WTOAAM/dataAnalysisBusiness/algorithm/tsrWindSpeedAnalyst.py

import os
import pandas as pd
import plotly.graph_objects as go
import seaborn as sns
from algorithmContract.confBusiness import *
from algorithmContract.contract import Contract
from behavior.analystWithGoodPoint import AnalystWithGoodPoint


class TSRWindSpeedAnalyst(AnalystWithGoodPoint):
    """
    风电机组叶尖速比分析
    """

    def typeAnalyst(self):
        return "tsr_windspeed"

    def selectColumns(self):
        return [Field_DeviceCode,Field_Time,Field_WindSpeed,Field_ActiverPower,Field_RotorSpeed,Field_GeneratorSpeed]

    # def turbineAnalysis(self, dataFrame, outputAnalysisDir, outputFilePath, conf: Contract, Field_NameOfTurbine):
    #
    #     self.tsr(dataFrame, outputFilePath, Field_WindSpeed, Field_RotorSpeed,
    #              Field_ActiverPower)

    def tsr(self, dataFrame : pd.DataFrame):

        #Add column field_name
        dataFrame[Field_PowerFarmName] = self.currPowerFarmInfo.loc[Field_PowerFarmName]
        # Alias the power column
        # dataFrame[Field_Power] = dataFrame[Field_ActiverPower]
        # Calculate 'wind_speed_floor'
        # dataFrame[Field_WindSpeedFloor] = (dataFrame[Field_WindSpeed] / 1).astype(int) + 0.5

        # Ensure the necessary columns are of float type
        # dataFrame['wind_speed'] = dataFrame[Field_WindSpeed].astype(float)
        dataFrame[Field_RotorSpeed] = dataFrame[Field_RotorSpeed].astype(float)
        dataFrame[Field_GeneratorSpeed] = dataFrame[Field_GeneratorSpeed].astype(float)

        # rotor_diameter = pd.to_numeric(rotor_diameter, errors='coerce')
        # # Calculate TSR
        # dataFrame['tsr'] = (dataFrame['rotor_speed'] * 0.104667 *
        #                     (rotor_diameter / 2)) / dataFrame['wind_speed']

        # Group by 'wind_speed_floor' and calculate median, max, and min of TSR
        grouped = dataFrame.groupby([Field_WindSpeedFloor,Field_CodeOfTurbine,Field_NameOfTurbine]).agg({
            Field_ActiverPower: 'median',
            Field_PowerFloor: 'median',
            Field_RotorSpeed : 'median',
            Field_GeneratorSpeed: 'median',
            Field_TSR : ['median', 'max', 'min'],
            Field_PowerFarmName: 'max'
        }).reset_index()

        # Rename columns for clarity post aggregation
        grouped.columns = [Field_WindSpeedFloor,  Field_CodeOfTurbine, Field_NameOfTurbine,Field_Power,Field_PowerFloor,
                           Field_RotorSpeed, Field_GeneratorSpeed, Field_TSR, Field_TSRMax, Field_TSRMin, Field_PowerFarmName]

        # Sort by 'wind_speed_floor'
        grouped.sort_values(by=[Field_NameOfTurbine, Field_PowerFloor])

        return grouped

    def turbinesAnalysis(self, outputAnalysisDir, conf: Contract, turbineCodes):
        dictionary = self.processTurbineData(turbineCodes,conf,self.selectColumns())
        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_TSR}
        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dataFrame
            dataFrame=currDataFrameOfTurbines.copy()
            returnData = self.plot_tsr_distribution(
                    self.tsr(dataFrame), outputAnalysisDir, conf, currTurbineModeInfo)
            returnDatas.append(returnData)

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


        return returnResult

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

        Parameters:
        - csvFileDirOfCp: 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 = 'wind_speed_floor'
        y_name = 'tsr'

        # upLimitOfTSR = 20

        # 设置绘图样式
        sns.set_palette('deep')

        # 初始化结果DataFrame
        # res = pd.DataFrame()
        #
        # # 遍历输入目录中的所有文件
        # for root, dir_names, file_names in dir.list_directory(csvFileDirOfCp):
        #     for file_name in file_names:
        #
        #         if not file_name.endswith(CSVSuffix):
        #             continue
        #
        #         file_path = os.path.join(root, file_name)
        #
        #         # 读取CSV文件
        #         frame = pd.read_csv(file_path, encoding=encoding)
        #         frame = frame[(frame[x_name] > 0)]
        #
        #         # 选择需要的列并合并到结果DataFrame中
        #         res = pd.concat([res, frame], axis=0)
        #
        # # 重置索引
        # ress = res.reset_index()
        # dataFrame[Field_NameOfTurbine] = dataFrame[Field_NameOfTurbine].astype(str)
        # dataFrame = dataFrame.sort_values(by=[Field_NameOfTurbine, x_name])
        # 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 dataFrame[Field_NameOfTurbine].unique():
            turbine_data = dataFrame[dataFrame[Field_NameOfTurbine] == turbine]
            fig.add_trace(go.Scatter(x=turbine_data[x_name], y=turbine_data[y_name],
                                     mode='lines',
                                     # line=dict(color=colors[idx % len(colors)]),
                                     name=turbine))
        fig.update_layout(
            title={
                "text": f'叶尖速比分布图-{turbineModelInfo[Field_MachineTypeCode]}',
                'x': 0.5
            },
            # 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
            # ),

            # legend=dict(title='Turbine',
            #             x=1.02,
            #             y=0.5,
            #             orientation='v',
            #             traceorder='normal',
            #             font=dict(size=12),
            #             bgcolor='rgba(255, 255, 255, 0)',
            #             bordercolor='rgba(255, 255, 255, 0)'),
            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
            ),
            xaxis=dict(
                title='风速',
                dtick=1,
                tickangle=-45,
                range=[0, 26]),
            yaxis=dict(
                title='叶尖风速比',
                dtick=self.axisStepTSR,
                range=[self.axisLowerLimitTSR,
                       self.axisUpperLimitTSR]
            )
        )
        # 设置x轴标签旋转
        fig.update_xaxes(tickangle=-45)
        # 保存图形
        # fig.write_image(csvFileDirOfCp + r"/{}-TSR-Distibute.png".format(confData.farm_name),format='png',width=800, height=500,scale=3)
        # fig.show()

        # 保存HTML
        htmlFileName = f"{dataFrame[Field_PowerFarmName].iloc[0]}-TSR-Distribution-{turbineModelInfo[Field_MillTypeCode]}.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 dataFrame.groupby([Field_NameOfTurbine, Field_CodeOfTurbine]):
            fig = go.Figure()
            # 循环绘制turbine的线条
            for turbine in dataFrame[Field_NameOfTurbine].unique():
                turbine_data = dataFrame[dataFrame[Field_NameOfTurbine] == turbine]
                fig.add_trace(go.Scatter(x=turbine_data[x_name],
                                         y=turbine_data[y_name],
                                         mode='lines',
                                         line=dict(color='lightgrey'),
                                         showlegend=False))
            fig.add_trace(go.Scatter(x=group[x_name],
                                     y=group[y_name],
                                     mode='lines',
                                     line=dict(color='darkblue'),
                                     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='风速最低阈值 ',
                    dtick=1,
                    tickangle=-45,
                    range=[0, 26]),
                yaxis=dict(
                    title='叶尖速比',
                    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