第三次作业

学号:2017****1073

姓名:王云鹏

我的码云仓库:https://gitee.com/WYPwangyunpeng/word_frequency/tree/SE1073

代码;

def process_file(dst):
try:
f = open(dst, 'r')
except IOError as s:
print(s)
return None
try:
bvffer = f.read()
except:
print("Read File Error!")
return None
f.close()
return bvffer
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[:6]:
print(item[0], item[1])

def process_buffer(bvffer):
if bvffer:
word_freq = {}
bvffer = bvffer.lower()
for ch in '“‘!;,.?”':
bvffer = bvffer.lower().replace(ch, " ")
words = bvffer.strip().split()
for word in words:
word_freq[word] = word_freq.get(word, 0)+1
return word_freq
if __name__ == "__main__":
dst ="C:/Users/Administrator/Desktop/wang/wyp.txt"
bvffer = process_file(dst)
word_freq = process_buffer(bvffer)
output_result(word_freq)

 

 

 

posted @ 2019-04-08 16:27  王大饽饽  阅读(104)  评论(1编辑  收藏  举报