基于python循环读取大文件夹中的子文件夹及文件

1. 尽管在matlab里面批量读取数据还是比较简单的，但是有时工作需要只能在python里面处理数据。

大文件夹里有两个子文件夹，大文件夹构成如下：

子文件夹构成如下：将所有文件名含有error的文件的第一列储存一起到新的excel中

为方便对比，excel都是如下图这样的三列数据

2. python代码如下

import numpy as np
#from sklearn.ensemble import RandomForestRegressor
#from sklearn.model_selection import RandomizedSearchCV
#import scipy.io as scio
import os
import pandas as pd

path = 'E:\学习资料\工作\File'
entries = os.listdir(path)
data_array = []
summ = 0

y_005 = {}
Y_005 = {}
i = 1
m = 1
for entry in entries:
    full_path = os.path.join(path, entry)


    if os.path.isdir(full_path):
        folder_path = full_path
        file_paths = []
        for file_name in os.listdir(folder_path):
            sum_of_error = 0


            if "error" in file_name:
                target_file = (os.path.join(folder_path, file_name))
                errors = pd.read_excel(target_file, header=None).iloc[:, 0:1]
                Y_005[m] = errors
                m += 1
                print(type(errors))
                data_array.append(errors.iloc[:, 0])
            if "data" in file_name:
                file_paths.append(os.path.join(folder_path, file_name))

        result_df = pd.concat (data_array, axis = 1)#重要
        y_005[i] = result_df
        y_006 = pd.concat(y_005, axis=1)
        i += 1
    t = 1
    if os.path.isdir(full_path):
        folder_path = full_path
        file_paths = []
        for file_name in os.listdir(folder_path):
            if "error" in file_name:
                target_file = (os.path.join(folder_path, "test"+file_name))##这一步是将每个error文件中的第一列数据单独保存到新的excel
                Y_005[t].to_excel(target_file, index=False, header=None)

target_file1 = (os.path.join(folder_path, 'file_error111.xlsx'))
result_df.to_excel(target_file1, index=False, header=None)##这一步是将每个error文件中的第一列数据合并保存到新的excel