From ec1adecbb72d291d7ef122fb0505bae53116e0e6 Mon Sep 17 00:00:00 2001 From: Davies Liu Date: Tue, 16 Sep 2014 12:51:58 -0700 Subject: [SPARK-3430] [PySpark] [Doc] generate PySpark API docs using Sphinx Using Sphinx to generate API docs for PySpark. requirement: Sphinx ``` $ cd python/docs/ $ make html ``` The generated API docs will be located at python/docs/_build/html/index.html It can co-exists with those generated by Epydoc. This is the first working version, after merging in, then we can continue to improve it and replace the epydoc finally. Author: Davies Liu Closes #2292 from davies/sphinx and squashes the following commits: 425a3b1 [Davies Liu] cleanup 1573298 [Davies Liu] move docs to python/docs/ 5fe3903 [Davies Liu] Merge branch 'master' into sphinx 9468ab0 [Davies Liu] fix makefile b408f38 [Davies Liu] address all comments e2ccb1b [Davies Liu] update name and version 9081ead [Davies Liu] generate PySpark API docs using Sphinx --- python/docs/Makefile | 179 +++++++++++++++++++++++ python/docs/conf.py | 332 ++++++++++++++++++++++++++++++++++++++++++ python/docs/epytext.py | 27 ++++ python/docs/index.rst | 37 +++++ python/docs/make.bat | 242 ++++++++++++++++++++++++++++++ python/docs/modules.rst | 7 + python/docs/pyspark.mllib.rst | 77 ++++++++++ python/docs/pyspark.rst | 18 +++ python/docs/pyspark.sql.rst | 10 ++ python/pyspark/broadcast.py | 3 + python/pyspark/context.py | 2 +- python/pyspark/serializers.py | 3 + python/pyspark/sql.py | 12 +- 13 files changed, 944 insertions(+), 5 deletions(-) create mode 100644 python/docs/Makefile create mode 100644 python/docs/conf.py create mode 100644 python/docs/epytext.py create mode 100644 python/docs/index.rst create mode 100644 python/docs/make.bat create mode 100644 python/docs/modules.rst create mode 100644 python/docs/pyspark.mllib.rst create mode 100644 python/docs/pyspark.rst create mode 100644 python/docs/pyspark.sql.rst (limited to 'python') diff --git a/python/docs/Makefile b/python/docs/Makefile new file mode 100644 index 0000000000..8a1324eecd --- /dev/null +++ b/python/docs/Makefile @@ -0,0 +1,179 @@ +# Makefile for Sphinx documentation +# + +# You can set these variables from the command line. +SPHINXOPTS = +SPHINXBUILD = sphinx-build +PAPER = +BUILDDIR = _build + +export PYTHONPATH=$(realpath ..):$(realpath ../lib/py4j-0.8.2.1-src.zip) + +# 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) . +# the i18n builder cannot share the environment and doctrees with the others +I18NSPHINXOPTS = $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) . + +.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 ' where 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/pyspark.qhcp" + @echo "To view the help file:" + @echo "# assistant -collectionFile $(BUILDDIR)/qthelp/pyspark.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/pyspark" + @echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/pyspark" + @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." diff --git a/python/docs/conf.py b/python/docs/conf.py new file mode 100644 index 0000000000..c368cf81a0 --- /dev/null +++ b/python/docs/conf.py @@ -0,0 +1,332 @@ +# -*- 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. +version = '1.1' +# The full version, including alpha/beta/rc tags. +release = '' + +# 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 HTML output ---------------------------------------------- + +# The theme to use for HTML and HTML Help pages. See the documentation for +# a list of builtin themes. +html_theme = 'default' + +# 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 +# " v 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 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 diff --git a/python/docs/epytext.py b/python/docs/epytext.py new file mode 100644 index 0000000000..61d731bff5 --- /dev/null +++ b/python/docs/epytext.py @@ -0,0 +1,27 @@ +import re + +RULES = ( + (r"<[\w.]+>", r""), + (r"L{([\w.()]+)}", r":class:`\1`"), + (r"[LC]{(\w+\.\w+)\(\)}", r":func:`\1`"), + (r"C{([\w.()]+)}", r":class:`\1`"), + (r"[IBCM]{(.+)}", r"`\1`"), + ('pyspark.rdd.RDD', 'RDD'), +) + +def _convert_epytext(line): + """ + >>> _convert_epytext("L{A}") + :class:`A` + """ + line = line.replace('@', ':') + for p, sub in RULES: + line = re.sub(p, sub, line) + return line + +def _process_docstring(app, what, name, obj, options, lines): + for i in range(len(lines)): + lines[i] = _convert_epytext(lines[i]) + +def setup(app): + app.connect("autodoc-process-docstring", _process_docstring) diff --git a/python/docs/index.rst b/python/docs/index.rst new file mode 100644 index 0000000000..25b3f9bd93 --- /dev/null +++ b/python/docs/index.rst @@ -0,0 +1,37 @@ +.. pyspark documentation master file, created by + sphinx-quickstart on Thu Aug 28 15:17:47 2014. + You can adapt this file completely to your liking, but it should at least + contain the root `toctree` directive. + +Welcome to PySpark API reference! +=================================== + +Contents: + +.. toctree:: + :maxdepth: 2 + + pyspark + pyspark.sql + pyspark.mllib + + +Core classes: +--------------- + + :class:`pyspark.SparkContext` + + Main entry point for Spark functionality. + + :class:`pyspark.RDD` + + A Resilient Distributed Dataset (RDD), the basic abstraction in Spark. + + +Indices and tables +================== + +* :ref:`genindex` +* :ref:`modindex` +* :ref:`search` + diff --git a/python/docs/make.bat b/python/docs/make.bat new file mode 100644 index 0000000000..adad44fd75 --- /dev/null +++ b/python/docs/make.bat @@ -0,0 +1,242 @@ +@ECHO OFF + +REM Command file for Sphinx documentation + +if "%SPHINXBUILD%" == "" ( + set SPHINXBUILD=sphinx-build +) +set BUILDDIR=_build +set ALLSPHINXOPTS=-d %BUILDDIR%/doctrees %SPHINXOPTS% . +set I18NSPHINXOPTS=%SPHINXOPTS% . +if NOT "%PAPER%" == "" ( + set ALLSPHINXOPTS=-D latex_paper_size=%PAPER% %ALLSPHINXOPTS% + set I18NSPHINXOPTS=-D latex_paper_size=%PAPER% %I18NSPHINXOPTS% +) + +if "%1" == "" goto help + +if "%1" == "help" ( + :help + echo.Please use `make ^` where ^ 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. text to make text files + echo. man to make manual pages + echo. texinfo to make Texinfo files + echo. gettext to make PO message catalogs + echo. changes to make an overview over 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 + goto end +) + +if "%1" == "clean" ( + for /d %%i in (%BUILDDIR%\*) do rmdir /q /s %%i + del /q /s %BUILDDIR%\* + goto end +) + + +%SPHINXBUILD% 2> nul +if errorlevel 9009 ( + echo. + echo.The 'sphinx-build' command was not found. Make sure you have Sphinx + echo.installed, then set the SPHINXBUILD environment variable to point + echo.to the full path of the 'sphinx-build' executable. Alternatively you + echo.may add the Sphinx directory to PATH. + echo. + echo.If you don't have Sphinx installed, grab it from + echo.http://sphinx-doc.org/ + exit /b 1 +) + +if "%1" == "html" ( + %SPHINXBUILD% -b html %ALLSPHINXOPTS% %BUILDDIR%/html + if errorlevel 1 exit /b 1 + echo. + echo.Build finished. The HTML pages are in %BUILDDIR%/html. + goto end +) + +if "%1" == "dirhtml" ( + %SPHINXBUILD% -b dirhtml %ALLSPHINXOPTS% %BUILDDIR%/dirhtml + if errorlevel 1 exit /b 1 + echo. + echo.Build finished. The HTML pages are in %BUILDDIR%/dirhtml. + goto end +) + +if "%1" == "singlehtml" ( + %SPHINXBUILD% -b singlehtml %ALLSPHINXOPTS% %BUILDDIR%/singlehtml + if errorlevel 1 exit /b 1 + echo. + echo.Build finished. The HTML pages are in %BUILDDIR%/singlehtml. + goto end +) + +if "%1" == "pickle" ( + %SPHINXBUILD% -b pickle %ALLSPHINXOPTS% %BUILDDIR%/pickle + if errorlevel 1 exit /b 1 + echo. + echo.Build finished; now you can process the pickle files. + goto end +) + +if "%1" == "json" ( + %SPHINXBUILD% -b json %ALLSPHINXOPTS% %BUILDDIR%/json + if errorlevel 1 exit /b 1 + echo. + echo.Build finished; now you can process the JSON files. + goto end +) + +if "%1" == "htmlhelp" ( + %SPHINXBUILD% -b htmlhelp %ALLSPHINXOPTS% %BUILDDIR%/htmlhelp + if errorlevel 1 exit /b 1 + echo. + echo.Build finished; now you can run HTML Help Workshop with the ^ +.hhp project file in %BUILDDIR%/htmlhelp. + goto end +) + +if "%1" == "qthelp" ( + %SPHINXBUILD% -b qthelp %ALLSPHINXOPTS% %BUILDDIR%/qthelp + if errorlevel 1 exit /b 1 + echo. + echo.Build finished; now you can run "qcollectiongenerator" with the ^ +.qhcp project file in %BUILDDIR%/qthelp, like this: + echo.^> qcollectiongenerator %BUILDDIR%\qthelp\pyspark.qhcp + echo.To view the help file: + echo.^> assistant -collectionFile %BUILDDIR%\qthelp\pyspark.ghc + goto end +) + +if "%1" == "devhelp" ( + %SPHINXBUILD% -b devhelp %ALLSPHINXOPTS% %BUILDDIR%/devhelp + if errorlevel 1 exit /b 1 + echo. + echo.Build finished. + goto end +) + +if "%1" == "epub" ( + %SPHINXBUILD% -b epub %ALLSPHINXOPTS% %BUILDDIR%/epub + if errorlevel 1 exit /b 1 + echo. + echo.Build finished. The epub file is in %BUILDDIR%/epub. + goto end +) + +if "%1" == "latex" ( + %SPHINXBUILD% -b latex %ALLSPHINXOPTS% %BUILDDIR%/latex + if errorlevel 1 exit /b 1 + echo. + echo.Build finished; the LaTeX files are in %BUILDDIR%/latex. + goto end +) + +if "%1" == "latexpdf" ( + %SPHINXBUILD% -b latex %ALLSPHINXOPTS% %BUILDDIR%/latex + cd %BUILDDIR%/latex + make all-pdf + cd %BUILDDIR%/.. + echo. + echo.Build finished; the PDF files are in %BUILDDIR%/latex. + goto end +) + +if "%1" == "latexpdfja" ( + %SPHINXBUILD% -b latex %ALLSPHINXOPTS% %BUILDDIR%/latex + cd %BUILDDIR%/latex + make all-pdf-ja + cd %BUILDDIR%/.. + echo. + echo.Build finished; the PDF files are in %BUILDDIR%/latex. + goto end +) + +if "%1" == "text" ( + %SPHINXBUILD% -b text %ALLSPHINXOPTS% %BUILDDIR%/text + if errorlevel 1 exit /b 1 + echo. + echo.Build finished. The text files are in %BUILDDIR%/text. + goto end +) + +if "%1" == "man" ( + %SPHINXBUILD% -b man %ALLSPHINXOPTS% %BUILDDIR%/man + if errorlevel 1 exit /b 1 + echo. + echo.Build finished. The manual pages are in %BUILDDIR%/man. + goto end +) + +if "%1" == "texinfo" ( + %SPHINXBUILD% -b texinfo %ALLSPHINXOPTS% %BUILDDIR%/texinfo + if errorlevel 1 exit /b 1 + echo. + echo.Build finished. The Texinfo files are in %BUILDDIR%/texinfo. + goto end +) + +if "%1" == "gettext" ( + %SPHINXBUILD% -b gettext %I18NSPHINXOPTS% %BUILDDIR%/locale + if errorlevel 1 exit /b 1 + echo. + echo.Build finished. The message catalogs are in %BUILDDIR%/locale. + goto end +) + +if "%1" == "changes" ( + %SPHINXBUILD% -b changes %ALLSPHINXOPTS% %BUILDDIR%/changes + if errorlevel 1 exit /b 1 + echo. + echo.The overview file is in %BUILDDIR%/changes. + goto end +) + +if "%1" == "linkcheck" ( + %SPHINXBUILD% -b linkcheck %ALLSPHINXOPTS% %BUILDDIR%/linkcheck + if errorlevel 1 exit /b 1 + echo. + echo.Link check complete; look for any errors in the above output ^ +or in %BUILDDIR%/linkcheck/output.txt. + goto end +) + +if "%1" == "doctest" ( + %SPHINXBUILD% -b doctest %ALLSPHINXOPTS% %BUILDDIR%/doctest + if errorlevel 1 exit /b 1 + echo. + echo.Testing of doctests in the sources finished, look at the ^ +results in %BUILDDIR%/doctest/output.txt. + goto end +) + +if "%1" == "xml" ( + %SPHINXBUILD% -b xml %ALLSPHINXOPTS% %BUILDDIR%/xml + if errorlevel 1 exit /b 1 + echo. + echo.Build finished. The XML files are in %BUILDDIR%/xml. + goto end +) + +if "%1" == "pseudoxml" ( + %SPHINXBUILD% -b pseudoxml %ALLSPHINXOPTS% %BUILDDIR%/pseudoxml + if errorlevel 1 exit /b 1 + echo. + echo.Build finished. The pseudo-XML files are in %BUILDDIR%/pseudoxml. + goto end +) + +:end diff --git a/python/docs/modules.rst b/python/docs/modules.rst new file mode 100644 index 0000000000..183564659f --- /dev/null +++ b/python/docs/modules.rst @@ -0,0 +1,7 @@ +. += + +.. toctree:: + :maxdepth: 4 + + pyspark diff --git a/python/docs/pyspark.mllib.rst b/python/docs/pyspark.mllib.rst new file mode 100644 index 0000000000..e95d19e97f --- /dev/null +++ b/python/docs/pyspark.mllib.rst @@ -0,0 +1,77 @@ +pyspark.mllib package +===================== + +Submodules +---------- + +pyspark.mllib.classification module +----------------------------------- + +.. automodule:: pyspark.mllib.classification + :members: + :undoc-members: + :show-inheritance: + +pyspark.mllib.clustering module +------------------------------- + +.. automodule:: pyspark.mllib.clustering + :members: + :undoc-members: + :show-inheritance: + +pyspark.mllib.linalg module +--------------------------- + +.. automodule:: pyspark.mllib.linalg + :members: + :undoc-members: + :show-inheritance: + +pyspark.mllib.random module +--------------------------- + +.. automodule:: pyspark.mllib.random + :members: + :undoc-members: + :show-inheritance: + +pyspark.mllib.recommendation module +----------------------------------- + +.. automodule:: pyspark.mllib.recommendation + :members: + :undoc-members: + :show-inheritance: + +pyspark.mllib.regression module +------------------------------- + +.. automodule:: pyspark.mllib.regression + :members: + :undoc-members: + :show-inheritance: + +pyspark.mllib.stat module +------------------------- + +.. automodule:: pyspark.mllib.stat + :members: + :undoc-members: + :show-inheritance: + +pyspark.mllib.tree module +------------------------- + +.. automodule:: pyspark.mllib.tree + :members: + :undoc-members: + :show-inheritance: + +pyspark.mllib.util module +------------------------- + +.. automodule:: pyspark.mllib.util + :members: + :undoc-members: + :show-inheritance: diff --git a/python/docs/pyspark.rst b/python/docs/pyspark.rst new file mode 100644 index 0000000000..a68bd62433 --- /dev/null +++ b/python/docs/pyspark.rst @@ -0,0 +1,18 @@ +pyspark package +=============== + +Subpackages +----------- + +.. toctree:: + :maxdepth: 1 + + pyspark.mllib + pyspark.sql + +Contents +-------- + +.. automodule:: pyspark + :members: + :undoc-members: diff --git a/python/docs/pyspark.sql.rst b/python/docs/pyspark.sql.rst new file mode 100644 index 0000000000..65b3650ae1 --- /dev/null +++ b/python/docs/pyspark.sql.rst @@ -0,0 +1,10 @@ +pyspark.sql module +================== + +Module contents +--------------- + +.. automodule:: pyspark.sql + :members: + :undoc-members: + :show-inheritance: diff --git a/python/pyspark/broadcast.py b/python/pyspark/broadcast.py index 5c7c9cc161..f124dc6c07 100644 --- a/python/pyspark/broadcast.py +++ b/python/pyspark/broadcast.py @@ -78,6 +78,9 @@ class Broadcast(object): return self._value def unpersist(self, blocking=False): + """ + Delete cached copies of this broadcast on the executors. + """ self._jbroadcast.unpersist(blocking) os.unlink(self.path) diff --git a/python/pyspark/context.py b/python/pyspark/context.py index a33aae87f6..a17f2c1203 100644 --- a/python/pyspark/context.py +++ b/python/pyspark/context.py @@ -53,7 +53,7 @@ class SparkContext(object): """ Main entry point for Spark functionality. A SparkContext represents the - connection to a Spark cluster, and can be used to create L{RDD}s and + connection to a Spark cluster, and can be used to create L{RDD} and broadcast variables on that cluster. """ diff --git a/python/pyspark/serializers.py b/python/pyspark/serializers.py index ec3c6f0554..44ac564283 100644 --- a/python/pyspark/serializers.py +++ b/python/pyspark/serializers.py @@ -110,6 +110,9 @@ class Serializer(object): def __ne__(self, other): return not self.__eq__(other) + def __repr__(self): + return "<%s object>" % self.__class__.__name__ + class FramedSerializer(Serializer): diff --git a/python/pyspark/sql.py b/python/pyspark/sql.py index 621a556ec6..8f6dbab240 100644 --- a/python/pyspark/sql.py +++ b/python/pyspark/sql.py @@ -289,7 +289,7 @@ class StructType(DataType): """Spark SQL StructType The data type representing rows. - A StructType object comprises a list of L{StructField}s. + A StructType object comprises a list of L{StructField}. """ @@ -904,7 +904,7 @@ class SQLContext(object): """Main entry point for Spark SQL functionality. - A SQLContext can be used create L{SchemaRDD}s, register L{SchemaRDD}s as + A SQLContext can be used create L{SchemaRDD}, register L{SchemaRDD} as tables, execute SQL over tables, cache tables, and read parquet files. """ @@ -994,7 +994,7 @@ class SQLContext(object): str(returnType)) def inferSchema(self, rdd): - """Infer and apply a schema to an RDD of L{Row}s. + """Infer and apply a schema to an RDD of L{Row}. We peek at the first row of the RDD to determine the fields' names and types. Nested collections are supported, which include array, @@ -1047,7 +1047,7 @@ class SQLContext(object): def applySchema(self, rdd, schema): """ - Applies the given schema to the given RDD of L{tuple} or L{list}s. + Applies the given schema to the given RDD of L{tuple} or L{list}. These tuples or lists can contain complex nested structures like lists, maps or nested rows. @@ -1183,6 +1183,7 @@ class SQLContext(object): Row(f1=1, f2=u'row1', f3=Row(field4=11, field5=None), f4=None) Row(f1=2, f2=None, f3=Row(field4=22,..., f4=[Row(field7=u'row2')]) Row(f1=None, f2=u'row3', f3=Row(field4=33, field5=[]), f4=None) + >>> srdd3 = sqlCtx.jsonFile(jsonFile, srdd1.schema()) >>> sqlCtx.registerRDDAsTable(srdd3, "table2") >>> srdd4 = sqlCtx.sql( @@ -1193,6 +1194,7 @@ class SQLContext(object): Row(f1=1, f2=u'row1', f3=Row(field4=11, field5=None), f4=None) Row(f1=2, f2=None, f3=Row(field4=22,..., f4=[Row(field7=u'row2')]) Row(f1=None, f2=u'row3', f3=Row(field4=33, field5=[]), f4=None) + >>> schema = StructType([ ... StructField("field2", StringType(), True), ... StructField("field3", @@ -1233,6 +1235,7 @@ class SQLContext(object): Row(f1=1, f2=u'row1', f3=Row(field4=11, field5=None), f4=None) Row(f1=2, f2=None, f3=Row(field4=22..., f4=[Row(field7=u'row2')]) Row(f1=None, f2=u'row3', f3=Row(field4=33, field5=[]), f4=None) + >>> srdd3 = sqlCtx.jsonRDD(json, srdd1.schema()) >>> sqlCtx.registerRDDAsTable(srdd3, "table2") >>> srdd4 = sqlCtx.sql( @@ -1243,6 +1246,7 @@ class SQLContext(object): Row(f1=1, f2=u'row1', f3=Row(field4=11, field5=None), f4=None) Row(f1=2, f2=None, f3=Row(field4=22..., f4=[Row(field7=u'row2')]) Row(f1=None, f2=u'row3', f3=Row(field4=33, field5=[]), f4=None) + >>> schema = StructType([ ... StructField("field2", StringType(), True), ... StructField("field3", -- cgit v1.2.3