feat(eda): render de models en markdown + PDF DB-level para profile_database (H4,H9)

- H4: render_eda_markdown anade seccion Modelos (PCA/KMeans/normalidad/outliers); render_eda_pdf formatea models/series/caveats como tablas (no str(dict) crudo) - H9: profile_database gana flag emit_pdf -> PDF movil DB-level (resumen tablas + join graph) via render_eda_pdf_relational; clave report_pdf_path - aditivos y retrocompatibles (flags default False). 38 tests verdes Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-29 04:05:38 +02:00
parent caf8c25d99
commit c4cff5ed5b
7 changed files with 706 additions and 15 deletions
@@ -173,3 +173,62 @@ def test_tolerates_empty_profile():
 def test_tolerates_none_profile():
    md = render_eda_markdown(None)
    assert "# EDA — (unnamed)" in md
+
+
+def _sample_models():
+    """Bloque `models` como el que produce run_eda_models (PCA/KMeans/...)."""
+    return {
+        "n_numeric_cols": 3,
+        "pca": {
+            "n_components": 2,
+            "n_rows_used": 1000,
+            "n_features": 3,
+            "explained_variance_ratio": [0.62, 0.21],
+            "cumulative": [0.62, 0.83],
+            "top_loadings": [
+                {"component": 0, "feature": "price", "loading": 0.71},
+                {"component": 1, "feature": "qty", "loading": -0.55},
+            ],
+        },
+        "kmeans": {
+            "best_k": 3,
+            "silhouette": 0.48,
+            "cluster_sizes": [500, 300, 200],
+            "scores_by_k": [
+                {"k": 2, "silhouette": 0.41, "inertia": 1200.0},
+                {"k": 3, "silhouette": 0.48, "inertia": 900.0},
+            ],
+        },
+        "outliers": {
+            "n_outliers": 35,
+            "outlier_pct": 3.5,
+            "threshold": -0.51,
+        },
+        "normality": {
+            "price": {"jarque_bera": {"p": 0.0001}, "is_normal": False},
+        },
+        "note": "",
+    }
+
+
+def test_models_section_rendered():
+    # H4: el bloque models antes se omitía en markdown; ahora tiene formatter.
+    profile = _sample_profile()
+    profile["models"] = _sample_models()
+    md = render_eda_markdown(profile)
+    assert "## Modelos" in md
+    assert "### PCA" in md
+    assert "### KMeans" in md
+    assert "### Outliers multivariante (Isolation Forest)" in md
+    assert "### Normalidad" in md
+    # Datos reales del PCA renderizados (varianza explicada ×100) y KMeans.
+    assert "62.0" in md  # explained_variance_ratio 0.62 -> 62.00%
+    assert "mejor k = 3" in md
+    # outlier_pct del modelo ya viene en escala 0-100: 3.5 -> "3.5%", no "350".
+    assert "3.5%" in md
+
+
+def test_models_absent_when_none():
+    # Edge: profile sin models (None) no produce sección Modelos ni rompe.
+    md = render_eda_markdown(_sample_profile())  # models=None en el sample
+    assert "## Modelos" not in md