spark-instrumented-optimizer/python/docs/conf.py

337 lines
10 KiB
Python
Raw Normal View History

# -*- coding: utf-8 -*-
#
# pyspark documentation build configuration file, created by
# sphinx-quickstart on Thu Aug 28 15:17:47 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
# 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.viewcode',
'epytext',
]
# 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'PySpark'
copyright = u'2014, Author'
# 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.
[SPARK-4586][MLLIB] Python API for ML pipeline and parameters This PR adds Python API for ML pipeline and parameters. The design doc can be found on the JIRA page. It includes transformers and an estimator to demo the simple text classification example code. TODO: - [x] handle parameters in LRModel - [x] unit tests - [x] missing some docs CC: davies jkbradley Author: Xiangrui Meng <meng@databricks.com> Author: Davies Liu <davies@databricks.com> Closes #4151 from mengxr/SPARK-4586 and squashes the following commits: 415268e [Xiangrui Meng] remove inherit_doc from __init__ edbd6fe [Xiangrui Meng] move Identifiable to ml.util 44c2405 [Xiangrui Meng] Merge pull request #2 from davies/ml dd1256b [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-4586 14ae7e2 [Davies Liu] fix docs 54ca7df [Davies Liu] fix tests 78638df [Davies Liu] Merge branch 'SPARK-4586' of github.com:mengxr/spark into ml fc59a02 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-4586 1dca16a [Davies Liu] refactor 090b3a3 [Davies Liu] Merge branch 'master' of github.com:apache/spark into ml 0882513 [Xiangrui Meng] update doc style a4f4dbf [Xiangrui Meng] add unit test for LR 7521d1c [Xiangrui Meng] add unit tests to HashingTF and Tokenizer ba0ba1e [Xiangrui Meng] add unit tests for pipeline 0586c7b [Xiangrui Meng] add more comments to the example 5153cff [Xiangrui Meng] simplify java models 036ca04 [Xiangrui Meng] gen numFeatures 46fa147 [Xiangrui Meng] update mllib/pom.xml to include python files in the assembly 1dcc17e [Xiangrui Meng] update code gen and make param appear in the doc f66ba0c [Xiangrui Meng] make params a property d5efd34 [Xiangrui Meng] update doc conf and move embedded param map to instance attribute f4d0fe6 [Xiangrui Meng] use LabeledDocument and Document in example 05e3e40 [Xiangrui Meng] update example d3e8dbe [Xiangrui Meng] more docs optimize pipeline.fit impl 56de571 [Xiangrui Meng] fix style d0c5bb8 [Xiangrui Meng] a working copy bce72f4 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-4586 17ecfb9 [Xiangrui Meng] code gen for shared params d9ea77c [Xiangrui Meng] update doc c18dca1 [Xiangrui Meng] make the example working dadd84e [Xiangrui Meng] add base classes and docs a3015cf [Xiangrui Meng] add Estimator and Transformer 46eea43 [Xiangrui Meng] a pipeline in python 33b68e0 [Xiangrui Meng] a working LR
2015-01-28 20:14:23 -05:00
version = '1.3-SNAPSHOT'
# The full version, including alpha/beta/rc tags.
[SPARK-4586][MLLIB] Python API for ML pipeline and parameters This PR adds Python API for ML pipeline and parameters. The design doc can be found on the JIRA page. It includes transformers and an estimator to demo the simple text classification example code. TODO: - [x] handle parameters in LRModel - [x] unit tests - [x] missing some docs CC: davies jkbradley Author: Xiangrui Meng <meng@databricks.com> Author: Davies Liu <davies@databricks.com> Closes #4151 from mengxr/SPARK-4586 and squashes the following commits: 415268e [Xiangrui Meng] remove inherit_doc from __init__ edbd6fe [Xiangrui Meng] move Identifiable to ml.util 44c2405 [Xiangrui Meng] Merge pull request #2 from davies/ml dd1256b [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-4586 14ae7e2 [Davies Liu] fix docs 54ca7df [Davies Liu] fix tests 78638df [Davies Liu] Merge branch 'SPARK-4586' of github.com:mengxr/spark into ml fc59a02 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-4586 1dca16a [Davies Liu] refactor 090b3a3 [Davies Liu] Merge branch 'master' of github.com:apache/spark into ml 0882513 [Xiangrui Meng] update doc style a4f4dbf [Xiangrui Meng] add unit test for LR 7521d1c [Xiangrui Meng] add unit tests to HashingTF and Tokenizer ba0ba1e [Xiangrui Meng] add unit tests for pipeline 0586c7b [Xiangrui Meng] add more comments to the example 5153cff [Xiangrui Meng] simplify java models 036ca04 [Xiangrui Meng] gen numFeatures 46fa147 [Xiangrui Meng] update mllib/pom.xml to include python files in the assembly 1dcc17e [Xiangrui Meng] update code gen and make param appear in the doc f66ba0c [Xiangrui Meng] make params a property d5efd34 [Xiangrui Meng] update doc conf and move embedded param map to instance attribute f4d0fe6 [Xiangrui Meng] use LabeledDocument and Document in example 05e3e40 [Xiangrui Meng] update example d3e8dbe [Xiangrui Meng] more docs optimize pipeline.fit impl 56de571 [Xiangrui Meng] fix style d0c5bb8 [Xiangrui Meng] a working copy bce72f4 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-4586 17ecfb9 [Xiangrui Meng] code gen for shared params d9ea77c [Xiangrui Meng] update doc c18dca1 [Xiangrui Meng] make the example working dadd84e [Xiangrui Meng] add base classes and docs a3015cf [Xiangrui Meng] add Estimator and Transformer 46eea43 [Xiangrui Meng] a pipeline in python 33b68e0 [Xiangrui Meng] a working LR
2015-01-28 20:14:23 -05:00
release = '1.3-SNAPSHOT'
# 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 = ['_build']
# 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 autodoc --------------------------------------------------
# Look at the first line of the docstring for function and method signatures.
autodoc_docstring_signature = True
# -- 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 = 'nature'
# 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 = []
# 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 = "../../docs/img/spark-logo-hd.png"
# 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".
[SPARK-3909][PySpark][Doc] A corrupted format in Sphinx documents and building warnings Sphinx documents contains a corrupted ReST format and have some warnings. The purpose of this issue is same as https://issues.apache.org/jira/browse/SPARK-3773. commit: 0e8203f4fb721158fb27897680da476174d24c4b output ``` $ cd ./python/docs $ make clean html rm -rf _build/* sphinx-build -b html -d _build/doctrees . _build/html Making output directory... Running Sphinx v1.2.3 loading pickled environment... not yet created building [html]: targets for 4 source files that are out of date updating environment: 4 added, 0 changed, 0 removed reading sources... [100%] pyspark.sql /Users/<user>/MyRepos/Scala/spark/python/pyspark/mllib/feature.py:docstring of pyspark.mllib.feature.Word2VecModel.findSynonyms:4: WARNING: Field list ends without a blank line; unexpected unindent. /Users/<user>/MyRepos/Scala/spark/python/pyspark/mllib/feature.py:docstring of pyspark.mllib.feature.Word2VecModel.transform:3: WARNING: Field list ends without a blank line; unexpected unindent. /Users/<user>/MyRepos/Scala/spark/python/pyspark/sql.py:docstring of pyspark.sql:4: WARNING: Bullet list ends without a blank line; unexpected unindent. looking for now-outdated files... none found pickling environment... done checking consistency... done preparing documents... done writing output... [100%] pyspark.sql writing additional files... (12 module code pages) _modules/index search copying static files... WARNING: html_static_path entry u'/Users/<user>/MyRepos/Scala/spark/python/docs/_static' does not exist done copying extra files... done dumping search index... done dumping object inventory... done build succeeded, 4 warnings. Build finished. The HTML pages are in _build/html. ``` Author: cocoatomo <cocoatomo77@gmail.com> Closes #2766 from cocoatomo/issues/3909-sphinx-build-warnings and squashes the following commits: 2c7faa8 [cocoatomo] [SPARK-3909][PySpark][Doc] A corrupted format in Sphinx documents and building warnings
2014-10-11 14:51:59 -04:00
#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 = False
# If false, no index is generated.
html_use_index = False
# 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 = 'pysparkdoc'
# -- 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', 'pyspark.tex', u'pyspark Documentation',
u'Author', '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', 'pyspark', u'pyspark Documentation',
[u'Author'], 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', 'pyspark', u'pyspark Documentation',
u'Author', 'pyspark', '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
# -- Options for Epub output ----------------------------------------------
# Bibliographic Dublin Core info.
epub_title = u'pyspark'
epub_author = u'Author'
epub_publisher = u'Author'
epub_copyright = u'2014, Author'
# The basename for the epub file. It defaults to the project name.
#epub_basename = u'pyspark'
# The HTML theme for the epub output. Since the default themes are not optimized
# for small screen space, using the same theme for HTML and epub output is
# usually not wise. This defaults to 'epub', a theme designed to save visual
# space.
#epub_theme = 'epub'
# The language of the text. It defaults to the language option
# or en if the language is not set.
#epub_language = ''
# The scheme of the identifier. Typical schemes are ISBN or URL.
#epub_scheme = ''
# The unique identifier of the text. This can be a ISBN number
# or the project homepage.
#epub_identifier = ''
# A unique identification for the text.
#epub_uid = ''
# A tuple containing the cover image and cover page html template filenames.
#epub_cover = ()
# A sequence of (type, uri, title) tuples for the guide element of content.opf.
#epub_guide = ()
# HTML files that should be inserted before the pages created by sphinx.
# The format is a list of tuples containing the path and title.
#epub_pre_files = []
# HTML files shat should be inserted after the pages created by sphinx.
# The format is a list of tuples containing the path and title.
#epub_post_files = []
# A list of files that should not be packed into the epub file.
epub_exclude_files = ['search.html']
# The depth of the table of contents in toc.ncx.
#epub_tocdepth = 3
# Allow duplicate toc entries.
#epub_tocdup = True
# Choose between 'default' and 'includehidden'.
#epub_tocscope = 'default'
# Fix unsupported image types using the PIL.
#epub_fix_images = False
# Scale large images.
#epub_max_image_width = 0
# How to display URL addresses: 'footnote', 'no', or 'inline'.
#epub_show_urls = 'inline'
# If false, no index is generated.
#epub_use_index = True