CodePattern/13 多计算单元/数据分包/2 多线程.py

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


#
# 多线程
#
stop_words = get_stopwords()

def process_chunk(chunk):
    # 过滤停用词    
    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对象的总和"""
    return sum(counts_list, Counter())


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


@timing_decorator
def main():    
    # 读数据，按1000个词一组分片
    chunks = get_chunks(testfilepath,1000)

    # 线程池    
    pool = ThreadPool(len(chunks))  # 随意指定的线程数       

    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()