clustering/cluster_power.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# time: 2023/5/11 14:43
# file: cluster_power.py
# author: David
# company: shenyang JY

import os
import numpy as np
import pandas as pd
# 从confinuous_data中拿数据
cluster = []


def cluster_power_list_file(cluster, turbine_id, input_path, output_path):
    """
    从turbine-*.csv的文件列表中进行聚类功率相加
    cluster:聚类的结果
    turbine_id:风机ID
    input_path:输入路径 output_filtered_csv_files 所在路径
    output_path:输出每个聚类的功率，和所有聚类的功率cluster_data
    """
    if not os.path.exists(output_path):
        os.makedirs(output_path)
    files = os.listdir(input_path)
    files.remove('turbine-144.csv')
    assert len(cluster) == len(files)
    dfs = [pd.read_csv(os.path.join(input_path, f)) for f in files]
    cfs = {}
    for j in range(1, max(cluster)+1):
        arr_j = np.where(cluster == j)[0]   # cluster中聚类j的索引列表
        cfs.setdefault(j, [turbine_id[k] for k in arr_j])
        dfs_j = [dfs[k] for k in arr_j]   # cluster
        dfj, time_series = dfs_j[0].loc[:, ['C_TIME','C_ACTIVE_POWER']], dfs_j[0]['C_TIME']
        for df in dfs_j[1:]:
            if df['C_TIME'].equals(time_series) is False:
                print("风机之间的日期不一致！")
                raise ValueError
            dfj['C_ACTIVE_POWER'] += df['C_ACTIVE_POWER']
        dfj.to_csv(os.path.join(output_path, 'power_' + str(j) + '.csv'), index=False)
        paint_cluster_power(output_path)
        for key, value in cfs.items():
            print("第{}组：{}".format(key, cfs[key]))


def cluster_power_list_folder(cluster, turbine_id, input_path, output_path):
    """
    从嵌套turbine-*.csv的多个文件夹列表中进行聚类功率相加
    cluster:聚类的结果
    turbine_id:风机ID
    input_path:输入路径 continuous_data 所在路径
    output_path:输出每个聚类的功率，和所有聚类的功率cluster_data
    """
    if not os.path.exists(output_path):
        os.makedirs(output_path)
    assert len(cluster) == len(turbine_id)
    continuous_data_path = input_path
    # 遍历整个continuous_data_path文件夹
    continuous_list = []
    for dirpath, dirnames, filenames in os.walk(continuous_data_path):
        dirname = dirpath.split('/')[-1]
        filenames = [file for file in filenames if not file.startswith('turbine-144')]
        x = [os.path.join(dirpath, filename) for filename in filenames]
        continuous_list.append((x, dirname))
    continuous_list.pop(0)
    for i in range(len(continuous_list)):
        cfs = {}
        dfs = [pd.read_csv(path) for path in continuous_list[i][0]]
        for j in range(1, max(cluster)+1):
            arr_j = np.where(cluster == j)[0]   # cluster中聚类j的索引列表
            cfs.setdefault(j, [turbine_id[k] for k in arr_j])
            dfs_j = [dfs[k] for k in arr_j]   # cluster
            dfj, time_series = dfs_j[0].loc[:, ['C_TIME','C_ACTIVE_POWER']], dfs_j[0]['C_TIME']
            for df in dfs_j[1:]:
                if df['C_TIME'].equals(time_series) is False:
                    print("风机之间的日期不一致！")
                    raise ValueError
                dfj['C_ACTIVE_POWER'] += df['C_ACTIVE_POWER']
            output_1 = os.path.join(output_path,  continuous_list[i][1])
            if not os.path.exists(output_1):
                os.makedirs(output_1)
            dfj.to_csv(os.path.join(output_1, 'power_' + str(j) + '.csv'), index=False)
        paint_cluster_power(output_1)
        print("------{}的分组信息----".format(continuous_list[i][1]))
        for key, value in cfs.items():
            print("第{}组：{}".format(key, cfs[key]))

def paint_cluster_power(cluster_path):
    dfs = [pd.read_csv(os.path.join(cluster_path, file_path)).rename(columns={'C_ACTIVE_POWER':file_path.split('/')[-1][:-4]}) for file_path in os.listdir(cluster_path)]
    df_cluster = pd.DataFrame({df.columns[-1]: df.iloc[:, -1] for df in dfs})
    df_cluster.insert(loc=0, column='C_TIME', value=dfs[0]['C_TIME'])
    df_cluster.to_csv(os.path.join(cluster_path, 'cluster_data.csv'), index=False)