WTOAAM/dataAnalysisBusiness/algorithm/cpAnalyst.py

import os
import pandas as pd
import numpy as np
import plotly.graph_objects as go
from plotly.subplots import make_subplots
import seaborn as sns
import matplotlib.pyplot as plt
from matplotlib.ticker import MultipleLocator
from behavior.analystExcludeRatedPower import AnalystExcludeRatedPower
from utils.directoryUtil import DirectoryUtil as dir
from algorithmContract.confBusiness import *


class CpAnalyst(AnalystExcludeRatedPower):
    """
    风电机组风能利用系数分析
    """

    def typeAnalyst(self):
        return "cp"        

    def turbinesAnalysis(self, dataFrameMerge:pd.DataFrame, outputAnalysisDir, confData: ConfBusiness):        
        # 检查所需列是否存在
        required_columns = {confData.field_wind_speed,
                            Field_Cp, Field_PowerFloor}
        if not required_columns.issubset(dataFrameMerge.columns):
            raise ValueError(f"DataFrame缺少必要的列。需要的列有: {required_columns}")
        
        self.drawLineGraphForTurbine(dataFrameMerge,outputAnalysisDir,confData)

    def drawLineGraphForTurbine(self,dataFrameMerge:pd.DataFrame, outputAnalysisDir, confData: ConfBusiness):
        sns.set_palette('deep')

        upLimitOfPower = confData.rated_power*0.9
        value_step = 0.5
        
        grouped = dataFrameMerge.groupby([Field_NameOfTurbine,Field_PowerFloor]).agg(
            cp=('cp', 'median'),
            cp_max=('cp', 'max'),
            cp_min=('cp', 'min'),
        ).reset_index()

        # Rename columns post aggregation for clarity
        grouped.columns = [Field_NameOfTurbine,Field_PowerFloor,  Field_CpMedian, 'cp_max', 'cp_min']
        # Sort by power_floor
        grouped = grouped.sort_values(by=[Field_NameOfTurbine,Field_PowerFloor])

        fig, ax = plt.subplots()

        ax = sns.lineplot(x=Field_PowerFloor, y=Field_CpMedian, data=grouped,
                          hue=Field_NameOfTurbine)
        # 绘制合同功率曲线  
        ax.plot(self.dataFrameContractOfTurbine[Field_PowerFloor], self.dataFrameContractOfTurbine[Field_Cp], marker='o',  
                c='red', label='Contract Guarantee Cp')  

        ax.xaxis.set_major_locator(MultipleLocator(confData.graphSets["activePower"]["step"] if not self.common.isNone(
                        confData.graphSets["activePower"]) and not self.common.isNone(
                        confData.graphSets["activePower"]["step"]) else 250))  # 创建一个刻度 ，将定位器应用到y轴上
        ax.set_xlim(0, upLimitOfPower)

        ax.yaxis.set_major_locator(MultipleLocator(
            confData.graphSets["cp"]["step"] if not self.common.isNone(confData.graphSets["cp"]["step"]) else value_step))  # 创建一个刻度 ，将定位器应用到y轴上
        ax.set_ylim(confData.graphSets["cp"]["min"] if not self.common.isNone(confData.graphSets["cp"]["min"])
                    else 0, confData.graphSets["cp"]["max"] if not self.common.isNone(confData.graphSets["cp"]["max"]) else 2)

        ax.set_title('Cp-Distribution')
        # plt.legend(ncol=4)
        plt.xticks(rotation=45)  # 旋转45度
        plt.legend(title='Turbine', bbox_to_anchor=(1.02, 0.5),
                   ncol=2, loc='center left', borderaxespad=0.)
        plt.savefig(os.path.join(
            outputAnalysisDir, "{}-Cp-Distribution.png".format(confData.farm_name)), bbox_inches='tight', dpi=300)
        plt.close()

        groupedX=grouped.groupby(Field_NameOfTurbine)

        for name,group in groupedX:
            color = ["lightgrey"] * len(dataFrameMerge[Field_NameOfTurbine].unique())
            fig, ax = plt.subplots(figsize=(8, 8))
            ax = sns.lineplot(x=Field_PowerFloor, y=Field_CpMedian, data=grouped, hue=Field_NameOfTurbine,
                              palette=sns.color_palette(color), legend=False)
            ax = sns.lineplot(x=Field_PowerFloor, y=Field_CpMedian, data=group,
                              color='darkblue', legend=False)
            
            # 绘制合同功率曲线  
            ax.plot(self.dataFrameContractOfTurbine[Field_PowerFloor], self.dataFrameContractOfTurbine[Field_Cp], marker='o',  
                c='red', label='Contract Guarantee Cp')  

            ax.xaxis.set_major_locator(
                MultipleLocator(confData.graphSets["activePower"]["step"] if not self.common.isNone(
                        confData.graphSets["activePower"]) and not self.common.isNone(
                        confData.graphSets["activePower"]["step"]) else 250))  # 创建一个刻度 ，将定位器应用到y轴上
            ax.set_xlim(0, upLimitOfPower)

            ax.yaxis.set_major_locator(MultipleLocator(
                confData.graphSets["cp"]["step"] if not self.common.isNone(confData.graphSets["cp"]["step"]) else value_step))  # 创建一个刻度 ，将定位器应用到y轴上
            ax.set_ylim(confData.graphSets["cp"]["min"] if not self.common.isNone(confData.graphSets["cp"]["min"])
                        else 0, confData.graphSets["cp"]["max"] if not self.common.isNone(confData.graphSets["cp"]["max"]) else 1)

            ax.set_title('turbine name={}'.format(name))
            plt.xticks(rotation=45)  # 旋转45度
            plt.legend(title='Turbine', bbox_to_anchor=(1.02, 0.5),
                   ncol=2, loc='center left', borderaxespad=0.)
            plt.savefig(os.path.join(outputAnalysisDir, "{}.png".format(
                name)), bbox_inches='tight', dpi=120)
            plt.close()


    def generate_cp_distribution(self, csvFileDirOfCp, confData: ConfBusiness, encoding='utf-8'):
        """
        Generates Cp 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'.
        """

        output_path = csvFileDirOfCp

        field_Name_Turbine = "turbine_name"
        x_name = 'power_floor'
        y_name = 'cp'
        upLimitOfPower = confData.rated_power*0.9
        value_step = 0.5

        sns.set_palette('deep')
        res = pd.DataFrame()
        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)
                print(file_path)
                frame = pd.read_csv(file_path, encoding=encoding)
                frame = frame[(frame[x_name] > 0)]
                turbine_name = file_name.split(CSVSuffix)[0]
                frame[field_Name_Turbine] = turbine_name

                res = pd.concat(
                    [res, frame.loc[:, [field_Name_Turbine, x_name, y_name]]], axis=0)

        ress = res.reset_index()

        fig, ax = plt.subplots()

        ax = sns.lineplot(x=x_name, y=y_name, data=ress,
                          hue=field_Name_Turbine)

        ax.xaxis.set_major_locator(MultipleLocator(200))  # 创建一个刻度 ，将定位器应用到y轴上
        ax.set_xlim(0, upLimitOfPower)

        ax.yaxis.set_major_locator(MultipleLocator(
            confData.graphSets["cp"]["step"] if not self.common.isNone(confData.graphSets["cp"]["step"]) else value_step))  # 创建一个刻度 ，将定位器应用到y轴上
        ax.set_ylim(confData.graphSets["cp"]["min"] if not self.common.isNone(confData.graphSets["cp"]["min"])
                    else 0, confData.graphSets["cp"]["max"] if not self.common.isNone(confData.graphSets["cp"]["max"]) else 2)

        ax.set_title('Cp-Distribution')
        # plt.legend(ncol=4)
        plt.xticks(rotation=45)  # 旋转45度
        plt.legend(title='turbine', bbox_to_anchor=(1.02, 0.5),
                   ncol=2, loc='center left', borderaxespad=0.)
        plt.savefig(os.path.join(
            output_path, "{}-Cp-Distribution.png".format(confData.farm_name)), bbox_inches='tight', dpi=300)
        plt.close()

        grouped = ress.groupby(field_Name_Turbine)
        for name, group in grouped:
            color = ["lightgrey"] * len(ress[field_Name_Turbine].unique())
            fig, ax = plt.subplots(figsize=(8, 8))
            ax = sns.lineplot(x=x_name, y=y_name, data=ress, hue=field_Name_Turbine,
                              palette=sns.color_palette(color), legend=False)
            ax = sns.lineplot(x=x_name, y=y_name, data=group,
                              color='darkblue', legend=False)

            ax.xaxis.set_major_locator(
                MultipleLocator(200))  # 创建一个刻度 ，将定位器应用到y轴上
            ax.set_xlim(0, upLimitOfPower)

            ax.yaxis.set_major_locator(MultipleLocator(
                confData.graphSets["cp"]["step"] if not self.common.isNone(confData.graphSets["cp"]["step"]) else value_step))  # 创建一个刻度 ，将定位器应用到y轴上
            ax.set_ylim(confData.graphSets["cp"]["min"] if not self.common.isNone(confData.graphSets["cp"]["min"])
                        else 0, confData.graphSets["cp"]["max"] if not self.common.isNone(confData.graphSets["cp"]["max"]) else 1)

            ax.set_title('turbine name={}'.format(name))
            plt.xticks(rotation=45)  # 旋转45度
            plt.savefig(os.path.join(output_path, "{}.png".format(
                name)), bbox_inches='tight', dpi=120)
            plt.close()

    def plot_cp_distribution(self, csvFileDir,  farm_name):
        field_Name_Turbine = "设备名"
        x_name = 'power_floor'
        y_name = 'cp'
        # Create the output path based on the farm name
        output_path = csvFileDir  # output_path_template.format(farm_name)
        # Ensure the output directory exists
        os.makedirs(output_path, exist_ok=True)
        print(csvFileDir)
        # Initialize a DataFrame to store results
        res = pd.DataFrame()

        # Walk through the input directory to process each file
        for root, _, file_names in dir.list_directory(csvFileDir):
            for file_name in file_names:
                full_path = os.path.join(root, file_name)
                frame = pd.read_csv(full_path, encoding='gbk')
                turbine_name = file_name.split(CSVSuffix)[0]
                print("turbine_name={}".format(turbine_name))
                frame[field_Name_Turbine] = turbine_name
                res = pd.concat(
                    [res, frame.loc[:, [field_Name_Turbine, x_name, y_name]]], axis=0)

        # Reset index for plotting
        ress = res.reset_index(drop=True)

        # Plot combined Cp distribution for all turbines
        fig = make_subplots(rows=1, cols=1)
        for name, group in ress.groupby(field_Name_Turbine):
            fig.add_trace(go.Scatter(
                x=group[x_name], y=group[y_name], mode='lines', name=name))

        fig.update_layout(title_text='{} Cp分布'.format(
            farm_name), xaxis_title=x_name, yaxis_title=y_name)
        fig.write_image(os.path.join(
            output_path, "{}Cp分布.png".format(farm_name)), scale=3)

        # Plot individual Cp distributions
        unique_turbines = ress[field_Name_Turbine].unique()
        for name in unique_turbines:
            individual_fig = make_subplots(rows=1, cols=1)
            # Add all turbines in grey
            for turbine in unique_turbines:
                group = ress[ress[field_Name_Turbine] == turbine]
                individual_fig.add_trace(go.Scatter(
                    x=group[x_name], y=group[y_name], mode='lines', name=turbine, line=dict(color='lightgrey')))

            # Highlight the current turbine in dark blue
            group = ress[ress[field_Name_Turbine] == name]
            individual_fig.add_trace(go.Scatter(
                x=group[x_name], y=group[y_name], mode='lines', name=name, line=dict(color='darkblue')))

            individual_fig.update_layout(title_text='设备名={}'.format(name))
            individual_fig.write_image(os.path.join(
                output_path, "all-{}.png".format(name)), scale=2)