python之词频统计

1、Hamlet英文词频统计

txt = open('hamlet.txt','r').read()

# 将大写变小写，排除大小写差异的干扰
txt = txt.lower()

# 将文本中的特殊字符转化为空格，统一分割方式
for ch in ',./?;:'"<>=+-[]{
   }!~%@()#':
    txt.replace(ch, ' ')     

words = txt.split()    # 按空格分隔，列表形式返回
counts = {
   }         #计数器
for word in words:
    counts[word] = counts.get(word, 0) + 1

# 按照词频从高到低排序
counts = sorted(counts.items(), key = lambda x: x[1], reverse = True)

for i in range(10):
    word, count = counts[i]
    print('{0:<10}:{0:>5}'.