CodePattern/计算设备/map-reduce/tf-31.py

# -*- coding: utf-8 -*-
from collections import Counter
from cppy.cp_util import *
from functools import reduce

# map - reduce
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(count1,count2):
    sum_counts = count1 + count2
    return sum_counts


@timing_decorator
def main():
    # 读取文件内容
    content = re_split(read_file(testfilepath))

    # 分割文件内容为多个块，每个块由一个进程处理
    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 map 方法和 process_chunk 函数处理每个分区
    counts_list = list(map(process_chunk, chunks))

    #  使用 reduce 和 merge_counts 函数统计所有分区的词频
    total_counts = (reduce(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()