python_使用多线程来处理数据写入Excel文件

因为pandas的ExcelWriter不支持并发写入同一个文件,所以如果需要的话，后期还要合并。

import pandas as pd
from io import BytesIO
import threading
import multiprocessing
import time
import math

# 假设我们有12万行的数据
data = pd.DataFrame({
    'A': range(120001),
    'B': range(120001),
    'C': range(120001)
})


def write_to_excel(df, filename):
    with pd.ExcelWriter(filename) as writer:
        df.to_excel(writer, index=False)

def thread_write(df, filename):
    thread = threading.Thread(target=write_to_excel, args=(df, filename))
    thread.start()
    return thread

def test_threading(data):
    threads = []
    # 分割数据
    split_size=30000
    #向上取整
    num_threads = math.ceil(120001/split_size)
    
    data_splits = [data[i:i + split_size] for i in range(0, len(data), split_size)]
    filenames = [f'D:\\desktop\\new\\thread_{i}.xlsx' for i in range(num_threads)]
    
    start_time = time.time()
    for i in range(num_threads):
        threads.append(thread_write(data_splits[i], filenames[i]))
    
    for thread in threads:
        #join方法用于等待线程完成
        thread.join()
    
    print(f"Threaded execution took {time.time() - start_time:.2f} seconds")

# 模拟主函数入口
if __name__ == '__main__':
    test_threading(data)