algorithm_platform/evaluation_processing/analysis_report.py

# -*- coding: utf-8 -*-
from plotly.subplots import make_subplots
from flask import Flask,request
import time
import random
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

app = Flask('analysis_report——service')

def put_analysis_report_to_html(args,df_clean,df_accuracy):
    col_time = args['col_time']
    col_x_env = args['col_x_env']
    col_x_pre = args['col_x_pre']
    label = args['label']
    label_pre = args['label_pre']
    farmId =  args['farmId']
    df_overview = pd.DataFrame(
        {'数据开始时间': [df_clean[col_time].min()], '数据结束时间': [df_clean[col_time].max()], '数据总记录数': [df_clean.shape[0]]})
    overview_html = df_overview.to_html(classes='table table-bordered table-striped', index=False)

    # -------------------- 数据描述 --------------------
    describe_html = df_clean.describe().reset_index().rename(columns={'index': '统计量'}).to_html(
        classes='table table-bordered table-striped', index=False)

    # -------------------- 实测气象与实际功率散点图--------------------

    # 生成实际功率与辐照度的散点图
    fig_scatter = px.scatter(df_clean, x=col_x_env, y=label)

    # 自定义散点图布局
    fig_scatter.update_layout(
        template='seaborn',
        plot_bgcolor='rgba(255, 255, 255, 0.8)',  # 背景色
        xaxis=dict(
            showgrid=True,
            gridcolor='rgba(200, 200, 200, 0.5)',
            title=col_x_env
        ),
        yaxis=dict(
            showgrid=True,
            gridcolor='rgba(200, 200, 200, 0.5)',
            title=label
        ),
        legend=dict(x=0.01, y=0.99, bgcolor='rgba(255, 255, 255, 0.7)', bordercolor='black', borderwidth=1)
    )

    # 将散点图保存为 HTML 片段
    scatter_html = pio.to_html(fig_scatter, full_html=False)

    # -------------------- 生成相关性热力图 --------------------

    # 计算相关矩阵
    correlation_matrix = df_clean.corr()

    # 生成热力图，带数值标签和新配色
    fig_heatmap = go.Figure(data=go.Heatmap(
        z=correlation_matrix.values,
        x=correlation_matrix.columns,
        y=correlation_matrix.columns,
        colorscale='RdBu',  # 使用红蓝配色：正相关为蓝色，负相关为红色
        text=correlation_matrix.round(2).astype(str),  # 将相关性值保留两位小数并转换为字符串
        texttemplate="%{text}",  # 显示数值标签
        colorbar=dict(title='Correlation'),
        zmin=-1, zmax=1  # 设置颜色映射的范围
    ))

    # 自定义热力图布局
    fig_heatmap.update_layout(
        # title='Correlation Matrix Heatmap',
        xaxis=dict(tickangle=45),
        yaxis=dict(autorange='reversed'),
        template='seaborn'
    )

    # 将热力图保存为 HTML 片段
    corr_html = pio.to_html(fig_heatmap, full_html=False)

    # -------------------- 实测气象与预测气象趋势曲线 --------------------

    # 生成折线图（以 C_GLOBALR 和 NWP预测总辐射 为例）
    fig_line = px.line(df_clean, x=col_time, y=[col_x_env, col_x_pre], markers=True)

    # 自定义趋势图布局
    fig_line.update_layout(
        template='seaborn',
        # title=dict(text=f"{col_x_env}与{col_x_pre}趋势曲线",
        # x=0.5, font=dict(size=24, color='darkblue')),
        plot_bgcolor='rgba(255, 255, 255, 0.8)',  # 改为白色背景
        xaxis=dict(
            showgrid=True,
            gridcolor='rgba(200, 200, 200, 0.5)',  # 网格线颜色
            rangeslider=dict(visible=True),  # 显示滚动条
            rangeselector=dict(visible=True)  # 显示预设的时间范围选择器
        ),
        yaxis=dict(showgrid=True, gridcolor='rgba(200, 200, 200, 0.5)'),
        legend=dict(x=0.01, y=0.99, bgcolor='rgba(255, 255, 255, 0.7)', bordercolor='black', borderwidth=1)
    )

    # 将折线图保存为 HTML 片段
    env_pre_html = pio.to_html(fig_line, full_html=False)

    # -------------------- 实测气象与预测气象偏差密度曲线 --------------------

    df_clean['deviation'] = df_clean[col_x_pre] - df_clean[col_x_env]
    # 生成预测与实测辐照度偏差的密度曲线图
    # 生成偏差的密度图
    fig_density = px.histogram(df_clean, x='deviation', nbins=30, marginal='rug', opacity=0.75,
                               histnorm='density')

    # 自定义密度曲线图布局
    fig_density.update_layout(
        template='seaborn',
        # # title=dict(text=f"{col_x_pre}与{col_x_env}偏差密度曲线",
        # x=0.5, font=dict(size=24, color='darkred')),
        plot_bgcolor='rgba(255, 255, 255, 0.8)',
        xaxis=dict(
            showgrid=True,
            gridcolor='rgba(200, 200, 200, 0.5)',
            title='偏差'
        ),
        yaxis=dict(
            showgrid=True,
            gridcolor='rgba(200, 200, 200, 0.5)',
            title='Density'
        ),
        legend=dict(x=0.01, y=0.99, bgcolor='rgba(255, 255, 255, 0.7)', bordercolor='black', borderwidth=1)
    )

    # 将密度曲线图保存为 HTML 片段
    density_html = pio.to_html(fig_density, full_html=False)

    # -------------------- 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）
    fig_line = px.line(df_clean, x='dateTime', y=[label, label_pre], markers=True)

    # 自定义趋势图布局
    fig_line.update_layout(
        template='seaborn',
        # title=dict(text=f"{label_pre}与{label}曲线",
        # x=0.5, font=dict(size=24, color='darkblue')),
        plot_bgcolor='rgba(255, 255, 255, 0.8)',  # 改为白色背景
        xaxis=dict(
            showgrid=True,
            gridcolor='rgba(200, 200, 200, 0.5)',  # 网格线颜色
            rangeslider=dict(visible=True),  # 显示滚动条
            rangeselector=dict(visible=True)  # 显示预设的时间范围选择器
        ),
        yaxis=dict(showgrid=True, gridcolor='rgba(200, 200, 200, 0.5)'),
        legend=dict(x=0.01, y=0.99, bgcolor='rgba(255, 255, 255, 0.7)', bordercolor='black', borderwidth=1)
    )

    # 将折线图保存为 HTML 片段
    power_html = pio.to_html(fig_line, full_html=False)

    # -------------------- 准确率表展示--------------------
    acc_html = df_accuracy.to_html(classes='table table-bordered table-striped', index=False)
    # -------------------- 生成完整 HTML 页面 --------------------

    html_content = f"""
    <!DOCTYPE html>
    <html lang="en">
    <head>
        <meta charset="UTF-8">
        <meta name="viewport" content="width=device-width, initial-scale=1.0">
        <title>Data Analysis Report</title>
        <!-- 引入 Bootstrap CSS -->
        <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/css/bootstrap.min.css" rel="stylesheet">
        <style>
            body {{
                background-color: #f4f4f9;
                font-family: Arial, sans-serif;
                padding: 20px;
            }}
            .container {{
                background-color: #fff;
                padding: 20px;
                border-radius: 10px;
                box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);
                margin-bottom: 30px;
            }}
           h1 {{
                text-align: center;
                color: #333;
                margin-bottom: 20px;
            }}
            .plot-container {{
                margin: 20px 0;
                max-height: 500px;  /* 限制高度 */
                overflow-y: auto;   /* 显示垂直滚动条 */
            }}
            .table-container {{
                margin-top: 30px;
                overflow-x: auto;   /* 水平滚动条 */
                max-width: 100%;     /* 限制宽度 */
                white-space: nowrap; /* 防止内容换行 */
            }}
            table {{
                width: 100%;
                font-size: 12px;  /* 设置字体大小为12px */
            }}
            th, td {{
                text-align: center;  /* 表头和单元格文字居中 */
            }}
        </style>
    </head>
    <body>
        <div class="container">
            <h1>分析报告</h1>
            <!-- Pandas DataFrame 表格 -->
            <div class="table-container">
                <h2>1. 数据总览</h2>
                {overview_html}
            </div>
            <!-- Pandas DataFrame 表格 -->
            <div class="table-container">
                <h2>2. 数据描述</h2>
                {describe_html}
            </div>
            <div class="plot-container">
                <h2>3. 数据清洗后实测气象与实际功率散点图</h2>
                {scatter_html}
            </div>
            <div class="plot-container">
                <h2>4. 相关性分析</h2>
                {corr_html}
            </div>
            <div class="plot-container">
                <h2>5. 实测气象与预测气象曲线趋势</h2>
                {env_pre_html}
            </div>
            <div class="plot-container">
                <h2>6. 预测气象与实测气象偏差曲线</h2>
                {density_html}
            </div>
            <div class="plot-container">
                <h2>7. 预测功率与实际功率曲线对比</h2>
                {power_html}
            </div>
            <!-- Pandas DataFrame 表格 -->
            <div class="table-container">
                <h2>8. 准确率对比</h2>
                {acc_html}
            </div>
        </div>
    </body>
    </html>
    """
    filename = f"{farmId}_{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)
    path = f"http://ds3:10010/{filename}"
    # 将 HTML 内容写入文件
    with open(file_path, "w", encoding="utf-8") as f:
        f.write(html_content)
    print("HTML report generated successfully!")
    return path
@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_clean, df_accuracy = get_df_list_from_mongo(args)[0], get_df_list_from_mongo(args)[1]
        path = put_analysis_report_to_html(args, df_clean, df_accuracy)
        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!")