You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
40 lines
1.2 KiB
40 lines
1.2 KiB
import re
|
|
import multiprocessing
|
|
from collections import Counter
|
|
from cppy.cp_util import *
|
|
|
|
stopwords = get_stopwords()
|
|
|
|
def process_chunk(chunk):
|
|
# 切词并过滤停用词
|
|
words = re.findall(r'\w+', chunk.lower())
|
|
words = [ word for word in words if word not in stopwords and len(word) > 2]
|
|
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
|
|
|
|
if __name__ == '__main__':
|
|
# 读取文件内容
|
|
content = 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)]
|
|
|
|
# 使用多进程处理每个块
|
|
pool = multiprocessing.Pool(processes=multiprocessing.cpu_count())
|
|
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
|
|
for word, count in total_counts.most_common(10):
|
|
print(f"{word}-- {count}") |