mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 20:28:20 +03:00
285 lines
12 KiB
Plaintext
285 lines
12 KiB
Plaintext
//- 💫 DOCS > USAGE > SPACY 101 > LIGHTNING TOUR
|
||
|
||
p
|
||
| The following examples and code snippets give you an overview of spaCy's
|
||
| functionality and its usage.
|
||
|
||
+h(3, "lightning-tour-models") Install models and process text
|
||
|
||
+code(false, "bash").
|
||
spacy download en
|
||
spacy download de
|
||
|
||
+code.
|
||
import spacy
|
||
nlp = spacy.load('en')
|
||
doc = nlp(u'Hello, world. Here are two sentences.')
|
||
|
||
nlp_de = spacy.load('de')
|
||
doc_de = nlp_de(u'Ich bin ein Berliner.')
|
||
|
||
+infobox
|
||
| #[+label-inline API:] #[+api("spacy#load") #[code spacy.load()]]
|
||
| #[+label-inline Usage:] #[+a("/usage/models") Models],
|
||
| #[+a("/usage/spacy-101") spaCy 101]
|
||
|
||
+h(3, "lightning-tour-tokens-sentences") Get tokens, noun chunks & sentences
|
||
+tag-model("dependency parse")
|
||
|
||
+code.
|
||
doc = nlp(u"Peach emoji is where it has always been. Peach is the superior "
|
||
u"emoji. It's outranking eggplant 🍑 ")
|
||
|
||
assert doc[0].text == u'Peach'
|
||
assert doc[1].text == u'emoji'
|
||
assert doc[-1].text == u'🍑'
|
||
assert doc[17:19].text == u'outranking eggplant'
|
||
assert list(doc.noun_chunks)[0].text == u'Peach emoji'
|
||
|
||
sentences = list(doc.sents)
|
||
assert len(sentences) == 3
|
||
assert sentences[1].text == u'Peach is the superior emoji.'
|
||
|
||
+infobox
|
||
| #[+label-inline API:] #[+api("doc") #[code Doc]], #[+api("token") #[code Token]]
|
||
| #[+label-inline Usage:] #[+a("/usage/spacy-101") spaCy 101]
|
||
|
||
+h(3, "lightning-tour-pos-tags") Get part-of-speech tags and flags
|
||
+tag-model("tagger")
|
||
|
||
+code.
|
||
doc = nlp(u'Apple is looking at buying U.K. startup for $1 billion')
|
||
apple = doc[0]
|
||
assert [apple.pos_, apple.pos] == [u'PROPN', 17049293600679659579]
|
||
assert [apple.tag_, apple.tag] == [u'NNP', 15794550382381185553]
|
||
assert [apple.shape_, apple.shape] == [u'Xxxxx', 16072095006890171862]
|
||
assert apple.is_alpha == True
|
||
assert apple.is_punct == False
|
||
|
||
billion = doc[10]
|
||
assert billion.is_digit == False
|
||
assert billion.like_num == True
|
||
assert billion.like_email == False
|
||
|
||
+infobox
|
||
| #[+label-inline API:] #[+api("token") #[code Token]]
|
||
| #[+label-inline Usage:] #[+a("/usage/linguistic-features#pos-tagging") Part-of-speech tagging]
|
||
|
||
+h(3, "lightning-tour-hashes") Use hash values for any string
|
||
|
||
+code.
|
||
doc = nlp(u'I love coffee')
|
||
coffee_hash = nlp.vocab.strings[u'coffee'] # 3197928453018144401
|
||
coffee_text = nlp.vocab.strings[coffee_hash] # 'coffee'
|
||
|
||
assert doc[2].orth == coffee_hash == 3197928453018144401
|
||
assert doc[2].text == coffee_text == u'coffee'
|
||
|
||
beer_hash = doc.vocab.strings.add(u'beer') # 3073001599257881079
|
||
beer_text = doc.vocab.strings[beer_hash] # 'beer'
|
||
|
||
unicorn_hash = doc.vocab.strings.add(u'🦄 ') # 18234233413267120783
|
||
unicorn_text = doc.vocab.strings[unicorn_hash] # '🦄 '
|
||
|
||
+infobox
|
||
| #[+label-inline API:] #[+api("stringstore") #[code stringstore]]
|
||
| #[+label-inline Usage:] #[+a("/usage/spacy-101#vocab") Vocab, hashes and lexemes 101]
|
||
|
||
+h(3, "lightning-tour-entities") Recongnise and update named entities
|
||
+tag-model("NER")
|
||
|
||
+code.
|
||
doc = nlp(u'San Francisco considers banning sidewalk delivery robots')
|
||
ents = [(ent.text, ent.start_char, ent.end_char, ent.label_) for ent in doc.ents]
|
||
assert ents == [(u'San Francisco', 0, 13, u'GPE')]
|
||
|
||
from spacy.tokens import Span
|
||
doc = nlp(u'Netflix is hiring a new VP of global policy')
|
||
doc.ents = [Span(doc, 0, 1, label=doc.vocab.strings[u'ORG'])]
|
||
ents = [(ent.start_char, ent.end_char, ent.label_) for ent in doc.ents]
|
||
assert ents == [(0, 7, u'ORG')]
|
||
|
||
+infobox
|
||
| #[+label-inline Usage:] #[+a("/usage/linguistic-features#named-entities") Named entity recognition]
|
||
|
||
+h(3, "lightning-tour-displacy") Visualize a dependency parse and named entities in your browser
|
||
+tag-model("dependency parse", "NER")
|
||
+tag-new(2)
|
||
|
||
+aside
|
||
.u-text-center(style="overflow: auto").
|
||
<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" class="o-svg" viewBox="270 35 125 240" width="400" height="150" style="max-width: none; color: #fff; background: #1a1e23; font-family: inherit; font-size: 2rem">
|
||
<text fill="currentColor" text-anchor="middle" y="222.0">
|
||
<tspan style="font-weight: bold" fill="currentColor" x="50">This</tspan>
|
||
<tspan dy="2em" class="u-color-theme" style="font-weight: bold" fill="currentColor" x="50">DT</tspan>
|
||
</text>
|
||
<text fill="currentColor" text-anchor="middle" y="222.0">
|
||
<tspan style="font-weight: bold" fill="currentColor" x="225">is</tspan>
|
||
<tspan dy="2em" class="u-color-theme" style="font-weight: bold" fill="currentColor" x="225">VBZ</tspan>
|
||
</text>
|
||
<text fill="currentColor" text-anchor="middle" y="222.0">
|
||
<tspan style="font-weight: bold" fill="currentColor" x="400">a</tspan>
|
||
<tspan dy="2em" class="u-color-theme" style="font-weight: bold" fill="currentColor" x="400">DT</tspan>
|
||
</text>
|
||
<text fill="currentColor" text-anchor="middle" y="222.0">
|
||
<tspan style="font-weight: bold" fill="currentColor" x="575">sentence.</tspan>
|
||
<tspan dy="2em" class="u-color-theme" style="font-weight: bold" fill="currentColor" x="575">NN</tspan>
|
||
</text>
|
||
<path id="arrow-0-0" stroke-width="2px" d="M70,177.0 C70,89.5 220.0,89.5 220.0,177.0" fill="none" stroke="currentColor"/>
|
||
<text dy="1.25em" style="font-size: 0.9em; letter-spacing: 2px">
|
||
<textPath xlink:href="#arrow-0-0" startOffset="50%" fill="currentColor" text-anchor="middle">nsubj</textPath>
|
||
</text>
|
||
<path d="M70,179.0 L62,167.0 78,167.0" fill="currentColor"/>
|
||
<path id="arrow-0-1" stroke-width="2px" d="M420,177.0 C420,89.5 570.0,89.5 570.0,177.0" fill="none" stroke="currentColor"/>
|
||
<text dy="1.25em" style="font-size: 0.9em; letter-spacing: 2px">
|
||
<textPath xlink:href="#arrow-0-1" startOffset="50%" fill="currentColor" text-anchor="middle">det</textPath>
|
||
</text>
|
||
<path d="M420,179.0 L412,167.0 428,167.0" fill="currentColor"/>
|
||
<path id="arrow-0-2" stroke-width="2px" d="M245,177.0 C245,2.0 575.0,2.0 575.0,177.0" fill="none" stroke="currentColor"/>
|
||
<text dy="1.25em" style="font-size: 0.9em; letter-spacing: 2px">
|
||
<textPath xlink:href="#arrow-0-2" startOffset="50%" fill="currentColor" text-anchor="middle">attr</textPath>
|
||
</text>
|
||
<path d="M575.0,179.0 L583.0,167.0 567.0,167.0" fill="currentColor"/>
|
||
</svg>
|
||
|
||
+code.
|
||
from spacy import displacy
|
||
|
||
doc_dep = nlp(u'This is a sentence.')
|
||
displacy.serve(doc_dep, style='dep')
|
||
|
||
doc_ent = nlp(u'When Sebastian Thrun started working on self-driving cars at Google '
|
||
u'in 2007, few people outside of the company took him seriously.')
|
||
displacy.serve(doc_ent, style='ent')
|
||
|
||
+infobox
|
||
| #[+label-inline API:] #[+api("top-level#displacy") #[code displacy]]
|
||
| #[+label-inline Usage:] #[+a("/usage/visualizers") Visualizers]
|
||
|
||
+h(3, "lightning-tour-word-vectors") Get word vectors and similarity
|
||
+tag-model("word vectors")
|
||
|
||
+code.
|
||
doc = nlp(u"Apple and banana are similar. Pasta and hippo aren't.")
|
||
apple = doc[0]
|
||
banana = doc[2]
|
||
pasta = doc[6]
|
||
hippo = doc[8]
|
||
assert apple.similarity(banana) > pasta.similarity(hippo)
|
||
assert apple.has_vector, banana.has_vector, pasta.has_vector, hippo.has_vector
|
||
|
||
p
|
||
| For the best results, you should run this example using the
|
||
| #[+a("/models/en#en_vectors_web_lg") #[code en_vectors_web_lg]] model.
|
||
|
||
+infobox
|
||
| #[+label-inline Usage:] #[+a("/usage/vectors-similarity") Word vectors and similarity]
|
||
|
||
+h(3, "lightning-tour-serialization") Simple and efficient serialization
|
||
|
||
+code.
|
||
import spacy
|
||
from spacy.tokens import Doc
|
||
from spacy.vocab import Vocab
|
||
|
||
nlp = spacy.load('en')
|
||
moby_dick = open('moby_dick.txt', 'r').read()
|
||
doc = nlp(moby_dick)
|
||
doc.to_disk('/moby_dick.bin')
|
||
|
||
new_doc = Doc(Vocab()).from_disk('/moby_dick.bin')
|
||
|
||
+infobox
|
||
| #[+label-inline API:] #[+api("language") #[code Language]],
|
||
| #[+api("doc") #[code Doc]]
|
||
| #[+label-inline Usage:] #[+a("/usage/models#saving-loading") Saving and loading models]
|
||
|
||
+h(3, "lightning-tour-rule-matcher") Match text with token rules
|
||
|
||
+code.
|
||
import spacy
|
||
from spacy.matcher import Matcher
|
||
|
||
nlp = spacy.load('en')
|
||
matcher = Matcher(nlp.vocab)
|
||
|
||
def set_sentiment(matcher, doc, i, matches):
|
||
doc.sentiment += 0.1
|
||
|
||
pattern1 = [{'ORTH': 'Google'}, {'UPPER': 'I'}, {'ORTH': '/'}, {'UPPER': 'O'}]
|
||
pattern2 = [[{'ORTH': emoji, 'OP': '+'}] for emoji in ['😀', '😂', '🤣', '😍']]
|
||
matcher.add('GoogleIO', None, pattern1) # match "Google I/O" or "Google i/o"
|
||
matcher.add('HAPPY', set_sentiment, *pattern2) # match one or more happy emoji
|
||
matches = nlp(LOTS_OF TEXT)
|
||
|
||
+infobox
|
||
| #[+label-inline API:] #[+api("matcher") #[code Matcher]]
|
||
| #[+label-inline Usage:] #[+a("/usage/linguistic-features#rule-based-matching") Rule-based matching]
|
||
|
||
+h(3, "lightning-tour-multi-threaded") Multi-threaded generator
|
||
|
||
+code.
|
||
texts = [u'One document.', u'...', u'Lots of documents']
|
||
# .pipe streams input, and produces streaming output
|
||
iter_texts = (texts[i % 3] for i in xrange(100000000))
|
||
for i, doc in enumerate(nlp.pipe(iter_texts, batch_size=50, n_threads=4)):
|
||
assert doc.is_parsed
|
||
if i == 100:
|
||
break
|
||
|
||
+infobox
|
||
| #[+label-inline API:] #[+api("doc") #[code Doc]]
|
||
| #[+label-inline Usage:] #[+a("/usage/processing-pipelines#multithreading") Processing pipelines]
|
||
|
||
+h(3, "lightning-tour-dependencies") Get syntactic dependencies
|
||
+tag-model("dependency parse")
|
||
|
||
+code.
|
||
def dependency_labels_to_root(token):
|
||
"""Walk up the syntactic tree, collecting the arc labels."""
|
||
dep_labels = []
|
||
while token.head is not token:
|
||
dep_labels.append(token.dep)
|
||
token = token.head
|
||
return dep_labels
|
||
|
||
+infobox
|
||
| #[+label-inline API:] #[+api("token") #[code Token]]
|
||
| #[+label-inline Usage:] #[+a("/usage/linguistic-features#dependency-parse") Using the dependency parse]
|
||
|
||
+h(3, "lightning-tour-numpy-arrays") Export to numpy arrays
|
||
|
||
+code.
|
||
from spacy.attrs import ORTH, LIKE_URL, IS_OOV
|
||
|
||
attr_ids = [ORTH, LIKE_URL, IS_OOV]
|
||
doc_array = doc.to_array(attr_ids)
|
||
assert doc_array.shape == (len(doc), len(attr_ids))
|
||
assert doc[0].orth == doc_array[0, 0]
|
||
assert doc[1].orth == doc_array[1, 0]
|
||
assert doc[0].like_url == doc_array[0, 1]
|
||
assert list(doc_array[:, 1]) == [t.like_url for t in doc]
|
||
|
||
+h(3, "lightning-tour-inline") Calculate inline markup on original string
|
||
|
||
+code.
|
||
def put_spans_around_tokens(doc, get_classes):
|
||
"""Given some function to compute class names, put each token in a
|
||
span element, with the appropriate classes computed. All whitespace is
|
||
preserved, outside of the spans. (Of course, HTML won't display more than
|
||
one whitespace character it – but the point is, no information is lost
|
||
and you can calculate what you need, e.g. <br />, <p> etc.)
|
||
"""
|
||
output = []
|
||
html = '<span class="{classes}">{word}</span>{space}'
|
||
for token in doc:
|
||
if token.is_space:
|
||
output.append(token.text)
|
||
else:
|
||
classes = ' '.join(get_classes(token))
|
||
output.append(html.format(classes=classes, word=token.text, space=token.whitespace_))
|
||
string = ''.join(output)
|
||
string = string.replace('\n', '')
|
||
string = string.replace('\t', ' ')
|
||
return string
|