initial codes for nanopq

Author: Yusuke Matsui

.gitignore

@@ -0,0 +1,92 @@
+.idea
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*,cover
+.hypothesis/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# IPython Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# dotenv
+.env
+
+# virtualenv
+.venv/
+venv/
+ENV/
+
+# Spyder project settings
+.spyderproject
+
+# Rope project settings
+.ropeproject

MANIFEST.in

@@ -0,0 +1 @@
+include LICENSE

Makefile

@@ -0,0 +1,8 @@
+.PHONY: init test
+
+init:
+	pip install -r requirements.txt
+
+test:
+	python -m unittest tests/*.py
+

README.md

@@ -0,0 +1,51 @@
+# nanopq
+
+Nano Product Quantization (nanopq): product quantization for nearest neighbor search in a single python file.
+
+This package contains a vanilla implementation of Product Quantization (PQ) and Optimized Product Quantization (OPQ) written in pure python without any third party dependencies.
+
+
+## Installing
+You can install the package via pip. This library works with Python 3.6+ on linux.
+```
+pip install nanopq
+```
+
+## Documentation
+- Tutorial
+- API
+
+## Example
+
+```python
+import nanopq
+import numpy as np
+
+X = np.random.random((10000, 128))
+query = np.random.random((128,))
+
+# Instantiate with M=8 sub-spaces
+pq = nanopq.PQ(M=8)
+
+# Train with the top 1000 vectors
+pq.fit(X[:1000])
+
+# Encode to pq-codes
+X_code = pq.encode(X)  # (10000, 8) with dtype=np.uint8
+
+# Results
+dtable = pq.dtable(query)  # Compute a distance table online
+dists = pq.adist(dtable, X_code)  # Asymmetric distance
+```
+
+## Author
+- [Yusuke Matsui](http://yusukematsui.me)
+
+
+## Reference
+- [H. Jegou, M. Douze, and C. Schmid, "Product Quantization for Nearest Neighbor Search", IEEE TPAMI 2011](https://ieeexplore.ieee.org/document/5432202/) (the original paper of PQ)
+- [T. Ge, K. He, Q. Ke, and J. Sun, "Optimized Product Quantization", IEEE TPAMI 2014](https://ieeexplore.ieee.org/document/6678503/) (the original paper of OPQ)
+- [Y. Matsui, Y. Uchida, H. Jegou, and S. Satoh, "A Survey of Product Quantization", ITE MTA 2018](https://www.jstage.jst.go.jp/article/mta/6/1/6_2/_pdf/) (a survey paper of PQ) 
+- [PQ in faiss](https://github.com/facebookresearch/faiss/wiki/Faiss-building-blocks:-clustering,-PCA,-quantization#pq-encoding--decoding) (Faiss contains an optimized implementation of PQ. See the difference to ours here)
+- [Rayuela.jl](https://github.com/una-dinosauria/Rayuela.jl) (Julia implementation of several encoding algorithms including PQ and OPQ)
+- [PQk-means](https://github.com/DwangoMediaVillage/pqkmeans) (clustering on PQ-codes. The implementation of nanopq is compatible to [that of PQk-means](https://github.com/DwangoMediaVillage/pqkmeans/blob/master/tutorial/1_pqkmeans.ipynb))

docs/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line.
+SPHINXOPTS    =
+SPHINXBUILD   = sphinx-build
+SPHINXPROJ    = nanopq
+SOURCEDIR     = .
+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)

docs/conf.py

@@ -0,0 +1,166 @@
+# -*- coding: utf-8 -*-
+#
+# Configuration file for the Sphinx documentation builder.
+#
+# This file does only contain a selection of the most common options. For a
+# full list see the documentation:
+# http://www.sphinx-doc.org/en/master/config
+
+# -- Path setup --------------------------------------------------------------
+
+# 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.
+#
+import os
+import sys
+sys.path.insert(0, os.path.abspath('../'))
+
+
+# -- Project information -----------------------------------------------------
+
+project = 'nanopq'
+copyright = '2018, Yusuke Matsui'
+author = 'Yusuke Matsui'
+
+# The short X.Y version
+version = ''
+# The full version, including alpha/beta/rc tags
+release = ''
+
+
+# -- 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.napoleon',
+]
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['_templates']
+
+# The suffix(es) of source filenames.
+# You can specify multiple suffix as a list of string:
+#
+# source_suffix = ['.rst', '.md']
+source_suffix = '.rst'
+
+# The master toctree document.
+master_doc = 'index'
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+#
+# This is also used if you do content translation via gettext catalogs.
+# Usually you set "language" from the command line for these cases.
+language = None
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This pattern also affects html_static_path and html_extra_path .
+exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = 'sphinx'
+
+
+# -- 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 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']
+
+# Custom sidebar templates, must be a dictionary that maps document names
+# to template names.
+#
+# The default sidebars (for documents that don't match any pattern) are
+# defined by theme itself.  Builtin themes are using these templates by
+# default: ``['localtoc.html', 'relations.html', 'sourcelink.html',
+# 'searchbox.html']``.
+#
+# html_sidebars = {}
+
+
+# -- Options for HTMLHelp output ---------------------------------------------
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = 'nanopqdoc'
+
+
+# -- 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': '',
+
+    # Latex figure (float) alignment
+    #
+    # 'figure_align': 'htbp',
+}
+
+# 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 = [
+    (master_doc, 'nanopq.tex', 'nanopq Documentation',
+     'Yusuke Matsui', 'manual'),
+]
+
+
+# -- Options for manual page output ------------------------------------------
+
+# One entry per manual page. List of tuples
+# (source start file, name, description, authors, manual section).
+man_pages = [
+    (master_doc, 'nanopq', 'nanopq Documentation',
+     [author], 1)
+]
+
+
+# -- 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 = [
+    (master_doc, 'nanopq', 'nanopq Documentation',
+     author, 'nanopq', 'One line description of project.',
+     'Miscellaneous'),
+]
+
+
+# -- Extension configuration -------------------------------------------------
+
+# Napoleon settings
+# napoleon_include_init_with_doc = True
+
+# autodoc
+autodoc_member_order = 'bysource'

docs/index.rst

@@ -0,0 +1,33 @@
+`nanopq <https://github.com/matsui528/nanopq>`_ documentation
+===================================================================
+
+
+
+Instalation
+-------------
+You can install the package via pip. This library works with Python 3.6+ on linux.
+
+::
+
+    $ pip install nanopq
+
+
+Contents
+--------
+
+.. toctree::
+   :maxdepth: 2
+
+   
+   tutorial
+   nanopq
+
+
+
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`