Develop (#12)

* add KernelMatrix,SaveOutput,LoadOutput Function Also, additional documentation for each class and function * Update orsvm.py some minor changes on the following functions: -SaveOutput: - function renamed - variables' names corrected -LoadOutput: - function renamed - some corrections to variable names * Update kernels.py Latest revision on comments, Variable corrections and function descriptions * DEBUG SupportMultipliers fucntion logging.info('** Strictly %s first elements of support vectors are selected!',n) replaced with: logging.info('** Strictly',n,' first elements of support vectors are selected!') * DEBUG on SupportMultipliers function correction on svd int type error * DEBUG wrong variable name corrected * DEBUG _IsScientific(n) fucntion logging error recovered * create PredictWithJson function some misspelling also corrected * binary classification encoding added * Update documentation for hyperparameter * Update documentation for hyperparameter * Update kernels.py Gegenbauer kernel Debug, correction on hyperparameter valid domain * Update kernels.py add rbf kernel class * Update orsvm.py * Update orsvm.py bugs about kernel name resolved * Update orsvm.py checking the Convexity of the kernel matrix * Update kernels.py Comments added to Jacobi class * Update kernels.py Gegenbauer hyper parameter check correction * Update kernels.py add hypereparameter range checking for jacobi kernel * Update orsvm.py log error when x shape is not compatible with y shape * Update orsvm.py log error when n_sample = 0 * Update kernels.py debug for order equal or smaller than 0 in chebyshev * Update kernels.py debug for order smaller or equal to zero in legendre kernel * Update kernels.py * Update orsvm.py log error when T is out of range * Update orsvm.py support vector determiner debug * Update kernels.py log error when form input of chebyshev is not valid * Update kernels.py correction on the warning message of chebyshev form error * Update kernels.py debug when KernelParam1 for Gegenbauer is None * Update orsvm.py log error in kernelMatrix function when input size is zero * Update orsvm.py check y.shape[0]!=0 * Update orsvm.py log error when kernel name is not valid in KernelMatrix function * Update orsvm.py Debug SaveToJson * Update orsvm.py Debug LoadJson * Update orsvm.py Debug predictWithJson.( log error when support multiplier is None or n_sample = 0) * Update kernels.py log error when order<0 for gegenbauer and jacobi * Update orsvm.py syntax error fixed * Update orsvm.py Update documentations * Update kernels.py update documentation * Update kernels.py Check range of gamma in rbf * Update orsvm.py Check C is positive or not * Update kernels.py add default value for psi and omega in jacobi * Update orsvm.py bug about C resolved * Update orsvm.py log bug resolved * Update orsvm.py check type of x ,y (should not contain string or bool column) * Update orsvm.py change order of checking bugs in ModelFit and ModelPredict * Update orsvm.py log error when dataset is different from the dataset it was fitted on in PredictWithJson * Update orsvm.py check range of T in Transform function * Update orsvm.py Correct comments to be more clear * Update __init__.py * Update orsvm.py a little bug in saveJson resolved * Update credits.rst * Update orsvm.py * Update orsvm.py logging format corrected * Update requirements.txt * Update .readthedocs.yaml * Update README.md Link to book added * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update setup.py * Delete docs directory Delete docs directory to replace it with a new format * Create test.txt * Add files via upload Adding Build directory of the docs for readthedocs * Add files via upload Uploading source directory of the docs , for readthedocs * Delete conf.py.bak * Delete index.rst.bak * Delete installation.rst.bak * Add files via upload make files and the requirement file of sphinx * Update README.md * Update README.md badges added Co-authored-by: shakiba <[email protected]>
AmirHoseinHadian · Nov 28, 2022 · b343168 · b343168
1 parent aa89945
commit b343168
Show file tree

Hide file tree

Showing 138 changed files with 9,383 additions and 5,804 deletions.
diff --git a/.readthedocs.yaml b/.readthedocs.yaml
@@ -7,5 +7,12 @@ python:
     - method: pip
       path: .
 
+ # Build documentation in the docs/ directory with Sphinx
+sphinx:
+   configuration: docs/source/conf.py     
 
+# Optionally declare the Python requirements required to build your docs
+python:
+   install:
+   - requirements: docs/requirements.txt
 
diff --git a/README.md b/README.md
@@ -1,15 +1,20 @@
-![LOGO](docs/_static/identicons.png)
+![LOGO](docs/source/_static//identicons.png)
 
+
+![PyPI - License](https://img.shields.io/pypi/l/orsvm)
+![PyPI](https://img.shields.io/pypi/v/orsvm)
+![PyPI - Status](https://img.shields.io/pypi/status/orsvm)
 # ORSVM 
 
-ORSVM is a free software package which provides a SVM classifier with  some novel orthogonal polynomial kernels.
+`ORSVM` is a free software package which provides a SVM classifier with  some novel orthogonal polynomial kernels.
 This library provides a complete path of using the SVM classifier from normalization to calculation of SVM equation and the final evaluation.
 In order to classify the dataset with ORSVM, there is a need to normalize the dataset whether using normal or fractional kernels.
 ORSVM library needs numpy and cvxopt libraries to be installed. Arrays, matrices and linear algebraic functions have been used repeatedly from numpy and
  the heart of SVM algorithm which is finding the Support Vectors is done by use of a convex quadratic solver from cvxopt library which is in turn a free python package for 
  convex optimization. 
+ For a comprehensive introduction to fractional orthogonal kernel function and the use cases in SVM, refer to [Learning with Fractional Orthogonal Kernel Classifiers in Support Vector Machines](https://link.springer.com/book/9789811965524) book.
 
- A suitable guide on this package is available at http://cvxopt.org about installation and how to use.
+A suitable guide on `cvxopt` package is available at http://cvxopt.org about installation and how to use.
 
 
  ## Install

diff --git a/docs/Makefile b/docs/Makefile
@@ -5,8 +5,8 @@
 # from the environment for the first two.
 SPHINXOPTS    ?=
 SPHINXBUILD   ?= sphinx-build
-SOURCEDIR     = .
-BUILDDIR      = _build
+SOURCEDIR     = source
+BUILDDIR      = build
 
 # Put it first so that "make" without argument is like "make help".
 help:

diff --git a/docs/_build/doctrees/credits.doctree b/docs/_build/doctrees/credits.doctree
diff --git a/docs/_build/doctrees/environment.pickle b/docs/_build/doctrees/environment.pickle
diff --git a/docs/_build/doctrees/index.doctree b/docs/_build/doctrees/index.doctree
diff --git a/docs/_build/doctrees/installation.doctree b/docs/_build/doctrees/installation.doctree
diff --git a/docs/_build/doctrees/nbsphinx/notebooks/Gegenbauer_fitting.ipynb b/docs/_build/doctrees/nbsphinx/notebooks/Gegenbauer_fitting.ipynb
diff --git a/docs/_build/doctrees/notebooks/Chebyshev_fitting.doctree b/docs/_build/doctrees/notebooks/Chebyshev_fitting.doctree
diff --git a/docs/_build/doctrees/notebooks/Gegenbauer_fitting.doctree b/docs/_build/doctrees/notebooks/Gegenbauer_fitting.doctree
diff --git a/docs/_build/doctrees/notebooks/How_to_use_orsvm.doctree b/docs/_build/doctrees/notebooks/How_to_use_orsvm.doctree
diff --git a/docs/_build/doctrees/notebooks/Jacobi_fitting.doctree b/docs/_build/doctrees/notebooks/Jacobi_fitting.doctree
diff --git a/docs/_build/doctrees/notebooks/Legendre_fitting.doctree b/docs/_build/doctrees/notebooks/Legendre_fitting.doctree
diff --git a/docs/_build/doctrees/references.doctree b/docs/_build/doctrees/references.doctree
diff --git a/docs/_build/html/_sources/credits.rst.txt b/docs/_build/html/_sources/credits.rst.txt
diff --git a/docs/_build/html/_sources/index.rst.txt b/docs/_build/html/_sources/index.rst.txt
diff --git a/docs/_build/html/_sources/installation.rst.txt b/docs/_build/html/_sources/installation.rst.txt