一個(gè)txt文檔，已經(jīng)用結(jié)巴分詞分完詞，怎么用python工具對(duì)這個(gè)分完詞的文檔進(jìn)行計(jì)算統(tǒng)計(jì)詞頻，求腳本，非

#!/usr/bin/env?python3

創(chuàng)新互聯(lián)建站服務(wù)項(xiàng)目包括安平網(wǎng)站建設(shè)、安平網(wǎng)站制作、安平網(wǎng)頁制作以及安平網(wǎng)絡(luò)營(yíng)銷策劃等。多年來，我們專注于互聯(lián)網(wǎng)行業(yè)，利用自身積累的技術(shù)優(yōu)勢(shì)、行業(yè)經(jīng)驗(yàn)、深度合作伙伴關(guān)系等，向廣大中小型企業(yè)、政府機(jī)構(gòu)等提供互聯(lián)網(wǎng)行業(yè)的解決方案，安平網(wǎng)站推廣取得了明顯的社會(huì)效益與經(jīng)濟(jì)效益。目前，我們服務(wù)的客戶以成都為中心已經(jīng)輻射到安平省份的部分城市，未來相信會(huì)繼續(xù)擴(kuò)大服務(wù)區(qū)域并繼續(xù)獲得客戶的支持與信任！

#-*-?coding:utf-8?-*-

import?os,random

#假設(shè)要讀取文件名為aa，位于當(dāng)前路徑

filename='aa.txt'

dirname=os.getcwd()

f_n=os.path.join(dirname,filename)

#注釋掉的程序段，用于測(cè)試腳本，它生成20行數(shù)據(jù)，每行有1-20隨機(jī)個(gè)數(shù)字，每個(gè)數(shù)字隨機(jī)1-20

'''

test=''

for?i?in?range(20):

for?j?in?range(random.randint(1,20)):

test+=str(random.randint(1,20))+'?'

test+='\n'

with?open(f_n,'w')?as?wf:

wf.write(test)

'''

with?open(f_n)?as?f:

s=f.readlines()

#將每一行數(shù)據(jù)去掉首尾的空格和換行符，然后用空格分割，再組成一維列表

words=[]

for?line?in?s:

words.extend(line.strip().split('?'))

#格式化要輸出的每行數(shù)據(jù)，首尾各占8位，中間占18位

def?geshi(a,b,c):

return?alignment(str(a))+alignment(str(b),18)+alignment(str(c))+'\n'

#中英文混合對(duì)齊?，參考?，二樓

#漢字與字母?格式化占位?format對(duì)齊出錯(cuò)?對(duì)不齊?漢字對(duì)齊數(shù)字?漢字對(duì)齊字母?中文對(duì)齊英文

#alignment函數(shù)用于英漢混合對(duì)齊、漢字英文對(duì)齊、漢英對(duì)齊、中英對(duì)齊

def?alignment(str1,?space=8,?align?=?'left'):

length?=?len(str1.encode('gb2312'))

space?=?space?-?length?if?space?=length?else?0

if?align?in?['left','l','L','Left','LEFT']:

str1?=?str1?+?'?'?*?space

elif?align?in?['right','r','R','Right','RIGHT']:

str1?=?'?'*?space?+str1

elif?align?in?['center','c','C','Center','CENTER','centre']:

str1?=?'?'?*?(space?//2)?+str1?+?'?'*?(space?-?space?//?2)

return?str1

w_s=geshi('序號(hào)','詞','頻率')

#由(詞,頻率)元組構(gòu)成列表，先按頻率降序排序，再按詞升序排序，多級(jí)排序，一組升，一組降，高級(jí)sorted

wordcount=sorted([(w,words.count(w))?for?w?in?set(words)],key=lambda?l:(-l[1],l[0]))

#要輸出的數(shù)據(jù)，每一行由：序號(hào)(占8位)詞(占20位)頻率(占8位)+'\n'構(gòu)成，序號(hào)=List.index(element)+1

for?(w,c)?in?wordcount:????

w_s+=geshi(wordcount.index((w,c))+1,w,c)

#將統(tǒng)計(jì)結(jié)果寫入文件ar.txt中

writefile='ar.txt'

w_n=os.path.join(dirname,writefile)

with?open(w_n,'w')?as?wf:

wf.write(w_s)

如何用python實(shí)現(xiàn)英文短文的雙詞頻統(tǒng)計(jì)？

import?re

from?itertools?import?imap?as?map

from?collections?import?Counter

def?parserwords(sentence):

preword?=?''

result?=?[]

for?word?in?re.findall('\w+',?sentence.lower()):

if?preword:

result.append((preword,?word))

preword?=?word

return?result

context?=?"""

Do?you?hear?the?people?sing,?singing?a?song?of?angry?men.?

It?is?the?music?of?a?people,?who?will?not?be?slaves?again,?

when?the?beating?of?your?heart?echoes?the?beating?of?the?drums.?

There?is?a?life?about?to?start?when?tomorrow?comes.

"""

words?=?[]

for?sentence?in?map(parserwords,?

re.split(r'[,.]',?context.lower())):

words.extend(sentence)

prefixcounter?=?Counter([word[0]?for?word?in?words])

counter?=?Counter(words)

meter?=?{}

for?pre,?post?in?counter.iterkeys():

meter[(pre,?post)]?=?1.?*?counter[(pre,?post)]?/?prefixcounter[pre]

result?=?sorted(meter.iteritems(),

cmp?=?lambda?a,?b:?cmp(b[1],?a[1])?or?cmp(a[0],?b[0])

)

print?result[:5]

如何用python對(duì)文章中文分詞并統(tǒng)計(jì)詞頻

使用結(jié)巴分詞，統(tǒng)計(jì)頻率可以使用Counter，即from collections import Counter

用Python統(tǒng)計(jì)詞頻

def statistics(astr):

# astr.replace("\n", "")

slist = list(astr.split("\t"))

alist = []

[alist.append(i) for i in slist if i not in alist]

alist[-1] = alist[-1].replace("\n", "")

return alist

if __name__ == "__main__":

code_doc = {}

with open("test_data.txt", "r", encoding='utf-8') as fs:

for ln in fs.readlines():

l = statistics(ln)

for t in l:

if t not in code_doc:

code_doc.setdefault(t, 1)

else:

code_doc[t] += 1

for keys in code_doc.keys():

print(keys + ' ' + str(code_doc[keys]))

Python詞頻統(tǒng)計(jì)問題

#下載一文到words.txt，內(nèi)容為（stu?ml?ds?ml?stu?stuee?zkz?wxj?Zkz?Wxj）

File?=?"words.txt"

number_list?=[]

with?open(File)?as?f:

for?line?in?f:

number_list.extend(?str(i)?for?i?in?line.split())

for?item?in?set(number_list):

L=[item,number_list.index(item),number_list.count(item)]

print(L)??#單詞??首次出現(xiàn)的位置??詞頻

with?open('Q1.txt','a')?as?F:

F.writelines(str(L))

如何用python和jieba分詞，統(tǒng)計(jì)詞頻？

#!?python3

#?-*-?coding:?utf-8?-*-

import?os,?codecs

import?jieba

from?collections?import?Counter

def?get_words(txt):

seg_list?=?jieba.cut(txt)

c?=?Counter()

for?x?in?seg_list:

if?len(x)1?and?x?!=?'\r\n':

c[x]?+=?1

print('常用詞頻度統(tǒng)計(jì)結(jié)果')

for?(k,v)?in?c.most_common(100):

print('%s%s?%s??%d'?%?('??'*(5-len(k)),?k,?'*'*int(v/3),?v))

if?__name__?==?'__main__':

with?codecs.open('19d.txt',?'r',?'utf8')?as?f:

txt?=?f.read()

get_words(txt)