awg commit algorithm components

evaluation_processing/analysis.py

@@ -7,9 +7,7 @@ import logging
 import traceback
 import os
 from common.database_dml import get_df_list_from_mongo, insert_data_into_mongo
-import plotly.express as px
 import plotly.graph_objects as go
-import pandas as pd
 import plotly.io as pio
 from bson.decimal128 import Decimal128
 import numbers
@@ -22,15 +20,16 @@ def put_analysis_report_to_html(args, df_predict, df_accuracy):
     label = args['label']
     label_pre = args['label_pre']
     farmId = args['farmId']
-
-    df_predict = df_predict.applymap(lambda x: float(x.to_decimal()) if isinstance(x, Decimal128) else float(x) if isinstance(x,
-                                                                                                         numbers.Number) else x).sort_values(by=col_time)
-    df_accuracy = df_accuracy.applymap(lambda x:float(x.to_decimal()) if isinstance(x, Decimal128) else float(x) if isinstance(x,
-                                                                                                         numbers.Number) else x).sort_values(by=col_time)
-
-    # -------------------- 预测功率与实际功率曲线 --------------------
-
-    # 生成折线图（以 C_GLOBALR 和 NWP预测总辐射 为例）
+    acc_flag = df_accuracy.shape[0]
+    df_predict = df_predict.applymap(
+        lambda x: float(x.to_decimal()) if isinstance(x, Decimal128) else float(x) if isinstance(x,
+                                                                                                 numbers.Number) else x).sort_values(
+        by=col_time)
+    if acc_flag > 0:
+        df_accuracy = df_accuracy.applymap(
+            lambda x: float(x.to_decimal()) if isinstance(x, Decimal128) else float(x) if isinstance(x,
+                                                                                                     numbers.Number) else x).sort_values(
+            by=col_time)
     # 创建一个图表对象
     fig = go.Figure()
 
@@ -42,8 +41,8 @@ def put_analysis_report_to_html(args, df_predict, df_accuracy):
         y=df_predict[label],
         mode='lines+markers',
         name='实际功率',  # 实际功率
-        line=dict(dash='dot', width=2),  # 虚线
-        marker=dict(symbol='cross'),
+        line=dict(width=1),  # 虚线
+        marker=dict(symbol='circle'),
     ))
     # 为每个模型添加预测值和实际功率的曲线
     for model in models:
@@ -101,40 +100,45 @@ def put_analysis_report_to_html(args, df_predict, df_accuracy):
     power_html = pio.to_html(fig, full_html=False)
 
     # -------------------- 准确率表展示--------------------
-    acc_html = df_accuracy.sort_values(by=col_time).to_html(classes='table table-bordered table-striped', index=False)
+    acc_html = ''
+    if acc_flag > 0:
+        acc_html = df_accuracy.sort_values(by=col_time).to_html(classes='table table-bordered table-striped',
+                                                                index=False)
     # -------------------- 准确率汇总展示--------------------
-    # 指定需要转换的列
-    cols_to_convert = ['MAE', 'accuracy', 'RMSE', 'deviationElectricity', 'deviationAssessment']
-    for col in cols_to_convert:
-        if col in df_accuracy.columns:
-            df_accuracy[col] = df_accuracy[col].apply(
-                lambda x: float(x.to_decimal()) if isinstance(x, Decimal128) else float(x) if isinstance(x,
-                                                                                                         numbers.Number) else np.nan)
+    summary_html = ''
+    if acc_flag > 0:
+        # 指定需要转换的列
+        cols_to_convert = ['MAE', 'accuracy', 'RMSE', 'deviationElectricity', 'deviationAssessment']
+        for col in cols_to_convert:
+            if col in df_accuracy.columns:
+                df_accuracy[col] = df_accuracy[col].apply(
+                    lambda x: float(x.to_decimal()) if isinstance(x, Decimal128) else float(x) if isinstance(x,
+                                                                                                             numbers.Number) else np.nan)
 
-    # 确定存在的列
-    agg_dict = {}
-    rename_cols = ['model']
-    if 'MAE' in df_accuracy.columns:
-        agg_dict['MAE'] = np.nanmean
-        rename_cols.append('MAE平均值')
-    if 'accuracy' in df_accuracy.columns:
-        agg_dict['accuracy'] = np.nanmean
-        rename_cols.append('准确率平均值')
-    if 'RMSE' in df_accuracy.columns:
-        agg_dict['RMSE'] = np.nanmean
-        rename_cols.append('RMSE平均值')
-    if 'deviationElectricity' in df_accuracy.columns:
-        agg_dict['deviationElectricity'] = [np.nanmean, np.nansum]
-        rename_cols.append('考核电量平均值')
-        rename_cols.append('考核总电量')
-    if 'deviationAssessment' in df_accuracy.columns:
-        agg_dict['deviationAssessment'] = [np.nanmean, np.nansum]
-        rename_cols.append('考核分数平均值')
-        rename_cols.append('考核总分数')
-    # 进行分组聚合，如果有需要聚合的列
-    summary_df = df_accuracy.groupby('model').agg(agg_dict).reset_index()
-    summary_df.columns = rename_cols
-    summary_html = summary_df.to_html(classes='table table-bordered table-striped', index=False)
+        # 确定存在的列
+        agg_dict = {}
+        rename_cols = ['model']
+        if 'MAE' in df_accuracy.columns:
+            agg_dict['MAE'] = np.nanmean
+            rename_cols.append('MAE平均值')
+        if 'accuracy' in df_accuracy.columns:
+            agg_dict['accuracy'] = np.nanmean
+            rename_cols.append('准确率平均值')
+        if 'RMSE' in df_accuracy.columns:
+            agg_dict['RMSE'] = np.nanmean
+            rename_cols.append('RMSE平均值')
+        if 'deviationElectricity' in df_accuracy.columns:
+            agg_dict['deviationElectricity'] = [np.nanmean, np.nansum]
+            rename_cols.append('考核电量平均值')
+            rename_cols.append('考核总电量')
+        if 'deviationAssessment' in df_accuracy.columns:
+            agg_dict['deviationAssessment'] = [np.nanmean, np.nansum]
+            rename_cols.append('考核分数平均值')
+            rename_cols.append('考核总分数')
+        # 进行分组聚合，如果有需要聚合的列
+        summary_df = df_accuracy.groupby('model').agg(agg_dict).reset_index()
+        summary_df.columns = rename_cols
+        summary_html = summary_df.to_html(classes='table table-bordered table-striped', index=False)
     # -------------------- 生成完整 HTML 页面 --------------------
 
     html_content = f"""
@@ -208,7 +212,6 @@ def put_analysis_report_to_html(args, df_predict, df_accuracy):
         <div class="container">
             <h1>分析报告</h1>
             <!-- Pandas DataFrame 表格 -->
-          
             <div class="plot-container">
                 <h2>1. 预测功率与实际功率曲线对比</h2>
                 {power_html}
@@ -244,8 +247,13 @@ def put_analysis_report_to_html(args, df_predict, df_accuracy):
         f.write(html_content)
     print("HTML report generated successfully!")
     return path
-
-
+import lightgbm as lgb
+gbm_model = lgb.train(params,
+                    lgb_train,
+                    num_boost_round=500,
+                    eval_metric=custom_loss,
+                    valid_sets=[lgb_train, lgb_eval],
+                    )
 @app.route('/analysis_report_small', methods=['POST'])
 def analysis_report():
     start_time = time.time()
@@ -259,7 +267,7 @@ def analysis_report():
         logger.info(args)
         # 获取数据
         df_predict, df_accuracy = get_df_list_from_mongo(args)[0], get_df_list_from_mongo(args)[1]
-        path = put_analysis_report_to_html(args,df_predict, df_accuracy)
+        path = put_analysis_report_to_html(args, df_predict, df_accuracy)
         success = 1
     except Exception as e:
         my_exception = traceback.format_exc()