Spacetutorial (continuous updating...)

The gods were silent - personal CSDN Blog Directory

Last updated ：2022.6.27
Earliest update time ：2022.6.27

In this paper, spacy How to use the model , namely spacy Of API Use the tutorial .spacy Bag API It basically depends on a specific model （trained pipeline） To use , This article is mainly in English （en_core_web_sm） And Chinese （zh_core_web_sm） To make the sample , After all, I only know these two languages .
spacy Model official website ：Trained Models & Pipelines · spaCy Models Documentation

1. participle

Official website example （ You can use it directly on the Internet docker function ）：

import spacy
from spacy.lang.en.examples import sentences 

nlp = spacy.load("en_core_web_sm")
doc = nlp(sentences[0])
print(doc.text)
for token in doc:
    print(token.text, token.pos_, token.dep_)

Output ：

Apple is looking at buying U.K. startup for $1 billion
Apple PROPN nsubj
is AUX aux
looking VERB ROOT
at ADP prep
buying VERB pcomp
U.K. PROPN dobj
startup NOUN advcl
for ADP prep
$ SYM quantmod
1 NUM compound
billion NUM pobj

You can see that the model has tokenize, And each token Part of speech of （pos_） and dependency relation（dep_）（ I don't know what this is . See ：DependencyParser · spaCy API Documentation）

2. Stop Thesaurus

Defaults See Language · spaCy API Documentation

import spacy
sp=spacy.load('en_core_web_sm')
StopWord=sp.Defaults.stop_words

StopWord Is a stop word （ String format ） Set of components .

3. Clause

Sentencizer See Sentencizer · spaCy API Documentation
The sentence here is the kind of complete sentence , The one that uses the criteria such as full stops as the division criteria .

import spacy
from spacy.lang.zh.examples import sentences

nlp = spacy.load("zh_core_web_sm")
total_doc=''.join(sentences)
nlp.add_pipe('sentencizer', name='sentence_segmenter', before='parser')
doc = nlp(total_doc)
print(doc.text)
for token in doc:
    print(token)
    print(token.is_sent_start)
for sent in doc.sents:
    print(sent)

Output omitted . All in all is_sent_start The attribute is True Of token Is the beginning of the sentence token,doc.sents Is an iterator of the sentence list .

in addition v2.0 edition spacy There is such a phrasing , stay v3.0（ I am a 3.2.4） Version of spacy Not available in , I haven't tried ：

from seg.newline.segmenter import NewLineSegmenter  # note that pip package is called spacyss
import spacy

nlseg = NewLineSegmenter()

nlp = spacy.load('en')
nlp.add_pipe(nlseg.set_sent_starts, name='sentence_segmenter', before='parser')

doc = nlp(my_doc_text)

The required package is ：spacyss · PyPI