日常工作或者科研,我们需要处理大量数据。这就需要我们批量处理数据,找到我们需要的值。
下面这段代码可以帮我们实现:
import numpy as np
import openpyxl as op
from natsort import ns,natsorted #这个很重要,有利于按照run_0~403.csv的顺序读取csv文件
import pandas as pd
import glob
import os
path_in = r'C:\PycharmProjects\ANN\Datas\Runs\perturbed' # 文件夹位置
file_names = os.listdir(path_in) # 文件夹位置
file_paths = glob.glob(os.path.join(path_in, "*.csv")) # 文件夹列表
file_paths = natsorted(file_paths, alg=ns.PATH)
# print(file_paths)
data_list = []
for i in list(range(0, 404)):
df = pd.read_csv(file_paths[i])
data = df.iloc[103]["HE.fluidFlow.heatTransfer.T[10]"]
#print(data)
data_list.append(data)
#print(data_list)
def write():
num_list = data_list
folder = op.load_workbook(r'C:\PycharmProjects\ANN\Datas\SCOPE.xlsx')
sheet = folder["Sheet1"]
for a in range(1, 405):
sheet.cell((a + 1), 7, num_list[a - 1])
#sheet.cell((a + 1), 8, num_list[a - 1])
folder.save("C:\PycharmProjects\ANN\Datas\SCOPE.xlsx")
write()