综合练习：词频统计

Posted 2020-10-28 phoenlix

f = open("peng.txt", "r", encoding=\'utf-8\')
song = f.read()
f.close()

sep = \'\'\',.?—!"\'\'\'

exclude = {\'the\', \'and\', \'i\', \'in\', "i\'m", \'a\', \'of\', \'an\', \'on\', \'to\', \'with\'}

for c in sep:
    song = song.replace(c, \' \')

swl = song.lower().split()

swd = {}

sws = set(swl) - exclude

for w in sws:
    swd[w] = swl.count(w)

fl = list(swd.items())

fl.sort(key=lambda x: x[1], reverse=True)

for i in fl:
    print(i)

f = open("result.txt", "w")
for i in range(20):
    f.write(fl[i][0] + "  " + str(fl[i][1]) + "\\n")
f.close()

　　

import jieba

f = open(\'weicheng.txt\', \'r\', encoding=\'utf-8\')
text = f.read()
f.close()

p = \'\'\'，。‘’“”：；（）！？、 \'\'\'
a = {
    \'的\', \'\\n\', \'\\u3000\',
    \'曰\', \'之\', \'不\', \'人\', \'一\', \'大\', \'马\', \'来\', \'有\', \'于\', \'下\', \'此\',
}
for i in p:
    text = text.replace(i, \'\')
print(list(jieba.cut(text)))
t = list(jieba.lcut(text))
print(t)
count = {}
wl = list(set(t) - a)
print(wl)

for i in range(0, len(wl)):
    count[wl[i]] = text.count(str(wl[i]))

cl = list(count.items())
cl.sort(key=lambda x: x[1], reverse=True)
print(cl)

f = open(\'wcCount.txt\', \'a\')
for i in range(20):
    f.write(cl[i][0] + \':\' + str(cl[i][1]) + \'\\n\')
f.close()