From 2d56b39e838896e8a1bb34c559c5be9d5070b554 Mon Sep 17 00:00:00 2001
From: Dominique Benielli <dominique.benielli@lis-lab.fr>
Date: Wed, 15 Jan 2020 19:46:13 +0100
Subject: [PATCH] packaging
---
.gitlab-ci.yml | 38 ++++
MANIFEST.in | 5 +
README.rst | 147 +++++++++++++++
copyright.py | 105 +++++++++++
copyrightstamp.txt | 39 ++++
doc/conf.py | 277 +++++++++++++++++++++++++++++
doc/index.rst | 50 ++++++
doc/reference/api.rst | 26 +++
docker/Dockerfile_ubuntu_18.04 | 26 +++
license.txt | 30 ++++
multimodal/__init__.py | 1 +
multimodal/boosting/__init__.py | 9 +-
multimodal/boosting/cumbo.py | 16 +-
multimodal/boosting/mumbo.py | 13 +-
multimodal/datasets/data_sample.py | 10 +-
multimodal/kernels/__init__.py | 5 +-
multimodal/kernels/lpMKL.py | 2 +
multimodal/kernels/mkernel.py | 39 +++-
multimodal/kernels/mvml.py | 30 +---
setup.cfg | 16 ++
setup.py | 68 +++++++
21 files changed, 892 insertions(+), 60 deletions(-)
create mode 100644 .gitlab-ci.yml
create mode 100644 MANIFEST.in
create mode 100644 README.rst
create mode 100644 copyright.py
create mode 100644 copyrightstamp.txt
create mode 100644 doc/conf.py
create mode 100644 doc/index.rst
create mode 100644 doc/reference/api.rst
create mode 100644 docker/Dockerfile_ubuntu_18.04
create mode 100644 license.txt
create mode 100644 setup.cfg
create mode 100644 setup.py
diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
new file mode 100644
index 0000000..72f9c51
--- /dev/null
+++ b/.gitlab-ci.yml
@@ -0,0 +1,38 @@
+# run the test suite
+tests:
+ image: registry.gitlab.lis-lab.fr:5005/dev/multimodal/ubuntu:18.04
+ tags:
+ - docker
+ script:
+ - python3 setup.py install
+ - pytest-3
+
+# generate the documentation
+doc:
+ image: registry.gitlab.lis-lab.fr:5005/dev/multimodal/ubuntu:18.04
+ tags:
+ - docker
+ only:
+ - master
+ script:
+ - export LC_ALL=$(locale -a | grep en_US)
+ - export LANG=$(locale -a | grep en_US)
+ - python3 setup.py build_sphinx
+
+# TODO: Replace the task doc by the following task pages when making the
+# project public
+#
+#pages:
+# image: registry.gitlab.lis-lab.fr:5005/dev/multimodal/ubuntu:18.04
+# tags:
+# - docker
+# only:
+# - master
+# script:
+# - export LC_ALL=$(locale -a | grep en_US)
+# - export LANG=$(locale -a | grep en_US)
+# - python3 setup.py build_sphinx
+# - cp -r build/sphinx/html public
+# artifacts:
+# paths:
+# - public
diff --git a/MANIFEST.in b/MANIFEST.in
new file mode 100644
index 0000000..ece9ebb
--- /dev/null
+++ b/MANIFEST.in
@@ -0,0 +1,5 @@
+include *.txt
+include *.rst
+include doc/*.rst doc/*.py
+include multimodal/tests/*.py
+include examples/*.py examples/*.txt
diff --git a/README.rst b/README.rst
new file mode 100644
index 0000000..e2bc4c4
--- /dev/null
+++ b/README.rst
@@ -0,0 +1,147 @@
+scikit-multimodallearn
+======================
+
+**scikit-multimodallearn** is a Python package implementing algorithms multimodal data.
+
+It is compatible with `scikit-learn <http://scikit-learn.org/>`_, a popular
+package for machine learning in Python.
+
+
+Documentation
+-------------
+
+The **documentation** including installation instructions, API documentation
+and examples is
+`available online <http://dev.pages.lis-lab.fr/multimodal>`_.
+
+
+Installation
+------------
+
+Dependencies
+~~~~~~~~~~~~
+
+**scikit-multimodallearn** works with **Python 3.5 or later**.
+
+**scikit-multimodallearn** depends on **scikit-learn** (version >= 0.19).
+
+Optionally, **matplotlib** is required to run the examples.
+
+Installation using pip
+~~~~~~~~~~~~~~~~~~~~~~
+
+**scikit-multimodallearn** is
+`available on PyPI <https://pypi.org/project/multiconfusion/>`_
+and can be installed using **pip**::
+
+ pip install scikit-multimodallearn
+
+
+Development
+-----------
+
+The development of this package follows the guidelines provided by the
+scikit-learn community.
+
+Refer to the `Developer's Guide <http://scikit-learn.org/stable/developers>`_
+of the scikit-learn project for more details.
+
+Source code
+~~~~~~~~~~~
+
+You can get the **source code** from the **Git** repository of the project::
+
+ git clone git@gitlab.lis-lab.fr:dev/multiconfusion.git
+
+Testing
+~~~~~~~
+
+**pytest** and **pytest-cov** are required to run the **test suite** with::
+
+ cd multiconfusion
+ pytest
+
+A code coverage report is displayed in the terminal when running the tests.
+An HTML version of the report is also stored in the directory **htmlcov**.
+
+
+Generating the documentation
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The generation of the documentation requires **sphinx**, **sphinx-gallery**,
+**numpydoc** and **matplotlib** and can be run with::
+
+ python setup.py build_sphinx
+
+The resulting files are stored in the directory **build/sphinx/html**.
+
+
+Credits
+-------
+
+**scikit-multimodallearn** is developped by the
+`development team <https://developpement.lis-lab.fr/>`_ of the
+`LIS <http://www.lis-lab.fr/>`_.
+
+If you use **scikit-multimodallearn** in a scientific publication, please cite the
+following paper::
+
+ @InProceedings{Koco:2011:BAMCC,
+ author={Ko\c{c}o, Sokol and Capponi, C{\'e}cile},
+ editor={Gunopulos, Dimitrios and Hofmann, Thomas and Malerba, Donato
+ and Vazirgiannis, Michalis},
+ title={A Boosting Approach to Multiview Classification with Cooperation},
+ booktitle={Proceedings of the 2011 European Conference on Machine Learning
+ and Knowledge Discovery in Databases - Volume Part II},
+ year={2011},
+ location={Athens, Greece},
+ publisher={Springer-Verlag},
+ address={Berlin, Heidelberg},
+ pages={209--228},
+ numpages = {20},
+ isbn={978-3-642-23783-6}
+ url={https://link.springer.com/chapter/10.1007/978-3-642-23783-6_14},
+ keywords={boosting, classification, multiview learning,
+ supervised learning},
+ }
+
+
+References
+~~~~~~~~~~
+* Sokol Koço, Cécile Capponi,
+ `"Learning from Imbalanced Datasets with cross-view cooperation"`
+ Linking and mining heterogeneous an multi-view data, Unsupervised and
+ semi-supervised learning Series Editor M. Emre Celeri, pp 161-182, Springer
+
+
+* Sokol Koço, Cécile Capponi,
+ `"A boosting approach to multiview classification with cooperation"
+ <https://link.springer.com/chapter/10.1007/978-3-642-23783-6_14>`_,
+ Proceedings of the 2011 European Conference on Machine Learning (ECML),
+ Athens, Greece, pp.209-228, 2011, Springer-Verlag.
+
+* Sokol Koço,
+ `"Tackling the uneven views problem with cooperation based ensemble
+ learning methods" <http://www.theses.fr/en/2013AIXM4101>`_,
+ PhD Thesis, Aix-Marseille Université, 2013.
+
+* Riikka Huusari, Hachem Kadri and Cécile Capponi,
+ "Multi-View Metric Learning in Vector-Valued Kernel Spaces"
+ in International Conference on Artificial Intelligence and Statistics (AISTATS) 2018
+
+Copyright
+~~~~~~~~~
+
+Université d'Aix Marseille (AMU) -
+Centre National de la Recherche Scientifique (CNRS) -
+Université de Toulon (UTLN).
+
+Copyright © 2017-2018 AMU, CNRS, UTLN
+
+License
+~~~~~~~
+
+**multiconfusion** is free software: you can redistribute it and/or modify
+it under the terms of the **GNU Lesser General Public License** as published by
+the Free Software Foundation, either **version 3** of the License, or
+(at your option) any later version.
diff --git a/copyright.py b/copyright.py
new file mode 100644
index 0000000..dcf2f20
--- /dev/null
+++ b/copyright.py
@@ -0,0 +1,105 @@
+# -*- coding: utf-8 -*-
+from __future__ import print_function, division
+import time
+import os
+import sys
+import fileinput
+
+
+def findFiles(directory, files=[]):
+ """scan a directory for py, pyx, pxd extension files."""
+ for filename in os.listdir(directory):
+ path = os.path.join(directory, filename)
+ if os.path.isfile(path) and (path.endswith(".py") or
+ path.endswith(".pyx") or
+ path.endswith(".pxd")):
+ if filename != "__init__.py" and filename != "version.py":
+ files.append(path)
+ elif os.path.isdir(path):
+ findFiles(path, files)
+ return files
+
+
+def fileUnStamping(filename):
+ """ Remove stamp from a file """
+ is_stamp = False
+ for line in fileinput.input(filename, inplace=1):
+ if line.find("# COPYRIGHT #") != -1:
+ is_stamp = not is_stamp
+ elif not is_stamp:
+ print(line, end="")
+
+
+def fileStamping(filename, stamp):
+ """ Write a stamp on a file
+
+ WARNING : The stamping must be done on an default utf8 machine !
+ """
+ old_stamp = False # If a copyright already exist over write it.
+ for line in fileinput.input(filename, inplace=1):
+ if line.find("# COPYRIGHT #") != -1:
+ old_stamp = not old_stamp
+ elif line.startswith("# -*- coding: utf-8 -*-"):
+ print(line, end="")
+ print(stamp)
+ elif not old_stamp:
+ print(line, end="")
+
+
+def getStamp(date, iw_version):
+ """ Return the corrected formated stamp """
+ stamp = open("copyrightstamp.txt").read()
+ stamp = stamp.replace("DATE", date)
+ stamp = stamp.replace("IW_VERSION", iw_version)
+ stamp = stamp.replace('\n', '\n# ')
+ stamp = "# " + stamp
+ stamp = stamp.replace("# \n", "#\n")
+ return stamp.strip()
+
+
+def getVersionsAndDate():
+ """ Return (date, iw_version) """
+ v_text = open('VERSION').read().strip()
+ v_text_formted = '{"' + v_text.replace('\n', '","').replace(':', '":"')
+ v_text_formted += '"}'
+ v_dict = eval(v_text_formted)
+ return (time.strftime("%Y"), v_dict['iw'])
+
+
+def writeStamp():
+ """ Write a copyright stamp on all files """
+ stamp = getStamp(*getVersionsAndDate())
+ files = findFiles(os.path.join(os.path.dirname(os.path.abspath(__file__)),
+ "iw"))
+ for filename in files:
+ fileStamping(filename, stamp)
+ fileStamping("setup.py", stamp)
+
+
+def eraseStamp():
+ """ Erase a copyright stamp from all files """
+ files = findFiles(os.path.join(os.path.dirname(os.path.abspath(__file__)),
+ "iw"))
+ for filename in files:
+ fileUnStamping(filename)
+ fileUnStamping("setup.py")
+
+
+def usage(arg):
+ print("Usage :")
+ print("\tpython %s stamping" % arg)
+ print("\tpython %s unstamping" % arg)
+
+
+if __name__ == "__main__":
+ if len(sys.argv) == 1:
+ usage(sys.argv[0])
+ elif len(sys.argv) == 2:
+ if sys.argv[1].startswith("unstamping"):
+ eraseStamp()
+ elif sys.argv[1].startswith("stamping"):
+ writeStamp()
+ else:
+ usage(sys.argv[0])
+ else:
+ usage(sys.argv[0])
diff --git a/copyrightstamp.txt b/copyrightstamp.txt
new file mode 100644
index 0000000..bb382b5
--- /dev/null
+++ b/copyrightstamp.txt
@@ -0,0 +1,39 @@
+######### COPYRIGHT #########
+
+Copyright(c) DATE
+-----------------
+
+* Université d'Aix Marseille (AMU) -
+* Centre National de la Recherche Scientifique (CNRS) -
+* Université de Toulon (UTLN).
+* Copyright © 2019-2020 AMU, CNRS, UTLN
+
+Contributors:
+------------
+
+* Sokol Koço <sokol.koco_AT_lis-lab.fr>
+* Cécile Capponi <cecile.capponi_AT_univ-amu.fr>
+* Florent Jaillet <florent.jaillet_AT_math.cnrs.fr>
+* Dominique Benielli <dominique.benielli_AT_univ-amu.fr>
+* Riikka Huusari <rikka.huusari_AT_univ-amu.fr>
+* Baptiste Bauvin <baptiste.bauvin_AT_univ-amu.fr>
+
+Description:
+-----------
+
+The multimodal package implement classifiers multiview,
+MumboClassifier class, MuCumboClassifier class, MVML class, MKL class.
+compatible with sklearn
+
+Version:
+-------
+
+* multimodal version = MULTIMODAL_VERSION
+
+Licence:
+-------
+
+License: LGPLv3+
+
+
+######### COPYRIGHT #########
diff --git a/doc/conf.py b/doc/conf.py
new file mode 100644
index 0000000..a45f0cf
--- /dev/null
+++ b/doc/conf.py
@@ -0,0 +1,277 @@
+# -*- coding: utf-8 -*-
+
+from datetime import date
+import os
+import sys
+sys.path.insert(0, os.path.abspath('../metriclearning'))
+sys.path.insert(0, os.path.abspath('../..'))
+sys.path.insert(0, os.path.abspath("."))
+sys.path.append(os.path.join(os.path.dirname(__name__), '..'))
+sys.path.append(os.path.join(os.path.abspath(os.path.dirname(__file__)), 'sphinxext'))
+import metriclearning
+
+# 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.imgmath',
+ 'numpydoc',
+ # 'sphinx_gallery.gen_gallery'
+]
+
+# 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'
+
+# The master toctree document.
+master_doc = 'index'
+
+# General information about the project.
+project = 'metriclearning'
+author = 'Dominique Benielli'
+copyright = '2017-{}, LIS UMR 7020'.format(date.today().year)
+
+# 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 = metriclearning.__version__
+# The full version, including alpha/beta/rc tags.
+release = metriclearning.__version__
+
+# 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 = '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 = 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 = '{}doc'.format(project)
+
+
+# -- Options for LaTeX output ---------------------------------------------
+
+latex_elements = {
+ # The paper size ('letterpaper' or 'a4paper').
+ 'papersize': 'a4paper',
+
+ # 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, '{}.tex'.format(project), '{} Documentation'.format(project),
+ 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 = [
+ (master_doc, project, '{} Documentation'.format(project),
+ [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 = [
+ (master_doc, project, '{} Documentation'.format(project), author, project,
+ 'Multi-View Metric Learning in Vector-Valued Kernel Spaces for machine learning.',
+ '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 = {
+ 'sklearn': ('http://scikit-learn.org/stable', None)
+}
+
+numpydoc_show_class_members = False
+
+sphinx_gallery_conf = {
+ 'doc_module': (project,),
+ 'backreferences_dir': 'backreferences',
+ # path to your examples scripts
+ 'examples_dirs': '../examples',
+ # path where to save gallery generated examples
+ 'gallery_dirs': 'auto_examples'}
+
+# Generate the plots for the gallery
+plot_gallery = 'True'
diff --git a/doc/index.rst b/doc/index.rst
new file mode 100644
index 0000000..a8fc552
--- /dev/null
+++ b/doc/index.rst
@@ -0,0 +1,50 @@
+.. metriclearning documentation master file, created by
+ sphinx-quickstart on Mon Sep 2 12:12:08 2019.
+ You can adapt this file completely to your liking, but it should at least
+ contain the root `toctree` directive.
+
+Welcome to scikit-multimodallearn's documentation!
+==================================================
+**scikit-multimodallearn** is a Python package implementing boost and kernel algorithms for
+machine learning with multimodal data.
+
+It is compatible with `scikit-learn <http://scikit-learn.org/>`_, a popular
+package for machine learning in Python.
+
+
+Documentation
+-------------
+
+.. toctree::
+ :maxdepth: 2
+ :caption: Contents:
+
+
+
+ reference/api
+ tutorial/install_devel
+ tutorial/auto_examples/index
+
+
+
+Documentation
+-------------
+
+:Release: |version|
+:Date: |today|
+
+.. toctree::
+ :maxdepth: 1
+
+ install_devel
+ api
+ auto_examples/index
+ credits
+
+
+Indices and tables
+------------------
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`
diff --git a/doc/reference/api.rst b/doc/reference/api.rst
new file mode 100644
index 0000000..815df9e
--- /dev/null
+++ b/doc/reference/api.rst
@@ -0,0 +1,26 @@
+API Documentation
+=================
+
+
+multimodal.boosting.mumbo
+-------------------------
+
+.. automodule:: multimodal.boosting.mumbo
+ :members:
+ :inherited-members:
+
+
+multimodal.boosting.cumbo
+-------------------------
+
+.. automodule:: multimodal.boosting.cumbo
+ :members:
+ :inherited-members:
+
+
+multimodal.boosting.boost
+-------------------------
+
+.. automodule:: multimodal.boosting.boost
+ :members:
+ :inherited-members:
diff --git a/docker/Dockerfile_ubuntu_18.04 b/docker/Dockerfile_ubuntu_18.04
new file mode 100644
index 0000000..309a621
--- /dev/null
+++ b/docker/Dockerfile_ubuntu_18.04
@@ -0,0 +1,26 @@
+FROM ubuntu:18.04
+MAINTAINER Dominique Benielli
+WORKDIR /
+ENV DEBIAN_FRONTEND noninteractive
+RUN apt-get update && \
+ apt-get upgrade -y && \
+ apt-get install -y --no-install-recommends \
+ python3 \
+ python3-setuptools \
+ python3-sklearn\
+ python3-pytest \
+ python3-pytest-cov \
+ python3-nose \
+ python3-sphinx \
+ python3-numpydoc \
+ python3-sphinx-gallery \
+ python3-matplotlib \
+ python3-pil \
+ && \
+ apt-get clean
+RUN apt-get install -y --no-install-recommends locales && \
+ apt-get clean && \
+ locale-gen en_US.UTF-8 && \
+ update-locale en_US.UTF-8 && \
+ echo "export LC_ALL=$(locale -a | grep en_US)" >> /root/.bashrc && \
+ echo "export LANG=$(locale -a | grep en_US)" >> /root/.bashrc
diff --git a/license.txt b/license.txt
new file mode 100644
index 0000000..1011e46
--- /dev/null
+++ b/license.txt
@@ -0,0 +1,30 @@
+New BSD License
+
+Copyright (c) 2020-15-01, The scit-multimodallearn developers.
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+ a. Redistributions of source code must retain the above copyright notice,
+ this list of conditions and the following disclaimer.
+ b. Redistributions in binary form must reproduce the above copyright
+ notice, this list of conditions and the following disclaimer in the
+ documentation and/or other materials provided with the distribution.
+ c. Neither the name of the IntertwiningWavelet developers nor the names of
+ its contributors may be used to endorse or promote products
+ derived from this software without specific prior written
+ permission.
+
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE FOR
+ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
+DAMAGE.
diff --git a/multimodal/__init__.py b/multimodal/__init__.py
index e69de29..1ff9679 100644
--- a/multimodal/__init__.py
+++ b/multimodal/__init__.py
@@ -0,0 +1 @@
+__version__ = '0.0.dev0'
diff --git a/multimodal/boosting/__init__.py b/multimodal/boosting/__init__.py
index 5b5a0e3..bb0d1af 100644
--- a/multimodal/boosting/__init__.py
+++ b/multimodal/boosting/__init__.py
@@ -1,11 +1,6 @@
from .mumbo import MumboClassifier
-
-__all__ = ['MumboClassifier']
-
-__version__ = '1.0.dev0'
-
from .cumbo import MuCumboClassifier
-__all__ = ['MuCumboClassifier']
+__all__ = ['MumboClassifier', 'MuCumboClassifier']
+
-__version__ = '1.0.dev0'
diff --git a/multimodal/boosting/cumbo.py b/multimodal/boosting/cumbo.py
index 0f928df..0d7eb4d 100644
--- a/multimodal/boosting/cumbo.py
+++ b/multimodal/boosting/cumbo.py
@@ -408,6 +408,7 @@ class MuCumboClassifier(BaseEnsemble, ClassifierMixin, UBoosting):
ValueError where `X` and `view_ind` are not compatibles
"""
warnings.filterwarnings("ignore")
+ self.X_ = self._global_X_transform(X, views_ind=views_ind)
if (self.base_estimator is None or
isinstance(self.base_estimator, (BaseDecisionTree,
BaseForest))):
@@ -416,16 +417,12 @@ class MuCumboClassifier(BaseEnsemble, ClassifierMixin, UBoosting):
else:
dtype = None
accept_sparse = ['csr', 'csc']
- if views_ind is None:
- if X.shape[1] > 1:
- views_ind = np.array([0, X.shape[1]//2, X.shape[1]])
- else:
- views_ind = np.array([0, X.shape[1]])
- self.X_ = self._global_X_transform(X, views_ind=views_ind)
- views_ind_, n_views = self.X_._validate_views_ind(views_ind,
- X.shape[1])
- check_X_y(self.X_, y, accept_sparse=accept_sparse, dtype=dtype)
+
+
+ views_ind_, n_views = self.X_._validate_views_ind(self.X_.views_ind,
+ self.X_.shape[1])
+ check_X_y(self.X_, y)
check_classification_targets(y)
self._validate_estimator()
@@ -472,7 +469,6 @@ class MuCumboClassifier(BaseEnsemble, ClassifierMixin, UBoosting):
# TO DO estimator_errors_ estimate
###########################################
-
#############self.estimator_errors_[current_iteration] = to do
# update C_t de g
diff --git a/multimodal/boosting/mumbo.py b/multimodal/boosting/mumbo.py
index f2c522d..6405e5d 100644
--- a/multimodal/boosting/mumbo.py
+++ b/multimodal/boosting/mumbo.py
@@ -344,13 +344,7 @@ class MumboClassifier(BaseEnsemble, ClassifierMixin, UBoosting):
else:
dtype = None
accept_sparse = ['csr', 'csc']
- # if views_ind is None:
- # if X.shape[1] > 1:
- # views_ind = np.array([0, X.shape[1]//2, X.shape[1]])
- # elif X.shape[1]==1:
- # views_ind = np.array([0, X.shape[1]])
- # else:
- # views_ind = np.array([0])
+
self.X_ = self._global_X_transform(X, views_ind=views_ind)
views_ind_, n_views = self.X_._validate_views_ind(self.X_.views_ind,
self.X_.shape[1])
@@ -442,10 +436,12 @@ class MumboClassifier(BaseEnsemble, ClassifierMixin, UBoosting):
Parameters
----------
- X : {array-like, sparse matrix}, shape = (n_samples, n_features)
+ X : { array-like, sparse matrix},
+ shape = (n_samples, n_views * n_features)
Multi-view input samples.
Sparse matrix can be CSC, CSR, COO, DOK, or LIL.
COO, DOK and LIL are converted to CSR.
+ maybe also MultimodalData
Returns
-------
@@ -493,6 +489,7 @@ class MumboClassifier(BaseEnsemble, ClassifierMixin, UBoosting):
Multi-view input samples.
Sparse matrix can be CSC, CSR, COO, DOK, or LIL.
COO, DOK and LIL are converted to CSR.
+ maybe also MultimodalData
Returns
-------
diff --git a/multimodal/datasets/data_sample.py b/multimodal/datasets/data_sample.py
index 9f6d730..7894518 100644
--- a/multimodal/datasets/data_sample.py
+++ b/multimodal/datasets/data_sample.py
@@ -1,9 +1,9 @@
# -*- coding: utf-8 -*-
-"""This module contains the DataSample class and Metriclearn_array class
+"""This module contains the DataSample class, MultiModalArray, MultiModalSparseArray, MultiModalSparseInfo and MultiModalData, class
The DataSample class encapsulates a sample 's components
nbL and nbEx numbers,
-Metriclearn_arra class inherit from numpy ndarray and contains a 2d data ndarray
+MultiModalArray class inherit from numpy ndarray and contains a 2d data ndarray
with the shape (n_samples, n_view_i * n_features_i)
0 1 2 3
@@ -19,8 +19,8 @@ xxxxxxxx xxxx xxxx xxxx
xxxxxxxx xxxx xxxx xxxx
======== ==== ==== ====
-the number nbL and nbEx and , the fourth dictionaries for sample,
-prefix, suffix and factor where they are computed
+MultiModalSparseArray inherit from scipy sparce matrix with the shape (n_samples, n_view_i * n_features_i)
+
"""
from abc import ABCMeta
import numpy as np
@@ -77,7 +77,7 @@ class MultiModalData(metaclass=ABCMeta):
def _validate_views_ind(self, views_ind, n_features):
"""Ensure proper format for views_ind and return number of views."""
- views_ind = np.array(views_ind)
+ # views_ind = np.array(views_ind)
if np.issubdtype(views_ind.dtype, np.integer) and views_ind.ndim == 1:
if len(views_ind) > 2 and np.any(views_ind[:-1] >= views_ind[1:]):
raise ValueError("Values in views_ind must be sorted.")
diff --git a/multimodal/kernels/__init__.py b/multimodal/kernels/__init__.py
index 7d48045..02895ab 100644
--- a/multimodal/kernels/__init__.py
+++ b/multimodal/kernels/__init__.py
@@ -1 +1,4 @@
-__all__ = ['MVML', 'MKernel', 'MVML']
+from .lpMKL import MKL
+from .mvml import MVML
+
+__all__ = ['MVML', 'MKL']
diff --git a/multimodal/kernels/lpMKL.py b/multimodal/kernels/lpMKL.py
index 1eca272..9de928a 100644
--- a/multimodal/kernels/lpMKL.py
+++ b/multimodal/kernels/lpMKL.py
@@ -36,6 +36,7 @@ class MKL(BaseEstimator, ClassifierMixin, MKernel):
n_loops : (default 50) number of iterions
+
Attributes
----------
lmbda : float coeficient for combined kernels
@@ -140,6 +141,7 @@ class MKL(BaseEstimator, ClassifierMixin, MKernel):
-------
return tuple (C, weights)
"""
+ C = None
views = self.K_.n_views
X = self.K_
p = 2
diff --git a/multimodal/kernels/mkernel.py b/multimodal/kernels/mkernel.py
index ac1ef5c..a550dcb 100644
--- a/multimodal/kernels/mkernel.py
+++ b/multimodal/kernels/mkernel.py
@@ -8,10 +8,22 @@ from multimodal.datasets.data_sample import DataSample, MultiModalArray
class MKernel(metaclass=ABCMeta):
"""
Abstract class MKL and MVML should inherit from
- for methods of transform kernel to/from data
+ for methods of transform kernel to/from data.
+
+
+ Attributes
+ ----------
+
+ W_sqrootinv_dict : dict of nyström approximation kernel
+ in the case of nystrom approximation
+ the a dictonary of reduced kernel is calculated
+
+ kernel_params : list of dict of corresponding kernels
+ params KERNEL_PARAMS
"""
def _get_kernel(self, X, Y=None, v=0):
+ met =None
if self.kernel_params is not None:
if isinstance(self.kernel_params, list):
ind = min(v, len(self.kernel) - 1)
@@ -30,9 +42,34 @@ class MKernel(metaclass=ABCMeta):
filter_params=True, **params)
def _global_kernel_transform(self, X, views_ind=None, Y=None):
+ """
+ Private function witch transforms X input format to
+ :class:`multimodal.datasets.MultiModalData` and internal kernels
+
+ Parameters
+ ----------
+ X : input data should be 'MultiModalArray'
+ array [n_samples_a, n_samples_a] if metric == “precomputed”,
+ or, [n_samples_a, n_view* n_features]
+ otherwise Array of pairwise kernels between samples,
+ or a feature array.
+
+ views_ind : list or numpy arra, (default : None) indicate
+ the struture of different views
+
+ Y : second input for pairing kernel by pairwise_kernels in the case
+ of
+
+
+ Returns
+ -------
+ (X_, K_) tuple tranform Data X_ in :class:`multimodal.datasets.MultiModalData`
+ K_ dict of kernels
+ """
kernel_dict = {}
X_ = None
+ y = None
if Y is None:
y = Y
if isinstance(X, np.ndarray) and X.ndim == 1:
diff --git a/multimodal/kernels/mvml.py b/multimodal/kernels/mvml.py
index 535d974..6ab1d62 100644
--- a/multimodal/kernels/mvml.py
+++ b/multimodal/kernels/mvml.py
@@ -14,39 +14,13 @@ from multimodal.datasets.data_sample import DataSample, MultiModalArray
from multimodal.kernels.mkernel import MKernel
"""
- Copyright (C) 2018 Riikka Huusari
-
- This program is free software: you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation, either version 3 of the License, or
- (at your option) any later version.
-
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY; without even the implied warranty of
- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- GNU General Public License for more details.
-
- You should have received a copy of the GNU General Public License
- along with this program. If not, see <http://www.gnu.org/licenses/>.
-
-
-This file contains algorithms for Multi-View Metric Learning (MVML) as introduced in
+This file contains algorithms for MultiModal Learning (MVML) as
+introduced in
Riikka Huusari, Hachem Kadri and Cécile Capponi:
Multi-View Metric Learning in Vector-Valued Kernel Spaces
in International Conference on Artificial Intelligence and Statistics (AISTATS) 2018
-Usage (see also demo.py for a more detailed example):
- create a MVML object via:
- mvml = MVML(kernel_dict, label_vector, regression_parameter_list, nystrom_param)
- learn the model:
- A, g, w = mvml.learn_mvml()
- predict with the model:
- predictions = predict_mvml(test_kernel_dict, g, w)
-
-(parameter names as in the paper)
-
-Code is tested with Python 3.5.2 and numpy 1.12.1
"""
diff --git a/setup.cfg b/setup.cfg
new file mode 100644
index 0000000..bf8d7b4
--- /dev/null
+++ b/setup.cfg
@@ -0,0 +1,16 @@
+[metadata]
+license_file = LICENSE.txt
+
+[tool:pytest]
+testpaths = multimodal
+addopts = --verbose
+ --cov-report=term-missing
+ --cov-report=html
+ --cov=multimodalboost
+ --doctest-modules
+
+[coverage:run]
+branch = True
+source = multimodal
+include = */multimodal/*
+omit = */tests/*
diff --git a/setup.py b/setup.py
new file mode 100644
index 0000000..030ae13
--- /dev/null
+++ b/setup.py
@@ -0,0 +1,68 @@
+
+import os
+from setuptools import setup, find_packages
+
+import multiconfusion
+
+
+def setup_package():
+ """Setup function"""
+
+ name = 'scikit-multimodallearn'
+ version = multiconfusion.__version__
+ description = 'A scikit-learn compatible package for multimodal Classifiers'
+ here = os.path.abspath(os.path.dirname(__file__))
+ with open(os.path.join(here, 'README.rst'), encoding='utf-8') as readme:
+ long_description = readme.read()
+ group = 'dev'
+ url = 'https://gitlab.lis-lab.fr/{}/{}'.format(group, name)
+ project_urls = {
+ 'Documentation': 'http://{}.pages.lis-lab.fr/{}'.format(group, name),
+ 'Source': url,
+ 'Tracker': '{}/issues'.format(url)}
+ author = 'Dominique Benielli'
+ author_email = 'contact.dev@lis-lab.fr'
+ license = 'newBSD'
+ classifiers = [
+ 'Development Status :: 5 - Production/Stable',
+ 'Intended Audience :: Science/Research',
+ 'License :: OSI Approved :: GNU Lesser General Public License'
+ ' v3 or later (LGPLv3+)',
+ 'Programming Language :: Python :: 3',
+ 'Programming Language :: Python :: 3.5',
+ 'Programming Language :: Python :: 3.6',
+ 'Topic :: Scientific/Engineering',
+ 'Topic :: Scientific/Engineering :: Artificial Intelligence',
+ 'Operating System :: Microsoft :: Windows',
+ 'Operating System :: POSIX :: Linux',
+ 'Operating System :: MacOS'],
+ keywords = ('machine learning, supervised learning, classification, '
+ 'ensemble methods, boosting, kernel')
+ packages = find_packages(exclude=['*.tests'])
+ install_requires = ['scikit-learn>=0.19', 'numpy', 'scipy', 'cvxopt' ]
+ python_requires = '>=3.5'
+ extras_require = {
+ 'dev': ['pytest', 'pytest-cov'],
+ 'doc': ['sphinx', 'numpydoc', 'sphinx_gallery', 'matplotlib']}
+ include_package_data = True
+
+ setup(name=name,
+ version=version,
+ description=description,
+ long_description=long_description,
+ url=url,
+ project_urls=project_urls,
+ author=author,
+ author_email=author_email,
+ license=license,
+ classifiers=classifiers,
+ keywords=keywords,
+ packages=packages,
+ install_requires=install_requires,
+ python_requires=python_requires,
+ extras_require=extras_require,
+ include_package_data=include_package_data)
+
+
+if __name__ == "__main__":
+ setup_package()
--
GitLab