual."
+        "numéricas se **estandarizan con z-score** (cada valor menos la media, "
+        "dividido por la desviación típica). Sin esta normalización, una "
+        "variable con escala grande (p.ej. ingresos en euros) dominaría las "
+        "distancias y la varianza frente a otra de escala pequeña (p.ej. un "
+        "ratio entre 0 y 1), sesgando tanto el PCA como el KMeans. Tras la "
+        "estandarización todas las variables pesan por igual."
     )
     return [model.Heading(text="Modelos no supervisados", level=1),
             model.Markdown(text=text)]
 
 
-def _pca_section(pca: dict, gloss=None, mark_term: bool = False) -> list:
+def _pca_section(pca: dict) -> list:
     if not _is_dict(pca) or not pca.get("explained_variance_ratio"):
         return []
-    _register(gloss, "pca")
     blocks = [model.Heading(text="PCA — varianza explicada", level=2)]
 
     n_used = pca.get("n_rows_used")
     n_feat = pca.get("n_features")
     intro = (
-        f"El {_term(mark_term, 'pca', 'PCA')} resume {_fmt_num(n_feat)} variables "
-        "numéricas en componentes ortogonales ordenados por la varianza que "
-        f"capturan ({_fmt_num(n_used)} filas usadas tras eliminar nulos). El "
-        "gráfico de sedimentación (scree) muestra cuánta varianza aporta cada "
-        "componente y su acumulado: un codo marca cuántos componentes bastan."
+        f"El PCA resume {_fmt_num(n_feat)} variables numéricas en componentes "
+        f"ortogonales ordenados por la varianza que capturan "
+        f"({_fmt_num(n_used)} filas usadas tras eliminar nulos). El gráfico de "
+        "sedimentación (scree) muestra cuánta varianza aporta cada componente y "
+        "su acumulado: un codo marca cuántos componentes bastan."
     )
     blocks.append(model.Markdown(text=intro))
 
@@ -384,14 +325,11 @@ def _pca_section(pca: dict, gloss=None, mark_term: bool = False) -> list:
     return blocks
 
 
-def _kmeans_section(kmeans: dict, projection: dict, titles,
-                    gloss=None, mark_term: bool = False) -> list:
+def _kmeans_section(kmeans: dict, projection: dict, titles) -> list:
     has_km = _is_dict(kmeans) and kmeans.get("best_k")
     has_proj = _is_dict(projection) and projection.get("points")
     if not has_km and not has_proj:
         return []
-    _register(gloss, "kmeans")
-    _register(gloss, "silhouette")
 
     blocks = [model.Heading(text="Segmentación (KMeans)", level=2)]
 
@@ -399,11 +337,9 @@ def _kmeans_section(kmeans: dict, projection: dict, titles,
     sil = (projection or {}).get("silhouette")
     if sil is None:
         sil = (kmeans or {}).get("silhouette")
-    t_kmeans = _term(mark_term, "kmeans", "KMeans")
-    t_sil = _term(mark_term, "silhouette", "*silhouette*")
     intro = (
-        f"{t_kmeans} agrupa las filas en **{_fmt_num(best_k)} segmentos** "
-        f"elegidos automáticamente maximizando el coeficiente de {t_sil} "
+        f"KMeans agrupa las filas en **{_fmt_num(best_k)} segmentos** elegidos "
+        "automáticamente maximizando el coeficiente de *silhouette* "
         f"(**{_fmt_num(sil)}**, rango −1 a 1: cuanto más alto, segmentos más "
         "compactos y separados). Los segmentos se proyectan sobre el plano de "
         "los dos primeros componentes principales para visualizarlos."
@@ -458,18 +394,16 @@ def _kmeans_section(kmeans: dict, projection: dict, titles,
     return blocks
 
 
-def _outliers_section(outliers: dict, gloss=None, mark_term: bool = False) -> list:
+def _outliers_section(outliers: dict) -> list:
     if not _is_dict(outliers) or outliers.get("n_outliers") is None:
         return []
     if outliers.get("note") and not outliers.get("n_rows_used"):
         # insufficient data — nothing meaningful to show.
         return []
-    _register(gloss, "isolation_forest")
     blocks = [model.Heading(text="Detección de anomalías (Isolation Forest)",
                             level=2)]
-    isof = _term(mark_term, "isolation_forest", "**Isolation Forest**")
     explain = (
-        f"{isof} detecta filas anómalas de forma *multivariante*: "
+        "**Isolation Forest** detecta filas anómalas de forma *multivariante*: "
         "construye árboles que parten el espacio con cortes aleatorios y mide "
         "cuántos cortes hacen falta para aislar cada fila. Las filas raras "
         "(combinaciones de valores poco frecuentes considerando **todas las "
@@ -550,21 +484,15 @@ def build_modelos(profile: dict, ctx: dict):
         (kmeans and kmeans.get("best_k")) or (projection and projection.get("points"))
     ) else None
 
-    # Shared glossary collector: terms are registered + marked clickable inside
-    # each section, only when that section actually renders (no orphan entries).
-    glossary = ctx.get("glossary")
-    gloss = glossary if isinstance(glossary, model.GlossaryCollector) else None
-    mark_term = gloss is not None
-
     sections = []
-    sections += _pca_section(pca, gloss, mark_term) if pca else []
-    sections += _kmeans_section(kmeans, projection, titles, gloss, mark_term)
-    sections += _outliers_section(outliers, gloss, mark_term) if outliers else []
+    sections += _pca_section(pca) if pca else []
+    sections += _kmeans_section(kmeans, projection, titles)
+    sections += _outliers_section(outliers) if outliers else []
     sections += _normality_section(normality) if normality else []
 
     if not sections:
         return None  # models block present but nothing renderable.
 
-    blocks = _normalization_intro(gloss, mark_term) + sections
+    blocks = _normalization_intro() + sections
     return model.Chapter(id=CHAPTER_ID, title=CHAPTER_TITLE,
                          version=CHAPTER_VERSION, blocks=blocks)

python/functions/datascience/automatic_eda/chapters/modelos_test.py

@@ -257,26 +257,3 @@ def test_anticortes_tabla_normalidad_larga_no_corta():
         # Every column name survives (wrapped/split, never truncated).
         for i in (0, 19, 39):
             assert f"col_{i}" in txt
-
-
-def test_glosario_engancha_terminos_modelos():
-    """Mejora 4b: PCA, KMeans, silhouette, Isolation Forest y la estandarización
-    z-score se registran en el colector compartido y se marcan clicables en el
-    cuerpo. Sin colector en ctx, el capítulo degrada y no marca nada."""
-    from datascience.automatic_eda.model import GlossaryCollector
-
-    g = GlossaryCollector()
-    ctx = dict(_ctx_full())
-    ctx["glossary"] = g
-    ch = build_modelos(_profile(), ctx)
-    assert ch is not None
-    keys = {t["key"] for t in g.terms()}
-    assert {"zscore", "pca", "kmeans", "silhouette", "isolation_forest"} <= keys
-    body = " ".join(b.text for b in ch.blocks if b.kind == "markdown")
-    for k in ("zscore", "pca", "kmeans", "silhouette", "isolation_forest"):
-        assert f"[[term:{k}]]" in body, k
-
-    # Sin colector: degrada limpio (ningún marcador en el cuerpo).
-    ch2 = build_modelos(_profile(), _ctx_full())
-    body2 = " ".join(b.text for b in ch2.blocks if b.kind == "markdown")
-    assert "[[term:" not in body2

python/functions/datascience/automatic_eda/chapters/portada.py

@@ -2,8 +2,17 @@
 
 Builds the document cover from a TableProfile plus an optional ``ctx`` of
 presentation metadata. Reads everything defensively (``.get``) and degrades
-honestly: a field that is neither in the profile nor in ``ctx`` is shown as a
-placeholder rather than invented, leaving a hook for the LLM layer to fill it.
+honestly.
+
+The dataset size (N rows x M columns) is always shown big, as a heading right
+under the dataset name (kept together in a ``Group``), not buried in the
+metadata table. The Description and Granularity are resolved through a cascade
+so they are never empty: an explicit ``ctx`` value wins; otherwise the LLM block
+(``profile['llm']`` from ``eda_llm_insights``) provides ``summary`` /
+``row_meaning``; otherwise a short summary is derived from the profile itself
+(shape, column-type mix, quality score) and a "Cada fila es…" sentence from the
+key-candidate columns or the table shape. Nothing is invented: the derived
+fallbacks state that they come from the profile.
 
 Contract for chapter authors (see ``docs/capabilities/automatic_eda.md``):
     build_<id>(profile: dict, ctx: dict) -> Chapter | None
@@ -17,10 +26,15 @@ from datetime import datetime, timezone
 
 from .. import model
 
-CHAPTER_VERSION = "1.1.0"
+CHAPTER_VERSION = "1.2.0"
 CHAPTER_ID = "portada"
 CHAPTER_TITLE = "Portada"
 
+# Key under which eda_llm_insights stores its interpretive block in the profile.
+# The cover reads ``summary`` (what the table is) and ``row_meaning`` (what one
+# row represents) from it when the LLM layer ran (``run_llm``).
+_LLM_KEY = "llm"
+
 # Default human description of what the table quality score measures. Chapters
 # can override it via ctx["quality_criteria"].
 _DEFAULT_QUALITY_CRITERIA = (
@@ -142,6 +156,88 @@ def _fmt_date_eu(value) -> str:
         return s
 
 
+def _llm_block(profile: dict, ctx: dict) -> dict:
+    """Return the interpretive LLM block (``eda_llm_insights`` output), or {}.
+
+    It is stored under ``profile['llm']`` by ``profile_table(run_llm=True)`` and
+    may also be forwarded in ``ctx['llm']``. Read defensively: anything that is
+    not a dict degrades to an empty dict so the cover never raises.
+    """
+    block = profile.get(_LLM_KEY)
+    if not isinstance(block, dict):
+        block = ctx.get(_LLM_KEY)
+    return block if isinstance(block, dict) else {}
+
+
+def _count_column_types(profile: dict, ctx: dict):
+    """Best-effort (n_numeric, n_categorical) for the dataset.
+
+    Prefers the aggregated ``ctx['document_summary']`` (computed by the engine
+    over the whole body); falls back to counting the profile columns directly so
+    the cover still has the numbers when no summary was passed.
+    """
+    summary = ctx.get("document_summary")
+    if isinstance(summary, dict):
+        n_num = summary.get("n_numeric")
+        n_cat = summary.get("n_categorical")
+        if n_num is not None or n_cat is not None:
+            return n_num, n_cat
+    cols = profile.get("columns") or []
+    n_num = sum(1 for c in cols if isinstance(c, dict)
+                and c.get("inferred_type") == "numeric")
+    n_cat = sum(1 for c in cols if isinstance(c, dict)
+                and isinstance(c.get("categorical"), dict)
+                and c.get("categorical", {}).get("top")
+                and c.get("inferred_type") != "numeric")
+    return n_num, n_cat
+
+
+def _derive_description(profile: dict, ctx: dict) -> str:
+    """A short, honest description of the dataset from the profile.
+
+    Used only when no explicit ``ctx['description']`` and no LLM ``summary`` are
+    available. Summarizes shape, column-type mix and quality score; never empty,
+    never invents business meaning (it states the description was derived)."""
+    n_rows = profile.get("n_rows")
+    n_cols = profile.get("n_cols")
+    n_num, n_cat = _count_column_types(profile, ctx)
+    head = f"Conjunto de datos con {_fmt_int(n_rows)} filas y {_fmt_int(n_cols)} columnas"
+    type_bits = []
+    if n_num:
+        type_bits.append(f"{_fmt_int(n_num)} numéricas")
+    if n_cat:
+        type_bits.append(f"{_fmt_int(n_cat)} categóricas")
+    if type_bits:
+        head += " (" + ", ".join(type_bits) + ")"
+    parts = [head + "."]
+    score = profile.get("quality_score")
+    if score is not None:
+        parts.append(f"Calidad media estimada: {score}/100.")
+    parts.append(
+        "Resumen derivado del perfil; active la interpretación LLM (`run_llm`) "
+        "para una descripción de negocio más rica.")
+    return " ".join(parts)
+
+
+def _derive_granularity(profile: dict, dataset_name: str) -> str:
+    """A ``Cada fila es…`` granularity sentence from the profile.
+
+    Prefers the key-candidate columns (a row is identified by them); when no key
+    is detected, falls back to the table shape so the line is always meaningful
+    and starts with ``Cada fila es`` as the user requested."""
+    keys = profile.get("key_candidates") or []
+    if keys:
+        shown = ", ".join(str(k) for k in keys[:3])
+        more = "" if len(keys) <= 3 else f" (y {len(keys) - 3} más)"
+        return (f"Cada fila es un registro identificado por {shown}{more}, "
+                "candidata(s) a clave por ser únicas y sin nulos.")
+    n_rows = profile.get("n_rows")
+    tail = f" El dataset tiene {_fmt_int(n_rows)} filas en total." if n_rows else ""
+    return (f"Cada fila es un registro de «{dataset_name}». No se detectó una "
+            "columna identificadora única, así que la granularidad se infiere "
+            "de la forma de la tabla." + tail)
+
+
 def build_portada(profile: dict, ctx: dict):
     """Build the cover Chapter, or None if there is truly nothing to show."""
     profile = profile or {}
@@ -166,30 +262,38 @@ def build_portada(profile: dict, ctx: dict):
     quality_criteria = ctx.get("quality_criteria") or _DEFAULT_QUALITY_CRITERIA
     quality_value = "—" if score is None else f"{score} / 100"
 
-    # Granularity: ctx wins; else derive from key candidates; else be honest.
+    llm = _llm_block(profile, ctx)
+
+    # Granularity: explicit ctx wins; then the LLM "row_meaning"; then the key
+    # candidates; finally a shape-based fallback. Always a real "Cada fila es…".
     granularity = ctx.get("granularity")
     if not granularity:
-        keys = profile.get("key_candidates") or []
-        if keys:
-            granularity = ("Cada fila parece identificada por "
-                           + ", ".join(str(k) for k in keys[:3]) + ".")
-        else:
-            granularity = ("Cada fila es… (granularidad no determinada — "
-                           "pendiente de la capa de cálculo/LLM).")
+        granularity = (llm.get("row_meaning") or "").strip() or None
+    if not granularity:
+        granularity = _derive_granularity(profile, str(dataset_name))
 
+    # Description: explicit ctx wins; then the LLM "summary"; finally a short
+    # profile-derived summary. Never the old empty placeholder.
     description = ctx.get("description")
     if not description:
-        description = ("Descripción no provista — pendiente de la capa LLM "
-                       "(`run_llm`) o de `ctx['description']`.")
+        description = (llm.get("summary") or "").strip() or None
+    if not description:
+        description = _derive_description(profile, ctx)
 
-    blocks = [
+    # Title + dataset size shown together and BIG (Heading) at the top, kept on
+    # the same page (Group). The size is no longer buried in the metadata table.
+    cover = [
         model.Heading(text=str(dataset_name), level=1),
         model.Markdown(text="**Automatic-EDA** · informe exploratorio automático"),
+        model.Heading(text=shape, level=2),
+    ]
+
+    blocks = [
+        model.Group(blocks=cover),
         model.KVTable(rows=[
             ("Fuente", source_origin),
             ("Almacenamiento", storage),
             ("Generado", when),
-            ("Tamaño", shape),
             ("Calidad", quality_value),
             ("Criterios de calidad", quality_criteria),
         ]),

python/functions/datascience/automatic_eda/chapters/portada_test.py

@@ -0,0 +1,197 @@
+"""Tests for the PORTADA (cover) chapter — DoD: golden + edges + render.
+
+Self-contained: builds synthetic TableProfiles (no DuckDB) so the suite is fast
+and deterministic. Verifies the Fase 4b improvements:
+
+1. The dataset size (N rows x M columns) is always shown BIG — as a level-2
+   heading kept together with the dataset name in a ``Group`` — and is no longer
+   a row of the metadata table.
+2. Description and Granularity are resolved through a real cascade and are never
+   the old empty placeholders: an explicit ``ctx`` value wins; otherwise the LLM
+   block (``profile['llm']``) provides ``summary`` / ``row_meaning``; otherwise a
+   short summary is derived from the profile and a "Cada fila es…" sentence from
+   the key-candidate columns or the table shape.
+3. The chapter degrades without raising on empty/None input.
+4. It renders inside the full document to both PDF and PPTX showing that content.
+"""
+
+import os
+import re
+import tempfile
+
+from pypdf import PdfReader
+from pptx import Presentation
+
+from datascience.automatic_eda.model import Group, Heading, KVTable, Markdown
+from datascience.automatic_eda.chapters.portada import (
+    CHAPTER_ID, CHAPTER_VERSION, build_portada,
+)
+from datascience.render_automatic_eda_pdf import render_automatic_eda_pdf
+from datascience.render_automatic_eda_pptx import render_automatic_eda_pptx
+
+
+def _profile(with_llm: bool = True, with_keys: bool = True) -> dict:
+    prof = {
+        "table": "titanic",
+        "source": "/data/titanic.csv",
+        "profiled_at": "2026-06-30T10:00:00+00:00",
+        "n_rows": 891,
+        "n_cols": 12,
+        "quality_score": 78.0,
+        "columns": [
+            {"name": "PassengerId", "inferred_type": "numeric",
+             "null_pct": 0.0, "numeric": {"mean": 446.0, "min": 1.0,
+                                          "max": 891.0, "std": 257.0}},
+            {"name": "Survived", "inferred_type": "numeric",
+             "null_pct": 0.0, "numeric": {"mean": 0.38, "min": 0.0,
+                                          "max": 1.0, "std": 0.49}},
+            {"name": "Sex", "inferred_type": "categorical", "null_pct": 0.0,
+             "categorical": {"top": [{"value": "male", "count": 577, "pct": 0.65},
+                                     {"value": "female", "count": 314,
+                                      "pct": 0.35}],
+                             "mode": "male", "n_distinct": 2, "entropy": 0.93}},
+        ],
+    }
+    if with_keys:
+        prof["key_candidates"] = ["PassengerId"]
+    if with_llm:
+        prof["llm"] = {
+            "summary": "Pasajeros del Titanic con su supervivencia y datos de viaje.",
+            "row_meaning": "Cada fila es un pasajero del Titanic.",
+            "dictionary": [], "pii": [], "cleaning": [], "analyses": [],
+        }
+    return prof
+
+
+def _pdf_text(path: str) -> str:
+    txt = "".join((pg.extract_text() or "") for pg in PdfReader(path).pages)
+    return re.sub(r"\s+", " ", txt)
+
+
+def _pptx_text(path: str) -> str:
+    prs = Presentation(path)
+    parts = []
+    for sl in prs.slides:
+        for sh in sl.shapes:
+            if sh.has_text_frame:
+                parts.append(sh.text_frame.text)
+            if sh.has_table:
+                tb = sh.table
+                for r in range(len(tb.rows)):
+                    for c in range(len(tb.columns)):
+                        parts.append(tb.cell(r, c).text)
+    return re.sub(r"\s+", " ", " ".join(parts))
+
+
+def _markdown_after(blocks, heading_text):
+    """Return the Markdown block that follows a Heading whose text matches."""
+    for i, b in enumerate(blocks):
+        if isinstance(b, Heading) and heading_text.lower() in b.text.lower():
+            for nb in blocks[i + 1:]:
+                if isinstance(nb, Markdown):
+                    return nb
+    return None
+
+
+def test_golden_tamano_grande_y_textos_llm():
+    ch = build_portada(_profile(), {})
+    assert ch is not None
+    assert ch.id == CHAPTER_ID
+    assert ch.version == CHAPTER_VERSION
+
+    # 1) Title + size kept together in a Group; size is a BIG level-2 heading.
+    group = next(b for b in ch.blocks if isinstance(b, Group))
+    inner = group.blocks
+    assert isinstance(inner[0], Heading) and inner[0].level == 1
+    assert inner[0].text == "titanic"
+    size_h = next(b for b in inner if isinstance(b, Heading) and b.level == 2)
+    assert "891" in size_h.text and "12" in size_h.text
+    assert "filas" in size_h.text and "columnas" in size_h.text
+
+    # 2) Size is no longer a row of the metadata table.
+    kv = next(b for b in ch.blocks if isinstance(b, KVTable))
+    labels = [r[0] for r in kv.rows]
+    assert "Tamaño" not in labels
+    assert "Fuente" in labels and "Calidad" in labels
+
+    # 3) Description and Granularity come from the LLM block.
+    desc = _markdown_after(ch.blocks, "Descripción")
+    gran = _markdown_after(ch.blocks, "Granularidad")
+    assert desc is not None and "Titanic" in desc.text
+    assert gran is not None and gran.text.startswith("Cada fila es")
+    assert "pasajero" in gran.text.lower()
+
+
+def test_fallback_sin_llm_usa_keys_y_perfil():
+    # No LLM block: description derived from the profile, granularity from keys.
+    ch = build_portada(_profile(with_llm=False, with_keys=True), {})
+    desc = _markdown_after(ch.blocks, "Descripción")
+    gran = _markdown_after(ch.blocks, "Granularidad")
+    # Description is the derived summary, never the old "pendiente" placeholder.
+    assert "pendiente" not in desc.text.lower()
+    assert "891" in desc.text and "columnas" in desc.text
+    assert "numéricas" in desc.text or "categóricas" in desc.text
+    # Granularity mentions the key candidate and starts with "Cada fila es".
+    assert gran.text.startswith("Cada fila es")
+    assert "PassengerId" in gran.text
+    assert "…" not in gran.text  # the old ellipsis placeholder is gone.
+
+
+def test_fallback_sin_llm_sin_keys_usa_forma():
+    ch = build_portada(_profile(with_llm=False, with_keys=False), {})
+    gran = _markdown_after(ch.blocks, "Granularidad")
+    assert gran.text.startswith("Cada fila es")
+    assert "titanic" in gran.text.lower()
+    assert "pendiente" not in gran.text.lower()
+
+
+def test_ctx_explicito_gana_sobre_llm():
+    ctx = {"description": "Descripción manual.",
+           "granularity": "Cada fila es una unidad manual."}
+    ch = build_portada(_profile(), ctx)
+    desc = _markdown_after(ch.blocks, "Descripción")
+    gran = _markdown_after(ch.blocks, "Granularidad")
+    assert desc.text == "Descripción manual."
+    assert gran.text == "Cada fila es una unidad manual."
+
+
+def test_edge_perfil_vacio_no_lanza():
+    # Empty / None never raise; the cover still shows a size and real texts.
+    for prof, ctx in (({}, {}), (None, None)):
+        ch = build_portada(prof, ctx)
+        assert ch is not None
+        group = next(b for b in ch.blocks if isinstance(b, Group))
+        size_h = next(b for b in group.blocks
+                      if isinstance(b, Heading) and b.level == 2)
+        assert "filas" in size_h.text and "columnas" in size_h.text
+        desc = _markdown_after(ch.blocks, "Descripción")
+        gran = _markdown_after(ch.blocks, "Granularidad")
+        assert desc.text and "pendiente" not in desc.text.lower()
+        assert gran.text.startswith("Cada fila es")
+
+
+def test_golden_render_pdf_muestra_portada():
+    prof = _profile()
+    with tempfile.TemporaryDirectory() as d:
+        out = os.path.join(d, "eda.pdf")
+        res = render_automatic_eda_pdf(prof, out, {"title": "EDA"})
+        assert res["path"] == out and os.path.exists(out)
+        assert CHAPTER_ID in [c["id"] for c in res["chapters"]]
+        txt = _pdf_text(out)
+        assert "titanic" in txt.lower()
+        assert "891" in txt and "filas" in txt and "columnas" in txt
+        assert "Titanic" in txt          # LLM summary in the Description.
+        assert "Cada fila es" in txt     # granularity sentence.
+
+
+def test_golden_render_pptx_muestra_portada():
+    prof = _profile()
+    with tempfile.TemporaryDirectory() as d:
+        out = os.path.join(d, "eda.pptx")
+        res = render_automatic_eda_pptx(prof, out, {"title": "EDA"})
+        assert res["path"] == out and os.path.exists(out)
+        assert CHAPTER_ID in [c["id"] for c in res["chapters"]]
+        txt = _pptx_text(out)
+        assert "titanic" in txt.lower()
+        assert "891" in txt and "columnas" in txt
+        assert "Cada fila es" in txt