# # -*- coding: utf-8 -*- # import pandas as pd # import matplotlib.pyplot as plt # from pymongo import MongoClient # import pickle # import numpy as np # import plotly.express as px # from plotly.subplots import make_subplots # import plotly.graph_objects as go # from flask import Flask,request,jsonify # from waitress import serve # import time # import random # import argparse # import logging # import traceback # import os # import lightgbm as lgb # # app = Flask('analysis_report——service') # def get_data_from_mongo(args): # # 1.读数据 # mongodb_connection,mongodb_database,all_table,accuracy_table,model_table,model_name = "mongodb://root:sdhjfREWFWEF23e@192.168.1.43:30000/",args['mongodb_database'],args['train_table'],args['accuracy_table'],args['model_table'],args['model_name'] # client = MongoClient(mongodb_connection) # # 选择数据库（如果数据库不存在，MongoDB 会自动创建） # db = client[mongodb_database] # # 将游标转换为列表，并创建 pandas DataFrame # df_all = pd.DataFrame(db[all_table].find({}, {'_id': 0})) # # df_accuracy = pd.DataFrame(db[accuracy_table].find({}, {'_id': 0})) # # model_data = db[model_table].find_one({"model_name": model_name}) # if model_data is not None: # model_binary = model_data['model'] # 确保这个字段是存储模型的二进制数据 # # 反序列化模型 # model = pickle.loads(model_binary) # client.close() # return df_all,df_accuracy,model # # # def draw_info(df_all,df_accuracy,model,features,args): # #1.数据描述 数据描述： # col_time = args['col_time'] # label = args['label'] # df_accuracy_beginTime = df_accuracy[col_time].min() # df_accuracy_endTime = df_accuracy[col_time].max() # df_train = df_all[df_all[col_time]lightgbm模型参数：{model.params}" # return text_content # # # # def draw_global_scatter(df,args): # # --- 1. 实际功率和辐照度的散点图 --- # col_x = args['scatter_col_x'] # col_y = args['label'] # scatter_fig = px.scatter( # df, # x=col_x, # y=col_y, # title=f"{col_x}和{col_y}的散点图", # labels={"辐照度": "辐照度 (W/m²)", "实际功率": "实际功率 (kW)"} # ) # return scatter_fig # # # # def draw_corr(df,features,args): # # # --- 2. 相关性热力图 --- # # 计算相关性矩阵 # label = args['label'] # features_coor = features+[label] # corr_matrix = df[features_coor].corr() # # 使用 Plotly Express 绘制热力图 # heatmap_fig = px.imshow(corr_matrix, # text_auto=True, # 显示数值 # color_continuous_scale='RdBu', # 配色方案 # title="Correlation Heatmap") # heatmap_fig.update_coloraxes(showscale=False) # # return heatmap_fig # # def draw_feature_importance(model,features): # # --- 3. 特征重要性排名 --- # # 获取特征重要性 # importance = model.feature_importance() # 'split' 或 'gain'，根据需求选择 # # # 转换为 DataFrame 方便绘图 # feature_importance_df = pd.DataFrame({ # 'Feature': features, # 'Importance': importance # }) # feature_importance_df = feature_importance_df.sort_values(by='Importance', ascending=False) # # # 使用 Plotly Express 绘制条形图 # importance_fig = px.bar(feature_importance_df, x='Feature', y='Importance', # title="特征重要性排名", # labels={'Feature': '特征', 'Importance': '重要性'}, # color='Importance', # color_continuous_scale='Viridis') # # 更新每个 trace，确保没有图例 # # importance_fig.update_layout(title="模型特征重要性排名", # showlegend=False # 移除图例 # ) # importance_fig.update_coloraxes(showscale=False) # return importance_fig # # # def draw_data_info_table(content): # # --- 4. 创建数据说明的表格 --- # # 转换为表格格式：1行1列，且填充文字说明 # # 转换为表格格式 # # 创建一个空的图 # table_fig = go.Figure() # # # 第一部分: 显示文字说明 # table_fig.add_trace(go.Table( # header=dict( # values=["说明"], # 表格只有一列：说明 # fill_color="paleturquoise", # align="center" # ), # cells=dict( # values=[[content]] , # 第一行填入文本说明 # fill_color="lavender", # align="center" # ) # )) # # # return table_fig # # # # def draw_accuracy_table(df,content): # # # --- 4. 每日的准确率表格 --- # # 转换为表格格式 # table_fig = go.Figure( # data=[ # go.Table( # header=dict( # values=list(df.columns), # fill_color="paleturquoise", # align="center" # ), # cells=dict( # values=[df[col] for col in df.columns], # fill_color="lavender", # align="center" # ) # ) # ] # ) # table_fig.update_layout(title="准确率表", showlegend=False) # return table_fig # # # @app.route('/analysis_report', methods=['POST']) # def analysis_report(): # start_time = time.time() # result = {} # success = 0 # path = "" # print("Program starts execution!") # try: # args = request.values.to_dict() # print('args',args) # logger.info(args) # #获取数据 # df_all, df_accuracy, model = get_data_from_mongo(args) # features = model.feature_name() # text_content = draw_info(df_all,df_accuracy,model,features,args) # text_fig,scatter_fig,heatmap_fig,importance_fig,table_fig=draw_data_info_table(text_content),draw_global_scatter(df_all,args),draw_corr(df_all,features,args),draw_feature_importance(model,features),\ # draw_accuracy_table(df_accuracy,text_content) # # --- 合并图表并保存到一个 HTML 文件 --- # # 创建子图布局 # combined_fig = make_subplots( # rows=5, cols=1, # subplot_titles=["数据-模型概览","辐照度和实际功率的散点图", "相关性","特征重要性排名", "准确率表"], # row_heights=[0.3, 0.6, 0.6, 0.6, 0.4], # specs=[[{"type": "table"}], [{"type": "xy"}], [{"type": "heatmap"}], [{"type": "xy"}],[{"type": "table"}]] # 指定每个子图类型 # ) # # 添加文本信息到子图（第一行） # # 添加文字说明 # for trace in text_fig.data: # combined_fig.add_trace(trace, row=1, col=1) # # # 添加散点图 # for trace in scatter_fig.data: # combined_fig.add_trace(trace, row=2, col=1) # # # 添加相关性热力图 # for trace in heatmap_fig.data: # combined_fig.add_trace(trace, row=3, col=1) # # # 添加特征重要性排名图 # for trace in importance_fig.data: # combined_fig.add_trace(trace, row=4, col=1) # # # 添加表格 # for trace in table_fig.data: # combined_fig.add_trace(trace, row=5, col=1) # # # 更新布局 # combined_fig.update_layout( # height=1500, # title_text="分析结果汇总", # 添加换行符以适应文本内容 # title_x=0.5, # 中心对齐标题 # showlegend=False, # ) # combined_fig.update_coloraxes(showscale=False) # filename = f"{int(time.time() * 1000)}_{random.randint(1000, 9999)}.html" # # 保存为 HTML # directory = '/usr/share/nginx/html' # if not os.path.exists(directory): # os.makedirs(directory) # file_path = os.path.join(directory, filename) # # combined_fig.write_html(f"D://usr//{filename}") # combined_fig.write_html(file_path) # path = f"http://ds2:10093/{filename}" # success = 1 # except Exception as e: # my_exception = traceback.format_exc() # my_exception.replace("\n","\t") # result['msg'] = my_exception # end_time = time.time() # result['success'] = success # result['args'] = args # result['start_time'] = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(start_time)) # result['end_time'] = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(end_time)) # result['file_path'] = path # print("Program execution ends!") # return result # # # if __name__=="__main__": # # print("Program starts execution!") # # logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s') # # logger = logging.getLogger("analysis_report log") # # from waitress import serve # # serve(app, host="0.0.0.0", port=10092) # # print("server start!")