feat: update clustering implementation and docs

backend/core/clustering.py

@@ -76,6 +76,8 @@ class KMeansAnalyzer:
         if self.model is None or self.n_clusters != n_clusters:
             self.fit(n_clusters)
         df = get_clean_data().reset_index(drop=True)
+        centers = self.scaler.inverse_transform(self.model.cluster_centers_)
+        names = self._generate_cluster_names(centers)
         if x_axis not in df.columns:
             x_axis = '月均加班时长'
         if y_axis not in df.columns:
@@ -102,23 +104,67 @@ class KMeansAnalyzer:
                 '3': '#E8684A',
                 '4': '#6DC8EC',
             },
+            'cluster_names': {
+                str(idx): names.get(idx, f'群体{idx + 1}')
+                for idx in range(self.n_clusters)
+            },
         }
 
     def _generate_cluster_names(self, centers):
-        names = {}
+        base_names = {}
         for idx, center in enumerate(centers):
             _, tenure, overtime, commute, bmi, absence = center
             if overtime > 38 and commute > 55 and absence > 8:
-                names[idx] = '高压通勤型'
+                base_names[idx] = '高压通勤型'
             elif bmi > 27 and absence > 8:
-                names[idx] = '健康波动型'
+                base_names[idx] = '健康波动型'
             elif tenure > 8 and absence < 6:
-                names[idx] = '稳定低风险型'
+                base_names[idx] = '稳定低风险型'
             elif overtime > 28 and absence > 7:
-                names[idx] = '轮班负荷型'
+                base_names[idx] = '轮班负荷型'
             else:
-                names[idx] = f'群体{idx + 1}'
-        return names
+                base_names[idx] = f'群体{idx + 1}'
+        return self._deduplicate_cluster_names(base_names, centers)
+
+    def _deduplicate_cluster_names(self, names, centers):
+        grouped = {}
+        for idx, name in names.items():
+            grouped.setdefault(name, []).append(idx)
+
+        deduplicated = names.copy()
+        for name, indices in grouped.items():
+            if len(indices) == 1:
+                continue
+
+            order = self._build_duplicate_order(indices, centers)
+            suffixes = self._suffix_candidates(name)
+            for rank, idx in enumerate(order):
+                suffix = suffixes[rank] if rank < len(suffixes) else f'{rank + 1}'
+                deduplicated[idx] = f'{name}{suffix}'
+        return deduplicated
+
+    def _build_duplicate_order(self, indices, centers):
+        return sorted(
+            indices,
+            key=lambda idx: (
+                centers[idx][5],  # 缺勤时长
+                centers[idx][2],  # 加班
+                centers[idx][1],  # 司龄
+                centers[idx][3],  # 通勤
+                centers[idx][4],  # BMI
+                centers[idx][0],  # 年龄
+            ),
+            reverse=True,
+        )
+
+    def _suffix_candidates(self, name):
+        suffix_map = {
+            '高压通勤型': ['-高风险组', '-关注组', '-观察组'],
+            '健康波动型': ['-重点关注组', '-预警组', '-观察组'],
+            '稳定低风险型': ['-资深组', '-成熟组', '-稳健组'],
+            '轮班负荷型': ['-高负荷组', '-轮班组', '-强化组'],
+        }
+        return suffix_map.get(name, [f'（{idx}）' for idx in range(1, 10)])
 
     def _generate_description(self, name):
         descriptions = {
@@ -127,6 +173,9 @@ class KMeansAnalyzer:
             '稳定低风险型': '司龄较长，缺勤水平稳定且偏低。',
             '轮班负荷型': '排班和工作负荷较重，缺勤风险较高。',
         }
+        for key, description in descriptions.items():
+            if name.startswith(key):
+                return description
         return descriptions.get(name, '常规员工群体。')