refactor(analyze_trading_data): 移除基础统计和相关性分析功能

移除不再需要的统计分析和相关性热图功能，简化分析报告生成逻辑

analyze_trading_data.py

@@ -7,6 +7,10 @@ import json
 import re
 from datetime import datetime
 
+# 配置matplotlib中文字体显示
+plt.rcParams['font.sans-serif'] = ['SimHei', 'Microsoft YaHei', 'DejaVu Sans']  # 用来正常显示中文标签
+plt.rcParams['axes.unicode_minus'] = False  # 用来正常显示负号
+
 def extract_timestamp(timestamp_str):
     """从时间戳字符串中提取日期时间"""
     if isinstance(timestamp_str, tuple):
@@ -149,14 +153,10 @@ def analyze_data(df):
     
     results = {}
     
-    # 基础统计分析
+    # 数值列定义（用于其他分析）
     numeric_columns = ['pct', 'openLimit', 'closeLimit', 'cexPrice', 'dexPrice', 
                        'exchangeOutAmount', 'profit', 'price_diff_pct', 'trade_value']
     
-    # 计算基础统计量
-    stats = df[numeric_columns].describe()
-    results['basic_stats'] = stats
-    
     # 按交易对分组统计
     if 'symbol' in df.columns:
         symbol_stats = df.groupby('symbol')['profit'].agg(['count', 'sum', 'mean', 'std']).reset_index()
@@ -186,11 +186,6 @@ def analyze_data(df):
         hourly_stats = df.groupby('hour')['profit'].agg(['count', 'sum', 'mean']).reset_index()
         results['hourly_stats'] = hourly_stats
     
-    # 相关性分析
-    if len(numeric_columns) > 1:
-        correlation = df[numeric_columns].corr()
-        results['correlation'] = correlation
-    
     return results
 
 def visualize_data(df, results, output_dir='analysis_results'):
@@ -251,27 +246,6 @@ def visualize_data(df, results, output_dir='analysis_results'):
         plt.savefig(os.path.join(output_dir, 'symbol_profit.png'))
         plt.close()
     
-    # 5. 相关性热图
-    if 'correlation' in results:
-        correlation = results['correlation']
-        plt.figure(figsize=(12, 10))
-        plt.imshow(correlation, cmap='coolwarm', vmin=-1, vmax=1)
-        plt.colorbar()
-        plt.title('特征相关性热图')
-        plt.xticks(range(len(correlation.columns)), correlation.columns, rotation=90)
-        plt.yticks(range(len(correlation.columns)), correlation.columns)
-        
-        # 在热图上添加相关系数值
-        for i in range(len(correlation.columns)):
-            for j in range(len(correlation.columns)):
-                plt.text(j, i, f'{correlation.iloc[i, j]:.2f}', 
-                         ha='center', va='center', 
-                         color='white' if abs(correlation.iloc[i, j]) > 0.5 else 'black')
-        
-        plt.tight_layout()
-        plt.savefig(os.path.join(output_dir, 'correlation_heatmap.png'))
-        plt.close()
-    
     # 6. 按小时的平均利润
     if 'hourly_stats' in results:
         hourly_stats = results['hourly_stats']
@@ -317,28 +291,6 @@ def generate_report(results, output_dir='analysis_results'):
         <p>生成时间: """ + datetime.now().strftime('%Y-%m-%d %H:%M:%S') + """</p>
     """
     
-    # 添加基础统计信息
-    if 'basic_stats' in results:
-        html_content += """
-        <h2>基础统计信息</h2>
-        <table>
-            <tr>
-                <th>指标</th>
-        """
-        
-        for col in results['basic_stats'].columns:
-            html_content += f"<th>{col}</th>"
-        
-        html_content += "</tr>"
-        
-        for idx, row in results['basic_stats'].iterrows():
-            html_content += f"<tr><td>{idx}</td>"
-            for col in results['basic_stats'].columns:
-                html_content += f"<td>{row[col]:.4f}</td>"
-            html_content += "</tr>"
-        
-        html_content += "</table>"
-    
     # 添加交易对统计
     if 'symbol_stats' in results:
         html_content += """
@@ -467,11 +419,6 @@ def generate_report(results, output_dir='analysis_results'):
             <img src="symbol_profit.png" alt="各交易对总利润">
         </div>
         
-        <div class="image-container">
-            <h3>特征相关性热图</h3>
-            <img src="correlation_heatmap.png" alt="特征相关性热图">
-        </div>
-        
         <div class="image-container">
             <h3>各小时平均利润</h3>
             <img src="hourly_avg_profit.png" alt="各小时平均利润">