spaCy/docs/redesign/docs.jade
2015-08-12 22:49:57 +02:00

706 lines
22 KiB
Plaintext

- var py_docs = '<a class="reference" href="http://docs.python.org/library/'
-
var types = {
'unicode': py_docs + 'functions.html#unicode"><em>unicode</em></a>',
'bool': py_docs + 'functions.html#bool"><em>bool</em></a>',
'int': py_docs + 'functions.html#int"><em>int</em></a>',
'generator': "",
'Vocab': "",
'Span': "",
'Doc': ""
}
mixin declare_class(name)
details
summary
span.declaration
span.label class
code #{name}
block
mixin method(name, parameters)
details(open=attributes.open)
summary
span.declaration
span.label #{name}
span.parameters
| self, #{parameters}
block
mixin params
ul
block
mixin param(name, type, value)
li
if type
<strong>#{name}</strong> (!{type}) &#8211;
else
<strong>#{name}</strong> &#8211;
block
mixin attribute(name, type, value)
details(open=attributes.open)
summary
span.declaration
span.label #{name}
block
mixin returns(name, type, value)
li
if type
<strong>#{name}</strong> (!{type}) &#8211;
else
<strong>#{name}</strong> &#8211;
block
mixin returns(type)
| tmp
mixin init
details
summary: h4 Init
block
mixin callable
details
summary: h4 Callable
block
mixin sequence
details
summary: h4 Sequence
block
mixin maptype
details
summary: h4 Map
block
mixin summary
block
mixin en_example
pre.language-python
code
| from spacy.en import English
| from spacy._doc_examples import download_war_and_peace
|
| unprocessed_unicode = download_war_and_peace()
|
| nlp = English()
| doc = nlp(unprocessed_unicode)
doctype html
html(lang="en")
head
meta(charset="utf-8")
title spaCy &ndash; Industrial-strength NLP
meta(name="description" content="")
meta(name="author" content="Matthew Honnibal")
link(rel="stylesheet" href="css/style.css")
<!--[if lt IE 9]>
script(src="http://html5shiv.googlecode.com/svn/trunk/html5.js")
<![endif]-->
body(id="docs")
header(role="banner")
h1.logo spaCy &ndash; Industrial-strength NLP
div.slogan API
nav(role="navigation")
ul
li: a(href="#") Home
li.active: a(href="#") Docs
li: a(href="#") License
li: a(href="#") Blog
main.docs#content
article
+declare_class("English")
p Load models into a callable object to process English text.
+summary
+en_example
+init
p
| Load the resources. Loading takes 20 seconds, and the instance
| consumes 2 to 3 gigabytes of memory.
p
| Intended use is for one instance to be created per process.
| You can create more if you're doing something unusual.
p
| You may wish to make the instance a global variable or "singleton".
| We usually instantiate the object in the <code>main()</code>
| function and pass it around as an explicit argument.
+method("__init__", "data_dir=True, Tagger=True, Parser=True, Entity=True, Matcher=True, Packer=None, load_vectors=True")(open="true")
+params
+param("data_dir")
| The data directory. May be #{None}, to disable any data loading
| (including the vocabulary).
+param("Tokenizer")
| A class/function that creates the tokenizer.
+param("Tagger")
| A class/function that creates the part-of-speech tagger.
+param("Parser")
| A class/function that creates the dependency parser.
+param("Entity")
| A class/function that creates the named entity recogniser.
+param("load_vectors")
| A boolean value to control whether the word vectors are loaded.
+callable
+method("__call__", "text, tag=True, parse=True, entity=True")
+params
+param("text", types.unicode)
| The text to be processed. No pre-processing needs to be applied,
| and any length of text can be submitted. Usually you will submit
| a whole document. Text may be zero-length. An exception is raised
| if byte strings are supplied.
+param("tag", bool_type)
| Whether to apply the part-of-speech tagger. Required for parsing
| and entity recognition.
+param("parse", bool_type)
| Whether to apply the syntactic dependency parser.
+param("entity", bool_type)
| Whether to apply the named entity recognizer.
pre.language-python
code
| from spacy.en import English
| nlp = English()
| doc = nlp(u'Some text.) # Applies tagger, parser, entity
| doc = nlp(u'Some text.', parse=False) # Applies tagger and entity, not parser
| doc = nlp(u'Some text.', entity=False) # Applies tagger and parser, not entity
| doc = nlp(u'Some text.', tag=False) # Does not apply tagger, entity or parser
| doc = nlp(u'') # Zero-length tokens, not an error
| # doc = nlp(b'Some text') <-- Error: need unicode
| doc = nlp(b'Some text'.decode('utf8')) # Encode to unicode first.
+declare_class("Doc")
p I'm a doc
+init
+method("__init__", "vocab")
+params
+param("vocab", vocab_type)
| A vocabulary object
+sequence
+method("__getitem__", "i", types.int)
+returns(types.Token)
+method("__getitem__", "start_end", types.slice)
+returns(types.Span)
+method("__iter__")
| Iterate over tokens
+method("__len__")
| Number of tokens in the document.
details
summary: h4 Spans
+attribute("sents", types.generator)
| Iterate over sentences in the document.
+attribute("ents", types.generator)
| Iterate over named entities in the document.
+attribute("noun_chunks", types.generator)
details
summary: h4 Export/Import
+method("to_array", "attr_ids")
| Given a list of M attribute IDs, export the tokens to a numpy ndarray
| of shape N*M, where N is the length of the sentence.
+params
+param("attr_ids", "list[int]")
| A list of attribute ID ints.
+returns("feat_array")
| A feature matrix, with one row per word, and one column per attribute
| indicated in the input attr_ids.
+method("count_by", "attr_id")
| Produce a dict of {attribute (int): count (ints)} frequencies, keyed
| by the values of the given attribute ID.
pre.language-python
code
| >>> from spacy.en import English, attrs
| >>> nlp = English()
| >>> tokens = nlp(u'apple apple orange banana')
| >>> tokens.count_by(attrs.ORTH)
| {12800L: 1, 11880L: 2, 7561L: 1}
| >>> tokens.to_array([attrs.ORTH])
| array([[11880],
| [11880],
| [7561],
| [12800]])
+method("from_array", "attrs, array")
| Load from array
+method("from_bytes")
| Deserialize, loading from bytes
+method("read_bytes")
| classmethod
//+method("merge", "int start_idx, int end_idx, unicode tag, unicode lemma, unicode ent_type")
// | Merge a multi-word expression into a single token. Currently
// | experimental; API is likely to change.
+declare_class("Token")
+init
+method("__init__", "vocab, doc, offset")
+params
+param("vocab", types.Vocab)
p A Vocab object
+param("doc", types.Doc)
p The parent sequence
+param("offset", types.int)
p The index of the token within the document
details
summary: h4 String Views
+attribute("orth / orth_")
| The form of the word with no string normalization or processing, as
| it appears in the string, without trailing whitespace.
+attribute("lemma / lemma_")
| The "base" of the word, with no inflectional suffixes, e.g. the lemma of
| "developing" is "develop", the lemma of "geese" is "goose", etc. Note that
| <em>derivational</em> suffixes are not stripped, e.g. the lemma of
| "instutitions" is "institution", not "institute". Lemmatization is
| performed using the WordNet data, but extended to also cover closed-class
| words such as pronouns. By default, the WN lemmatizer returns "hi"
| as the lemma of "his". We assign pronouns the lemma -PRON-.
+attribute("lower / lower_")
| The form of the word, but forced to lower-case, i.e.
pre.language-python: code lower = word.orth\_.lower()
//+attribute("norm / norm_")
// | The form of the word, after language-specific normalizations has been
// | applied.
+attribute("shape / shape_")
| A transform of the word's string, to show orthographic features.
| The characters a-z are mapped to x, A-Z is mapped to X, 0-9 is mapped
| to d. After these mappings, sequences of 4 or more of the same character
| are truncated to length 4. Examples: C3Po --> XdXx, favorite --> xxxx,
| :) --> :)
+attribute("prefix / prefix_")
| A length-N substring from the start of the word. Length may vary by
| language; currently for English n=1, i.e.
pre.language-python: code prefix = word.orth\_[:1]
+attribute("suffix / suffix_")
| A length-N substring from the end of the word. Length may vary by
| language; currently for English n=3, i.e.
pre.language-python: code suffix = word.orth\_[-3:]
//+attribute("lex_id")
// | lex_id
details
summary: h4 Alignment and Output
+attribute("idx")
p Start index of the token in the string
+method("__len__", "")
p Length of the token's orth string, in unicode code-points.
+method("__unicode__", "")
p Same as token.orth_
+method("__str__", "")
p Varies between Python 2 and Python 3
+attribute("string")
p
| The form of the word as it appears in the string, <strong>including
| trailing whitespace</strong>. This is useful when you need to use
| linguistic features to add inline mark-up to the string.
+method("nbor, i=1")
+params
+param("i")
p Offset relative to token
details
summary: h4 Distributional Features
+attribute("repvec")
p
| A "word embedding" representation: a dense real-valued vector that supports
| similarity queries between words. By default, spaCy currently loads
| vectors produced by the Levy and Goldberg (2014) dependency-based word2vec
| model.
+attribute("cluster")
p
| The Brown cluster ID of the word. These are often useful features for
| linear models. If you're using a non-linear model, particularly a
| neural net or random forest, consider using the real-valued word
| representation vector, in Token.repvec, instead.
+attribute("prob")
p
| The unigram log-probability of the word, estimated from counts from a
| large corpus, smoothed using Simple Good Turing estimation.
details
summary: h4 Syntactic Tags
+attribute("pos / pos_")
p
| A part-of-speech tag, from the Google Universal Tag Set, e.g.
| code>NOUN</code>, <code>VERB</code>, <code>ADV</code>. Constants for
| the 17 tag values are provided in <code>spacy.parts_of_speech.</code>
+attribute("tag / tag_")
p
| A morphosyntactic tag, e.g. <code>NN</code>, <code>VBZ</code>,
| <code>DT</code>, etc. These tags are language/corpus specific, and
| typically describe part-of-speech and some amount of morphological
| information. For instance, in the Penn Treebank tag set, <code>VBZ</code>
| is assigned to a present-tense singular verb.
+attribute("dep / dep_")
p
| The type of syntactic dependency relation between the word and its
| syntactic head.
details
summary: h4 Navigating the Parse Tree
+attribute("head")
p
| The Token that is the immediate syntactic head of the word. If the
| word is the root of the dependency tree, the same word is returned.
+attribute("lefts")
p
| An iterator for the immediate leftward syntactic children of the
| word.
+attribute("rights")
p
| An iterator for the immediate rightward syntactic children of the
| word.
+attribute("n_lefts")
p
| The number of immediate syntactic children preceding the word in
| the string.
+attribute("n_rights")
p
| The number of immediate syntactic children following the word in
| the string.
+attribute("children")
p
| An iterator that yields from lefts, and then yields from rights.
+attribute("subtree")
p
| An iterator for the part of the sentence syntactically governed by
| the word, including the word itself.
+attribute("left_edge")
p The leftmost edge of the token's subtree
+attribute("right_edge")
p The rightmost edge of the token's subtree
details
summary: h4 Named Entities
+attribute("ent_type")
p If the token is part of an entity, its entity type.
+attribute("ent_iob")
p The IOB (inside, outside, begin) entity recognition tag for the token.
details
summary: h4 Lexeme Flags
+method("check_flag", "flag_id")
+params
+param("flag_id")
| flag ID
+attribute("is_oov")
+attribute("is_alpha")
+attribute("is_ascii")
+attribute("is_digit")
+attribute("is_lower")
+attribute("is_title")
+attribute("is_punct")
+attribute("is_space")
+attribute("like_url")
+attribute("like_num")
+attribute("like_email")
//+attribute("conjuncts")
// | Conjuncts
+declare_class("Span")
+init
+method("__init__")
Temp
<code>span = doc[0:4]</code>
+sequence
+method("__getitem__")
p Get item
+method("__iter__")
p Iter
+method("__len__")
p Len
details
summary: h4 Parse
+attribute("root")
p Syntactic head
+attribute("lefts")
p Tokens that are:
ol
li To the left of the span;
li Syntactic children of words within the span
p i.e.
pre.language-python
code
| lefts = [span.doc[i] for i in range(0, span.start)
| if span.doc[i].head in span]
+attribute("rights")
p Tokens that are:
ol
li To the right of the span;
li Syntactic children of words within the span
p i.e.
pre.language-python
code
| rights = [span.doc[i] for i in range(span.end, len(span.doc))
| if span.doc[i].head in span]
+attribute("subtree")
p String
details
summary: h4 String Views
+attribute("string")
p String
+attribute("lemma / lemma_")
p String
+attribute("label / label_")
p String
+declare_class("Lexeme")
p
| The Lexeme object represents a lexical type, stored in the vocabulary
| &ndash; as opposed to a token, occurring in a document.
p
| Lexemes store various features, so that these features can be computed
| once per type, rather than once per token. As job sizes grow, this
| can amount to a substantial efficiency improvement.
p
| All Lexeme attributes are therefore context independent, as a single
| lexeme is reused for all usages of that word. Lexemes are keyed by
| the “orth” attribute.
p
All Lexeme attributes are accessible directly on the Token object.
+init
+method("__init__")
p Init
details
summary: h4 String Features
+attribute("orth / orth_")
p
| The form of the word with no string normalization or processing,
| as it appears in the string, without trailing whitespace.
+attribute("lower / lower_")
p Tmp
+attribute("norm / norm_")
p Tmp
+attribute("shape / shape_")
p Tmp
+attribute("prefix / prefix_")
p Tmp
+attribute("suffix / suffix_")
p TMP
+declare_class("Vocab", "data_dir=None, lex_props_getter=None")
+sequence
+method("__len__")
+returns
p Number of words in the vocabulary.
+method("__iter__")
+returns
p Lexeme
+maptype
+method("__getitem__", "key_int")
+params
+param("key")
p Integer ID
+returns: p A Lexeme object
+method("__getitem__", "key_str")
+params
+param("key_str", types.unicode)
p A string in the vocabulary
+returns("Lexeme")
+method("__setitem__", "orth_str", "props")
+params
+param("orth_str", types.unicode)
p The orth key
+param("props", types.dict)
p A props dictionary
+returns("None")
details
summary: h4 Import/Export
+method("dump", "loc")
+params
+param("loc", types.unicode)
p Path where the vocabulary should be saved
+method("load_lexemes", "loc")
+params
+param("loc", types.unicode)
p Path to load the lexemes.bin file from
+method("load_vectors", "loc")
+params
+param("loc", types.unicode)
p Path to load the vectors.bin from
+declare_class("StringStore")
+init
Tmp
+sequence
+method("__len__")
+returns("int")
p Number of strings in the string-store
+method("__iter__")
+returns
p Lexeme
+maptype
+method("__getitem__", "key_int")
+params
+param("key_int")
p An integer key
+returns(types.unicode)
p The string that the integer key maps to
+method("__getitem__", "key_unicode")
+params
+param("key_unicode")
p A key, as a unicode string
+returns(types.int)
p The integer ID of the string.
+method("__getitem__", "key_utf8_bytes")
+params
+param("key_utf8_bytes", types.bytes)
p p A key, as a UTF-8 encoded byte-string
+returns(types.int)
p The integer ID of the string.
details
summary: h4 Import/Export
+method("dump", "loc")
+params
+param("loc")
p File path to save the strings.txt to.
+method("load")
+params
+param("loc")
p File path to load the strings.txt from.
script(src="js/prism.js")