explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-12 18:26:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update What's new in v2 docs

Browse Source
This commit is contained in:
ines 2017-05-23 23:18:53 +02:00
parent b6209e2427
commit b6c62baab3
1 changed files with 31 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
website/docs/usage/v2.jade
View File

@ -55,7 +55,23 @@ p
| #[strong API:] #[+api("spacy#load") #[code spacy.load]] | #[strong API:] #[+api("spacy#load") #[code spacy.load]]
| #[strong Usage:] #[+a("/docs/usage/saving-loading") Saving and loading] | #[strong Usage:] #[+a("/docs/usage/saving-loading") Saving and loading]
+h(3, "features-language") Improved language data and processing pipelines +h(3, "features-language") Improved language data and lazy loading
p
| Language-specfic data now lives in its own submodule, #[code spacy.lang].
| Languages are lazy-loaded, i.e. only loaded when you import a
| #[code Language] class, or load a model that initialises one. This allows
| languages to contain more custom data, e.g. lemmatizer lookup tables, or
| complex regular expressions. The language data has also been tidied up
| and simplified. It's now also possible to overwrite the functions that
| compute lexical attributes like #[code like_num], and supply
| language-specific syntax iterators, e.g. to determine noun chunks.
+infobox
| #[strong Code:] #[+src(gh("spaCy", "spacy/lang")) spacy/lang]
| #[strong Usage:] #[+a("/docs/usage/adding-languages") Adding languages]
+h(3, "features-pipelines") Improved processing pipelines
+aside-code("Example"). +aside-code("Example").
from spacy.language import Language from spacy.language import Language
@ -64,7 +80,7 @@ p
+infobox +infobox
| #[strong API:] #[+api("language") #[code Language]] | #[strong API:] #[+api("language") #[code Language]]
| #[strong Usage:] #[+a("/docs/usage/adding-languages") Adding languages] | #[strong Usage:] #[+a("/docs/usage/processing-text") Processing text]
+h(3, "features-lemmatizer") Simple lookup-based lemmatization +h(3, "features-lemmatizer") Simple lookup-based lemmatization
@ -95,7 +111,7 @@ p
from spacy.matcher import Matcher from spacy.matcher import Matcher
from spacy.attrs import LOWER, IS_PUNCT from spacy.attrs import LOWER, IS_PUNCT
matcher = Matcher(nlp.vocab) matcher = Matcher(nlp.vocab)
matcher.add('HelloWorld', on_match=None, matcher.add('HelloWorld', None,
[{LOWER: 'hello'}, {IS_PUNCT: True}, {LOWER: 'world'}], [{LOWER: 'hello'}, {IS_PUNCT: True}, {LOWER: 'world'}],
[{LOWER: 'hello'}, {LOWER: 'world'}]) [{LOWER: 'hello'}, {LOWER: 'world'}])
assert len(matcher) == 1 assert len(matcher) == 1
@ -128,6 +144,18 @@ p
+h(2, "incompat") Backwards incompatibilities +h(2, "incompat") Backwards incompatibilities
+table(["Old", "New"]) +table(["Old", "New"])
+row
+cell
| #[code spacy.en]
| #[code spacy.xx]
+cell
| #[code spacy.lang.en]
| #[code spacy.lang.xx]
+row
+cell #[code spacy.orth]
+cell #[code spacy.lang.xx.lex_attrs]
+row +row
+cell #[code Language.save_to_directory] +cell #[code Language.save_to_directory]
+cell #[+api("language#to_disk") #[code Language.to_disk]] +cell #[+api("language#to_disk") #[code Language.to_disk]]