explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-04-09 19:54:14 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'upstream/master' into web-doc-patches

Browse Source
This commit is contained in:
Pradeep Kumar Tippa 2018-02-08 19:27:33 +05:30
commit 76cee1a1c3
4 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
website/api/matcher.jade
View File

@ -89,7 +89,7 @@ p Match a stream of documents, yielding them in turn.
+aside-code("Example").
from spacy.matcher import Matcher
matcher = Matcher(nlp.vocab)
for doc in matcher.pipe(texts, batch_size=50, n_threads=4):
for doc in matcher.pipe(docs, batch_size=50, n_threads=4):
pass
+table(["Name", "Type", "Description"])

10
website/usage/_linguistic-features/_rule-based-matching.jade
View File

@ -88,8 +88,8 @@ p
+cell The exact verbatim text of a token.
+row
+cell.u-nowrap #[code LOWER], #[code UPPER]
+cell The lowercase, uppercase form of the token text.
+cell.u-nowrap #[code LOWER]
+cell The lowercase form of the token text.
+row
+cell.u-nowrap #[code IS_ALPHA], #[code IS_ASCII], #[code IS_DIGIT]
@ -161,7 +161,7 @@ p
p
| The #[code +] and #[code *] operators are usually interpretted
| "greedily", i.e. longer matches are returned where possible.
| "greedily", i.e. longer matches are returned where possible.
+h(3, "adding-phrase-patterns") Adding phrase patterns
@ -222,8 +222,8 @@ p
doc.ents += ((EVENT, start, end),)
matcher.add('GoogleIO', add_event_ent,
[{'ORTH': 'Google'}, {'UPPER': 'I'}, {'ORTH': '/'}, {'UPPER': 'O'}],
[{'ORTH': 'Google'}, {'UPPER': 'I'}, {'ORTH': '/'}, {'UPPER': 'O'}, {'IS_DIGIT': True}])
[{'ORTH': 'Google'}, {'ORTH': 'I'}, {'ORTH': '/'}, {'ORTH': 'O'}],
[{'ORTH': 'Google'}, {'ORTH': 'I'}, {'ORTH': '/'}, {'ORTH': 'O'}, {'IS_DIGIT': True}])
p
| In addition to mentions of "Google I/O", your data also contains some

2
website/usage/_spacy-101/_lightning-tour.jade
View File

@ -231,7 +231,7 @@ p
def set_sentiment(matcher, doc, i, matches):
doc.sentiment += 0.1
pattern1 = [{'ORTH': 'Google'}, {'UPPER': 'I'}, {'ORTH': '/'}, {'UPPER': 'O'}]
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

2
website/usage/_v2/_migrating.jade
View File

@ -127,7 +127,7 @@ p
| #[+api("pipe") #[code Pipe]], fully trainable and serializable,
| and follow the same API. Instead of updating the model and telling
| spaCy when to #[em stop], you can now explicitly call
| #[+api("language#begin_training") #[code begin_taining]], which
| #[+api("language#begin_training") #[code begin_training]], which
| returns an optimizer you can pass into the
| #[+api("language#update") #[code update]] function. While #[code update]
| still accepts sequences of #[code Doc] and #[code GoldParse] objects,