explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-26 01:46:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Re-add docs, sorting out mess from gh-pages

Browse Source
This commit is contained in:
Matthew Honnibal 2014-09-25 18:42:20 +02:00
parent aba4a7c7ea
commit bfab6403bc
9 changed files with 690 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

177
docs/Makefile Normal file
View File

@ -0,0 +1,177 @@
# Makefile for Sphinx documentation
#
# You can set these variables from the command line.
SPHINXOPTS =
SPHINXBUILD = sphinx-build
PAPER =
BUILDDIR = ../../docs-spacy
# User-friendly check for sphinx-build
ifeq ($(shell which $(SPHINXBUILD) >/dev/null 2>&1; echo $$?), 1)
$(error The '$(SPHINXBUILD)' command was not found. Make sure you have Sphinx installed, then set the SPHINXBUILD environment variable to point to the full path of the '$(SPHINXBUILD)' executable. Alternatively you can add the directory with the executable to your PATH. If you don't have Sphinx installed, grab it from http://sphinx-doc.org/)
endif
# Internal variables.
PAPEROPT_a4 = -D latex_paper_size=a4
PAPEROPT_letter = -D latex_paper_size=letter
ALLSPHINXOPTS = -d $(BUILDDIR)/doctrees $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) source
# the i18n builder cannot share the environment and doctrees with the others
I18NSPHINXOPTS = $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) source
.PHONY: help clean html dirhtml singlehtml pickle json htmlhelp qthelp devhelp epub latex latexpdf text man changes linkcheck doctest gettext
help:
@echo "Please use \`make <target>' where <target> is one of"
@echo " html to make standalone HTML files"
@echo " dirhtml to make HTML files named index.html in directories"
@echo " singlehtml to make a single large HTML file"
@echo " pickle to make pickle files"
@echo " json to make JSON files"
@echo " htmlhelp to make HTML files and a HTML help project"
@echo " qthelp to make HTML files and a qthelp project"
@echo " devhelp to make HTML files and a Devhelp project"
@echo " epub to make an epub"
@echo " latex to make LaTeX files, you can set PAPER=a4 or PAPER=letter"
@echo " latexpdf to make LaTeX files and run them through pdflatex"
@echo " latexpdfja to make LaTeX files and run them through platex/dvipdfmx"
@echo " text to make text files"
@echo " man to make manual pages"
@echo " texinfo to make Texinfo files"
@echo " info to make Texinfo files and run them through makeinfo"
@echo " gettext to make PO message catalogs"
@echo " changes to make an overview of all changed/added/deprecated items"
@echo " xml to make Docutils-native XML files"
@echo " pseudoxml to make pseudoxml-XML files for display purposes"
@echo " linkcheck to check all external links for integrity"
@echo " doctest to run all doctests embedded in the documentation (if enabled)"
clean:
rm -rf $(BUILDDIR)/*
html:
$(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html
@echo
@echo "Build finished. The HTML pages are in $(BUILDDIR)/html."
dirhtml:
$(SPHINXBUILD) -b dirhtml $(ALLSPHINXOPTS) $(BUILDDIR)/dirhtml
@echo
@echo "Build finished. The HTML pages are in $(BUILDDIR)/dirhtml."
singlehtml:
$(SPHINXBUILD) -b singlehtml $(ALLSPHINXOPTS) $(BUILDDIR)/singlehtml
@echo
@echo "Build finished. The HTML page is in $(BUILDDIR)/singlehtml."
pickle:
$(SPHINXBUILD) -b pickle $(ALLSPHINXOPTS) $(BUILDDIR)/pickle
@echo
@echo "Build finished; now you can process the pickle files."
json:
$(SPHINXBUILD) -b json $(ALLSPHINXOPTS) $(BUILDDIR)/json
@echo
@echo "Build finished; now you can process the JSON files."
htmlhelp:
$(SPHINXBUILD) -b htmlhelp $(ALLSPHINXOPTS) $(BUILDDIR)/htmlhelp
@echo
@echo "Build finished; now you can run HTML Help Workshop with the" \
".hhp project file in $(BUILDDIR)/htmlhelp."
qthelp:
$(SPHINXBUILD) -b qthelp $(ALLSPHINXOPTS) $(BUILDDIR)/qthelp
@echo
@echo "Build finished; now you can run "qcollectiongenerator" with the" \
".qhcp project file in $(BUILDDIR)/qthelp, like this:"
@echo "# qcollectiongenerator $(BUILDDIR)/qthelp/spaCy.qhcp"
@echo "To view the help file:"
@echo "# assistant -collectionFile $(BUILDDIR)/qthelp/spaCy.qhc"
devhelp:
$(SPHINXBUILD) -b devhelp $(ALLSPHINXOPTS) $(BUILDDIR)/devhelp
@echo
@echo "Build finished."
@echo "To view the help file:"
@echo "# mkdir -p $$HOME/.local/share/devhelp/spaCy"
@echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/spaCy"
@echo "# devhelp"
epub:
$(SPHINXBUILD) -b epub $(ALLSPHINXOPTS) $(BUILDDIR)/epub
@echo
@echo "Build finished. The epub file is in $(BUILDDIR)/epub."
latex:
$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
@echo
@echo "Build finished; the LaTeX files are in $(BUILDDIR)/latex."
@echo "Run \`make' in that directory to run these through (pdf)latex" \
"(use \`make latexpdf' here to do that automatically)."
latexpdf:
$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
@echo "Running LaTeX files through pdflatex..."
$(MAKE) -C $(BUILDDIR)/latex all-pdf
@echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
latexpdfja:
$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
@echo "Running LaTeX files through platex and dvipdfmx..."
$(MAKE) -C $(BUILDDIR)/latex all-pdf-ja
@echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
text:
$(SPHINXBUILD) -b text $(ALLSPHINXOPTS) $(BUILDDIR)/text
@echo
@echo "Build finished. The text files are in $(BUILDDIR)/text."
man:
$(SPHINXBUILD) -b man $(ALLSPHINXOPTS) $(BUILDDIR)/man
@echo
@echo "Build finished. The manual pages are in $(BUILDDIR)/man."
texinfo:
$(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
@echo
@echo "Build finished. The Texinfo files are in $(BUILDDIR)/texinfo."
@echo "Run \`make' in that directory to run these through makeinfo" \
"(use \`make info' here to do that automatically)."
info:
$(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
@echo "Running Texinfo files through makeinfo..."
make -C $(BUILDDIR)/texinfo info
@echo "makeinfo finished; the Info files are in $(BUILDDIR)/texinfo."
gettext:
$(SPHINXBUILD) -b gettext $(I18NSPHINXOPTS) $(BUILDDIR)/locale
@echo
@echo "Build finished. The message catalogs are in $(BUILDDIR)/locale."
changes:
$(SPHINXBUILD) -b changes $(ALLSPHINXOPTS) $(BUILDDIR)/changes
@echo
@echo "The overview file is in $(BUILDDIR)/changes."
linkcheck:
$(SPHINXBUILD) -b linkcheck $(ALLSPHINXOPTS) $(BUILDDIR)/linkcheck
@echo
@echo "Link check complete; look for any errors in the above output " \
"or in $(BUILDDIR)/linkcheck/output.txt."
doctest:
$(SPHINXBUILD) -b doctest $(ALLSPHINXOPTS) $(BUILDDIR)/doctest
@echo "Testing of doctests in the sources finished, look at the " \
"results in $(BUILDDIR)/doctest/output.txt."
xml:
$(SPHINXBUILD) -b xml $(ALLSPHINXOPTS) $(BUILDDIR)/xml
@echo
@echo "Build finished. The XML files are in $(BUILDDIR)/xml."
pseudoxml:
$(SPHINXBUILD) -b pseudoxml $(ALLSPHINXOPTS) $(BUILDDIR)/pseudoxml
@echo
@echo "Build finished. The pseudo-XML files are in $(BUILDDIR)/pseudoxml."

8
docs/source/api/index.rst Normal file
View File

@ -0,0 +1,8 @@
API
===
.. toctree::
:maxdepth: 2
tokenizers/index.rst
lexicon.rst

6
docs/source/api/lexicon.rst Normal file
View File

@ -0,0 +1,6 @@
spacy.word.Lexeme
=================
.. autoclass:: spacy.word.Lexeme
:members:

94
docs/source/api/tokenizers/en.rst Normal file
View File

@ -0,0 +1,94 @@
spacy.en.EN
============
.. automodule:: spacy.en
Tokenizer API
-------------
.. automethod:: spacy.en.EN.tokenize
:noindex:
.. automethod:: spacy.en.EN.lookup
:noindex:
Lexeme Features Flag IDs
------------------------
A number of boolean features are computed for English Lexemes. To access a feature,
pass its ID to the :py:meth:`spacy.word.Lexeme.check_flag` function.
Orthographic Features
---------------------
These features describe the `orthographic` (lettering) type of the word. The
function used to compute the value is listed along with the flag.
.. data:: IS_ALPHA
:py:func:`spacy.orth.is_alpha`
.. data:: IS_DIGIT
:py:func:`spacy.orth.is_digit`
.. data:: IS_UPPER
:py:func:`spacy.orth.is_upper`
.. data:: IS_PUNCT
:py:func:`spacy.orth.is_punct`
.. data:: IS_SPACE
:py:func:`spacy.orth.is_space`
.. data:: IS_ASCII
:py:func:`spacy.orth.is_ascii`
.. data:: IS_TITLE
:py:func:`spacy.orth.is_title`
.. data:: IS_LOWER
:py:func:`spacy.orth.is_lower`
.. data:: IS_UPPER
:py:func:`spacy.orth.is_upper`
Distributional Orthographic Features
------------------------------------
These features describe how often the lower-cased form of the word appears
in various case-styles in a large sample of English text. See :py:func:`spacy.orth.oft_case`
.. data:: OFT_UPPER
.. data:: OFT_LOWER
.. data:: OFT_TITLE
Tag Dictionary Features
-----------------------
These features describe whether the word commonly occurs with a given
part-of-speech, in a large text corpus, using a part-of-speech tagger designed
to reduce the tag-dictionary bias of its training corpus. See
:py:func:`spacy.orth.can_tag`.
.. data:: CAN_PUNCT
.. data:: CAN_CONJ
.. data:: CAN_NUM
.. data:: CAN_DET
.. data:: CAN_ADP
.. data:: CAN_ADJ
.. data:: CAN_ADV
.. data:: CAN_VERB
.. data:: CAN_NOUN
.. data:: CAN_PDT
.. data:: CAN_POS
.. data:: CAN_PRON
.. data:: CAN_PRT

8
docs/source/api/tokenizers/index.rst Normal file
View File

@ -0,0 +1,8 @@
Tokenizers
===================================
Each module listed here implements a different tokenization scheme, usually
intended for a specific language.
.. toctree::
en.rst

270
docs/source/conf.py Normal file
View File

@ -0,0 +1,270 @@
# -*- coding: utf-8 -*-
#
# spaCy documentation build configuration file, created by
# sphinx-quickstart on Thu Sep 25 17:47:15 2014.
#
# This file is execfile()d with the current directory set to its
# containing dir.
#
# Note that not all possible configuration values are present in this
# autogenerated file.
#
# All configuration values have a default; values that are commented out
# serve to show the default.
import sys
import os
import sphinx_rtd_theme
# If extensions (or modules to document with autodoc) are in another directory,
# add these directories to sys.path here. If the directory is relative to the
# documentation root, use os.path.abspath to make it absolute, like shown here.
#sys.path.insert(0, os.path.abspath('.'))
# -- General configuration ------------------------------------------------
# If your documentation needs a minimal Sphinx version, state it here.
#needs_sphinx = '1.0'
# Add any Sphinx extension module names here, as strings. They can be
# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
# ones.
extensions = [
'sphinx.ext.autodoc',
'sphinx.ext.doctest',
'sphinx.ext.intersphinx',
'sphinx.ext.viewcode',
'sphinxcontrib.napoleon'
]
# Add any paths that contain templates here, relative to this directory.
templates_path = ['_templates']
# The suffix of source filenames.
source_suffix = '.rst'
# The encoding of source files.
#source_encoding = 'utf-8-sig'
# The master toctree document.
master_doc = 'index'
# General information about the project.
project = u'spaCy'
copyright = u'2014, Matthew Honnibal'
# The version info for the project you're documenting, acts as replacement for
# |version| and |release|, also used in various other places throughout the
# built documents.
#
# The short X.Y version.
version = '1.0'
# The full version, including alpha/beta/rc tags.
release = '1.0'
# The language for content autogenerated by Sphinx. Refer to documentation
# for a list of supported languages.
#language = None
# There are two options for replacing |today|: either, you set today to some
# non-false value, then it is used:
#today = ''
# Else, today_fmt is used as the format for a strftime call.
#today_fmt = '%B %d, %Y'
# List of patterns, relative to source directory, that match files and
# directories to ignore when looking for source files.
exclude_patterns = []
# The reST default role (used for this markup: `text`) to use for all
# documents.
#default_role = None
# If true, '()' will be appended to :func: etc. cross-reference text.
#add_function_parentheses = True
# If true, the current module name will be prepended to all description
# unit titles (such as .. function::).
#add_module_names = True
# If true, sectionauthor and moduleauthor directives will be shown in the
# output. They are ignored by default.
#show_authors = False
# The name of the Pygments (syntax highlighting) style to use.
pygments_style = 'sphinx'
# A list of ignored prefixes for module index sorting.
#modindex_common_prefix = []
# If true, keep warnings as "system message" paragraphs in the built documents.
#keep_warnings = False
# -- Options for HTML output ----------------------------------------------
# The theme to use for HTML and HTML Help pages. See the documentation for
# a list of builtin themes.
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
# documentation.
#html_theme_options = {}
# Add any paths that contain custom themes here, relative to this directory.
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".
#html_title = None
# A shorter title for the navigation bar. Default is the same as html_title.
#html_short_title = None
# The name of an image file (relative to this directory) to place at the top
# of the sidebar.
#html_logo = None
# The name of an image file (within the static path) to use as favicon of the
# docs. This file should be a Windows icon file (.ico) being 16x16 or 32x32
# pixels large.
#html_favicon = None
# Add any paths that contain custom static files (such as style sheets) here,
# relative to this directory. They are copied after the builtin static files,
# so a file named "default.css" will overwrite the builtin "default.css".
html_static_path = ['_static']
# Add any extra paths that contain custom files (such as robots.txt or
# .htaccess) here, relative to this directory. These files are copied
# directly to the root of the documentation.
#html_extra_path = []
# If not '', a 'Last updated on:' timestamp is inserted at every page bottom,
# using the given strftime format.
#html_last_updated_fmt = '%b %d, %Y'
# If true, SmartyPants will be used to convert quotes and dashes to
# typographically correct entities.
#html_use_smartypants = True
# Custom sidebar templates, maps document names to template names.
#html_sidebars = {}
# Additional templates that should be rendered to pages, maps page names to
# template names.
#html_additional_pages = {}
# If false, no module index is generated.
#html_domain_indices = True
# If false, no index is generated.
#html_use_index = True
# If true, the index is split into individual pages for each letter.
#html_split_index = False
# If true, links to the reST sources are added to the pages.
#html_show_sourcelink = True
# If true, "Created using Sphinx" is shown in the HTML footer. Default is True.
#html_show_sphinx = True
# If true, "(C) Copyright ..." is shown in the HTML footer. Default is True.
#html_show_copyright = True
# If true, an OpenSearch description file will be output, and all pages will
# contain a <link> tag referring to it. The value of this option must be the
# base URL from which the finished HTML is served.
#html_use_opensearch = ''
# This is the file name suffix for HTML files (e.g. ".xhtml").
#html_file_suffix = None
# Output file base name for HTML help builder.
htmlhelp_basename = 'spaCydoc'
# -- Options for LaTeX output ---------------------------------------------
latex_elements = {
# The paper size ('letterpaper' or 'a4paper').
#'papersize': 'letterpaper',
# The font size ('10pt', '11pt' or '12pt').
#'pointsize': '10pt',
# Additional stuff for the LaTeX preamble.
#'preamble': '',
}
# Grouping the document tree into LaTeX files. List of tuples
# (source start file, target name, title,
# author, documentclass [howto, manual, or own class]).
latex_documents = [
('index', 'spaCy.tex', u'spaCy Documentation',
u'Matthew Honnibal', 'manual'),
]
# The name of an image file (relative to this directory) to place at the top of
# the title page.
#latex_logo = None
# For "manual" documents, if this is true, then toplevel headings are parts,
# not chapters.
#latex_use_parts = False
# If true, show page references after internal links.
#latex_show_pagerefs = False
# If true, show URL addresses after external links.
#latex_show_urls = False
# Documents to append as an appendix to all manuals.
#latex_appendices = []
# If false, no module index is generated.
#latex_domain_indices = True
# -- Options for manual page output ---------------------------------------
# One entry per manual page. List of tuples
# (source start file, name, description, authors, manual section).
man_pages = [
('index', 'spacy', u'spaCy Documentation',
[u'Matthew Honnibal'], 1)
]
# If true, show URL addresses after external links.
#man_show_urls = False
# -- Options for Texinfo output -------------------------------------------
# Grouping the document tree into Texinfo files. List of tuples
# (source start file, target name, title, author,
# dir menu entry, description, category)
texinfo_documents = [
('index', 'spaCy', u'spaCy Documentation',
u'Matthew Honnibal', 'spaCy', 'One line description of project.',
'Miscellaneous'),
]
# Documents to append as an appendix to all manuals.
#texinfo_appendices = []
# If false, no module index is generated.
#texinfo_domain_indices = True
# How to display URL addresses: 'footnote', 'no', or 'inline'.
#texinfo_show_urls = 'footnote'
# If true, do not generate a @detailmenu in the "Top" node's menu.
#texinfo_no_detailmenu = False
# Example configuration for intersphinx: refer to the Python standard library.
intersphinx_mapping = {'http://docs.python.org/': None}

22
docs/source/guide/install.rst Normal file
View File

@ -0,0 +1,22 @@
Installation
============
pip install spacy
-----------------
The easiest way to install is from PyPi via pip::
pip install spacy
git clone http://github.com/honnibal/spaCy.git
----------------------------------------------
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

71
docs/source/guide/overview.rst Normal file
View File

@ -0,0 +1,71 @@
Overview
========
What and Why
------------
spaCy is a lightning-fast, full-cream NLP tokenizer and lexicon.
Most tokenizers give you a sequence of strings. That's barbaric.
Giving you strings invites you to compute on every *token*, when what
you should be doing is computing on every *type*. Remember
`Zipf's law <http://en.wikipedia.org/wiki/Zipf's_law>`_: you'll
see exponentially fewer types than tokens.
Instead of strings, spaCy gives you references to Lexeme objects, from which you
can access an excellent set of pre-computed orthographic and distributional features:
::
>>> from spacy import en
>>> apples, are, nt, oranges, dots = en.EN.tokenize(u"Apples aren't oranges...")
>>> are.prob >= oranges.prob
True
>>> apples.check_flag(en.IS_TITLE)
True
>>> apples.check_flag(en.OFT_TITLE)
False
>>> are.check_flag(en.CAN_NOUN)
False
spaCy makes it easy to write very efficient NLP applications, because your feature
functions have to do almost no work: almost every lexical property you'll want
is pre-computed for you. See the tutorial for an example POS tagger.
Benchmark
---------
The tokenizer itself is also very efficient:
+--------+-------+--------------+--------------+
| System | Time | Words/second | Speed Factor |
+--------+-------+--------------+--------------+
| NLTK | 6m4s | 89,000 | 1.00 |
+--------+-------+--------------+--------------+
| spaCy | 9.5s | 3,093,000 | 38.30 |
+--------+-------+--------------+--------------+
The comparison refers to 30 million words from the English Gigaword, on
a Maxbook Air. For context, calling string.split() on the data completes in
about 5s.
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)
- Security concerns, from memory management
- Higher memory usage (up to 1gb)
- More conceptually complicated
- Tokenization rules expressed in code, not as data

34
docs/source/index.rst Normal file
View File

@ -0,0 +1,34 @@
.. spaCy documentation master file, created by
sphinx-quickstart on Tue Aug 19 16:27:38 2014.
You can adapt this file completely to your liking, but it should at least
contain the root `toctree` directive.
spaCy NLP Tokenizer and Lexicon
================================
.. toctree::
:maxdepth: 3
guide/overview.rst
guide/install.rst
api/index.rst
modules/index.rst
Source (GitHub)
----------------
http://github.com/honnibal/spaCy
License
-------
Copyright Matthew Honnibal
Non-commercial use: $0
Commercial trial use: $0
Full commercial license: $500
honnibal@gmail.com