python统计词频并进行可视化显示_python统计词频

一、程序分析

(1)读取文件到缓冲区

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

(2)缓冲区字符串分割成带有词频的字典

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

(3)将字典按词频排序并输出排名前十的词频对

def output_result(word_freq):

if word_freq: