WTOAAM/dataAnalysisBusiness/demo/SCADA_10min_category_2.py

import os
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.pyplot import MultipleLocator
import math


intervalPower = 25  # For example
intervalWindspeed = 0.25  # For example

fieldRatedPower="额定功率"
fieldRatedWindSpeed="额定风速"
fieldWindSpeedCutIn="切入风速"
fieldWindSpeedCutOut="切出风速"

fieldTime="时间"
fieldWindSpeed="风速"
fieldActivePower="变频器电网侧有功功率"
fieldLabel="lab"

# 1. 数据加载和预处理函数
def loadData(filePathSCADA:str, filePathTurbineInfo:str):
    dataFrameSCADA = pd.read_csv(filePathSCADA, encoding="utf-8")
    dataFrameTurbineInfo = pd.read_csv(filePathTurbineInfo)
    return dataFrameSCADA, dataFrameTurbineInfo

def extractTurbineParameters(turbineInfo:pd.DataFrame):
    """
    解析风电机组参数 

    参数：
        turbineInfo 风电机组信息DataFrame

    返回：
        PRated 额定功率（kw）
        VCutOut 切出风速（m/s）
        VCutIn 切入风速（m/s）
        VRated 额定风速（m/s）
    """
    ratedPower = turbineInfo.loc[:, [fieldRatedPower]].values
    windSpeedCutIn = turbineInfo.loc[:, [fieldWindSpeedCutIn]].values
    windSpeedCutOut = turbineInfo.loc[:, [fieldWindSpeedCutOut]].values
    ratedWindSpeed = turbineInfo.loc[:, [fieldRatedWindSpeed]].values

    return ratedPower, windSpeedCutOut, windSpeedCutIn, ratedWindSpeed

def preprocessData(dataFrameOfSCADA:pd.DataFrame):
    """
    获取机组SCADA数据的 时间、有功功率、风速，构建新的DataFrame变量

    参数：
        dataFrameOfSCADA 机组SCADA数据

    返回：
        由机组SCADA数据的 时间、有功功率、风速，构建新的DataFrame变量

    """
    timeStamp = dataFrameOfSCADA.loc[:, ['时间']]
    activePower = dataFrameOfSCADA.loc[:, ['变频器电网侧有功功率']]
    windSpeed = dataFrameOfSCADA.loc[:, ['风速']]
    dataFramePartOfSCADA = pd.concat([timeStamp, activePower, windSpeed], axis=1)

    dataFramePartOfSCADA[fieldLabel]=0
    dataFramePartOfSCADA[fieldLabel]=dataFramePartOfSCADA[fieldLabel].astype(int)

    return dataFramePartOfSCADA

# 2. 数据标签分配和分箱计算
def calculateIntervals(activePowerMax, ratedPower, windSpeedCutOut):
    """
    按有功功率（以25kw为间隔）、风速（以0.25m/s为间隔）分仓

    参数：
        max_power 当前机组的有功功率最大值
        PRated  机组额定功率
        wind_speed_cutout  切出风速

    返回：
        interval_power 有功功率分仓间隔
        interval_windspeed 风速分仓间隔
        PNum  有功功率分仓数量
        VNum 风速分仓数量
    """
    binNumOfPower = math.floor(activePowerMax / intervalPower) + 1 if activePowerMax >= ratedPower else math.floor(ratedPower / intervalPower)
    binNumOfWindSpeed = math.ceil(windSpeedCutOut / intervalWindspeed)

    return binNumOfPower, binNumOfWindSpeed

def labelData(dataFramePartOfSCADA:pd.DataFrame, conditions):
    """
    根据特定条件对数据进行标签分配，例如功率和风速阈值。
    
    参数:
        LM (DataFrame): 包含功率和风速数据的DataFrame。
        conditions (dict): 字典，键为条件名称，值为相应的阈值。
    
    返回:
        DataFrame: 带有新的'label'列的原始DataFrame。
    """
    # 初始化标签列
    dataFramePartOfSCADA['label'] = 0
    
    # 根据条件进行数据标签分配
    for condition, threshold in conditions.items():
        if condition == 'power_below':
            dataFramePartOfSCADA.loc[dataFramePartOfSCADA[fieldActivePower] <= threshold, 'label'] = -1
        elif condition == 'power_above':
            dataFramePartOfSCADA.loc[dataFramePartOfSCADA[fieldActivePower] >= threshold, 'label'] = 1
    
    return dataFramePartOfSCADA

def computeBins(data, intervals):
    """为给定数据计算统计箱。
    
    参数:
        data (DataFrame): 需要进行分箱的数据。
        intervals (dict): 字典，为每个列指定间隔大小。
    
    返回:
        DataFrame: 分箱数据作为区间内的计数或百分比。
    """
    binsResults = {}
    for column, interval in intervals.items():
        minValue = data[column].min()
        maxValue = data[column].max()
        bins = np.arange(minValue, maxValue + interval, interval)
        binnedData = pd.cut(data[column], bins, include_lowest=True)
        binCounts = pd.value_counts(binnedData, sort=False)
        binsResults[column] = binCounts
    
    return pd.DataFrame(binsResults)

# 3. 应用标签函数
def applyLabels(data, labels):
    """根据外部或计算出的标签对数据应用标签。
    
    参数:
        data (DataFrame): 需要应用标签的数据。
        labels (Series或array): 应用的标签；必须与数据的索引或长度相匹配。
    
    返回:
        DataFrame: 应用标签后的数据。
    """
    data['label'] = labels
    return data

# 4. 数据可视化
def plot_data(ws:list, ap:list):
    fig = plt.figure()
    plt.scatter(ws, ap, s=1, c='black', marker='.')
    ax = plt.gca()
    ax.xaxis.set_major_locator(MultipleLocator(5))
    ax.yaxis.set_major_locator(MultipleLocator(500))
    plt.xlim((0, 30))
    plt.ylim((0, 2200))
    plt.tick_params(labelsize=8)
    plt.xlabel("V/(m$·$s$^{-1}$)", fontsize=8)
    plt.ylabel("P/kW", fontsize=8)
    plt.show()

# 5. Main Execution
def main():
    turbine=82
    filePathSCADA = r'E:\BaiduNetdiskDownload\test\min_scada_LuoTuoGou\72\{}.csv'.format(turbine)
    filePathTurbineInfo = r'E:\BaiduNetdiskDownload\test\min_scada_LuoTuoGou\72\info.csv'
    outputFilePathOfSCADA=r"E:\BaiduNetdiskDownload\test\min_scada_LuoTuoGou\72\labeled\labeled_{}.csv".format(turbine)

    dataFrameOfSCADA, turbineInfo = loadData(filePathSCADA, filePathTurbineInfo)
    ratedPower, windSpeedCutOut, windSpeedCutIn, ratedWindSpeed = extractTurbineParameters(turbineInfo)
    dataFramePartOfSCADA = preprocessData(dataFrameOfSCADA)

    powerMax=dataFramePartOfSCADA[fieldActivePower].max()
    binNumOfPower, binNumOfWindSpeed=calculateIntervals(powerMax,ratedPower,windSpeedCutOut)
    
    # 根据功率阈值对数据进行标签分配
    conditions = {'power_below': 10, 'power_above': ratedPower[0][0]}
    labeledData = labelData(dataFramePartOfSCADA, conditions)
    
    # 为功率和风速计算分箱
    intervals = {fieldActivePower: 100, fieldWindSpeed: 1}
    binnedData = computeBins(labeledData, intervals)
    
    # 应用标签（假设某些外部标签被提供或在其他地方计算）
    externalLabels = np.random.choice([0, 1], size=len(labeledData))  # 随机示例
    labeledData = applyLabels(labeledData, externalLabels)

    labeledData.to_csv(outputFilePathOfSCADA)
    
    plot_data(labeledData[fieldWindSpeed], labeledData[fieldActivePower])

if __name__ == '__main__':
    main()