explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-10-31 07:57:35 +03:00
Code Issues Packages Projects Releases Wiki Activity
6ec834dc72
spaCy/website/usage/_spacy-101/_lightning-tour.jade
GolanLevy 72d7e80f94 adding a missing apostrophe (#2436)
2018-06-11 17:47:24 +02:00

363 lines
14 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

//- 💫 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").
python -m spacy download en_core_web_sm
python -m spacy download de_core_news_sm
+code-exec.
import spacy
nlp = spacy.load('en_core_web_sm')
doc = nlp(u'Hello, world. Here are two sentences.')
print([t.text for t in doc])
nlp_de = spacy.load('de_core_news_sm')
doc_de = nlp_de(u'Ich bin ein Berliner.')
print([t.text for t in doc_de])
+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-exec.
import spacy
nlp = spacy.load('en_core_web_sm')
doc = nlp(u"Peach emoji is where it has always been. Peach is the superior "
u"emoji. It's outranking eggplant 🍑 ")
print(doc[0].text) # Peach
print(doc[1].text) # emoji
print(doc[-1].text) # 🍑
print(doc[17:19].text) # outranking eggplant
noun_chunks = list(doc.noun_chunks)
print(noun_chunks[0].text) # Peach emoji
sentences = list(doc.sents)
assert len(sentences) == 3
print(sentences[1].text) # '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-exec.
import spacy
nlp = spacy.load('en_core_web_sm')
doc = nlp(u'Apple is looking at buying U.K. startup for $1 billion')
apple = doc[0]
print('Fine-grained POS tag', apple.pos_, apple.pos)
print('Coarse-grained POS tag', apple.tag_, apple.tag)
print('Word shape', apple.shape_, apple.shape)
print('Alphanumeric characters?', apple.is_alpha)
print('Punctuation mark?', apple.is_punct)
billion = doc[10]
print('Digit?', billion.is_digit)
print('Like a number?', billion.like_num)
print('Like an email address?', billion.like_email)
+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-exec.
import spacy
nlp = spacy.load('en_core_web_sm')
doc = nlp(u'I love coffee')
coffee_hash = nlp.vocab.strings[u'coffee'] # 3197928453018144401
coffee_text = nlp.vocab.strings[coffee_hash] # 'coffee'
print(coffee_hash, coffee_text)
print(doc[2].orth, coffee_hash) # 3197928453018144401
print(doc[2].text, coffee_text) # 'coffee'
beer_hash = doc.vocab.strings.add(u'beer') # 3073001599257881079
beer_text = doc.vocab.strings[beer_hash] # 'beer'
print(beer_hash, beer_text)
unicorn_hash = doc.vocab.strings.add(u'🦄 ') # 18234233413267120783
unicorn_text = doc.vocab.strings[unicorn_hash] # '🦄 '
print(unicorn_hash, unicorn_text)
+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") Recognise and update named entities
+tag-model("NER")
+code-exec.
import spacy
nlp = spacy.load('en_core_web_sm')
doc = nlp(u'San Francisco considers banning sidewalk delivery robots')
for ent in doc.ents:
print(ent.text, ent.start_char, ent.end_char, ent.label_)
from spacy.tokens import Span
doc = nlp(u'FB is hiring a new VP of global policy')
doc.ents = [Span(doc, 0, 1, label=doc.vocab.strings[u'ORG'])]
for ent in doc.ents:
print(ent.text, ent.start_char, ent.end_char, ent.label_)
+infobox
| #[+label-inline Usage:] #[+a("/usage/linguistic-features#named-entities") Named entity recognition]
+h(3, "lightning-tour-training") Train and update neural network models
+tag-model
+code.
import spacy
import random
nlp = spacy.load('en')
train_data = [("Uber blew through $1 million", {'entities': [(0, 4, 'ORG')]})]
with nlp.disable_pipes(*[pipe for pipe in nlp.pipe_names if pipe != 'ner']):
optimizer = nlp.begin_training()
for i in range(10):
random.shuffle(train_data)
for text, annotations in train_data:
nlp.update([text], [annotations], sgd=optimizer)
nlp.to_disk('/model')
+infobox
| #[+label-inline API:] #[+api("language#update") #[code Language.update]]
| #[+label-inline Usage:] #[+a("/usage/training") Training spaCy's statistical models]
+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-exec.
import spacy
nlp = spacy.load('en_core_web_md')
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]
print('apple <-> banana', apple.similarity(banana))
print('pasta <-> hippo', pasta.similarity(hippo))
print(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
| (currently not available in the live demo).
+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')
customer_feedback = open('customer_feedback_627.txt').read()
doc = nlp(customer_feedback)
doc.to_disk('/tmp/customer_feedback_627.bin')
new_doc = Doc(Vocab()).from_disk('/tmp/customer_feedback_627.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-exec.
import spacy
from spacy.matcher import Matcher
nlp = spacy.load('en_core_web_sm')
matcher = Matcher(nlp.vocab)
def set_sentiment(matcher, doc, i, matches):
doc.sentiment += 0.1
pattern1 = [{'ORTH': 'Google'}, {'ORTH': 'I'}, {'ORTH': '/'}, {'ORTH': '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
doc = nlp(u"A text about Google I/O 😀😀")
matches = matcher(doc)
for match_id, start, end in matches:
string_id = nlp.vocab.strings[match_id]
span = doc[start:end]
print(string_id, span.text)
print('Sentiment', doc.sentiment)
+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-exec.
import spacy
nlp = spacy.load('en_core_web_sm')
doc = 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.")
dep_labels = []
for token in doc:
while token.head != token:
dep_labels.append(token.dep_)
token = token.head
print(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-exec.
import spacy
from spacy.attrs import ORTH, LIKE_URL
nlp = spacy.load('en_core_web_sm')
doc = nlp(u"Check out https://spacy.io")
for token in doc:
print(token.text, token.orth, token.like_url)
attr_ids = [ORTH, LIKE_URL]
doc_array = doc.to_array(attr_ids)
print(doc_array.shape)
print(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]
print(list(doc_array[:, 1]))
+h(3, "lightning-tour-inline") Calculate inline markup on original string
+code-exec.
import spacy
def put_spans_around_tokens(doc):
"""Here, we're building a custom "syntax highlighter" for
part-of-speech tags and dependencies. We put each token in a
span element, with the appropriate classes computed. All whitespace is
preserved, outside of the spans. (Of course, HTML will only display
multiple whitespace if enabled – but the point is, no information is lost
and you can calculate what you need, e.g. &lt;br /&gt;, &lt;p&gt; etc.)
"""
output = []
html = '&lt;span class="{classes}"&gt;{word}&lt;/span&gt;{space}'
for token in doc:
if token.is_space:
output.append(token.text)
else:
classes = 'pos-{} dep-{}'.format(token.pos_, token.dep_)
output.append(html.format(classes=classes, word=token.text, space=token.whitespace_))
string = ''.join(output)
string = string.replace('\n', '')
string = string.replace('\t', ' ')
return '&lt;pre&gt;{}&lt;/pre&gt;'.format(string)
nlp = spacy.load('en_core_web_sm')
doc = nlp(u"This is a test.\n\nHello world.")
html = put_spans_around_tokens(doc)
print(html)
Reference in New Issue View Git Blame Copy Permalink