explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 17:36:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Port over docs changes [ci skip]

Browse Source
This commit is contained in:
ines 2018-03-24 17:12:48 +01:00
parent 74cc6bb06a
commit 53680642af
13 changed files with 67 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
website/api/_top-level/_displacy.jade
View File

@ -208,7 +208,7 @@ p
+row
+cell #[code word_spacing]
+cell int
+cell Horizontal spacing between words and arcs in px.
+cell Vertical spacing between words and arcs in px.
+cell #[code 45]
+row

2
website/api/doc.jade
View File

@ -674,7 +674,7 @@ p
| token vectors.
+aside-code("Example").
apples = nlp(u'I like apples')
doc = nlp(u'I like apples')
assert doc.vector.dtype == 'float32'
assert doc.vector.shape == (300,)

25
website/api/goldcorpus.jade
View File

@ -12,11 +12,24 @@ p Create a #[code GoldCorpus].
+table(["Name", "Type", "Description"])
+row
+cell #[code train_path]
+cell unicode or #[code Path]
+cell File or directory of training data.
+cell #[code train]
+cell unicode or #[code Path] or iterable
+cell
| Training data, as a path (file or directory) or iterable. If an
| iterable, each item should be a #[code (text, paragraphs)]
| tuple, where each paragraph is a tuple
| #[code.u-break (sentences, brackets)],and each sentence is a
| tuple #[code.u-break (ids, words, tags, heads, ner)]. See the
| implementation of
| #[+src(gh("spacy", "spacy/gold.pyx")) #[code gold.read_json_file]]
| for further details.
+row
+cell #[code dev_path]
+cell unicode or #[code Path]
+cell File or directory of development data.
+cell #[code dev]
+cell unicode or #[code Path] or iterable
+cell Development data, as a path (file or directory) or iterable.
+row("foot")
+cell returns
+cell #[code GoldCorpus]
+cell The newly constructed object.

6
website/api/lexeme.jade
View File

@ -325,6 +325,12 @@ p The L2 norm of the lexeme's vector representation.
+cell bool
+cell Is the lexeme a quotation mark?
+row
+cell #[code is_currency]
+tag-new("2.0.8")
+cell bool
+cell Is the lexeme a currency symbol?
+row
+cell #[code like_url]
+cell bool

19
website/api/matcher.jade
View File

@ -111,6 +111,25 @@ p Match a stream of documents, yielding them in turn.
| parallel, if the #[code Matcher] implementation supports
| multi-threading.
+row
+cell #[code return_matches]
+tag-new(2.1)
+cell bool
+cell
| Yield the match lists along with the docs, making results
| #[code (doc, matches)] tuples.
+row
+cell #[code as_tuples]
+tag-new(2.1)
+cell bool
+cell
| Interpret the input stream as #[code (doc, context)] tuples, and
| yield #[code (result, context)] tuples out. If both
| #[code return_matches] and #[code as_tuples] are #[code True],
| the output will be a sequence of
| #[code ((doc, matches), context)] tuples.
+row("foot")
+cell yields
+cell #[code Doc]

2
website/api/pipe.jade
View File

@ -209,7 +209,7 @@ p
+row
+cell #[code drop]
+cell int
+cell float
+cell The dropout rate.
+row

6
website/api/token.jade
View File

@ -740,6 +740,12 @@ p The L2 norm of the token's vector representation.
+cell bool
+cell Is the token a quotation mark?
+row
+cell #[code is_currency]
+tag-new("2.0.8")
+cell bool
+cell Is the token a currency symbol?
+row
+cell #[code like_url]
+cell bool

BIN
website/assets/img/social/preview_alpha.jpg
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 378 KiB

16
website/models/_data.json
View File

@ -76,13 +76,15 @@
},
"MODEL_LICENSES": {
"CC BY-SA": "https://creativecommons.org/licenses/by-sa/3.0/",
"CC BY-SA 3.0": "https://creativecommons.org/licenses/by-sa/3.0/",
"CC BY-SA 4.0": "https://creativecommons.org/licenses/by-sa/4.0/",
"CC BY-NC": "https://creativecommons.org/licenses/by-nc/3.0/",
"CC BY-NC 3.0": "https://creativecommons.org/licenses/by-nc/3.0/",
"GPL": "https://www.gnu.org/licenses/gpl.html",
"LGPL": "https://www.gnu.org/licenses/lgpl.html"
"CC BY 4.0": "https://creativecommons.org/licenses/by/4.0/",
"CC BY-SA": "https://creativecommons.org/licenses/by-sa/3.0/",
"CC BY-SA 3.0": "https://creativecommons.org/licenses/by-sa/3.0/",
"CC BY-SA 4.0": "https://creativecommons.org/licenses/by-sa/4.0/",
"CC BY-NC": "https://creativecommons.org/licenses/by-nc/3.0/",
"CC BY-NC 3.0": "https://creativecommons.org/licenses/by-nc/3.0/",
"CC-BY-NC-SA 3.0": "https://creativecommons.org/licenses/by-nc-sa/3.0/",
"GPL": "https://www.gnu.org/licenses/gpl.html",
"LGPL": "https://www.gnu.org/licenses/lgpl.html"
},
"MODEL_BENCHMARKS": {

4
website/usage/_processing-pipelines/_pipelines.jade
View File

@ -40,7 +40,7 @@ p
+item
| Make the #[strong model data] available to the #[code Language] class
| by calling #[+api("language#from_disk") #[code from_disk]] with the
| path to the model data ditectory.
| path to the model data directory.
p
| So when you call this...
@ -53,7 +53,7 @@ p
| pipeline #[code.u-break ["tagger", "parser", "ner"]]. spaCy will then
| initialise #[code spacy.lang.en.English], and create each pipeline
| component and add it to the processing pipeline. It'll then load in the
| model's data from its data ditectory and return the modified
| model's data from its data directory and return the modified
| #[code Language] class for you to use as the #[code nlp] object.
p

2
website/usage/_spacy-101/_similarity.jade
View File

@ -37,7 +37,7 @@ p
+cell.u-text-label.u-color-theme=label
for cell in cells
+cell.u-text-center
- var result = cell > 0.5 ? ["yes", "similar"] : cell != 1 ? ["no", "dissimilar"] : ["neutral", "identical"]
- var result = cell < 0.5 ? ["no", "dissimilar"] : cell != 1 ? ["yes", "similar"] : ["neutral", "identical"]
| #[code=cell.toFixed(2)] #[+procon(...result)]
p

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

@ -163,7 +163,7 @@ p
nlp = English().from_disk('/path/to/nlp')
p
| spay's serialization API has been made consistent across classes and
| spaCy's serialization API has been made consistent across classes and
| objects. All container classes, i.e. #[code Language], #[code Doc],
| #[code Vocab] and #[code StringStore] now have a #[code to_bytes()],
| #[code from_bytes()], #[code to_disk()] and #[code from_disk()] method

2
website/usage/spacy-101.jade
View File

@ -68,7 +68,7 @@ p
+item #[strong spaCy is not research software].
| It's built on the latest research, but it's designed to get
| things done. This leads to fairly different design decisions than
| #[+a("https://github./nltk/nltk") NLTK]
| #[+a("https://github.com/nltk/nltk") NLTK]
| or #[+a("https://stanfordnlp.github.io/CoreNLP/") CoreNLP], which were
| created as platforms for teaching and research. The main difference
| is that spaCy is integrated and opinionated. spaCy tries to avoid asking