feat: add percentile-based truncated histogram option

src/data_profiling/config.py

@@ -153,6 +153,8 @@ class Histogram(BaseModel):
     max_bins: int = 250
     x_axis_labels: bool = True
     density: bool = False
+    # Percentile cutoff for truncated histogram (0.0 to disable, e.g. 0.05 for 5-95%)
+    percentile_cutoff: float = 0.0
 
 
 class CatFrequencyPlot(BaseModel):

src/data_profiling/model/summary_algorithms.py

@@ -106,6 +106,42 @@ def histogram_compute(
     )
 
     stats[name] = hist
+
+    # Compute truncated histogram if percentile_cutoff is set
+    cutoff = hist_config.percentile_cutoff
+    if cutoff > 0.0:
+        lower = np.percentile(finite, cutoff * 100)
+        upper = np.percentile(finite, (1 - cutoff) * 100)
+        mask = (finite_values >= lower) & (finite_values <= upper)
+        truncated_values = finite_values[mask]
+        truncated_weights = weights[mask] if weights is not None else None
+
+        if len(truncated_values) > 0:
+            t_vmin = float(np.min(truncated_values))
+            t_vmax = float(np.max(truncated_values))
+            t_range = t_vmax - t_vmin
+
+            if t_range == 0:
+                eps = 0.5 if t_vmin == 0 else abs(t_vmin) * 0.1
+                t_bins = np.array([t_vmin - eps, t_vmin + eps])
+            else:
+                requested_bins = hist_config.bins if hist_config.bins > 0 else "auto"
+                if isinstance(requested_bins, int):
+                    safe_bins = min(requested_bins, n_unique, hist_config.max_bins)
+                    safe_bins = max(1, safe_bins)
+                    t_bins = np.linspace(t_vmin, t_vmax, safe_bins + 1)
+                else:
+                    t_bins = np.histogram_bin_edges(truncated_values, bins="auto")
+                    if len(t_bins) - 1 > hist_config.max_bins:
+                        t_bins = np.linspace(t_vmin, t_vmax, hist_config.max_bins + 1)
+
+            stats[f"{name}_truncated"] = np.histogram(
+                truncated_values,
+                bins=t_bins,
+                weights=truncated_weights,
+                density=hist_config.density,
+            )
+
     return stats
 
 

src/data_profiling/report/structure/variables/render_real.py

@@ -119,6 +119,7 @@ def render_real(config: Settings, summary: dict) -> dict:
     )
 
     summary_histogram = summary.get("histogram", [])
+    summary_histogram_truncated = summary.get("histogram_truncated", None)
 
     mini_hist_data = None
 
@@ -268,7 +269,6 @@ def render_real(config: Settings, summary: dict) -> dict:
                 f"<strong>Histogram with fixed size bins</strong> "
                 f"(bins={len(summary_histogram[1]) - 1})"
             )
-
     hist = image_or_empty(
         hist_data,
         alt="Histogram",
@@ -277,6 +277,20 @@ def render_real(config: Settings, summary: dict) -> dict:
         name="Histogram",
         anchor_id=f"{varid}histogram",
     )
+    # Truncated histogram
+    truncated_hist_data = None
+    if summary_histogram_truncated is not None:
+        cutoff = config.plot.histogram.percentile_cutoff
+        truncated_hist_data = histogram(config, *summary_histogram_truncated)
+
+    truncated_hist = image_or_empty(
+        truncated_hist_data,
+        alt="Truncated Histogram",
+        image_format=image_format,
+        caption=f"<strong>Histogram (truncated)</strong> ({cutoff:.0%} - {1-cutoff:.0%} percentile)" if truncated_hist_data else None,
+        name="Truncated Histogram",
+        anchor_id=f"{varid}histogram_truncated",
+    )
 
     fq = FrequencyTable(
         template_variables["freq_table_rows"],
@@ -306,7 +320,7 @@ def render_real(config: Settings, summary: dict) -> dict:
     )
 
     template_variables["bottom"] = Container(
-        [statistics, hist, fq, evs],
+        [statistics, hist, truncated_hist, fq, evs],
         sequence_type="tabs",
         anchor_id=f"{varid}bottom",
     )