WTOAAM/dataAnalysisBusiness/algorithm/tsrCpPowerAnalyst.py

import os
import pandas as pd
import math
import numpy as np
from plotly.subplots import make_subplots
import plotly.express as px
import pandas as pd
import plotly.graph_objects as go
import seaborn as sns
from matplotlib.ticker import MultipleLocator
from behavior.analystWithGoodPoint import AnalystWithGoodPoint
from utils.directoryUtil import DirectoryUtil as dir
from algorithmContract.confBusiness import *
from algorithmContract.contract import Contract


class TSRCpPowerAnalyst(AnalystWithGoodPoint):
    """
    风电机组叶尖速比-Cp-功率分析
    """

    def typeAnalyst(self):
        return "tsr_cp_power"

    def turbinesAnalysis(self, outputAnalysisDir, conf: Contract, turbineCodes):
        dictionary = self.processTurbineData(turbineCodes,conf,[Field_DeviceCode,Field_Time,Field_WindSpeed,Field_ActiverPower,Field_RotorSpeed, Field_GeneratorSpeed])
        dataFrameOfTurbines = self.userDataFrame(
            dictionary, conf.dataContract.configAnalysis, self)
        # 检查所需列是否存在
        required_columns = {Field_WindSpeed, Field_RotorSpeed,Field_PowerFloor,Field_GeneratorSpeed,Field_Cp}
        if not required_columns.issubset(dataFrameOfTurbines.columns):
            raise ValueError(f"DataFrame缺少必要的列。需要的列有: {required_columns}")

        turbrineInfos = self.common.getTurbineInfos(
            conf.dataContract.dataFilter.powerFarmID, turbineCodes, self.turbineInfo)

        groupedOfTurbineModel = turbrineInfos.groupby(Field_MillTypeCode)

        returnDatas = []
        for turbineModelCode, group in groupedOfTurbineModel:
            currTurbineCodes = group[Field_CodeOfTurbine].unique().tolist()
            currTurbineModeInfo = self.common.getTurbineModelByCode(
                turbineModelCode, self.turbineModelInfo)

            currDataFrameOfTurbines = dataFrameOfTurbines[dataFrameOfTurbines[Field_CodeOfTurbine].isin(
                currTurbineCodes)]

            #创建一个与dataFrameOfTurbines相同的dataFrameMerge
            dataFrameMerge=currDataFrameOfTurbines.copy()

            # return self.plot_tsr_distribution(self.tsr(dataFrameMerge), outputAnalysisDir, conf)
            dataFrameMerge[Field_PowerFarmName] = self.currPowerFarmInfo.loc[Field_PowerFarmName]
            # Calculate 'power_floor'
            dataFrameMerge[Field_PowerFloor] = (
                dataFrameMerge[Field_ActiverPower] / 10).astype(int) * 10
            # Ensure the necessary columns are of float type
            dataFrameMerge[Field_WindSpeed] = dataFrameMerge[Field_WindSpeed].astype(float)
            dataFrameMerge[Field_RotorSpeed] = dataFrameMerge[Field_RotorSpeed].astype(float)
            dataFrameMerge[Field_Cp] = dataFrameMerge[Field_Cp].astype(float)
            dataFrameMerge[Field_GeneratorSpeed] = dataFrameMerge[Field_GeneratorSpeed].astype(float)

            max_cutin = self.turbineModelInfo[Field_CutInWS].max()
            min_rated = self.turbineModelInfo[Field_RatedWindSpeed].min()
            dataFrameMerge = dataFrameMerge[(dataFrameMerge[Field_WindSpeed] > max_cutin) & (dataFrameMerge[Field_WindSpeed] < min_rated)]

            # Group by 'power_floor' and calculate median, max, and min of TSR
            dataFrameMerge[Field_TSRModified] = dataFrameMerge[Field_TSR] / (dataFrameMerge[Field_Cp] ** (1/3))

            grouped = dataFrameMerge.groupby([Field_PowerFloor, Field_CodeOfTurbine, Field_NameOfTurbine]).agg({
                Field_WindSpeed: 'median',
                Field_RotorSpeed: 'median',
                Field_GeneratorSpeed: 'median',
                'tsr_modified': 'median',
                Field_Cp: 'median',
                Field_PowerFarmName: 'max'
            }).reset_index()

            # Rename columns for clarity post aggregation
            grouped.columns = [Field_PowerFloor,  Field_CodeOfTurbine, Field_NameOfTurbine, Field_WindSpeed,
                               Field_RotorSpeed, Field_GeneratorSpeed, Field_TSRModified, Field_Cp, Field_PowerFarmName]

            # Sort by 'power_floor'
            grouped = grouped.sort_values(by=[Field_CodeOfTurbine, Field_PowerFloor])
            returnData = self.plot_tsrcp_distribution(
                    grouped, outputAnalysisDir, conf, currTurbineModeInfo)
            returnDatas.append(returnData)

        returnResult = pd.concat(returnDatas, ignore_index=True)

        return returnResult


        # ---------------------------------------------------
        # dataFrameMerge = self.userDataFrame(dictionary,conf.dataContract.configAnalysis,self)
        # # return self.plot_tsr_distribution(self.tsr(dataFrameMerge), outputAnalysisDir, conf)
        # dataFrameMerge[Field_PowerFarmName] = self.currPowerFarmInfo.loc[Field_PowerFarmName]
        # # Calculate 'power_floor'
        # dataFrameMerge[Field_PowerFloor] = (
        #     dataFrameMerge[Field_ActiverPower] / 10).astype(int) * 10
        # # Ensure the necessary columns are of float type
        # dataFrameMerge[Field_WindSpeed] = dataFrameMerge[Field_WindSpeed].astype(float)
        # dataFrameMerge[Field_RotorSpeed] = dataFrameMerge[Field_RotorSpeed].astype(float)
        # dataFrameMerge[Field_Cp] = dataFrameMerge[Field_Cp].astype(float)
        # dataFrameMerge[Field_GeneratorSpeed] = dataFrameMerge[Field_GeneratorSpeed].astype(float)

        # max_cutin = self.turbineModelInfo[Field_CutInWS].max()
        # min_rated = self.turbineModelInfo[Field_RatedWindSpeed].min()
        # dataFrameMerge = dataFrameMerge[(dataFrameMerge[Field_WindSpeed] > max_cutin) & (dataFrameMerge[Field_WindSpeed] < min_rated)]

        # # Group by 'power_floor' and calculate median, max, and min of TSR
        # dataFrameMerge[Field_TSRModified] = dataFrameMerge[Field_TSR] / (dataFrameMerge[Field_Cp] ** (1/3))

        # grouped = dataFrameMerge.groupby([Field_PowerFloor, Field_CodeOfTurbine, Field_NameOfTurbine]).agg({
        #     Field_WindSpeed: 'median',
        #     Field_RotorSpeed: 'median',
        #     Field_GeneratorSpeed: 'median',
        #     'tsr_modified': 'median',
        #     Field_Cp: 'median',
        #     Field_PowerFarmName: 'max'
        # }).reset_index()

        # # Rename columns for clarity post aggregation
        # grouped.columns = [Field_PowerFloor,  Field_CodeOfTurbine, Field_NameOfTurbine, Field_WindSpeed,
        #                    Field_RotorSpeed, Field_GeneratorSpeed, Field_TSRModified, Field_Cp, Field_PowerFarmName]

        # # Sort by 'power_floor'
        # grouped = grouped.sort_values(by=[Field_CodeOfTurbine, Field_PowerFloor])

        # return self.plot_tsrcp_distribution(grouped, outputAnalysisDir, conf)

    def plot_tsrcp_distribution(self, dataFrameMerge: pd.DataFrame, outputAnalysisDir, conf: Contract, turbineModelInfo: pd.Series):
        """
        Generates tsr distribution plots for turbines in a wind farm.

        Parameters:
        - outputAnalysisDir: str, path to the directory containing input CSV files.
        - farm_name: str, name of the wind farm.
        - encoding: str, encoding of the input CSV files. Defaults to 'utf-8'.
        """
        x_name = Field_PowerFloor
        y_name = Field_TSRModified

        upLimitOfTSR = 20

        # 绘制全场TSR分布图
        fig = go.Figure()
        # colors = px.colors.sequential.Turbo
        # 遍历不同的turbine来添加线条
        for turbine in dataFrameMerge[Field_NameOfTurbine].unique():
            turbine_data = dataFrameMerge[dataFrameMerge[Field_NameOfTurbine] == turbine]
            fig.add_trace(go.Scatter(x=turbine_data[x_name], y=turbine_data[y_name],
                                     mode='lines',
                                     line=dict(width=1.2),
                                     # line=dict(color=colors[idx % len(colors)]),
                                     name=turbine))

        fig.update_layout(
            title={
                "text": f'叶尖速比-风能利用系数分析-功率分布图-{turbineModelInfo[Field_MachineTypeCode]}',
                'x': 0.5
            },

            xaxis=dict(
                title='功率',
                dtick=200,
                tickangle=-45,
                range=[0, 1800]),
            yaxis=dict(
                title= '叶尖速比/风能利用系数分析^(1/3)', # r"$\frac{TSR}{Cp^{1/3}}$"  # 仅在.png格式下正确显示
                dtick=self.axisStepTSR,
                range=[self.axisLowerLimitTSR,
                       self.axisUpperLimitTSR]
            ),
            legend=dict(
                orientation="h",  # Horizontal orientation
                xanchor="center",  # Anchor the legend to the center
                x=0.5,  # Position legend at the center of the x-axis
                y=-0.2,  # Position legend below the x-axis
                # itemsizing='constant',  # Keep the size of the legend entries constant
                # itemwidth=50
            )
        )

        # 设置x轴标签旋转
        fig.update_xaxes(tickangle=-45)

        # 保存图形
        # fig.write_image(outputAnalysisDir + r"/{}-TSR-Distibute.png".format(confData.farm_name),format='png',width=800, height=500,scale=3)
        # fig.show()

        # 保存HTML
        # htmlFileName = f"{dataFrameMerge[Field_PowerFarmName].iloc[0]}-TSR-Cp-Power-Distribution.html"
        htmlFileName = f"{turbineModelInfo[Field_MillTypeCode]}-TSR-Cp-Power-Distribution.html"
        htmlFilePath = os.path.join(outputAnalysisDir, htmlFileName)
        fig.write_html(htmlFilePath)

        result_rows = []
        result_rows.append({
            Field_Return_TypeAnalyst: self.typeAnalyst(),
            Field_PowerFarmCode: conf.dataContract.dataFilter.powerFarmID,
            Field_Return_BatchCode: conf.dataContract.dataFilter.dataBatchNum,
            Field_CodeOfTurbine: 'total',
            Field_Return_FilePath: htmlFilePath,
                Field_Return_IsSaveDatabase: True
        })

        # 绘制每个设备的TSR分布图
        for name, group in dataFrameMerge.groupby([Field_NameOfTurbine, Field_CodeOfTurbine]):
            fig = go.Figure()
            # 循环绘制turbine的线条
            for turbine in dataFrameMerge[Field_NameOfTurbine].unique():
                turbine_data = dataFrameMerge[dataFrameMerge[Field_NameOfTurbine] == turbine]
                fig.add_trace(go.Scatter(x=turbine_data[x_name],
                                         y=turbine_data[y_name],
                                         mode='lines',
                                         line=dict(color='lightgrey', width=1.2),
                                         showlegend=False))
            fig.add_trace(go.Scatter(x=group[x_name],
                                     y=group[y_name],
                                     mode='lines',
                                     line=dict(color='darkblue', width=1.5),
                                     showlegend=False))

            fig.update_layout(
                title={"text": '机组: {}'.format(name[0])},
                # margin=dict(
                # t=35,  # 顶部 margin，减小这个值可以使标题更靠近图形
                # l=60,  # 左侧 margin
                # r=60,  # 右侧 margin
                # b=40,  # 底部 margin
                # ),
                xaxis=dict(
                    title='功率',
                    dtick=200,
                    tickangle=-45,
                    range=[0, 1800]),
                yaxis=dict(
                    title= '叶尖速比/风能利用系数分析^(1/3)', # r"$\frac{TSR}{Cp^{1/3}}$"  # 仅在.png格式下正确显示
                    dtick=self.axisStepTSR,
                    range=[self.axisLowerLimitTSR,
                           self.axisUpperLimitTSR]
                )
            )
            fig.update_xaxes(tickangle=-45)

            # 保存图像
            pngFileName = f"{name[0]}.png"
            pngFilePath = os.path.join(outputAnalysisDir, pngFileName)
            fig.write_image(pngFilePath, scale=3)

            # 保存HTML
            htmlFileName = f"{name[0]}.html"
            htmlFilePath = os.path.join(outputAnalysisDir, htmlFileName)
            fig.write_html(htmlFilePath)

            result_rows.append({
                Field_Return_TypeAnalyst: self.typeAnalyst(),
                Field_PowerFarmCode: conf.dataContract.dataFilter.powerFarmID,
                Field_Return_BatchCode: conf.dataContract.dataFilter.dataBatchNum,
                Field_CodeOfTurbine: name[1],
                Field_Return_FilePath: pngFilePath,
                Field_Return_IsSaveDatabase: False
            })

            result_rows.append({
                Field_Return_TypeAnalyst: self.typeAnalyst(),
                Field_PowerFarmCode: conf.dataContract.dataFilter.powerFarmID,
                Field_Return_BatchCode: conf.dataContract.dataFilter.dataBatchNum,
                Field_CodeOfTurbine: name[1],
                Field_Return_FilePath: htmlFilePath,
                Field_Return_IsSaveDatabase: True
            })

        result_df = pd.DataFrame(result_rows)
        return result_df