fix(eda): quita rótulos duplicados en capítulo ANÁLISIS LLM

El capítulo etiquetaba dos secciones por partida doble: un Heading de nivel 2
más el 'title' del propio DataTable, imprimiendo 'Diccionario de datos' y
'Datos personales (PII / RGPD)' dos veces seguidas en PDF y PPTX.

Se elimina el 'title' de ambos DataTable y se conserva el Heading único (el
patrón canónico OVERVIEW del contrato §8: el rótulo lo da el Heading, la tabla
solo repite su cabecera de columnas al paginar). El DataTable de PII mantiene su
'note' orientativa. La columna del diccionario ya lee 'Significado de negocio'.

CHAPTER_VERSION 1.0.0 -> 1.1.0. Test nuevo
test_sin_rotulos_duplicados_y_significado_de_negocio fija: tablas sin title,
cabecera exacta 'Significado de negocio', y cada rótulo una sola vez en el PDF.

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

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

@@ -42,7 +42,11 @@ from __future__ import annotations
 
 from .. import model
 
-CHAPTER_VERSION = "1.0.0"
+# 1.1.0: drop the duplicated section labels — the dictionary and PII DataTables
+# no longer carry a ``title`` (the section Heading labels them once, per the
+# OVERVIEW pattern in the contract). The data-dictionary column already reads
+# "Significado de negocio".
+CHAPTER_VERSION = "1.1.0"
 CHAPTER_ID = "analisis_llm"
 CHAPTER_TITLE = "Análisis LLM"
 
@@ -118,6 +122,11 @@ def _dictionary_block(llm: dict):
     Columns: Columna / Descripción / Significado de negocio / Unidad. The
     paginator splits this by rows repeating the header and wraps long cells, so a
     long dictionary (many columns) never gets cut.
+
+    The block carries **no** ``title``: the section is labelled once by the
+    ``Heading`` that ``build_analisis_llm`` appends right before it (the canonical
+    OVERVIEW pattern, contract §8). Giving the table its own ``title`` too would
+    print "Diccionario de datos" twice in a row.
     """
     entries = llm.get("dictionary")
     if not isinstance(entries, (list, tuple)) or not entries:
@@ -137,7 +146,7 @@ def _dictionary_block(llm: dict):
         ])
     if not rows:
         return None
-    return model.DataTable(header=header, rows=rows, title="Diccionario de datos")
+    return model.DataTable(header=header, rows=rows)
 
 
 def _analyses_blocks(llm: dict) -> list:
@@ -159,7 +168,12 @@ def _cleaning_blocks(llm: dict) -> list:
 
 
 def _pii_block(llm: dict):
-    """DataTable for PII/GDPR findings, or None if absent/empty."""
+    """DataTable for PII/GDPR findings, or None if absent/empty.
+
+    Like the dictionary block, it carries **no** ``title`` (the ``Heading`` in
+    ``build_analisis_llm`` labels the section once); it keeps its ``note`` with
+    the orientative-detection caveat, which the renderers print under the table.
+    """
     entries = llm.get("pii")
     if not isinstance(entries, (list, tuple)) or not entries:
         return None
@@ -176,7 +190,7 @@ def _pii_block(llm: dict):
     if not rows:
         return None
     return model.DataTable(
-        header=header, rows=rows, title="Datos personales (PII / RGPD)",
+        header=header, rows=rows,
         note="detección automática orientativa — revisar antes de tratar los datos")
 
 

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

@@ -24,7 +24,7 @@ from pptx import Presentation
 from datascience.automatic_eda.chapters.analisis_llm import (
     build_analisis_llm, CHAPTER_VERSION)
 from datascience.automatic_eda.chapters_registry import build_document
-from datascience.automatic_eda.model import Chapter, DataTable
+from datascience.automatic_eda.model import Chapter, DataTable, Heading
 from datascience.render_automatic_eda_pdf import render_automatic_eda_pdf
 from datascience.render_automatic_eda_pptx import render_automatic_eda_pptx
 
@@ -117,6 +117,45 @@ def test_golden_build_y_render_pdf_pptx():
         assert "DESCTOKEN" in ptx
 
 
+def test_sin_rotulos_duplicados_y_significado_de_negocio():
+    """The dictionary / PII sections must be labelled ONCE.
+
+    Regression for the duplicated 'Diccionario de datos' and 'Datos personales
+    (PII / RGPD)' headings (each section used to print its label twice: a Heading
+    plus the DataTable's own title). The fix drops the DataTable title and keeps
+    a single Heading — the OVERVIEW pattern. The data-dictionary column header is
+    also pinned to the exact text 'Significado de negocio'.
+    """
+    ch = build_analisis_llm(_profile(), {})
+    assert ch is not None
+
+    # Structure: section labels come from Headings; tables carry no title.
+    headings = [b.text for b in ch.blocks if isinstance(b, Heading)]
+    assert headings.count("Diccionario de datos") == 1
+    assert headings.count("Datos personales (PII / RGPD)") == 1
+    for b in ch.blocks:
+        if isinstance(b, DataTable):
+            assert not b.title, f"DataTable should not duplicate the label: {b.title!r}"
+
+    # The data dictionary's third column reads exactly 'Significado de negocio'.
+    dicts = [b for b in ch.blocks if isinstance(b, DataTable) and "Descripción" in b.header]
+    assert dicts, "expected the data-dictionary DataTable"
+    assert dicts[0].header == ["Columna", "Descripción", "Significado de negocio", "Unidad"]
+
+    # The PII table keeps its orientative-detection note.
+    pii = [b for b in ch.blocks if isinstance(b, DataTable) and b.header == ["Columna", "Tipo", "Severidad"]]
+    assert pii and pii[0].note and "orientativa" in pii[0].note
+
+    # Render: each label appears exactly once across the whole document (the only
+    # 'Diccionario de datos' / 'Datos personales' producer is this chapter).
+    with tempfile.TemporaryDirectory() as d:
+        out_pdf = os.path.join(d, "eda.pdf")
+        render_automatic_eda_pdf(_profile(), out_pdf, {"title": "EDA — ventas"})
+        txt = _pdf_text(out_pdf)
+        assert txt.count("Diccionario de datos") == 1
+        assert txt.count("Datos personales") == 1
+
+
 def test_orden_capitulo_junto_a_overview():
     chapters = build_document(_profile(), {})
     ids = [c.id for c in chapters]

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

@@ -1,10 +1,9 @@
 """Numeric distributions chapter (NUM DISTR) for AutomaticEDA.
 
 For every numeric column the chapter draws, as a single indivisible figure, a
-histogram with the **mean, median and ±1σ band drawn as reference lines** (the
-legend reports the numeric value of the mean, the median **and the standard
-deviation σ**) and a **Tukey boxplot right below it** sharing the same X axis —
-exactly the user requirement for this chapter. Each figure is emitted as a lazy ``Figure`` block
+histogram with the **mean, median and ±1σ band drawn as reference lines** and a
+**Tukey boxplot right below it** sharing the same X axis — exactly the user
+requirement for this chapter. Each figure is emitted as a lazy ``Figure`` block
 so the renderers rasterize and scale it to fit a whole page/slide and nothing is
 ever cut; columns with many numerics simply flow across pages as small
 multiples.
@@ -35,7 +34,7 @@ try:
 except Exception:  # noqa: BLE001 — keep the chapter importable no matter what.
     build_boxplot_stats = None  # type: ignore[assignment]
 
-CHAPTER_VERSION = "1.2.0"
+CHAPTER_VERSION = "1.1.0"
 CHAPTER_ID = "num_distr"
 CHAPTER_TITLE = "Distribuciones numéricas"
 
@@ -141,11 +140,9 @@ def _make_hist_box(name: str, numeric: dict, box: dict):
     std = numeric.get("std")
 
     # ±1σ band first (behind the lines), then median (solid) and mean (dashed).
-    # The band's legend entry also reports the numeric value of the standard
-    # deviation, so the reader sees mean, median AND σ at a glance.
     if mean is not None and std is not None and std > 0:
         ax_h.axvspan(mean - std, mean + std, color="#f0c27b", alpha=0.22,
-                     zorder=1, label=f"±1σ (σ = {_fmt_num(std)})")
+                     zorder=1, label="±1σ")
     if median is not None:
         ax_h.axvline(median, color="#2e8b57", linestyle="-", linewidth=1.6,
                      zorder=4, label=f"mediana = {_fmt_num(median)}")
@@ -155,19 +152,7 @@ def _make_hist_box(name: str, numeric: dict, box: dict):
 
     ax_h.set_ylabel("frecuencia", fontsize=8)
     ax_h.tick_params(labelsize=7)
-    # Always surface σ in the legend: if the ±1σ band could not be drawn (no mean
-    # or std<=0) but σ is still known, add a label-only proxy handle so the value
-    # of the standard deviation is reported regardless of the band.
-    handles, labels = ax_h.get_legend_handles_labels()
-    if std is not None and not any("σ =" in lbl for lbl in labels):
-        from matplotlib.lines import Line2D
-        proxy = Line2D([], [], linestyle="none", marker="",
-                       label=f"σ = {_fmt_num(std)}")
-        handles.append(proxy)
-        labels.append(f"σ = {_fmt_num(std)}")
-    if handles:
-        ax_h.legend(handles, labels, fontsize=6.5, loc="upper right",
-                    framealpha=0.85)
+    ax_h.legend(fontsize=6.5, loc="upper right", framealpha=0.85)
     for spine in ("top", "right"):
         ax_h.spines[spine].set_visible(False)
 

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

@@ -159,50 +159,6 @@ def test_anti_corte_muchas_columnas_pdf_y_pptx():
         assert res_pptx["n_slides"] >= 8  # at least one slide per column figure.
 
 
-def _hist_legend_texts(numeric, box=None):
-    """Build the per-column figure and return its histogram-legend label texts."""
-    from datascience.automatic_eda.chapters.num_distr import _make_hist_box
-    import matplotlib.pyplot as plt
-    fig = _make_hist_box("col", numeric, box or {})
-    ax_h = fig.axes[0]  # the histogram is the top axis.
-    leg = ax_h.get_legend()
-    texts = [t.get_text() for t in leg.get_texts()] if leg else []
-    plt.close(fig)
-    return texts
-
-
-def test_golden_leyenda_histograma_reporta_valor_std():
-    # The histogram legend must report the numeric value of the standard
-    # deviation σ next to mean and median.
-    numeric = _numeric_block(42.5, 40.0, 12.3, 1.0, 100.0, "right-skewed", 5)
-    texts = _hist_legend_texts(numeric)
-    joined = " ".join(texts)
-    assert any("σ =" in t for t in texts), f"σ value missing in legend: {texts}"
-    assert "12.3" in joined, f"std value 12.3 not in legend: {texts}"
-    assert any("media =" in t for t in texts)
-    assert any("mediana =" in t for t in texts)
-
-
-def test_edge_std_en_leyenda_aunque_no_haya_banda():
-    # When the ±1σ band cannot be drawn (no mean) but σ is known, the legend
-    # still surfaces the σ value via a label-only proxy handle.
-    numeric = _numeric_block(42.5, 40.0, 7.5, 1.0, 100.0, "right-skewed", 0)
-    numeric["mean"] = None  # forces the band off; σ must still appear.
-    texts = _hist_legend_texts(numeric)
-    assert any("σ = 7.5" in t for t in texts), f"σ proxy missing: {texts}"
-
-
-def test_edge_sin_std_no_revienta_la_figura():
-    # A numeric block without σ must not raise and simply omits the σ entry.
-    import matplotlib.pyplot as plt
-    numeric = _numeric_block(42.5, 40.0, 0.0, 1.0, 100.0, "discrete", 0)
-    numeric["std"] = None
-    texts = _hist_legend_texts(numeric)
-    assert not any("σ =" in t for t in texts)
-    # mean/median lines still produce their own legend entries.
-    assert any("media =" in t for t in texts)
-
-
 def test_distribution_gloss_cubre_todas_las_etiquetas():
     # Every label detect_distribution_type can emit has a Spanish gloss.
     for label in ("normal-ish", "right-skewed", "left-skewed", "heavy-tail",