mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-10 19:57:17 +03:00
* Improving docs
This commit is contained in:
Matthew Honnibal
parent
cab7f63fc2
commit
cbda38e2d9
|
|
@ -1,5 +1,45 @@
|
|||
Python API
|
||||
==========
|
||||
|
||||
Cheat Sheet
|
||||
-----------
|
||||
.. py:currentmodule:: spacy.en
|
||||
|
||||
To and from unicode strings
|
||||
---------------------------
|
||||
|
||||
.. autofunction:: tokenize
|
||||
.. autofunction:: lookup
|
||||
.. autofunction:: unhash
|
||||
|
||||
Access (Hashed) String Views
|
||||
----------------------------
|
||||
|
||||
.. autofunction:: lex_of
|
||||
.. autofunction:: norm_of
|
||||
.. autofunction:: shape_of
|
||||
.. autofunction:: last3_of
|
||||
|
||||
Access String Properties
|
||||
------------------------
|
||||
|
||||
.. autofunction:: length_of
|
||||
.. autofunction:: first_of
|
||||
|
||||
Check Orthographic Flags
|
||||
-------------------------
|
||||
|
||||
.. autofunction:: is_alpha
|
||||
.. autofunction:: is_digit
|
||||
.. autofunction:: is_punct
|
||||
.. autofunction:: is_space
|
||||
.. autofunction:: is_lower
|
||||
.. autofunction:: is_upper
|
||||
.. autofunction:: is_title
|
||||
.. autofunction:: is_ascii
|
||||
|
||||
Access Distributional Information
|
||||
---------------------------------
|
||||
|
||||
.. autofunction:: prob_of
|
||||
.. autofunction:: cluster_of
|
||||
.. autofunction:: check_tag_flag
|
||||
.. autofunction:: check_dist_flag
|
||||
|
|
|
|||
|
|
@ -15,6 +15,7 @@
|
|||
import sys
|
||||
import os
|
||||
import os.path
|
||||
import sphinx_rtd_theme
|
||||
|
||||
sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
|
||||
# If extensions (or modules to document with autodoc) are in another directory,
|
||||
|
|
@ -105,7 +106,8 @@ pygments_style = 'sphinx'
|
|||
|
||||
# The theme to use for HTML and HTML Help pages. See the documentation for
|
||||
# a list of builtin themes.
|
||||
html_theme = 'default'
|
||||
|
||||
html_theme = 'sphinx_rtd_theme'
|
||||
|
||||
# Theme options are theme-specific and customize the look and feel of a theme
|
||||
# further. For a list of options available for each theme, see the
|
||||
|
|
@ -113,7 +115,7 @@ html_theme = 'default'
|
|||
#html_theme_options = {}
|
||||
|
||||
# Add any paths that contain custom themes here, relative to this directory.
|
||||
#html_theme_path = []
|
||||
html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
|
||||
|
||||
# The name for this set of Sphinx documents. If None, it defaults to
|
||||
# "<project> v<release> documentation".
|
||||
|
|
@ -166,7 +168,7 @@ html_static_path = ['_static']
|
|||
#html_split_index = False
|
||||
|
||||
# If true, links to the reST sources are added to the pages.
|
||||
#html_show_sourcelink = True
|
||||
html_show_sourcelink = False
|
||||
|
||||
# If true, "Created using Sphinx" is shown in the HTML footer. Default is True.
|
||||
#html_show_sphinx = True
|
||||
|
|
|
|||
|
|
@ -0,0 +1,16 @@
|
|||
Installation
|
||||
============
|
||||
|
||||
Installation via pip::
|
||||
|
||||
pip install spacy
|
||||
|
||||
Installation From source via `GitHub <https://github.com/honnibal/spaCy>`_, using virtualenv::
|
||||
|
||||
$ git clone http://github.com/honnibal/spaCy.git
|
||||
$ cd spaCy
|
||||
$ virtualenv .env
|
||||
$ source .env/bin/activate
|
||||
$ pip install -r requirements.txt
|
||||
$ fab make
|
||||
$ fab test
|
||||
|
|
@ -3,81 +3,28 @@
|
|||
You can adapt this file completely to your liking, but it should at least
|
||||
contain the root `toctree` directive.
|
||||
|
||||
spaCy API Reference
|
||||
=================================
|
||||
spaCy Natural Language Tokenizer
|
||||
================================
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 2
|
||||
:maxdepth: 3
|
||||
|
||||
api/python
|
||||
api/cython
|
||||
api/extending
|
||||
guide/overview
|
||||
guide/install
|
||||
api/languages/index.rst
|
||||
api/modules/index.rst
|
||||
|
||||
Overview
|
||||
--------
|
||||
|
||||
spaCy is a tokenizer for natural languages, tightly coupled to a global
|
||||
vocabulary store.
|
||||
|
||||
Instead of a list of strings, spaCy returns references to lexical types. All
|
||||
of the string-based features you might need are pre-computed for you:
|
||||
|
||||
::
|
||||
|
||||
>>> from spacy import en
|
||||
>>> example = u"Apples aren't oranges..."
|
||||
>>> apples, are, nt, oranges, ellipses = en.tokenize(example)
|
||||
>>> en.is_punct(ellipses)
|
||||
True
|
||||
>>> en.get_string(en.word_shape(apples))
|
||||
'Xxxx'
|
||||
|
||||
You also get lots of distributional features, calculated from a large
|
||||
sample of text:
|
||||
|
||||
::
|
||||
|
||||
>>> en.prob_of(are) > en.prob_of(oranges)
|
||||
True
|
||||
>>> en.can_noun(are)
|
||||
False
|
||||
>>> en.is_oft_title(apples)
|
||||
False
|
||||
|
||||
Pros and Cons
|
||||
-------------
|
||||
|
||||
Pros:
|
||||
|
||||
- All tokens come with indices into the original string
|
||||
- Full unicode support
|
||||
- Extensible to other languages
|
||||
- Batch operations computed efficiently in Cython
|
||||
- Cython API
|
||||
- numpy interoperability
|
||||
|
||||
Cons:
|
||||
|
||||
- It's new (released September 2014)
|
||||
- Higher memory usage (up to 1gb)
|
||||
- More conceptually complicated
|
||||
- Tokenization rules expressed in code, not as data
|
||||
|
||||
Installation
|
||||
Project Home
|
||||
------------
|
||||
|
||||
Installation via pip:
|
||||
http://honnibal.github.io/spaCy/
|
||||
|
||||
pip install spacy
|
||||
Source (GitHub)
|
||||
----------------
|
||||
|
||||
From source, using virtualenv:
|
||||
http://github.com/honnibal/spaCy
|
||||
|
||||
::
|
||||
License
|
||||
-------
|
||||
|
||||
$ git clone http://github.com/honnibal/spaCy.git
|
||||
$ cd spaCy
|
||||
$ virtualenv .env
|
||||
$ source .env/bin/activate
|
||||
$ pip install -r requirements.txt
|
||||
$ fab make
|
||||
$ fab test
|
||||
TODO
|
||||
|
|
|
|||
Loading…
Reference in New Issue
Block a user