在一系列 CSV 上循环函数

问：

我这里有代码来查找强度图中特定峰的平均大小和stdev。我让它适用于单个文件，但我希望能够一次运行多个文件并将平均值和 stdev 合并为一个平均值和一个 stdev。我一直在使用目录让它工作时遇到问题。我也不能将它们合并到一个巨大的数据文件中，因为重叠会弄乱我的数据，所以我需要先单独计算它们，然后再将它们组合在一起。任何帮助将不胜感激！

这是我的代码：

import os
from tkinter import filedialog
from tkinter import Tk
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import math
from shapely.geometry import LineString


def process_file(file_name):
    
        df = pd.read_csv(file_name, skiprows=0) # fill with the position of your CSV file for the intensity plot
        
        Distance = df.iloc[:, 0] # calls the column with the specific header
        intensity = df.iloc[:, 1] # calls the column with the specific header
        intensity_norm = (intensity - intensity.min())/ (intensity.max() - intensity.min()) # normalizing of the intensity
          
        x = Distance
        y = intensity_norm
        
        #y2= np.full_like(intensity_norm, 1 / math.exp(2))  # array made to be the same size as the intensity filled with the scalar value 1/e^2
        y2= np.full_like(intensity_norm, 0.5)  # array made to be the same size as the intensity filled with the scalar value 0.5 (the full width half max)
        
        plt.plot(x, intensity_norm) # intensity plot
        #plt.axhline(y=1/math.exp(2), color='r', linestyle='-') # horizontal line at 0.5 (the full width half max)
        plt.axhline(y=0.5, color='r', linestyle='-') # horizontal line at 1/e^2
        
        first_line = LineString(np.column_stack((x, y2))) # makes the first linestring based off of the horizontal line
        second_line = LineString(np.column_stack((x, y))) # makes line string based off of the normalized intensity plot
        intersection = first_line.intersection(second_line) # finds the intersecting points between first and second linestring
        xValues = [p.x for p in intersection.geoms] # calls only the X values of the intersecting points
        #print(xValues)
        
        diff_list = []
        for i in range(1,len(xValues)): # for every number in the range of values excluding the first value because there is no number before it
            xV = xValues[i] - xValues[i-1] #subtracts every number in the set by the previous value in the set
            diff_list.append(xV) #creates a new list with the resulting values from previous line
        
        size=[]
        for x in range(len(diff_list)):
            if 35<diff_list[x]<70:     # remove every number smaller then a certain value as well as those greater then a certain value determined by you
                size.append(diff_list[x])  #have size represent this new data set
                
        average = np.average(size) # average all the sizes 
        stdev = np.std(size) # stdev of all the sizes
        return average, stdev, N


root_folder = "C:\\Users\\Kyle\\Desktop\\test_test_test"
# files = ['file1.csv','file2.csv']
files = list(os.path.listdir(root_folder))
results = []
for file in files:
    results.append(process_file(os.path.join(root_folder,file)))
    
total_average = 0
total_var = 0
total_N = 0
for (average, std_dev, N) in results:
    total_average += average * N
    total_var += std_dev**2 * N
    total_N += N
total_average = total_average / total_N
total_std_dev = np.sqrt(total_var / total_N)

我尝试将它们组合在一起，但这会带来一些问题，即结果对于我正在寻找的内容不准确。我也尝试将它们放在一个目录中并运行代码，但这也不起作用