This is an automated email from the ASF dual-hosted git repository. charlie pushed a commit to branch python-docs in repository https://gitbox.apache.org/repos/asf/datasketches-cpp.git
commit 9ca1cbad61f85f6ef1f1d38a3d68aad9ac126f3f Author: Charlie Dickens <[email protected]> AuthorDate: Thu Jul 27 17:13:29 2023 -0700 Initial docs draft --- python/docs/Makefile | 20 +++++++++++ python/docs/make.bat | 35 +++++++++++++++++++ python/docs/source/conf.py | 41 +++++++++++++++++++++++ python/docs/source/cpc.rst | 7 ++++ python/docs/source/frequent_items.rst | 6 ++++ python/docs/source/hyper_log_log.rst | 7 ++++ python/docs/source/index.rst | 63 +++++++++++++++++++++++++++++++++++ python/docs/source/kll.rst | 19 +++++++++++ python/docs/source/theta.rst | 8 +++++ 9 files changed, 206 insertions(+) diff --git a/python/docs/Makefile b/python/docs/Makefile new file mode 100644 index 0000000..d0c3cbf --- /dev/null +++ b/python/docs/Makefile @@ -0,0 +1,20 @@ +# Minimal makefile for Sphinx documentation +# + +# You can set these variables from the command line, and also +# from the environment for the first two. +SPHINXOPTS ?= +SPHINXBUILD ?= sphinx-build +SOURCEDIR = source +BUILDDIR = build + +# Put it first so that "make" without argument is like "make help". +help: + @$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) + +.PHONY: help Makefile + +# Catch-all target: route all unknown targets to Sphinx using the new +# "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS). +%: Makefile + @$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) diff --git a/python/docs/make.bat b/python/docs/make.bat new file mode 100644 index 0000000..747ffb7 --- /dev/null +++ b/python/docs/make.bat @@ -0,0 +1,35 @@ +@ECHO OFF + +pushd %~dp0 + +REM Command file for Sphinx documentation + +if "%SPHINXBUILD%" == "" ( + set SPHINXBUILD=sphinx-build +) +set SOURCEDIR=source +set BUILDDIR=build + +%SPHINXBUILD% >NUL 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.https://www.sphinx-doc.org/ + exit /b 1 +) + +if "%1" == "" goto help + +%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O% +goto end + +:help +%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O% + +:end +popd diff --git a/python/docs/source/conf.py b/python/docs/source/conf.py new file mode 100644 index 0000000..aedd563 --- /dev/null +++ b/python/docs/source/conf.py @@ -0,0 +1,41 @@ +# Configuration file for the Sphinx documentation builder. +# +# For the full list of built-in configuration values, see the documentation: +# https://www.sphinx-doc.org/en/master/usage/configuration.html + +# -- Project information ----------------------------------------------------- +# https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information + +import sys +import os +#PATH = os.path.abspath(os.path.join(os.path.dirname(os.path.abspath(__file__)), '../../datasketches')) +sys.path.insert(0, os.path.abspath("../../datasketches")) +sys.path.insert(0, os.path.abspath("../../src")) +#print("Adding path:\n", PATH) +print("*****") +#sys.path.insert(0, PATH) #os.path.join(PATH, "cppyml")) +# sys.path.insert(0, os.path.join(PATH, "cppyml")) +# sys.path.insert(0, os.path.abspath('.')) +for sp in sys.path: + print(sp) + +project = 'datasketches' +copyright = '2023, charlie' +author = 'charlie' +release = '0.1' + +# -- General configuration --------------------------------------------------- +# https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration + +extensions = ["sphinx.ext.autodoc","sphinx.ext.autosummary"] + +templates_path = ['_templates'] +exclude_patterns = [] + + + +# -- Options for HTML output ------------------------------------------------- +# https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output + +html_theme = 'sphinx_rtd_theme' +html_static_path = ['_static'] diff --git a/python/docs/source/cpc.rst b/python/docs/source/cpc.rst new file mode 100644 index 0000000..ac18638 --- /dev/null +++ b/python/docs/source/cpc.rst @@ -0,0 +1,7 @@ +Compressed Probabilistic Counting (CPC) +--------------------------------------- +The *Compressed Probabilistic Counting* sketch is a space-efficient method for estimating cardinalities of sets. + +.. autoclass:: _datasketches.cpc_sketch + :members: + :undoc-members: diff --git a/python/docs/source/frequent_items.rst b/python/docs/source/frequent_items.rst new file mode 100644 index 0000000..c5f40fc --- /dev/null +++ b/python/docs/source/frequent_items.rst @@ -0,0 +1,6 @@ +Frequent Items +----------- + +.. autoclass:: _datasketches.frequent_items_sketch + :members: + :undoc-members: diff --git a/python/docs/source/hyper_log_log.rst b/python/docs/source/hyper_log_log.rst new file mode 100644 index 0000000..7253d9e --- /dev/null +++ b/python/docs/source/hyper_log_log.rst @@ -0,0 +1,7 @@ +HyperLogLog +----------- +The HyperLogLog sketch is a space-efficient method for estimating cardinalities of sets. + +.. autoclass:: _datasketches.hll_sketch + :members: + :undoc-members: diff --git a/python/docs/source/index.rst b/python/docs/source/index.rst new file mode 100644 index 0000000..ac8396c --- /dev/null +++ b/python/docs/source/index.rst @@ -0,0 +1,63 @@ +.. datasketches documentation master file, created by + sphinx-quickstart on Tue Jul 25 11:04:59 2023. + You can adapt this file completely to your liking, but it should at least + contain the root `toctree` directive. + +Apache DataSketches +================================================= + +**DataSketches** are highly-efficient algorithms to analyze big data quickly. + + +Distinct Counting +################# +.. + maxdepth: 1 means only the heading is printed in the contents +.. toctree:: + :maxdepth: 1 + + hyper_log_log + cpc + theta + +Quantile Estimation +################### + +.. toctree:: + :maxdepth: 1 + + kll + +Frequent Items +########################## +This problem may be known as **heavy hitters** or **TopK** + +.. toctree:: + :maxdepth: 1 + + frequent_items + + +.. note:: + + This project is under active development. + + +Indices and tables +================== + +* :ref:`genindex` +* :ref:`modindex` +* :ref:`search` + + +.. .. automodule:: datasketches +.. :members: + +.. .. automodule:: _datasketches +.. :members: + +.. +.. + +.. distinct_count diff --git a/python/docs/source/kll.rst b/python/docs/source/kll.rst new file mode 100644 index 0000000..312fd34 --- /dev/null +++ b/python/docs/source/kll.rst @@ -0,0 +1,19 @@ +KLL Sketch +---------- + +.. autoclass:: _datasketches.kll_ints_sketch + :members: + :undoc-members: + +.. autoclass:: _datasketches.kll_floats_sketch + :members: + :undoc-members: + +.. autoclass:: _datasketches.kll_doubles_sketch + :members: + :undoc-members: + +.. autoclass:: _datasketches.kll_items_sketch + :members: + :undoc-members: + diff --git a/python/docs/source/theta.rst b/python/docs/source/theta.rst new file mode 100644 index 0000000..bf85d9f --- /dev/null +++ b/python/docs/source/theta.rst @@ -0,0 +1,8 @@ +Theta Sketch +------------ +The *Theta Sketch* sketch is a space-efficient method for estimating cardinalities of sets. +It can also easily handle set operations (such as union, intersection, difference) while maintaining good accuarcy. + +.. autoclass:: _datasketches.theta_sketch + :members: + :undoc-members: --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
