mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 17:36:30 +03:00
Rewrite examples in lightning tour
This commit is contained in:
ines
parent
87c976e04c
commit
4b5540cc63
|
|
@ -6,40 +6,138 @@ p
|
|||
| The following examples and code snippets give you an overview of spaCy's
|
||||
| functionality and its usage.
|
||||
|
||||
+h(2, "models") Install and load models
|
||||
+h(2, "models") Install models and process text
|
||||
|
||||
+code(false, "bash").
|
||||
python -m spacy download en
|
||||
python -m spacy download de
|
||||
|
||||
+code.
|
||||
import spacy
|
||||
nlp = spacy.load('en')
|
||||
doc = nlp(u'Hello, world. Here are two sentences.')
|
||||
|
||||
+h(2, "examples-resources") Load resources and process text
|
||||
nlp_de = spacy.load('de')
|
||||
doc_de = nlp_de(u'Ich bin ein Berliner.')
|
||||
|
||||
+infobox
|
||||
| #[strong API:] #[+api("spacy#load") #[code spacy.load()]]
|
||||
| #[strong Usage:] #[+a("/docs/usage/models") Models],
|
||||
| #[+a("/docs/usage/spacy-101") spaCy 101]
|
||||
|
||||
+h(2, "examples-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] == u'outranking eggplant'
|
||||
assert doc.noun_chunks[0].text == u'Peach emoji'
|
||||
|
||||
sentences = list(doc.sents)
|
||||
assert len(sentences) == 3
|
||||
assert sentences[0].text == u'Peach is the superior emoji.'
|
||||
|
||||
+infobox
|
||||
| #[strong API:] #[+api("doc") #[code Doc]], #[+api("token") #[code Token]]
|
||||
| #[strong Usage:] #[+a("/docs/usage/spacy-101") spaCy 101]
|
||||
|
||||
+h(2, "examples-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', 94]
|
||||
assert [apple.tag_, apple.tag] == [u'NNP', 475]
|
||||
assert [apple.shape_, apple.shape] == [u'Xxxxx', 684]
|
||||
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
|
||||
| #[strong API:] #[+api("token") #[code Token]]
|
||||
| #[strong Usage:] #[+a("/docs/usage/pos-tagging") Part-of-speech tagging]
|
||||
|
||||
+h(2, "examples-integer-ids") Use integer IDs for any string
|
||||
|
||||
+code.
|
||||
hello_id = nlp.vocab.strings['Hello']
|
||||
hello_str = nlp.vocab.strings[hello_id]
|
||||
assert token.text == hello_id == 3125
|
||||
assert token.text == hello_str == 'Hello'
|
||||
|
||||
+h(2, "examples-entities") Recongnise and update named entities
|
||||
+tag-model("NER")
|
||||
|
||||
+code.
|
||||
doc = nlp(u'San Francisco considers banning sidewalk delivery robots')
|
||||
ents = [(e.text, e.start_char, e.end_char, e.label_) for e 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 = [(e.start_char, e.end_char, e.label_) for ent in doc.ents]
|
||||
assert ents == [(0, 7, u'ORG')]
|
||||
|
||||
+infobox
|
||||
| #[strong Usage:] #[+a("/docs/usage/entity-recognition") Named entity recognition]
|
||||
|
||||
+h(2, "displacy") Visualize a dependency parse and named entities in your browser
|
||||
+tag-model("dependency parse", "NER")
|
||||
|
||||
+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 '
|
||||
u'Google in 2007, few people outside of the company took him seriously.')
|
||||
displacy.serve(doc_ent, style='ent')
|
||||
|
||||
+infobox
|
||||
| #[strong API:] #[+api("displacy") #[code displacy]]
|
||||
| #[strong Usage:] #[+a("/docs/usage/visualizers") Visualizers]
|
||||
|
||||
+h(2, "examples-word-vectors") Word vectors
|
||||
+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)
|
||||
|
||||
+infobox
|
||||
| #[strong Usage:] #[+a("/docs/usage/word-vectors-similarities") Word vectors and similarity]
|
||||
|
||||
+h(2, "examples-serialization") Simple and efficient serialization
|
||||
|
||||
+code.
|
||||
import spacy
|
||||
en_nlp = spacy.load('en')
|
||||
de_nlp = spacy.load('de')
|
||||
en_doc = en_nlp(u'Hello, world. Here are two sentences.')
|
||||
de_doc = de_nlp(u'ich bin ein Berliner.')
|
||||
from spacy.tokens.doc import Doc
|
||||
|
||||
+h(2, "displacy-dep") Visualize a dependency parse in your browser
|
||||
nlp = spacy.load('en')
|
||||
moby_dick = open('moby_dick.txt', 'r')
|
||||
doc = nlp(moby_dick)
|
||||
doc.to_disk('/moby_dick.bin')
|
||||
|
||||
+code.
|
||||
from spacy import displacy
|
||||
new_doc = Doc().from_disk('/moby_dick.bin')
|
||||
|
||||
doc = nlp(u'This is a sentence.')
|
||||
displacy.serve(doc, style='dep')
|
||||
|
||||
+h(2, "displacy-ent") Visualize named entities in your browser
|
||||
|
||||
+code.
|
||||
from spacy import displacy
|
||||
|
||||
doc = nlp(u'When Sebastian Thrun started working on self-driving cars at '
|
||||
u'Google in 2007, few people outside of the company took him seriously.')
|
||||
displacy.serve(doc, style='ent')
|
||||
+infobox
|
||||
| #[strong Usage:] #[+a("/docs/usage/saving-loading") Saving and loading]
|
||||
|
||||
+h(2, "multi-threaded") Multi-threaded generator
|
||||
|
||||
|
|
@ -52,37 +150,25 @@ p
|
|||
if i == 100:
|
||||
break
|
||||
|
||||
+h(2, "examples-tokens-sentences") Get tokens and sentences
|
||||
+infobox
|
||||
| #[strong API:] #[+api("doc") #[code Doc]]
|
||||
| #[strong Usage:] #[+a("/docs/usage/production-usage") Production usage]
|
||||
|
||||
+h(2, "examples-dependencies") Get syntactic dependencies
|
||||
+tag-model("dependency parse")
|
||||
|
||||
+code.
|
||||
token = doc[0]
|
||||
sentence = next(doc.sents)
|
||||
assert token is sentence[0]
|
||||
assert sentence.text == 'Hello, world.'
|
||||
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
|
||||
|
||||
+h(2, "examples-integer-ids") Use integer IDs for any string
|
||||
|
||||
+code.
|
||||
hello_id = nlp.vocab.strings['Hello']
|
||||
hello_str = nlp.vocab.strings[hello_id]
|
||||
|
||||
assert token.orth == hello_id == 3125
|
||||
assert token.orth_ == hello_str == 'Hello'
|
||||
|
||||
+h(2, "examples-string-views-flags") Get and set string views and flags
|
||||
|
||||
+code.
|
||||
assert token.shape_ == 'Xxxxx'
|
||||
for lexeme in nlp.vocab:
|
||||
if lexeme.is_alpha:
|
||||
lexeme.shape_ = 'W'
|
||||
elif lexeme.is_digit:
|
||||
lexeme.shape_ = 'D'
|
||||
elif lexeme.is_punct:
|
||||
lexeme.shape_ = 'P'
|
||||
else:
|
||||
lexeme.shape_ = 'M'
|
||||
assert token.shape_ == 'W'
|
||||
+infobox
|
||||
| #[strong API:] #[+api("token") #[code Token]]
|
||||
| #[strong Usage:] #[+a("/docs/usage/dependency-parse") Using the dependency parse]
|
||||
|
||||
+h(2, "examples-numpy-arrays") Export to numpy arrays
|
||||
|
||||
|
|
@ -97,70 +183,6 @@ p
|
|||
assert doc[0].like_url == doc_array[0, 1]
|
||||
assert list(doc_array[:, 1]) == [t.like_url for t in doc]
|
||||
|
||||
+h(2, "examples-word-vectors") Word vectors
|
||||
|
||||
+code.
|
||||
doc = nlp("Apples and oranges are similar. Boots and hippos aren't.")
|
||||
|
||||
apples = doc[0]
|
||||
oranges = doc[2]
|
||||
boots = doc[6]
|
||||
hippos = doc[8]
|
||||
|
||||
assert apples.similarity(oranges) > boots.similarity(hippos)
|
||||
|
||||
+h(2, "examples-pos-tags") Part-of-speech tags
|
||||
|
||||
+code.
|
||||
from spacy.parts_of_speech import ADV
|
||||
|
||||
def is_adverb(token):
|
||||
return token.pos == spacy.parts_of_speech.ADV
|
||||
|
||||
# These are data-specific, so no constants are provided. You have to look
|
||||
# up the IDs from the StringStore.
|
||||
NNS = nlp.vocab.strings['NNS']
|
||||
NNPS = nlp.vocab.strings['NNPS']
|
||||
def is_plural_noun(token):
|
||||
return token.tag == NNS or token.tag == NNPS
|
||||
|
||||
def print_coarse_pos(token):
|
||||
print(token.pos_)
|
||||
|
||||
def print_fine_pos(token):
|
||||
print(token.tag_)
|
||||
|
||||
+h(2, "examples-dependencies") Syntactic dependencies
|
||||
|
||||
+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
|
||||
|
||||
+h(2, "examples-entities") Named entities
|
||||
|
||||
+code.
|
||||
def iter_products(docs):
|
||||
for doc in docs:
|
||||
for ent in doc.ents:
|
||||
if ent.label_ == 'PRODUCT':
|
||||
yield ent
|
||||
|
||||
def word_is_in_entity(word):
|
||||
return word.ent_type != 0
|
||||
|
||||
def count_parent_verb_by_person(docs):
|
||||
counts = defaultdict(lambda: defaultdict(int))
|
||||
for doc in docs:
|
||||
for ent in doc.ents:
|
||||
if ent.label_ == 'PERSON' and ent.root.head.pos == VERB:
|
||||
counts[ent.orth_][ent.root.head.lemma_] += 1
|
||||
return counts
|
||||
|
||||
+h(2, "examples-inline") Calculate inline mark-up on original string
|
||||
|
||||
+code.
|
||||
|
|
@ -187,17 +209,3 @@ p
|
|||
string = string.replace('\n', '')
|
||||
string = string.replace('\t', ' ')
|
||||
return string
|
||||
|
||||
+h(2, "examples-binary") Efficient binary serialization
|
||||
|
||||
+code.
|
||||
import spacy
|
||||
from spacy.tokens.doc import Doc
|
||||
|
||||
byte_string = doc.to_bytes()
|
||||
open('moby_dick.bin', 'wb').write(byte_string)
|
||||
|
||||
nlp = spacy.load('en')
|
||||
for byte_string in Doc.read_bytes(open('moby_dick.bin', 'rb')):
|
||||
doc = Doc(nlp.vocab)
|
||||
doc.from_bytes(byte_string)
|
||||
|
|
|
|||
Loading…
Reference in New Issue
Block a user