学号:2017****7006
姓名:陈天明
码云:https://gitee.com/chenhaoming1/word_frequency/tree/SE1006
filename: word_freq.py
注意:代码风格
def process_file(dst): # 读文件到缓冲区
try: # 打开文件
f1=open(dst,"r")
except IOError as s:
print (s)
return None
try: # 读文件到缓冲区
bvffer=f1.read()
except:
print ("Read File Error!")
return None
f1.close()
return 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
bvffer=bvffer.lower()
for x in '~!@#$%^&*()_+/*-+][':
bvffer=bvffer.replace(x, " ")
words=bvffer.strip().split()
for word in words:
word_freq[word]=word_freq.get(word,0)+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)
def main():
dst = "Gone_with_the_wind.txt"
bvffer = process_file(dst)
word_freq = process_buffer(bvffer)
output_result(word_freq)
if name == "main":
import cProfile
import pstats
cProfile.run("main()", "result")
p = pstats.Stats("result")
p.strip_dirs().sort_stats("call").print_stats()
p.strip_dirs().sort_stats("cumulative").print_stats()
p.print_callers(0.5, "process_file")
p.print_callers(0.5, "process_buffer")
p.print_callers(0.5, "output_result")
程序运行命令、结果截图
此次任务完成情况的总结反思
我还有跟多不足的地方 我还是需要努力 、学习。加油加油我最强,加油加油我最棒