import nltk.stem.porter as pt
import nltk.stem.lancaster as lc
import nltk.stem.snowball as sb
words = [
'table', 'probably', 'wolves', 'playing', 'is', 'dog', 'the', 'beaches',
'grounded', 'dreamt', 'envision'
]
pt_stemmer = pt.PorterStemmer() # 波特词干提取器，偏宽松
lc_stemmer = lc.LancasterStemmer() # 朗卡斯特词干提取器，偏严格
sb_stemmer = sb.SnowballStemmer('english') # 思诺博词干提取器，偏中庸
for word in words:
pt_stem = pt_stemmer.stem(word)
lc_stem = lc_stemmer.stem(word)
sb_stem = sb_stemmer.stem(word)
print('%8s %8s %8s %8s' % (word, pt_stem, lc_stem, sb_stem))
def word_lemmatizer(word):
"stem words"
lc_stemmer = lc.LancasterStemmer()
lc_stem = lc_stemmer.stem(word)
return lc_stem
import nltk.stem.porter as pt
import nltk.stem.lancaster as lc
import nltk.stem.snowball as sb
import nltk.stem as ns
words = ['table', 'probably', 'wolves', 'playing', 'is', 'the',
'beaches', 'grounded', 'dreamt', 'envision']
pt_stemmer = pt.PorterStemmer() # 偏宽松
lc_stemmer = lc.LancasterStemmer() # 偏严格
sb_stemmer = sb.SnowballStemmer('english') # 偏中庸
lemmetizer = ns.WordNetLemmatizer()
for word in words:
pt_stem = pt_stemmer.stem(word)
lc_stem = lc_stemmer.stem(word)
sb_stem = sb_stemmer.stem(word)
print('%8s %8s %8s %8s' % (word, pt_stem, lc_stem, sb_stem))
import nltk.stem.porter as pt
import nltk.stem.lancaster as lc
import nltk.stem.snowball as sb
words = [
'table', 'probably', 'wolves', 'playing', 'is', 'dog', 'the ', 'beeches',
'grounded', 'dreamt', 'envision'
]
stemmer = pt.PorterStemmer()
for word in words:
stem = stemmer.stem(word)
print(stem)
print('-' * 80)
stemmer = lc.LancasterStemmer()
for word in words:
stem = stemmer.stem(word)
print(stem)
print('-' * 80)
stemmer = sb.SnowballStemmer('english')
for word in words:
stem = stemmer.stem(word)
print(stem)
@author: Administrator
"""
import nltk.stem.porter as pt
import nltk.stem.lancaster as lc
import nltk.stem.snowball as sb
words = [
'table', 'probably', 'wolves', 'dreamt', 'palying', 'is', 'beaches',
'envision', 'grounded'
]
'''
提取词干
'''
stemmer_porter = pt.PorterStemmer() # 偏宽松
stemmer_lancaster = lc.LancasterStemmer() # 偏严格
stemmer_snowball = sb.SnowballStemmer('english') # 适中
for word in words:
pstem = stemmer_porter.stem(word)
lstem = stemmer_lancaster.stem(word)
sstem = stemmer_snowball.stem(word)
print('{:10} {:10} {:10} {:10}'.format(word, pstem, lstem, sstem))
#table tabl tabl tabl
#probably probabl prob probabl
#wolves wolv wolv wolv
#dreamt dreamt dreamt dreamt
#palying pali paly pali
#is is is is
#beaches beach beach beach
#envision envis envid envis
#grounded ground ground ground