From 1c91ba42ab20e835175b67223bc3332167a6dd12 Mon Sep 17 00:00:00 2001
From: tianjianyong <11429339@qq.com>
Date: Sun, 1 Dec 2024 21:22:11 +0800
Subject: [PATCH] =?UTF-8?q?=E4=BF=AE=E6=94=B9=E4=BA=86=E7=89=B9=E5=BE=81?=
 =?UTF-8?q?=E5=88=86=E6=9E=90=E5=9B=BE=E8=A1=A8=E7=9A=84=E6=98=BE=E7=A4=BA?=
 =?UTF-8?q?=E5=92=8C=E7=83=AD=E5=8A=9B=E5=9B=BE=E8=AF=B4=E6=98=8E?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 frontend/src/views/AnalysisPage.vue | 28 +++++++++++++++++++++++++---
 src/feature_analysis.py             | 13 +++++++++++--
 2 files changed, 36 insertions(+), 5 deletions(-)

diff --git a/frontend/src/views/AnalysisPage.vue b/frontend/src/views/AnalysisPage.vue
index 504051c..c501f8b 100644
--- a/frontend/src/views/AnalysisPage.vue
+++ b/frontend/src/views/AnalysisPage.vue
@@ -67,12 +67,18 @@
         <h3>特征重要性</h3>
         <div class="chart-container">
           <div ref="importanceChartRef" style="width: 100%; height: 600px"></div>
+          <div class="chart-note">
+            <p>说明：F-特征分数是基于F统计量的特征重要性度量，用于评估各个特征与预测目标之间的相关程度。F分数越高，表示该特征与预测目标之间的相关性越强，但不一定是线性关系。F分数没有固定的上限，其值取决于数据的特征分布和样本量。</p>
+          </div>
         </div>
         
         <!-- 相关性分析 -->
         <h3>相关性分析</h3>
         <div class="chart-container">
           <div ref="correlationChartRef" style="width: 100%; height: 800px"></div>
+          <div class="chart-note">
+            <p>说明：热力图展示了各特征之间的相关系数，范围从-1到1。正值（蓝色）表示正相关，负值（红色）表示负相关，0（白色）表示无相关性。相关系数的绝对值越接近1，表示相关性越强；越接近0，表示相关性越弱。</p>
+          </div>
         </div>
 
         <!-- 火箭炮特有的图表 -->
@@ -404,19 +410,27 @@ const renderCharts = () => {
           
           // 设置基本图表的选项
           const importanceOption = {
-            title: { text: '特征重要性排序' },
+            title: { 
+              text: '特征重要性排序',
+              left: 'center'
+            },
             tooltip: {
               trigger: 'item',
               axisPointer: {
                 type: 'shadow'
               },
               formatter: function(params) {
-                return `${params.name}: ${params.value.toFixed(1)}`
+                return `${params.name}: ${params.value.toFixed(2)}`
               }
             },
             xAxis: {
               type: 'value',
-              name: '重要性得分'
+              name: 'F-特征分数',
+              axisLabel: {
+                formatter: function(value) {
+                  return value.toFixed(1)
+                }
+              }
             },
             yAxis: {
               type: 'category',
@@ -1106,4 +1120,12 @@ function debounce(fn, delay) {
     }
   }
 }
+
+.chart-note {
+  margin-top: 10px;
+  padding: 10px;
+  color: #666;
+  font-size: 14px;
+  line-height: 1.5;
+}
 </style>
\ No newline at end of file
diff --git a/src/feature_analysis.py b/src/feature_analysis.py
index 4a45ea7..3e61aa3 100644
--- a/src/feature_analysis.py
+++ b/src/feature_analysis.py
@@ -212,11 +212,20 @@ class FeatureAnalysis:
             
             # 创建特征重要性列表（使用中文名称）
             important_features = []
+            
+            # 过滤掉无效的分数
+            valid_scores = importance_scores[~np.isnan(importance_scores)]
+            
+            # 记录一些统计信息
+            logger.info(f"F-score statistics:")
+            logger.info(f"min={np.min(valid_scores):.2f}, max={np.max(valid_scores):.2f}, "
+                       f"mean={np.mean(valid_scores):.2f}, median={np.median(valid_scores):.2f}")
+                
             for idx, (name, score) in enumerate(zip(feature_names, importance_scores)):
                 if not np.isnan(score):
                     important_features.append({
-                        'name': self.feature_name_map.get(name, name),  # 使用中文名称
-                        'importance': float(score)
+                        'name': self.feature_name_map.get(name, name),
+                        'importance': float(score)  # 保持原始F-score
                     })
             
             # 按重要性排序