Python统计一篇英文的单词出现的频率

首先，去除标点符号，并用空格代替。

接着，用字典匹配，对于没有出现的单词就直接加在里面，以后出现的就直接在dict字典的key+1.

最后，还可以匹配关键字。

def amount0(data):
    signal1=dict()
    data1=list(data)
    except_signal={' ','\n','\u3000','-'}

    l=len(data1)
    for i in range(l):
        if not data1[i].isalnum():
            if data[i] in except_signal:
                data1[i] = ' '
                continue
            if not signal1.__contains__(data1[i]):
                signal1[data1[i]]=0
            else:
                signal1[data1[i]]=signal1[data1[i]]+1
            data1[i]=' '
    print(signal1)
    for k, v in signal1.items():
        print("%s %s" % (k, v), file=datafile)
    data2="".join(data1)
    return data2

def amount1(data):
    data1=data
    words1=data1.split()
    words2=list(set(words1))
    l2=len(words2)
    l1=len(words1)
    n=[0]*l2
    dictwords=dict(zip(words2,n))
    for i in range(l1):
        dictwords[words1[i]]=dictwords[words1[i]]+1
    for k, v in dictwords.items():
        print("%s %s" % (k, v), file=datafile)
    print(dictwords)


def amount2(data, keywords):
    n=[]
    data1=data.replace(",", ' ').replace(";", ' ').replace(".", ' ')
    words1=data1.split()
    l=len(keywords)
    for i in range(l):
        n.append(words1.count(keywords[i]))
    answer=dict(zip(keywords, n))
    print(answer)
    for k, v in answer.items():
        print("%s %s" % (k, v), file=datafile)

f=open("data.txt", "r", encoding='GBK')
datafile=open("output.txt", "w")
data=f.read().lower()
data1=amount0(data)
amount1(data1)
keywords=["if", "sun", "the", "to", "is"]
amount2(data, keywords)

f.close()