From 83a7e91f3c9540df6642f52a70656026ef2cc822 Mon Sep 17 00:00:00 2001 From: Matthew Honnibal Date: Sat, 24 Jan 2015 20:49:44 +1100 Subject: [PATCH] * Edt API docs --- docs/source/api.rst | 151 ++++++++++++-------------------------------- 1 file changed, 42 insertions(+), 109 deletions(-) diff --git a/docs/source/api.rst b/docs/source/api.rst index be09146ef..b68ca66b7 100644 --- a/docs/source/api.rst +++ b/docs/source/api.rst @@ -2,27 +2,28 @@ Documentation =============== -Quick Ref ---------- -.. class:: spacy.en.__init__.English(self, data_dir=join(dirname(__file__, 'data'))) + +.. py:currentmodule:: spacy + +.. class:: en.English(self, data_dir=join(dirname(__file__, 'data'))) :noindex: .. method:: __call__(self, unicode text, tag=True, parse=False) --> Tokens - +-----------+--------------+--------------+ - | Attribute | Type | Useful | - +===========+==============+==============+ - | strings | StingStore | __getitem__ | - +-----------+--------------+--------------+ - | vocab | Vocab | __getitem__ | - +-----------+--------------+--------------+ - | tokenizer | Tokenizer | __call__ | - +-----------+--------------+--------------+ - | tagger | EnPosTagger | __call__ | - +-----------+--------------+--------------+ - | parser | GreedyParser | __call__ | - +-----------+--------------+--------------+ + +-----------+----------------------------------------+-------------+--------------------------+ + | Attribute | Type | Attr API | NoteS | + +===========+========================================+=============+==========================+ + | strings | :py:class:`strings.StringStore` | __getitem__ | string <-> int mapping | + +-----------+----------------------------------------+-------------+--------------------------+ + | vocab | :py:class:`vocab.Vocab` | __getitem__ | Look up Lexeme object | + +-----------+----------------------------------------+-------------+--------------------------+ + | tokenizer | :py:class:`tokenizer.Tokenizer` | __call__ | Get Tokens given unicode | + +-----------+----------------------------------------+-------------+--------------------------+ + | tagger | :py:class:`en.pos.EnPosTagger` | __call__ | Set POS tags on Tokens | + +-----------+----------------------------------------+-------------+--------------------------+ + | parser | :py:class:`syntax.parser.GreedyParser` | __call__ | Set parse on Tokens | + +-----------+----------------------------------------+-------------+--------------------------+ .. py:class:: spacy.tokens.Tokens(self, vocab: Vocab, string_length=0) @@ -58,32 +59,30 @@ Quick Ref .. py:attribute:: head: Token - .. py:method:: check_flag(self, attr_id: int) --> bool - - +-----------+------+-----------+---------+-----------+-------+ - | Attribute | Type | Attribute | Type | Attribute | Type | - +===========+======+===========+=========+===========+=======+ - | sic | int | sic_ | unicode | idx | int | - +-----------+------+-----------+---------+-----------+-------+ - | lemma | int | lemma_ | unicode | cluster | int | - +-----------+------+-----------+---------+-----------+-------+ - | norm1 | int | norm1_ | unicode | length | int | - +-----------+------+-----------+---------+-----------+-------+ - | norm2 | int | norm2_ | unicode | prob | float | - +-----------+------+-----------+---------+-----------+-------+ - | shape | int | shape_ | unicode | sentiment | float | - +-----------+------+-----------+---------+-----------+-------+ - | prefix | int | prefix_ | unicode | | - +-----------+------+-----------+---------+-------------------+ - | suffix | int | suffix_ | unicode | | - +-----------+------+-----------+---------+-------------------+ - | pos | int | pos_ | unicode | | - +-----------+------+-----------+---------+-------------------+ - | fine_pos | int | fine_pos_ | unicode | | - +-----------+------+-----------+---------+-------------------+ - | dep_tag | int | dep_tag_ | unicode | | - +-----------+------+-----------+---------+-------------------+ + +-----------+------+-----------+---------+-----------+------------------------------------+ + | Attribute | Type | Attribute | Type | Attribute | Type | + +===========+======+===========+=========+===========+====================================+ + | orth | int | orth\_ | unicode | idx | int | + +-----------+------+-----------+---------+-----------+------------------------------------+ + | lemma | int | lemma\_ | unicode | cluster | int | + +-----------+------+-----------+---------+-----------+------------------------------------+ + | lower | int | lower\_ | unicode | length | int | + +-----------+------+-----------+---------+-----------+------------------------------------+ + | norm | int | norm\_ | unicode | prob | float | + +-----------+------+-----------+---------+-----------+------------------------------------+ + | shape | int | shape\_ | unicode | repvec | ndarray(shape=(300,), dtype=float) | + +-----------+------+-----------+---------+-----------+------------------------------------+ + | prefix | int | prefix\_ | unicode | | + +-----------+------+-----------+---------+------------------------------------------------+ + | suffix | int | suffix\_ | unicode | | + +-----------+------+-----------+---------+------------------------------------------------+ + | pos | int | pos\_ | unicode | | + +-----------+------+-----------+---------+------------------------------------------------+ + | tag | int | tag\_ | unicode | | + +-----------+------+-----------+---------+------------------------------------------------+ + | dep | int | dep\_ | unicode | | + +-----------+------+-----------+---------+------------------------------------------------+ .. py:class:: spacy.vocab.Vocab(self, data_dir=None, lex_props_getter=None) @@ -94,7 +93,7 @@ Quick Ref .. py:method:: __getitem__(self, string: unicode) --> int - .. py:method:: __setitem__(self, py_str: unicode, props: Dict[str, int|float]) --> None + .. py:method:: __setitem__(self, py_str: unicode, props: Dict[str, int[float]) --> None .. py:method:: dump(self, loc: unicode) --> None @@ -108,7 +107,7 @@ Quick Ref .. py:method:: __getitem__(self, id: int) --> unicode - .. py:method:: __getitem__(self, string: byts) --> id + .. py:method:: __getitem__(self, string: bytes) --> id .. py:method:: __getitem__(self, string: unicode) --> id @@ -137,69 +136,3 @@ Quick Ref .. py:method:: __call__(self, tokens: spacy.tokens.Tokens) --> None .. py:method:: train(self, spacy.tokens.Tokens) --> None - - - -spaCy is designed to easily extend to multiple languages, although presently -only English components are implemented. The components are organised into -a pipeline in the spacy.en.English class. - -Usually, you will only want to create one spacy.en.English object, and pass it -around your application. It manages the string-to-integers mapping, and you -will usually want only a single mapping for all strings. - -English Pipeline ----------------- - -The spacy.en package exports a single class, English, and several constants, -under spacy.en.defs. - -.. autoclass:: spacy.en.English - :members: - -.. autommodule:: spacy.en.pos - :members: - -.. automodule:: spacy.en.attrs - :members: - :undoc-members: - - -Tokens ------- - -.. autoclass:: spacy.tokens.Tokens - :members: - -.. autoclass:: spacy.tokens.Token - :members: - -.. autoclass:: spacy.lexeme.Lexeme - :members: - -Lexicon -------- - -.. automodule:: spacy.vocab - :members: - -.. automodule:: spacy.strings - :members: - -Tokenizer ---------- - -.. automodule:: spacy.tokenizer - :members: - -Parser ------- - -.. automodule:: spacy.syntax.parser - :members: - -Utility Functions ------------------ - -.. automodule:: spacy.orth - :members: