fix(cluster_detail): show raw data rows instead of entity profiles

analysis/views/clustering.py

@@ -161,7 +161,9 @@ def _get_globe_flows(run, max_rows=500):
 
 
 def cluster_detail(request, display_id, cluster_label):
-    """Detailed view of a single cluster with entity list, SVD features, and NL summary."""
+    """Detailed view of a single cluster with raw data rows, SVD features, and NL summary."""
+    import json
+    import polars as pl
     run = get_object_or_404(AnalysisRun, display_id=display_id)
     try:
         cluster_label = int(cluster_label)
@@ -169,29 +171,50 @@ def cluster_detail(request, display_id, cluster_label):
         raise Http404("Invalid cluster label")
     cluster = get_object_or_404(ClusterResult, run=run, cluster_label=cluster_label)
     features = cluster.features.all().order_by('-distinguishing_score')[:50]
-    entities = cluster.entities.all()[:100]
+
+    # Load raw data rows for this cluster from EP row indices
+    row_data = []
+    try:
+        from analysis.data_loader import load_csv_directory, load_from_db
+        lf = None
+        if run.sqlite_table:
+            lf = load_from_db(run.sqlite_table)
+        if lf is None and run.csv_glob:
+            lf, _, _, _, _ = load_csv_directory(run.csv_glob)
+        if lf is not None:
+            # Get row indices assigned to this cluster from EntityProfile
+            eps = cluster.entities.all().order_by('entity_value')[:100]
+            indices = []
+            for ep in eps:
+                try:
+                    idx = int(ep.entity_value.replace('row_', ''))
+                    indices.append(idx)
+                except (ValueError, AttributeError):
+                    continue
+            if indices:
+                df = lf.collect(streaming=True)
+                df_filtered = df[indices]
+                # Convert to dict list for template (limit columns for display)
+                cols = df_filtered.columns[:20]  # show first 20 columns
+                for row_idx, row in enumerate(df_filtered.select(cols).iter_rows(named=True)):
+                    entry = {'index': indices[row_idx] if row_idx < len(indices) else row_idx}
+                    for k, v in row.items():
+                        entry[k] = v
+                    row_data.append(entry)
+    except Exception as exc:
+        logger.warning(f'Failed to load raw data for cluster detail: {exc}')
+
     nl_summary = ''
     feats_list = [{'feature_name': f.feature_name, 'score': f.distinguishing_score,
                    'mean': f.mean, 'std': f.std} for f in features[:10]]
     if feats_list:
         nl_summary = nl_describe.describe_cluster(feats_list)
 
-    # Build entity data with feature_json values
-    entity_data = []
-    for e in entities:
-        entry = {'id': e.id, 'value': e.entity_value,
-                 'embedding_x': e.embedding_x, 'embedding_y': e.embedding_y}
-        if e.feature_json:
-            entry['features'] = {k: round(float(v), 4) if isinstance(v, (int, float)) else str(v)
-                                 for k, v in e.feature_json.items()}
-        entity_data.append(entry)
-
     return render(request, 'analysis/cluster_detail.html', {
         'run': run,
         'cluster': cluster,
         'features': features,
-        'entities': entities,
-        'entity_data_json': json.dumps(entity_data),
+        'row_data': row_data,
         'nl_summary': nl_summary,
     })
 

templates/analysis/cluster_detail.html

@@ -3,14 +3,12 @@
 {% block title %}簇 #{{ cluster.cluster_label }} — 运行 #{{ run.display_id }}{% endblock %}
 {% block content %}
 <style>
-.entity-card { border:1px solid #e0e0e0; border-radius:6px; padding:0.6rem; margin-bottom:0.4rem; background:#fafafa; }
-.entity-card .val { font-weight:600; font-size:0.85rem; }
-.entity-card .feat { font-size:0.75rem; color:#666; display:inline-block; margin-right:0.5rem; }
+.feat-table { width:100%; border-collapse:collapse; font-size:0.8rem; }
+.feat-table th { background:#f5f5f5; padding:0.3rem 0.5rem; text-align:left; font-weight:600; border-bottom:2px solid #ddd; white-space:nowrap; }
+.feat-table td { padding:0.25rem 0.5rem; border-bottom:1px solid #eee; }
+.feat-table td code { font-size:0.72rem; }
 .feat-positive { color:#2e7d32; }
 .feat-negative { color:#c62828; }
-.feat-table { width:100%; border-collapse:collapse; font-size:0.8rem; }
-.feat-table th { background:#f5f5f5; padding:0.3rem 0.5rem; text-align:left; font-weight:600; border-bottom:2px solid #ddd; }
-.feat-table td { padding:0.25rem 0.5rem; border-bottom:1px solid #eee; }
 </style>
 
 <div class="card">
@@ -93,28 +91,34 @@
 {% endwith %}
 {% endif %}
 
-<!-- ── Entity List ── -->
+<!-- ── Raw Data Rows ── -->
 <div class="card">
-    <h3>👤 行列表 <span style="font-weight:400;font-size:0.8rem;color:#888;">{{ entities|length }} 条</span></h3>
-    <div id="entityList">
-    {% for e in entities %}
-        <div class="entity-card">
-            <div style="display:flex;justify-content:space-between;align-items:center;">
-                <span class="val">{{ e.entity_value }}</span>
-                <a href="{% url 'analysis:entity_profile' e.id %}" class="btn btn-sm" style="font-size:0.75rem;padding:0.2rem 0.6rem;background:#4361ee;color:#fff;text-decoration:none;border-radius:4px;">画像</a>
-            </div>
-            {% if e.feature_json %}
-            <div style="margin-top:0.3rem;">
-                {% for k, v in e.feature_json.items|slice:":8" %}
-                <span class="feat"><strong>{{ k }}</strong>: {% if v is None %}-{% else %}{{ v|floatformat:2 }}{% endif %}</span>
+    <h3>📋 数据行 <span style="font-weight:400;font-size:0.8rem;color:#888;">{{ row_data|length }} 条</span></h3>
+    {% if row_data %}
+    <div style="overflow-x:auto;">
+    <table class="feat-table" style="font-size:0.75rem;">
+        <thead>
+            <tr>
+                <th>#</th>
+                {% for k, v in row_data.0.items %}
+                <th>{{ k }}</th>
                 {% endfor %}
-                {% if e.feature_json.items|length > 8 %}<span class="feat" style="color:#999;">+{{ e.feature_json.items|length|add:"-8" }} more</span>{% endif %}
-            </div>
-            {% endif %}
-        </div>
-    {% empty %}
-        <div class="empty-state"><p>该簇无数据行</p></div>
-    {% endfor %}
+            </tr>
+        </thead>
+        <tbody>
+            {% for row in row_data %}
+            <tr>
+                <td>{{ forloop.counter }}</td>
+                {% for k, v in row.items %}
+                <td><code>{{ v|default:"-" }}</code></td>
+                {% endfor %}
+            </tr>
+            {% endfor %}
+        </tbody>
+    </table>
     </div>
+    {% else %}
+    <div class="empty-state"><p>该簇无数据行</p></div>
+    {% endif %}
 </div>
 {% endblock %}