Python 脚本：使用 NumPy 和 Pandas 计算 CSV 文件中样本的电导率

import numpy as np
import pandas as pd
import os

def calculate_conductivity(df, df_saline_median):
    conductivity_list = [976, 1987, 3850, 5650, 7450, 9238]
    conductivity_list.reverse()
    result = []
    for i in range(len(freq_list)):
        ans = df_saline_median.iloc[:, i:i + 1]
        ans = ans.values.tolist()
        new_ans = sorted([ans[j][0] for j in range(len(ans))])
        result.append(np.interp(df.iloc[:, i + 2:i + 3].median(), new_ans, conductivity_list))
    return result

# 定义文件夹路径
folder_path = './test1/'

# 遍历文件夹内的所有csv文件
for entry in os.scandir(folder_path):
    if entry.is_file() and entry.name.endswith('.csv'):
        # 读取csv文件
        df = pd.read_csv(entry.path, encoding='utf-8')
        df = df.iloc[:, 1:18]
        df_tumor = df[df['name'] == 'tumor']
        df_peritumor = df[df['name'] == 'peritumor']
        df['name'] = df['name'] + df['property']
        # 将每个样本按照property分组
        tumor_dict = {}
        peritumor_dict = {}
        for name in ['A', 'B', 'C', 'D', 'E', 'F', 'G', 'H']:
            df_tumor_name = df_tumor[df_tumor['property'] == name]
            df_peritumor_name = df_peritumor[df_peritumor['property'] == name]
            tumor_dict[name] = df_tumor_name
            peritumor_dict[name] = df_peritumor_name

            # 计算saline的中位数
        concentration_list = ['saline0.05%', 'saline0.10%', 'saline0.20%', 'saline0.30%', 'saline0.40%', 'saline0.50%']
        df_saline_median = pd.DataFrame(columns=['1kHz_mag', '2kHz_mag', '3kHz_mag', '7kHz_mag', '11kHz_mag', '17kHz_mag',
                                                 '23kHz_mag', '31kHz_mag', '43kHz_mag', '61kHz_mag', '89kHz_mag', '127kHz_mag',
                                                 '179kHz_mag', '251kHz_mag', '349kHz_mag'])
        for i in concentration_list:
            saline_group = df[df['name'] == i]
            saline_median = saline_group[['1kHz_mag', '2kHz_mag', '3kHz_mag', '7kHz_mag', '11kHz_mag', '17kHz_mag',
                                          '23kHz_mag', '31kHz_mag', '43kHz_mag', '61kHz_mag', '89kHz_mag', '127kHz_mag',
                                          '179kHz_mag', '251kHz_mag', '349kHz_mag']].median()
            df_saline_median.loc[i] = saline_median
        # 计算每个样本的电导率并存储结果
        freq_list = [1, 2, 3, 7, 11, 17, 23, 31, 43, 61, 89, 127, 179, 251, 349]
        conductivity_list = [976, 1987, 3850, 5650, 7450, 9238]
        conductivity_list.reverse()
        for name in ['A', 'B', 'C', 'D', 'E', 'F', 'G', 'H']:
            tumor_result = calculate_conductivity(tumor_dict[name], df_saline_median)
            tumor_result = ' '.join(str(i[0]) for i in tumor_result)
            with open(os.path.join(folder_path, entry.name[:-4] + f'_tumor_{name}.txt'), 'w') as f:
                f.write(tumor_result)

            peritumor_result = calculate_conductivity(peritumor_dict[name], df_saline_median)
            with open(os.path.join(folder_path, entry.name[:-4] + f'_peritumor_{name}.txt'), 'w') as f:
                f.write(' '.join(str(i) for i in peritumor_result))

该代码使用 os.scandir() 函数遍历文件夹，并通过 entry.is_file() 和 entry.name.endswith('.csv') 筛选出符合条件的 CSV 文件。然后使用 entry.path 读取文件内容，并进行后续的计算和保存操作。