使用python脚本将文件分离到文件夹和子文件夹

Question

在下面的代码中，所有输出文件都被写入T1文件夹中。如何将这些输出文件分成与原始子文件夹同名的子文件夹（原始csv文件所在的子文件夹）？谢谢

import pandas as pd
import numpy as np
import glob
import os

path = '/root/Desktop/TT1/'
mystep = 0.4

#define the function
def data_splitter(df, name):
    max_time = df['Time'].max() # get max value of Time for the current csv file (df)
    myrange= np.arange(0, max_time, mystep) # build the threshold range
    for k in range(len(myrange)):
        # build the upper values 
        temp = df[(df['Time'] >= myrange[k]) & (df['Time'] < myrange[k] + mystep)]
        temp.to_csv("/root/Desktop/T1/{}_{}.csv".format(name, k))

# use os.walk(path) on the main path to get ALL subfolders inside path
for root,dirs,_ in os.walk(path):
    for d in dirs:
        path_sub = os.path.join(root,d) # this is the current subfolder
        for filename in glob.glob(os.path.join(path_sub, '*.csv')):
            df = pd.read_csv(filename)
            name = os.path.split(filename)[1] # get the name of the current csv file
            data_splitter(df, name)

Answer 1

这应该有帮助

演示：

as.factor(cutree(X,k=X))

Answer 2

类似的方法应该在这里起作用

import pandas as pd
import numpy as np
import glob
import os

input_root = '/root/Desktop/TT1'
output_root = '/root/Desktop/T1'

mystep = 0.4

#define the function
def data_splitter(input_file, output_path, output_basename):

    df = pd.read_csv(input_file)
    max_time = df['Time'].max() # get max value of Time for the current csv file (df)
    myrange = np.arange(0, max_time, mystep) # build the threshold range

    for k in range(len(myrange)):
        # build the upper values 
        temp = df[(df['Time'] >= myrange[k]) & (df['Time'] < myrange[k] + mystep)]
        temp.to_csv(os.path.join(output_path, f"{output_basename}_{k}.csv"))


# use os.walk(path) on the main path to get ALL subfolders inside path
for dirpath, dirnames, filenames in os.walk(input_root):
    for filename in filenames:
        if filename.lower().endswith('.csv'):
            input_file = os.path.join(dirpath, filename)
            sub_folders = dirpath[len(input_root)+1:]
            output_path = os.path.join(output_root, sub_folders)
            os.makedirs(output_path, exist_ok=True)  # Ensure the output folder exists
            output_basename = os.path.join(output_path, os.path.splitext(filename)[0] + '.csv')

            data_splitter(input_file, output_path, output_basename)

这应该导致在输出根文件夹中重新创建了文件夹结构。