explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 01:16:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update and fix lightning tour examples

Browse Source
This commit is contained in:
ines 2017-05-25 11:15:56 +02:00
parent 4b5540cc63
commit dcb10da615
1 changed files with 32 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

50
website/docs/usage/lightning-tour.jade
View File

@ -101,15 +101,15 @@ p
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.')
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
| #[strong API:] #[+api("displacy") #[code displacy]]
| #[strong Usage:] #[+a("/docs/usage/visualizers") Visualizers]
+h(2, "examples-word-vectors") Word vectors
+h(2, "examples-word-vectors") Get word vectors and similarity
+tag-model("word vectors")
+code.
@ -119,6 +119,7 @@ p
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
+infobox
| #[strong Usage:] #[+a("/docs/usage/word-vectors-similarities") Word vectors and similarity]
@ -139,6 +140,23 @@ p
+infobox
| #[strong Usage:] #[+a("/docs/usage/saving-loading") Saving and loading]
+h(2, "rule-matcher") Match text with token rules
+code.
import spacy
from spacy.matcher import Matcher
nlp = spacy.load('en')
matcher = Matcher(nlp.vocab)
# match "Google I/O" or "Google i/o"
pattern = [{'ORTH': 'Google'}, {'UPPER': 'I'}, {'ORTH': '/'}, {'UPPER': 'O'}]
matcher.add('GoogleIO', None, pattern)
matches = nlp(LOTS_OF TEXT)
+infobox
| #[strong API:] #[+api("matcher") #[code Matcher]]
| #[strong Usage:] #[+a("/docs/usage/rule-based-matching") Rule-based matching]
+h(2, "multi-threaded") Multi-threaded generator
+code.
@ -183,28 +201,24 @@ 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-inline") Calculate inline mark-up on original string
+h(2, "examples-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. (Yes, I know HTML
won't display it. But the point is no information is lost, so you can
calculate what you need, e.g. <br /> tags, <p> tags, etc.)
'''
"""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. &lt;br /&gt;, &lt;p&gt; etc.)
"""
output = []
template = '<span classes="{classes}">{word}</span>{space}'
html = '&lt;span class="{classes}"&gt;{word}&lt;/span&gt;{space}'
for token in doc:
if token.is_space:
output.append(token.orth_)
output.append(token.text)
else:
output.append(
template.format(
classes=' '.join(get_classes(token)),
word=token.orth_,
space=token.whitespace_))
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', ' ')