Cleaning dataset list

Author: marinkaz

Diff for: .gitignore

@@ -34,6 +34,3 @@ distribute*.tar.gz
 
 # Ignore virtualenv folder
 venv
-
-# Ignore datasets
-nimfa/datasets/*

Diff for: .travis.yml

@@ -15,8 +15,7 @@ addons:
     - liblapack-dev
 python:
   - "2.7"
-  - "3.4"
-  - "3.5"
+#  - "3.4"
 
 before_install:
   - wget http://repo.continuum.io/miniconda/Miniconda-latest-Linux-x86_64.sh -O miniconda.sh

Diff for: AUTHORS.rst renamed to AUTHORS.md

@@ -1,9 +1,9 @@
 recursive-include docs *
 recursive-include nimfa/datasets/ALL_AML *
-recursive-include nimfa/datasets/CBCL_faces placeholder*
-recursive-include nimfa/datasets/Medlars placeholder*
+recursive-include nimfa/datasets/CBCL_faces/README.md
+recursive-include nimfa/datasets/Medlars/README.md
 recursive-include nimfa/datasets/Medulloblastoma *
-recursive-include nimfa/datasets/MovieLens placeholder*
+recursive-include nimfa/datasets/MovieLens/README.md
 recursive-include nimfa/datasets/ORL_faces *
-recursive-include nimfa/datasets/S_cerevisiae_FC placeholder*
-include *.py *.txt *.rst
+recursive-include nimfa/datasets/S_cerevisiae_FC/README.md
+include *.py *.txt *.rst *.md

Diff for: MANIFEST.in

@@ -1,19 +1,13 @@
 Nimfa
 -----
 
-|Travis|_
-|Coverage|_
-
-.. |Travis| image:: https://travis-ci.org/marinkaz/nimfa.svg?branch=master
-.. _Travis: https://travis-ci.org/marinkaz/nimfa
-
-.. |Coverage| image:: https://coveralls.io/repos/marinkaz/nimfa/badge.svg?branch=master&service=github
-.. _Coverage: https://coveralls.io/github/marinkaz/nimfa?branch=master
+[![build: passing](https://img.shields.io/travis/marinkaz/nimfa.svg)](https://travis-ci.org/marinkaz/nimfa)
+[![build: passing](https://coveralls.io/repos/marinkaz/nimfa/badge.svg)](https://coveralls.io/github/marinkaz/nimfa?branch=master)
 
 Nimfa is a Python module that implements many algorithms for nonnegative matrix factorization. Nimfa is distributed under the BSD license.
 
 The project was started in 2011 by Marinka Zitnik as a Google Summer of Code project, and since
-then many volunteers have contributed. See the AUTHORS.rst file for a complete list of contributors.
+then many volunteers have contributed. See AUTHORS file for a complete list of contributors.
 
 It is currently maintained by a team of volunteers.
 
@@ -28,7 +22,7 @@ Important links
 Dependencies
 ------------
 
-Nimfa is tested to work under Python 2.6, Python 2.7, and Python 3.4.
+Nimfa is tested to work under Python 2.7 and Python 3.4.
 
 The required dependencies to build the software are NumPy >= 1.7.0,
 SciPy >= 0.12.0.
@@ -39,13 +33,13 @@ Install
 -------
 
 This package uses setuptools, which is a common way of installing
-python modules. To install in your home directory, use::
+python modules. To install in your home directory, use:
 
-  python setup.py install --user
+    python setup.py install --user
 
-To install for all users on Unix/Linux::
-
-  sudo python setup.py install
+To install for all users on Unix/Linux:
+    
+    sudo python setup.py install
 
 For more detailed installation instructions,
 see the web page http://nimfa.biolab.si
@@ -72,8 +66,6 @@ Run alternating least squares nonnegative matrix factorization with projected gr
 Cite
 ----
 
-::
-
     @article{Zitnik2012,
       title     = {Nimfa: A Python Library for Nonnegative Matrix Factorization},
       author    = {Zitnik, Marinka and Zupan, Blaz},

Diff for: README.rst renamed to README.md

@@ -12,7 +12,7 @@
 """
 
 __license__ = 'BSD'
-__version__ = '1.3.1'
+__version__ = '1.3.2'
 __maintainer__ = 'Marinka Zitnik'
 __email__ = '[email protected]'
 

Diff for: nimfa/__init__.py

@@ -0,0 +1,21 @@
+# CBCL face images
+
+CBCL face images data set:
+* 19 x 19 Grayscale PGM format images,
+* Training set: 2429 faces, 4548 nonfaces, 
+* Test set: 472 faces, 23573 nonfaces.
+
+Dataset is at: http://cbcl.mit.edu/cbcl/software-datasets/FaceData2.html. 
+
+Directory structure should look like:
+
+    datasets/
+      CBCL_faces/
+        README
+        face/
+          face00001.pgm
+          [...]
+          face02429.pgm
+        non-face/
+          [...]
+      [...]

Diff for: nimfa/datasets/CBCL_faces/README.md

@@ -0,0 +1,10 @@
+# Medlars
+
+Dataset is at: http://web.eecs.utk.edu/research/lsi. This is a collection of 1033 medical abstracts. 
+
+Directory structure should look like:
+
+    datasets/
+      Medlars/
+        med.all
+      [...]

Diff for: nimfa/datasets/CBCL_faces/placeholder_CBCL_faces

@@ -0,0 +1,15 @@
+# Movielens
+
+Dataset is at: http://www.grouplens.org/node/12. Select the stable benchmark dataset with 100000 
+ratings from 1000 users on 1700 movies.  
+
+Directory structure should look like:
+
+    datasets/
+      MovieLens/
+        ua.base
+        ua.test
+        ub.base
+        ub.test
+        [...]
+      [...]

Diff for: nimfa/datasets/Medlars/README.md

@@ -0,0 +1,26 @@
+# S. Cerevisiae MIPS's molecular functions 
+
+Dataset is at: http://dtai.cs.kuleuven.be/clus/hmc-ens. 
+
+Directory structure should look like:
+
+    datasets/
+      S_cerevisiae_FC/
+        hom_yeast_FUN/
+            hom_yeast_FUN.test.arff
+            hom_yeast_FUN.train.arff
+            hom_yeast_FUN.valid.arff
+        pheno_yeast_FUN/
+            pheno_yeast_FUN.test.arff
+            pheno_yeast_FUN.valid.arff
+            pheno_yeast_FUN.train.arff
+        seq_yeast_FUN/
+            seq_yeast_FUN.train.arff
+            seq_yeast_FUN.test.arff
+            seq_yeast_FUN.valid.arff
+        struc_yeast_FUN/
+            struc_yeast_FUN.train.arff
+            struc_yeast_FUN.test.arff
+            struc_yeast_FUn.valid.arff
+        [...]
+      [...]

Diff for: nimfa/datasets/Medlars/placeholder_Medlars

@@ -9,13 +9,13 @@
 MAINTAINER = 'Marinka Zitnik'
 MAINTAINER_EMAIL = '[email protected]'
 DESCRIPTION = 'A Python module for nonnegative matrix factorization'
-LONG_DESCRIPTION = open('README.rst').read()
+LONG_DESCRIPTION = open('README.md').read()
 URL = 'http://nimfa.biolab.si'
 DOWNLOAD_URL = 'http://github.com/marinkaz/nimfa'
 KEYWORDS = ['matrix factorization', 'nonnegative matrix factorization',
             'bioinformatics', 'data mining', 'machine learning']
 LICENSE = 'BSD'
-VERSION = '1.3.1'
+VERSION = '1.3.2'
 ISRELEASED = True
 
 INSTALL_REQUIRES = (
@@ -90,10 +90,10 @@ def write_version_py(filename='nimfa/version.py'):
         GIT_REVISION = git_version()
     elif os.path.exists('nimfa/version.py'):
         # must be a source distribution, use existing version file
-        version = imp.load_source("nimfa.version", "nimfa/version.py")
+        version = imp.load_source('nimfa.version', 'nimfa/version.py')
         GIT_REVISION = version.git_revision
     else:
-        GIT_REVISION = "Unknown"
+        GIT_REVISION = 'Unknown'
 
     if not ISRELEASED:
         FULLVERSION += '.dev0+' + GIT_REVISION[:7]
@@ -124,8 +124,8 @@ def setup_package():
         keywords=KEYWORDS,
         install_requires=INSTALL_REQUIRES,
         packages=find_packages(),
-        package_dir={DISTNAME: "./nimfa"},
-        package_data={DISTNAME: get_package_data("datasets")},
+        package_dir={DISTNAME: './nimfa'},
+        package_data={DISTNAME: get_package_data('datasets')},
         license=LICENSE,
         long_description=LONG_DESCRIPTION,
         classifiers=['Intended Audience :: Science/Research',