From 740f5aabff3ab4b2f8990cadab7c3af7f17c0f34 Mon Sep 17 00:00:00 2001
From: pbr4nzfkh <18879212807@163.com>
Date: Sun, 17 Mar 2024 10:21:08 +0800
Subject: [PATCH] =?UTF-8?q?Delete=20'=E8=AE=A1=E7=AE=97=E8=AE=BE=E5=A4=87/?=
 =?UTF-8?q?map-reduce/tf=5F92.py'?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 计算设备/map-reduce/tf_92.py | 44 --------------------------------
 1 file changed, 44 deletions(-)
 delete mode 100644 计算设备/map-reduce/tf_92.py

diff --git a/计算设备/map-reduce/tf_92.py b/计算设备/map-reduce/tf_92.py
deleted file mode 100644
index 525181e..0000000
--- a/计算设备/map-reduce/tf_92.py
+++ /dev/null
@@ -1,44 +0,0 @@
-import multiprocessing  
-from collections import Counter
-from cppy.cp_util import *  
-
-#
-# 多进程
-#
-def process_chunk(chunk):  
-    # 切词并过滤停用词       
-    words = extract_str_words( chunk.lower() )
-    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    
-
-@timing_decorator
-def 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
-    print_word_freqs( total_counts.most_common(10) )        
-
-
-if __name__ == '__main__':  
-    main()
-    
\ No newline at end of file