Doctorado-ML/bayesclass
1
0
Fork 0
mirror of https://github.com/Doctorado-ML/bayesclass.git synced 2025-08-15 15:45:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Initial commit

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2022-11-04 11:53:06 +01:00
parent 89bacb501e
commit 3689852205
36 changed files with 1962 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
.circleci/config.yml Normal file
View File

@@ -0,0 +1,38 @@
version: 2
jobs:
build:
docker:
- image: circleci/python:3.10.0a7
working_directory: ~/repo
steps:
- checkout
- run:
name: install dependencies
command: |
wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -O miniconda.sh
chmod +x miniconda.sh && ./miniconda.sh -b -p ~/miniconda
export PATH="~/miniconda/bin:$PATH"
conda update --yes --quiet conda
conda create -n testenv --yes --quiet python=3
source activate testenv
conda install --yes pip numpy scipy scikit-learn matplotlib sphinx sphinx_rtd_theme numpydoc pillow
pip install sphinx-gallery
pip install .
cd doc
make html
- store_artifacts:
path: doc/_build/html/
destination: doc
- store_artifacts:
path: ~/log.txt
- run: ls -ltrh doc/_build/html
filters:
branches:
ignore: gh-pages
workflows:
version: 2
workflow:
jobs:
- build

21
.coveragerc Normal file
View File

@@ -0,0 +1,21 @@
# Configuration for coverage.py
[run]
branch = True
source = bayesclass
include = */bayesclass/*
omit =
*/setup.py
[report]
exclude_lines =
pragma: no cover
def __repr__
if self.debug:
if settings.DEBUG
raise AssertionError
raise NotImplementedError
if 0:
if __name__ == .__main__.:
if self.verbose:
show_missing = True

67
.gitignore vendored Normal file
View File

@@ -0,0 +1,67 @@
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class
# C extensions
*.so
# scikit-learn specific
doc/_build/
doc/auto_examples/
doc/modules/generated/
doc/datasets/generated/
# 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
# Sphinx documentation
doc/_build/
doc/generated/
# PyBuilder
target/

8
.readthedocs.yml Normal file
View File

@@ -0,0 +1,8 @@
formats:
- none
requirements_file: requirements.txt
python:
pip_install: true
extra_requirements:
- tests
- docs

50
.travis.yml Normal file
View File

@@ -0,0 +1,50 @@
dist: trusty
sudo: false
language: python
cache:
directories:
- $HOME/.cache/pip
matrix:
include:
- env: PYTHON_VERSION="3.5" NUMPY_VERSION="1.13.1" SCIPY_VERSION="0.19.1"
SKLEARN_VERSION="0.19.1"
- env: PYTHON_VERSION="3.6" NUMPY_VERSION="1.13.1" SCIPY_VERSION="0.19.1"
SKLEARN_VERSION="0.20.3"
- env: PYTHON_VERSION="3.7" NUMPY_VERSION="*" SCIPY_VERSION="*"
SKLEARN_VERSION="*"
- env: PYTHON_VERSION="3.7" NUMPY_VERSION="*" SCIPY_VERSION="*"
SKLEARN_VERSION="nightly"
install:
# install miniconda
- deactivate
- wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -O miniconda.sh
- MINICONDA_PATH=/home/travis/miniconda
- chmod +x miniconda.sh && ./miniconda.sh -b -p $MINICONDA_PATH
- export PATH=$MINICONDA_PATH/bin:$PATH
- conda update --yes conda
# create the testing environment
- conda create -n testenv --yes python=$PYTHON_VERSION pip
- source activate testenv
- |
if [ $SKLEARN_VERSION = "nightly" ]; then
conda install --yes -c conda-forge numpy==$NUMPY_VERSION scipy==$SCIPY_VERSION
# install nightly wheels
pip install --pre -f https://sklearn-nightly.scdn8.secure.raxcdn.com scikit-learn
else
conda install --yes -c conda-forge numpy==$NUMPY_VERSION scipy==$SCIPY_VERSION scikit-learn==$SKLEARN_VERSION
fi
- pip install codecov cython nose pytest pytest-cov
- pip install .
script:
- pytest -v doc/*rst
- mkdir for_test
- cd for_test
- pytest -v --cov=bayesclass --pyargs bayesclass
after_success:
- codecov

2
LICENSE
View File

@@ -1,6 +1,6 @@
MIT License
Copyright (c) 2022 Doctorado-ML
Copyright (c) 2020-2022, Ricardo Montañana Gómez
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal

1
MANIFEST.in Normal file
View File

@@ -0,0 +1 @@
include requirements.txt

38
README.rst Normal file
View File

@@ -0,0 +1,38 @@
.. -*- mode: rst -*-
|Travis|_ |AppVeyor|_ |Codecov|_ |CircleCI|_ |ReadTheDocs|_
.. |Travis| image:: https://travis-ci.org/scikit-learn-contrib/project-template.svg?branch=master
.. _Travis: https://travis-ci.org/scikit-learn-contrib/project-template
.. |AppVeyor| image:: https://ci.appveyor.com/api/projects/status/coy2qqaqr1rnnt5y/branch/master?svg=true
.. _AppVeyor: https://ci.appveyor.com/project/glemaitre/project-template
.. |Codecov| image:: https://codecov.io/gh/scikit-learn-contrib/project-template/branch/master/graph/badge.svg
.. _Codecov: https://codecov.io/gh/scikit-learn-contrib/project-template
.. |CircleCI| image:: https://circleci.com/gh/scikit-learn-contrib/project-template.svg?style=shield&circle-token=:circle-token
.. _CircleCI: https://circleci.com/gh/scikit-learn-contrib/project-template/tree/master
.. |ReadTheDocs| image:: https://readthedocs.org/projects/sklearn-template/badge/?version=latest
.. _ReadTheDocs: https://sklearn-template.readthedocs.io/en/latest/?badge=latest
project-template - A template for scikit-learn contributions
============================================================
.. _scikit-learn: https://scikit-learn.org
**project-template** is a template project for scikit-learn_ compatible
extensions.
It aids development of estimators that can be used in scikit-learn pipelines
and (hyper)parameter search, while facilitating testing (including some API
compliance), documentation, open source development, packaging, and continuous
integration.
.. _documentation: https://sklearn-template.readthedocs.io/en/latest/quick_start.html
Refer to the documentation_ to modify the template for your own scikit-learn
contribution.
*Thank you for cleanly contributing to the scikit-learn ecosystem!*

37
appveyor.yml Normal file
View File

@@ -0,0 +1,37 @@
build: false
environment:
matrix:
- PYTHON: "C:\\Miniconda3-x64"
PYTHON_VERSION: "3.5.x"
PYTHON_ARCH: "32"
NUMPY_VERSION: "1.13.1"
SCIPY_VERSION: "0.19.1"
SKLEARN_VERSION: "0.19.1"
- PYTHON: "C:\\Miniconda3-x64"
PYTHON_VERSION: "3.6.x"
PYTHON_ARCH: "64"
NUMPY_VERSION: "*"
SCIPY_VERSION: "*"
SKLEARN_VERSION: "*"
install:
# Prepend miniconda installed Python to the PATH of this build
# Add Library/bin directory to fix issue
# https://github.com/conda/conda/issues/1753
- "SET PATH=%PYTHON%;%PYTHON%\\Scripts;%PYTHON%\\Library\\bin;%PATH%"
# install the dependencies
- "conda install --yes -c conda-forge pip numpy==%NUMPY_VERSION% scipy==%SCIPY_VERSION% scikit-learn==%SKLEARN_VERSION%"
- pip install codecov nose pytest pytest-cov
- pip install .
test_script:
- mkdir for_test
- cd for_test
- pytest -v --cov=bayesclass --pyargs bayesclass
after_test:
- cp .coverage %APPVEYOR_BUILD_FOLDER%
- cd %APPVEYOR_BUILD_FOLDER%
- codecov

5
bayesclass/__init__.py Normal file
View File

@@ -0,0 +1,5 @@
from ._estimators import TAN
from ._version import __version__
__all__ = ["TAN", "__version__"]

136
bayesclass/_estimators.py Normal file
View File

@@ -0,0 +1,136 @@
"""
This is a module to be used as a reference for building other modules
"""
import numpy as np
from sklearn.base import ClassifierMixin, BaseEstimator
from sklearn.utils.validation import check_X_y, check_array, check_is_fitted
from sklearn.utils.multiclass import unique_labels
import networkx as nx
import pandas as pd
import matplotlib.pyplot as plt
from pgmpy.models import BayesianNetwork
from benchmark import Datasets
class TAN(ClassifierMixin, BaseEstimator):
"""An example classifier which implements a 1-NN algorithm.
For more information regarding how to build your own classifier, read more
in the :ref:`User Guide <user_guide>`.
Parameters
----------
demo_param : str, default='demo'
A parameter used for demonstation of how to pass and store paramters.
Attributes
----------
X_ : ndarray, shape (n_samples, n_features)
The input passed during :meth:`fit`.
y_ : ndarray, shape (n_samples,)
The labels passed during :meth:`fit`.
classes_ : ndarray, shape (n_classes,)
The classes seen at :meth:`fit`.
"""
def __init__(self, demo_param="demo"):
self.demo_param = demo_param
def fit(self, X, y):
"""A reference implementation of a fitting function for a classifier.
Parameters
----------
X : array-like, shape (n_samples, n_features)
The training input samples.
y : array-like, shape (n_samples,)
The target values. An array of int.
Returns
-------
self : object
Returns self.
"""
# Check that X and y have correct shape
X, y = check_X_y(X, y)
# Store the classes seen during fit
self.classes_ = unique_labels(y)
self.X_ = X
self.y_ = y
self.__train()
# Return the classifier
return self
def __train(self):
dt = Datasets()
data = dt.load("balance-scale", dataframe=True)
features = dt.dataset.features
class_name = dt.dataset.class_name
factorization, class_factors = pd.factorize(data[class_name])
data[class_name] = factorization
data.head()
net = [(class_name, feature) for feature in features]
model = BayesianNetwork(net)
# 1st feature correlates with other features
first_node = features[0]
edges2 = [
(first_node, feature)
for feature in features
if feature != first_node
]
edges = []
for i in range(len(features)):
for j in range(i + 1, len(features)):
edges.append((features[i], features[j]))
print(edges2)
model.add_edges_from(edges2)
nx.draw_circular(
model,
with_labels=True,
arrowsize=30,
node_size=800,
alpha=0.3,
font_weight="bold",
)
plt.show()
discretiz = MDLP()
Xdisc = discretiz.fit_transform(
data[features].to_numpy(), data[class_name].to_numpy()
)
features_discretized = pd.DataFrame(Xdisc, columns=features)
dataset_discretized = features_discretized.copy()
dataset_discretized[class_name] = data[class_name]
dataset_discretized
model.fit(dataset_discretized)
from pgmpy.estimators import TreeSearch
# learn graph structure
est = TreeSearch(dataset_discretized, root_node=first_node)
dag = est.estimate(estimator_type="tan", class_node=class_name)
nx.draw_circular(
dag,
with_labels=True,
arrowsize=30,
node_size=800,
alpha=0.3,
font_weight="bold",
)
plt.show()
def predict(self, X):
"""A reference implementation of a prediction for a classifier.
Parameters
----------
X : array-like, shape (n_samples, n_features)
The input samples.
Returns
-------
y : ndarray, shape (n_samples,)
The label for each sample is the label of the closest sample
seen during fit.
"""
# Check is fit had been called
check_is_fitted(self, ["X_", "y_"])
# Input validation
X = check_array(X)
closest = np.argmin(euclidean_distances(X, self.X_), axis=1)
return self.y_[closest]

1
bayesclass/_version.py Normal file
View File

@@ -0,0 +1 @@
__version__ = "0.0.1"

0
bayesclass/tests/__init__.py Normal file
View File

14
bayesclass/tests/test_common.py Normal file
View File

@@ -0,0 +1,14 @@
import pytest
from sklearn.utils.estimator_checks import check_estimator
from bayesclass import TemplateEstimator
from bayesclass import TemplateClassifier
from bayesclass import TemplateTransformer
@pytest.mark.parametrize(
"estimator", [TemplateEstimator(), TemplateTransformer(), TemplateClassifier()]
)
def test_all_estimators(estimator):
return check_estimator(estimator)

65
bayesclass/tests/test_template.py Normal file
View File

@@ -0,0 +1,65 @@
import pytest
import numpy as np
from sklearn.datasets import load_iris
from numpy.testing import assert_array_equal
from numpy.testing import assert_allclose
from bayesclass import TemplateEstimator
from bayesclass import TemplateTransformer
from bayesclass import TemplateClassifier
@pytest.fixture
def data():
return load_iris(return_X_y=True)
def test_template_estimator(data):
est = TemplateEstimator()
assert est.demo_param == "demo_param"
est.fit(*data)
assert hasattr(est, "is_fitted_")
X = data[0]
y_pred = est.predict(X)
assert_array_equal(y_pred, np.ones(X.shape[0], dtype=np.int64))
def test_template_transformer_error(data):
X, y = data
trans = TemplateTransformer()
trans.fit(X)
with pytest.raises(ValueError, match="Shape of input is different"):
X_diff_size = np.ones((10, X.shape[1] + 1))
trans.transform(X_diff_size)
def test_template_transformer(data):
X, y = data
trans = TemplateTransformer()
assert trans.demo_param == "demo"
trans.fit(X)
assert trans.n_features_ == X.shape[1]
X_trans = trans.transform(X)
assert_allclose(X_trans, np.sqrt(X))
X_trans = trans.fit_transform(X)
assert_allclose(X_trans, np.sqrt(X))
def test_template_classifier(data):
X, y = data
clf = TemplateClassifier()
assert clf.demo_param == "demo"
clf.fit(X, y)
assert hasattr(clf, "classes_")
assert hasattr(clf, "X_")
assert hasattr(clf, "y_")
y_pred = clf.predict(X)
assert y_pred.shape == (X.shape[0],)

184
doc/Makefile Normal file
View File

@@ -0,0 +1,184 @@
# Makefile for Sphinx documentation
#
# You can set these variables from the command line.
SPHINXOPTS =
SPHINXBUILD = sphinx-build
PAPER =
BUILDDIR = _build
# 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 <target>' where <target> 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)/*
-rm -rf auto_examples/
-rm -rf generated/*
-rm -rf modules/generated/*
html:
# These two lines make the build a bit more lengthy, and the
# the embedding of images more robust
rm -rf $(BUILDDIR)/html/_images
#rm -rf _build/doctrees/
$(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/project-template.qhcp"
@echo "To view the help file:"
@echo "# assistant -collectionFile $(BUILDDIR)/qthelp/project-template.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/project-template"
@echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/project-template"
@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."

16
doc/_static/css/project-template.css vendored Normal file
View File

@@ -0,0 +1,16 @@
@import url("theme.css");
.highlight a {
text-decoration: underline;
}
.deprecated p {
padding: 10px 7px 10px 10px;
color: #b94a48;
background-color: #F3E5E5;
border: 1px solid #eed3d7;
}
.deprecated p span.versionmodified {
font-weight: bold;
}

63
doc/_static/js/copybutton.js vendored Normal file
View File

@@ -0,0 +1,63 @@
$(document).ready(function() {
/* Add a [>>>] button on the top-right corner of code samples to hide
* the >>> and ... prompts and the output and thus make the code
* copyable. */
var div = $('.highlight-python .highlight,' +
'.highlight-python3 .highlight,' +
'.highlight-pycon .highlight,' +
'.highlight-default .highlight')
var pre = div.find('pre');
// get the styles from the current theme
pre.parent().parent().css('position', 'relative');
var hide_text = 'Hide the prompts and output';
var show_text = 'Show the prompts and output';
var border_width = pre.css('border-top-width');
var border_style = pre.css('border-top-style');
var border_color = pre.css('border-top-color');
var button_styles = {
'cursor':'pointer', 'position': 'absolute', 'top': '0', 'right': '0',
'border-color': border_color, 'border-style': border_style,
'border-width': border_width, 'color': border_color, 'text-size': '75%',
'font-family': 'monospace', 'padding-left': '0.2em', 'padding-right': '0.2em',
'border-radius': '0 3px 0 0'
}
// create and add the button to all the code blocks that contain >>>
div.each(function(index) {
var jthis = $(this);
if (jthis.find('.gp').length > 0) {
var button = $('<span class="copybutton">&gt;&gt;&gt;</span>');
button.css(button_styles)
button.attr('title', hide_text);
button.data('hidden', 'false');
jthis.prepend(button);
}
// tracebacks (.gt) contain bare text elements that need to be
// wrapped in a span to work with .nextUntil() (see later)
jthis.find('pre:has(.gt)').contents().filter(function() {
return ((this.nodeType == 3) && (this.data.trim().length > 0));
}).wrap('<span>');
});
// define the behavior of the button when it's clicked
$('.copybutton').click(function(e){
e.preventDefault();
var button = $(this);
if (button.data('hidden') === 'false') {
// hide the code output
button.parent().find('.go, .gp, .gt').hide();
button.next('pre').find('.gt').nextUntil('.gp, .go').css('visibility', 'hidden');
button.css('text-decoration', 'line-through');
button.attr('title', show_text);
button.data('hidden', 'true');
} else {
// show the code output
button.parent().find('.go, .gp, .gt').show();
button.next('pre').find('.gt').nextUntil('.gp, .go').css('visibility', 'visible');
button.css('text-decoration', 'none');
button.attr('title', hide_text);
button.data('hidden', 'false');
}
});
});

17
doc/_templates/class.rst vendored Normal file
View File

@@ -0,0 +1,17 @@
:mod:`{{module}}`.{{objname}}
{{ underline }}==============
.. currentmodule:: {{ module }}
.. autoclass:: {{ objname }}
:members:
{% block methods %}
.. automethod:: __init__
{% endblock %}
.. include:: {{module}}.{{objname}}.examples
.. raw:: html
<div style='clear:both'></div>

12
doc/_templates/function.rst vendored Normal file
View File

@@ -0,0 +1,12 @@
:mod:`{{module}}`.{{objname}}
{{ underline }}====================
.. currentmodule:: {{ module }}
.. autofunction:: {{ objname }}
.. include:: {{module}}.{{objname}}.examples
.. raw:: html
<div style='clear:both'></div>

16
doc/_templates/numpydoc_docstring.py vendored Normal file
View File

@@ -0,0 +1,16 @@
{{index}}
{{summary}}
{{extended_summary}}
{{parameters}}
{{returns}}
{{yields}}
{{other_parameters}}
{{attributes}}
{{raises}}
{{warns}}
{{warnings}}
{{see_also}}
{{notes}}
{{references}}
{{examples}}
{{methods}}

34
doc/api.rst Normal file
View File

@@ -0,0 +1,34 @@
####################
project-template API
####################
This is an example on how to document the API of your own project.
.. currentmodule:: bayesclass
Estimator
=========
.. autosummary::
:toctree: generated/
:template: class.rst
TemplateEstimator
Transformer
===========
.. autosummary::
:toctree: generated/
:template: class.rst
TemplateTransformer
Predictor
=========
.. autosummary::
:toctree: generated/
:template: class.rst
TemplateClassifier

335
doc/conf.py Normal file
View File

@@ -0,0 +1,335 @@
# -*- coding: utf-8 -*-
#
# project-template documentation build configuration file, created by
# sphinx-quickstart on Mon Jan 18 14:44:12 2016.
#
# 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
import sphinx_gallery
import sphinx_rtd_theme
# Add to sys.path the top-level directory where the package is located.
sys.path.insert(0, os.path.abspath(".."))
# 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.autosummary",
"sphinx.ext.doctest",
"sphinx.ext.intersphinx",
"sphinx.ext.viewcode",
"numpydoc",
"sphinx_gallery.gen_gallery",
]
# this is needed for some reason...
# see https://github.com/numpy/numpydoc/issues/69
numpydoc_show_class_members = False
# pngmath / imgmath compatibility layer for different sphinx versions
import sphinx
from distutils.version import LooseVersion
if LooseVersion(sphinx.__version__) < LooseVersion("1.4"):
extensions.append("sphinx.ext.pngmath")
else:
extensions.append("sphinx.ext.imgmath")
autodoc_default_flags = ["members", "inherited-members"]
# Add any paths that contain templates here, relative to this directory.
templates_path = ["_templates"]
# generate autosummary even if no references
autosummary_generate = True
# The suffix of source filenames.
source_suffix = ".rst"
# The encoding of source files.
# source_encoding = 'utf-8-sig'
# Generate the plots for the gallery
plot_gallery = True
# The master toctree document.
master_doc = "index"
# General information about the project.
project = "sklearn-template"
copyright = "2016, Vighnesh Birodkar"
# 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.
from bayesclass import __version__
version = __version__
# The full version, including alpha/beta/rc tags.
release = __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 = ["_build", "_templates"]
# 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"
# Custom style
html_style = "css/project-template.css"
# 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 = "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 themes here, relative to this directory.
html_theme_path = [sphinx_rtd_theme.get_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 = "project-templatedoc"
# -- 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",
"project-template.tex",
"project-template Documentation",
"Vighnesh Birodkar",
"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",
"project-template",
"project-template Documentation",
["Vighnesh Birodkar"],
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",
"project-template",
"project-template Documentation",
"Vighnesh Birodkar",
"project-template",
"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
# Example configuration for intersphinx: refer to the Python standard library.
# intersphinx configuration
intersphinx_mapping = {
"python": ("https://docs.python.org/{.major}".format(sys.version_info), None),
"numpy": ("https://docs.scipy.org/doc/numpy/", None),
"scipy": ("https://docs.scipy.org/doc/scipy/reference", None),
"matplotlib": ("https://matplotlib.org/", None),
"sklearn": ("http://scikit-learn.org/stable", None),
}
# sphinx-gallery configuration
sphinx_gallery_conf = {
"doc_module": "bayesclass",
"backreferences_dir": os.path.join("generated"),
"reference_url": {"bayesclass": None},
}
def setup(app):
# a copy button to copy snippet of code from the documentation
app.add_javascript("js/copybutton.js")

52
doc/index.rst Normal file
View File

@@ -0,0 +1,52 @@
.. project-template documentation master file, created by
sphinx-quickstart on Mon Jan 18 14:44:12 2016.
You can adapt this file completely to your liking, but it should at least
contain the root `toctree` directive.
Welcome to sklearn-template's documentation!
============================================
This project is a reference implementation to anyone who wishes to develop
scikit-learn compatible classes.
.. toctree::
:maxdepth: 2
:hidden:
:caption: Getting Started
quick_start
.. toctree::
:maxdepth: 2
:hidden:
:caption: Documentation
user_guide
api
.. toctree::
:maxdepth: 2
:hidden:
:caption: Tutorial - Examples
auto_examples/index
`Getting started <quick_start.html>`_
-------------------------------------
Information regarding this template and how to modify it for your own project.
`User Guide <user_guide.html>`_
-------------------------------
An example of narrative documentation.
`API Documentation <api.html>`_
-------------------------------
An example of API documentation.
`Examples <auto_examples/index.html>`_
--------------------------------------
A set of examples. It complements the `User Guide <user_guide.html>`_.

242
doc/make.bat Normal file
View File

@@ -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 ^<target^>` where ^<target^> 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\project-template.qhcp
echo.To view the help file:
echo.^> assistant -collectionFile %BUILDDIR%\qthelp\project-template.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

131
doc/quick_start.rst Normal file
View File

@@ -0,0 +1,131 @@
#####################################
Quick Start with the project-template
#####################################
This package serves as a skeleton package aiding at developing compatible
scikit-learn contribution.
Creating your own scikit-learn contribution package
===================================================
1. Download and setup your repository
-------------------------------------
To create your package, you need to clone the ``project-template`` repository::
$ git clone https://github.com/scikit-learn-contrib/project-template.git
Before to reinitialize your git repository, you need to make the following
changes. Replace all occurrences of ``bayesclass`` and ``sklearn-template``
with the name of you own contribution. You can find all the occurrences using
the following command::
$ git grep bayesclass
$ git grep sklearn-template
To remove the history of the template package, you need to remove the `.git`
directory::
$ cd project-template
$ rm -rf .git
Then, you need to initialize your new git repository::
$ git init
$ git add .
$ git commit -m 'Initial commit'
Finally, you create an online repository on GitHub and push your code online::
$ git remote add origin https://github.com/your_remote/your_contribution.git
$ git push origin master
2. Develop your own scikit-learn estimators
-------------------------------------------
.. _check_estimator: http://scikit-learn.org/stable/modules/generated/sklearn.utils.estimator_checks.check_estimator.html#sklearn.utils.estimator_checks.check_estimator
.. _`Contributor's Guide`: http://scikit-learn.org/stable/developers/
.. _PEP8: https://www.python.org/dev/peps/pep-0008/
.. _PEP257: https://www.python.org/dev/peps/pep-0257/
.. _NumPyDoc: https://github.com/numpy/numpydoc
.. _doctests: https://docs.python.org/3/library/doctest.html
You can modify the source files as you want. However, your custom estimators
need to pass the check_estimator_ test to be scikit-learn compatible. You can
refer to the :ref:`User Guide <user_guide>` to help you create a compatible
scikit-learn estimator.
In any case, developers should endeavor to adhere to scikit-learn's
`Contributor's Guide`_ which promotes the use of:
* algorithm-specific unit tests, in addition to ``check_estimator``'s common
tests;
* PEP8_-compliant code;
* a clearly documented API using NumpyDoc_ and PEP257_-compliant docstrings;
* references to relevant scientific literature in standard citation formats;
* doctests_ to provide succinct usage examples;
* standalone examples to illustrate the usage, model visualisation, and
benefits/benchmarks of particular algorithms;
* efficient code when the need for optimization is supported by benchmarks.
3. Edit the documentation
-------------------------
.. _Sphinx: http://www.sphinx-doc.org/en/stable/
The documentation is created using Sphinx_. In addition, the examples are
created using ``sphinx-gallery``. Therefore, to generate locally the
documentation, you are required to install the following packages::
$ pip install sphinx sphinx-gallery sphinx_rtd_theme matplotlib numpydoc pillow
The documentation is made of:
* a home page, ``doc/index.rst``;
* an API documentation, ``doc/api.rst`` in which you should add all public
objects for which the docstring should be exposed publicly.
* a User Guide documentation, ``doc/user_guide.rst``, containing the narrative
documentation of your package, to give as much intuition as possible to your
users.
* examples which are created in the `examples/` folder. Each example
illustrates some usage of the package. the example file name should start by
`plot_*.py`.
The documentation is built with the following commands::
$ cd doc
$ make html
4. Setup the continuous integration
-----------------------------------
The project template already contains configuration files of the continuous
integration system. Basically, the following systems are set:
* Travis CI is used to test the package in Linux. You need to activate Travis
CI for your own repository. Refer to the Travis CI documentation.
* AppVeyor is used to test the package in Windows. You need to activate
AppVeyor for your own repository. Refer to the AppVeyor documentation.
* Circle CI is used to check if the documentation is generated properly. You
need to activate Circle CI for your own repository. Refer to the Circle CI
documentation.
* ReadTheDocs is used to build and host the documentation. You need to activate
ReadTheDocs for your own repository. Refer to the ReadTheDocs documentation.
* CodeCov for tracking the code coverage of the package. You need to activate
CodeCov for you own repository.
* PEP8Speaks for automatically checking the PEP8 compliance of your project for
each Pull Request.
Publish your package
====================
.. _PyPi: https://packaging.python.org/tutorials/packaging-projects/
.. _conda-foge: https://conda-forge.org/
You can make your package available through PyPi_ and conda-forge_. Refer to
the associated documentation to be able to upload your packages such that
it will be installable with ``pip`` and ``conda``. Once published, it will
be possible to install your package with the following commands::
$ pip install your-scikit-learn-contribution
$ conda install -c conda-forge your-scikit-learn-contribution

180
doc/user_guide.rst Normal file
View File

@@ -0,0 +1,180 @@
.. title:: User guide : contents
.. _user_guide:
==================================================
User guide: create your own scikit-learn estimator
==================================================
Estimator
---------
The central piece of transformer, regressor, and classifier is
:class:`sklearn.base.BaseEstimator`. All estimators in scikit-learn are derived
from this class. In more details, this base class enables to set and get
parameters of the estimator. It can be imported as::
>>> from sklearn.base import BaseEstimator
Once imported, you can create a class which inherate from this base class::
>>> class MyOwnEstimator(BaseEstimator):
... pass
Transformer
-----------
Transformers are scikit-learn estimators which implement a ``transform`` method.
The use case is the following:
* at ``fit``, some parameters can be learned from ``X`` and ``y``;
* at ``transform``, `X` will be transformed, using the parameters learned
during ``fit``.
.. _mixin: https://en.wikipedia.org/wiki/Mixin
In addition, scikit-learn provides a
mixin_, i.e. :class:`sklearn.base.TransformerMixin`, which
implement the combination of ``fit`` and ``transform`` called ``fit_transform``::
One can import the mixin class as::
>>> from sklearn.base import TransformerMixin
Therefore, when creating a transformer, you need to create a class which
inherits from both :class:`sklearn.base.BaseEstimator` and
:class:`sklearn.base.TransformerMixin`. The scikit-learn API imposed ``fit`` to
**return ``self``**. The reason is that it allows to pipeline ``fit`` and
``transform`` imposed by the :class:`sklearn.base.TransformerMixin`. The
``fit`` method is expected to have ``X`` and ``y`` as inputs. Note that
``transform`` takes only ``X`` as input and is expected to return the
transformed version of ``X``::
>>> class MyOwnTransformer(BaseEstimator, TransformerMixin):
... def fit(self, X, y=None):
... return self
... def transform(self, X):
... return X
We build a basic example to show that our :class:`MyOwnTransformer` is working
within a scikit-learn ``pipeline``::
>>> from sklearn.datasets import load_iris
>>> from sklearn.pipeline import make_pipeline
>>> from sklearn.linear_model import LogisticRegression
>>> X, y = load_iris(return_X_y=True)
>>> pipe = make_pipeline(MyOwnTransformer(),
... LogisticRegression(random_state=10,
... solver='lbfgs'))
>>> pipe.fit(X, y) # doctest: +ELLIPSIS
Pipeline(...)
>>> pipe.predict(X) # doctest: +ELLIPSIS
array([...])
Predictor
---------
Regressor
~~~~~~~~~
Similarly, regressors are scikit-learn estimators which implement a ``predict``
method. The use case is the following:
* at ``fit``, some parameters can be learned from ``X`` and ``y``;
* at ``predict``, predictions will be computed using ``X`` using the parameters
learned during ``fit``.
In addition, scikit-learn provides a mixin_, i.e.
:class:`sklearn.base.RegressorMixin`, which implements the ``score`` method
which computes the :math:`R^2` score of the predictions.
One can import the mixin as::
>>> from sklearn.base import RegressorMixin
Therefore, we create a regressor, :class:`MyOwnRegressor` which inherits from
both :class:`sklearn.base.BaseEstimator` and
:class:`sklearn.base.RegressorMixin`. The method ``fit`` gets ``X`` and ``y``
as input and should return ``self``. It should implement the ``predict``
function which should output the predictions of your regressor::
>>> import numpy as np
>>> class MyOwnRegressor(BaseEstimator, RegressorMixin):
... def fit(self, X, y):
... return self
... def predict(self, X):
... return np.mean(X, axis=1)
We illustrate that this regressor is working within a scikit-learn pipeline::
>>> from sklearn.datasets import load_diabetes
>>> X, y = load_diabetes(return_X_y=True)
>>> pipe = make_pipeline(MyOwnTransformer(), MyOwnRegressor())
>>> pipe.fit(X, y) # doctest: +ELLIPSIS
Pipeline(...)
>>> pipe.predict(X) # doctest: +ELLIPSIS
array([...])
Since we inherit from the :class:`sklearn.base.RegressorMixin`, we can call
the ``score`` method which will return the :math:`R^2` score::
>>> pipe.score(X, y) # doctest: +ELLIPSIS
-3.9...
Classifier
~~~~~~~~~~
Similarly to regressors, classifiers implement ``predict``. In addition, they
output the probabilities of the prediction using the ``predict_proba`` method:
* at ``fit``, some parameters can be learned from ``X`` and ``y``;
* at ``predict``, predictions will be computed using ``X`` using the parameters
learned during ``fit``. The output corresponds to the predicted class for each sample;
* ``predict_proba`` will give a 2D matrix where each column corresponds to the
class and each entry will be the probability of the associated class.
In addition, scikit-learn provides a mixin, i.e.
:class:`sklearn.base.ClassifierMixin`, which implements the ``score`` method
which computes the accuracy score of the predictions.
One can import this mixin as::
>>> from sklearn.base import ClassifierMixin
Therefore, we create a classifier, :class:`MyOwnClassifier` which inherits
from both :class:`slearn.base.BaseEstimator` and
:class:`sklearn.base.ClassifierMixin`. The method ``fit`` gets ``X`` and ``y``
as input and should return ``self``. It should implement the ``predict``
function which should output the class inferred by the classifier.
``predict_proba`` will output some probabilities instead::
>>> class MyOwnClassifier(BaseEstimator, ClassifierMixin):
... def fit(self, X, y):
... self.classes_ = np.unique(y)
... return self
... def predict(self, X):
... return np.random.randint(0, self.classes_.size,
... size=X.shape[0])
... def predict_proba(self, X):
... pred = np.random.rand(X.shape[0], self.classes_.size)
... return pred / np.sum(pred, axis=1)[:, np.newaxis]
We illustrate that this regressor is working within a scikit-learn pipeline::
>>> X, y = load_iris(return_X_y=True)
>>> pipe = make_pipeline(MyOwnTransformer(), MyOwnClassifier())
>>> pipe.fit(X, y) # doctest: +ELLIPSIS
Pipeline(...)
Then, you can call ``predict`` and ``predict_proba``::
>>> pipe.predict(X) # doctest: +ELLIPSIS
array([...])
>>> pipe.predict_proba(X) # doctest: +ELLIPSIS
array([...])
Since our classifier inherits from :class:`sklearn.base.ClassifierMixin`, we
can compute the accuracy by calling the ``score`` method::
>>> pipe.score(X, y) # doctest: +ELLIPSIS
0...

6
environment.yml Normal file
View File

@@ -0,0 +1,6 @@
name: bayesclass
dependencies:
- numpy
- scipy
- scikit-learn
- pgmpy

6
examples/README.txt Normal file
View File

@@ -0,0 +1,6 @@
.. _general_examples:
General examples
================
Introductory examples.

44
examples/plot_classifier.py Normal file
View File

@@ -0,0 +1,44 @@
"""
============================
Plotting Template Classifier
============================
An example plot of :class:`bayesclass.template.TemplateClassifier`
"""
import numpy as np
from matplotlib import pyplot as plt
from bayesclass import TemplateClassifier
X = [[0, 0], [1, 1]]
y = [0, 1]
clf = TemplateClassifier()
clf.fit(X, y)
rng = np.random.RandomState(13)
X_test = rng.rand(500, 2)
y_pred = clf.predict(X_test)
X_0 = X_test[y_pred == 0]
X_1 = X_test[y_pred == 1]
p0 = plt.scatter(0, 0, c="red", s=100)
p1 = plt.scatter(1, 1, c="blue", s=100)
ax0 = plt.scatter(X_0[:, 0], X_0[:, 1], c="crimson", s=50)
ax1 = plt.scatter(X_1[:, 0], X_1[:, 1], c="deepskyblue", s=50)
leg = plt.legend(
[p0, p1, ax0, ax1],
["Point 0", "Point 1", "Class 0", "Class 1"],
loc="upper left",
fancybox=True,
scatterpoints=1,
)
leg.get_frame().set_alpha(0.5)
plt.xlabel("Feature 1")
plt.ylabel("Feature 2")
plt.xlim([-0.5, 1.5])
plt.show()

17
examples/plot_template.py Normal file
View File

@@ -0,0 +1,17 @@
"""
===========================
Plotting Template Estimator
===========================
An example plot of :class:`bayesclass.template.TemplateEstimator`
"""
import numpy as np
from matplotlib import pyplot as plt
from bayesclass import TemplateEstimator
X = np.arange(100).reshape(100, 1)
y = np.zeros((100,))
estimator = TemplateEstimator()
estimator.fit(X, y)
plt.plot(estimator.predict(X))
plt.show()

26
examples/plot_transformer.py Normal file
View File

@@ -0,0 +1,26 @@
"""
=============================
Plotting Template Transformer
=============================
An example plot of :class:`bayesclass.template.TemplateTransformer`
"""
import numpy as np
from matplotlib import pyplot as plt
from bayesclass import TemplateTransformer
X = np.arange(50, dtype=np.float).reshape(-1, 1)
X /= 50
estimator = TemplateTransformer()
X_transformed = estimator.fit_transform(X)
plt.plot(X.flatten(), label="Original Data")
plt.plot(X_transformed.flatten(), label="Transformed Data")
plt.title("Plots of original and transformed data")
plt.legend(loc="best")
plt.grid(True)
plt.xlabel("Index")
plt.ylabel("Value of Data")
plt.show()

16
pyproject.toml Normal file
View File

@@ -0,0 +1,16 @@
[tool.black]
line-length = 79
include = '\.pyi?$'
exclude = '''
/(
\.git
| \.hg
| \.mypy_cache
| \.tox
| \.venv
| _build
| buck-out
| build
| dist
)/
'''

4
requirements.txt Normal file
View File

@@ -0,0 +1,4 @@
numpy
scipy
scikit-learn
pgmpy

8
setup.cfg Normal file
View File

@@ -0,0 +1,8 @@
[metadata]
description-file = README.rst
[aliases]
test = pytest
[tool:pytest]
addopts = --doctest-modules

71
setup.py Normal file
View File

@@ -0,0 +1,71 @@
#! /usr/bin/env python
"""A collection of Bayesian Estimators."""
import codecs
import os
from setuptools import find_packages, setup
# get __version__ from _version.py
ver_file = os.path.join("bayesclass", "_version.py")
with open(ver_file) as f:
exec(f.read())
DISTNAME = "bayesclass"
DESCRIPTION = "A collection of Bayesian Estimators."
with codecs.open("README.rst", encoding="utf-8-sig") as f:
LONG_DESCRIPTION = f.read()
MAINTAINER = "Ricardo Montañana"
MAINTAINER_EMAIL = "rmontanana@gmail.com"
URL = "https://github.com/doctorado-ml/bayesclass"
LICENSE = "MIT"
DOWNLOAD_URL = "https://github.com/doctorado-ml/bayesclass"
VERSION = __version__
INSTALL_REQUIRES = ["numpy", "scipy", "scikit-learn"]
CLASSIFIERS = [
"Intended Audience :: Science/Research",
"Intended Audience :: Developers",
"License :: OSI Approved",
"Programming Language :: Python",
"Topic :: Software Development",
"Topic :: Scientific/Engineering",
"Operating System :: Microsoft :: Windows",
"Operating System :: POSIX",
"Operating System :: Unix",
"Operating System :: MacOS",
"Programming Language :: Python :: 2.7",
"Programming Language :: Python :: 3.5",
"Programming Language :: Python :: 3.6",
"Programming Language :: Python :: 3.7",
"Programming Language :: Python :: 3.8",
"Programming Language :: Python :: 3.9",
"Programming Language :: Python :: 3.10",
"Programming Language :: Python :: 3.11",
]
EXTRAS_REQUIRE = {
"tests": ["pytest", "pytest-cov"],
"docs": [
"sphinx",
"sphinx-gallery",
"sphinx_rtd_theme",
"numpydoc",
"matplotlib",
],
}
setup(
name=DISTNAME,
maintainer=MAINTAINER,
maintainer_email=MAINTAINER_EMAIL,
description=DESCRIPTION,
license=LICENSE,
url=URL,
version=VERSION,
download_url=DOWNLOAD_URL,
long_description=LONG_DESCRIPTION,
zip_safe=False, # the package can run out of an .egg file
classifiers=CLASSIFIERS,
packages=find_packages(),
install_requires=INSTALL_REQUIRES,
extras_require=EXTRAS_REQUIRE,
)