2017 07073的第三次课后作业

2017*******7073

孙瑞岐

码云地址 https://gitee.com/srq-568/word_frequency.git

from string import punctuation
def process_file(dst):
try:
f = open(dst)
except IOError as s:
print (s)
return None
try: # 读文件到缓冲区
bvffer = f.read()
except:
print ("Read File Error!")
return None
f.close()
return bvffer
#打开读取文档并将文档存储到bvffer
def process_buffer(bvffer):
if bvffer:
word_freq = {}
# 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_fred:
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)

查询结果：

 

改进前

 

 

 改进后

 

 

 

 

 通过这次学习我学会了词频统计和效能分析，并且还学会了get新建分支，还有python好难。