feat(eda): build_boxplot_stats — estadísticas de boxplot Tukey desde sub-bloque numeric

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

python/functions/datascience/build_boxplot_stats_test.py

@@ -0,0 +1,108 @@
+"""Tests para build_boxplot_stats."""
+
+import os
+import sys
+
+sys.path.insert(0, os.path.dirname(__file__))
+
+from build_boxplot_stats import build_boxplot_stats
+
+# Keys that a non-empty result dict must always contain.
+_EXPECTED_KEYS = {
+    "q1", "median", "q3", "iqr", "lower_fence", "upper_fence",
+    "whisker_lo", "whisker_hi", "min", "max",
+    "has_low_outliers", "has_high_outliers", "n_outliers",
+}
+
+
+def test_boxplot_tukey_basico():
+    """Golden: bloque numeric con outlier alto claro -> fences IQR de Tukey."""
+    numeric = {
+        "min": 1.0, "max": 100.0,
+        "p25": 10.0, "median": 25.0, "p75": 40.0,
+        "iqr": 30.0, "n_outliers": 3,
+    }
+    box = build_boxplot_stats(numeric)
+
+    assert set(box.keys()) == _EXPECTED_KEYS
+
+    assert box["q1"] == 10.0
+    assert box["median"] == 25.0
+    assert box["q3"] == 40.0
+    # iqr recomputado desde los cuartiles.
+    assert box["iqr"] == 30.0
+    # lower = 10 - 1.5*30 = -35 ; upper = 40 + 1.5*30 = 85.
+    assert box["lower_fence"] == -35.0
+    assert box["upper_fence"] == 85.0
+    # whisker_lo = max(min=1, -35) = 1 ; whisker_hi = min(max=100, 85) = 85.
+    assert box["whisker_lo"] == 1.0
+    assert box["whisker_hi"] == 85.0
+    assert box["min"] == 1.0
+    assert box["max"] == 100.0
+    # Solo hay outliers altos (100 > 85), no bajos (1 no < -35).
+    assert box["has_low_outliers"] is False
+    assert box["has_high_outliers"] is True
+    # n_outliers se propaga del bloque z-score (informativo).
+    assert box["n_outliers"] == 3
+
+
+def test_percentiles_faltan_devuelve_vacio():
+    """Si falta p25/median/p75 -> {} (caller omite el boxplot)."""
+    # Falta p25.
+    assert build_boxplot_stats({"median": 25.0, "p75": 40.0}) == {}
+    # Falta p75.
+    assert build_boxplot_stats({"p25": 10.0, "median": 25.0}) == {}
+    # Falta median y p50.
+    assert build_boxplot_stats({"p25": 10.0, "p75": 40.0}) == {}
+    # numeric None / no dict tambien es vacio, nunca lanza.
+    assert build_boxplot_stats(None) == {}
+    assert build_boxplot_stats({}) == {}
+
+
+def test_median_cae_a_p50():
+    """median ausente cae a p50."""
+    numeric = {"min": 0.0, "max": 10.0, "p25": 2.0, "p50": 5.0, "p75": 8.0}
+    box = build_boxplot_stats(numeric)
+    assert box["median"] == 5.0
+    assert box["q1"] == 2.0
+    assert box["q3"] == 8.0
+
+
+def test_whiskers_usan_fence_si_falta_min_max():
+    """Sin min/max los bigotes caen a las fences y no hay outliers marcados."""
+    numeric = {"p25": 10.0, "median": 25.0, "p75": 40.0}  # sin min ni max
+    box = build_boxplot_stats(numeric)
+
+    assert box["min"] is None
+    assert box["max"] is None
+    # iqr = 30, fences -35 / 85; los bigotes caen a las fences.
+    assert box["whisker_lo"] == box["lower_fence"] == -35.0
+    assert box["whisker_hi"] == box["upper_fence"] == 85.0
+    # Sin extremos reales, no se afirma que haya outliers.
+    assert box["has_low_outliers"] is False
+    assert box["has_high_outliers"] is False
+    # n_outliers ausente -> 0.
+    assert box["n_outliers"] == 0
+
+
+def test_tipos_salida_float_bool_int():
+    """Numericos en float, flags bool nativos, n_outliers int."""
+    numeric = {
+        "min": -50.0, "max": 200.0,
+        "p25": 10.0, "median": 25.0, "p75": 40.0,
+        "n_outliers": 7,
+    }
+    box = build_boxplot_stats(numeric)
+
+    for key in ("q1", "median", "q3", "iqr", "lower_fence", "upper_fence",
+                "whisker_lo", "whisker_hi", "min", "max"):
+        assert isinstance(box[key], float), f"{key} debe ser float"
+
+    assert isinstance(box["has_low_outliers"], bool)
+    assert isinstance(box["has_high_outliers"], bool)
+    assert isinstance(box["n_outliers"], int) and not isinstance(box["n_outliers"], bool)
+
+    # min=-50 < lower_fence=-35 -> outlier bajo ; max=200 > upper_fence=85 -> alto.
+    assert box["has_low_outliers"] is True
+    assert box["has_high_outliers"] is True
+    assert box["n_outliers"] == 7