spacy 英文模型

import spacy
nlp = spacy.load('en') #加载英文模型
doc = nlp(u"it's word tokenize test for spacy")
print(doc)
for d in doc:
    print(d)
test_doc = nlp(u"you are best. it is lemmatize test for spacy. I love these books")
for t in test_doc:
    print(t , t.lemma_ , t.lemma) #词干化
for t in test_doc:
    print(t , t.pos_ , t.pos) #词性标注
test_doc = nlp(u"Rami Eid is studying at Stony Brook University in New York")
for ent in test_doc.ents:
    print(ent, ent.label_, ent.label) #命名实体

输出：

it's word tokenize test for spacy
it
's
word
tokenize
test
for
spacy
you -PRON- 757862
are be 536
best good 673
. . 453
it -PRON- 757862
is be 536
lemmatize lemmatize 776982
test test 1877
for for 531
spacy spacy 776981
. . 453
I -PRON- 757862
love love 949
these these 742
books book 1300
you PRON 93
are VERB 98
best ADJ 82
. PUNCT 95
it PRON 93
is VERB 98
lemmatize ADJ 82
test NOUN 90
for ADP 83
spacy NOUN 90
. PUNCT 95
I PRON 93
love VERB 98
these DET 88
books NOUN 90
Rami Eid PERSON 377
Stony Brook University ORG 380