CodePattern/13 计算设备/map-reduce/tf-91.py

# -*- coding: utf-8 -*-
from collections import Counter
from cppy.cp_util import *
from multiprocessing.pool import ThreadPool


#
# 多线程
#
def process_chunk(chunk):
    # 过滤停用词
    stop_words = get_stopwords()
    words = [ w for w in chunk if ( not w in stop_words ) and len(w) >= 3 ]
    return Counter(words)


def merge_counts(counts_list):
    # 合并多个Counter对象
    total_counts = Counter()
    for counts in counts_list:
        total_counts += counts
    return total_counts


def thread_function(chunk, counts_list):
    word_count = process_chunk(chunk)
    counts_list.append(word_count)


@timing_decorator
def main():
    # 读取文件内容
    content = re_split(read_file(testfilepath))
    chunk_size = 1000 # 可以根据实际情况调整块大小
    chunks = [content[i:i + chunk_size] for i in range(0, len(content), chunk_size)]

    # 使用多线程池，每个线程处理一个块
    pool = ThreadPool(len(content)//chunk_size+1)
    counts_list = pool.map(process_chunk, chunks)
    pool.close()
    pool.join()

    # 合并计数
    total_counts = merge_counts(counts_list)

    # 输出最高频的n个词
    print_word_freqs(total_counts.most_common(10))


if __name__ == '__main__':
    main()