课后作业3

20170****7253  董昕诚

码云地址：https://gitee.com/dxcaly/word_frequency

 d = open(dst)
except IOError as s:
    print (s)       
打开文件只读模式并调试输出序列化

    bvffer = d.read()
except:
    print ("Read File Error!")
    return None
d.close()
转换成bvffer类并序列化

# 下面添加处理缓冲区 bvffer代码，统计每个单词的频率，存放在字典word_freq
for item in bvffer.strip().split():
    word = item.strip(punctuation + ' ')
    if word in word_freq.keys():
        word_freq[word] += 1
    else:
        word_freq[word] = 1

return word_freq

def output_result(word_freq):
    if word_freq:
        sorted_word_freq = sorted(word_freq.items(), key=lambda v: v[1], reverse=True)
        for item in sorted_word_freq[:10]:  # 输出 Top 10 的单词
            print(item)

if __name__ == "__main__":
    import argparse
    parser = argparse.ArgumentParser()
    parser.add_argument('dst')
    args = parser.parse_args()
    dst = args.dst
    bvffer = process_file(dst)
    word_freq = process_buffer(bvffer)
    output_result(word_freq)
name赋值給main执行以下进行修改语句

if word in word_freq.keys():
        word_freq[word] += 1
    else:
        word_freq[word] = 1

return word_freq

修改删掉.keys使其不再浪费多余进程时间

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

转载于:https://www.cnblogs.com/dxc12581/p/10645893.html