All unittests added

docs/installation.rst

@@ -1,7 +1,7 @@
 Installation
 ##################################
 
-To install PyDeep, first download it from `GitHub <https://github.com/MelJan/PyDeep>`_.
+To install PyDeep, first download it from `GitHub/MelJan <https://github.com/MelJan/PyDeep>`_.
 Then simply change to the PyDeep folder and run the setup script:
 
 .. code-block:: bash

docs/welcome.rst

@@ -8,9 +8,9 @@ its extensive use of unittests assures a high level of reliability and correctne
 
 News
 ''''''''''''''''''''''''''''''''''''''''''''''''''''
-- The documentation is updated to restructured text
-- Documentation hosted
-- Next the unit tests will be added
+- The documentation updated to restructured text (DONE)
+- Documentation hosted (DONE)
+- Next the unit tests added  (DONE)
 - Upcoming: Tutorials will be added
 - Upcoming: Auto encoders will be added
 - Upcoming: MDP integration will be added

pydeep/examples/eigenfaces.py

@@ -0,0 +1,86 @@
+""" Example for Eigenfaces (Principal component analysis on face images).
+
+    :Version:
+        1.1.0
+
+    :Date:
+        08.04.2017
+
+    :Author:
+        Jan Melchior
+
+    :Contact:
+        JanMelchior@gmx.de
+
+    :License:
+
+        Copyright (C) 2017 Jan Melchior
+
+        This file is part of the Python library PyDeep.
+
+        PyDeep 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/>.
+
+"""
+# Import PCA, numpy, input output functions, and visualization functions
+import numpy as numx
+from pydeep.preprocessing import PCA
+import pydeep.misc.io as io
+import pydeep.misc.visualization as vis
+
+# Set the random seed (optional, if stochastic processes are involved we always get the same results)
+numx.random.seed(42)
+
+# Load the data
+data = io.load_olivetti_faces(path='../../../data/olivettifaces.mat')
+
+# Specify image width and height for displaying
+width = height = 64
+
+# Create a PCA node and train it
+pca = PCA(input_dim=width * height)
+pca.train(data=data)
+
+# Show the first 100 eigenvectors of the covariance matrix
+eigenvectors = vis.tile_matrix_rows(matrix=pca.projection_matrix,
+                                    tile_width=width,
+                                    tile_height=height,
+                                    num_tiles_x=10,
+                                    num_tiles_y=10,
+                                    border_size=1,
+                                    normalized=True)
+vis.imshow_matrix(matrix=eigenvectors,
+                  windowtitle='First 100 Eigenvectors of the covariance matrix')
+
+# Show the first 100 images
+images = vis.tile_matrix_rows(matrix=data[0:100].T,
+                              tile_width=width,
+                              tile_height=height,
+                              num_tiles_x=10,
+                              num_tiles_y=10,
+                              border_size=1,
+                              normalized=True)
+vis.imshow_matrix(matrix=images,
+                  windowtitle='First 100 Face images')
+
+# Plot the cumulative sum of teh Eigenvalues.
+eigenvalue_sum = numx.cumsum(pca.eigen_values / numx.sum(pca.eigen_values))
+vis.imshow_plot(matrix=eigenvalue_sum,
+                windowtitle="Cumulative sum of Eigenvalues")
+vis.xlabel("Eigenvalue index")
+vis.ylabel("Sum of Eigenvalues 0 to index")
+vis.ylim(0, 1)
+vis.xlim(0, 400)
+
+# Show all windows.
+vis.show()

pydeep/examples/ica_on_natural_images.py

@@ -0,0 +1,117 @@
+""" Example for the Independent component analysis on natural image patches.
+
+    :Version:
+        1.1.0
+
+    :Date:
+        08.04.2017
+
+    :Author:
+        Jan Melchior
+
+    :Contact:
+        JanMelchior@gmx.de
+
+    :License:
+
+        Copyright (C) 2017 Jan Melchior
+
+        This file is part of the Python library PyDeep.
+
+        PyDeep 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/>.
+
+"""
+# Import PCA, numpy, input output functions, and visualization functions
+import numpy as numx
+from pydeep.preprocessing import ICA, ZCA
+import pydeep.misc.io as io
+import pydeep.misc.visualization as vis
+
+# Set the random seed (optional, if stochastic processes are involved we always get the same results)
+numx.random.seed(42)
+
+# Load the data
+data = io.load_natural_image_patches('../../../data/NaturalImage.mat')
+
+# Specify image width and height for displaying
+width = height = 14
+
+# Create a ZCA node to whiten the data and train it (you could also use PCA whitened=True)
+zca = ZCA(input_dim=width * height)
+zca.train(data=data)
+
+# ZCA projects the whitened data back to the original space, thus does not perform a
+# dimensionality reduction but a whitening in the original space
+whitened_data = zca.project(data)
+
+# Create a ZCA node and train it (you could also use PCA whitened=True)
+ica = ICA(input_dim=width * height)
+ica.train(data=whitened_data,
+          iterations=100,
+          convergence=1.0,
+          status=True)
+
+# Show eigenvectors of the covariance matrix
+eigenvectors = vis.tile_matrix_rows(matrix=zca.projection_matrix,
+                                    tile_width=width,
+                                    tile_height=height,
+                                    num_tiles_x=width,
+                                    num_tiles_y=height,
+                                    border_size=1,
+                                    normalized=True)
+vis.imshow_matrix(matrix=eigenvectors,
+                  windowtitle='Eigenvectors of the covariance matrix')
+
+# Show whitened images
+images = vis.tile_matrix_rows(matrix=data[0:width*height].T,
+                              tile_width=width,
+                              tile_height=height,
+                              num_tiles_x=width,
+                              num_tiles_y=height,
+                              border_size=1,
+                              normalized=True)
+vis.imshow_matrix(matrix=images,
+                  windowtitle='Some image patches')
+
+# Show some whitened images
+images = vis.tile_matrix_rows(matrix=whitened_data[0:width*height].T,
+                              tile_width=width,
+                              tile_height=height,
+                              num_tiles_x=width,
+                              num_tiles_y=height,
+                              border_size=1,
+                              normalized=True)
+vis.imshow_matrix(matrix=images,
+                  windowtitle='Some whitened image patches')
+
+# Plot the cumulative sum of teh Eigenvalues.
+eigenvalue_sum = numx.cumsum(zca.eigen_values)
+vis.imshow_plot(matrix=eigenvalue_sum,
+                windowtitle="Cumulative sum of Eigenvalues")
+vis.xlabel("Eigenvalue index")
+vis.ylabel("Sum of Eigenvalues 0 to index")
+
+# Show the ICA filters/bases
+ica_filters = vis.tile_matrix_rows(matrix=ica.projection_matrix,
+                                   tile_width=width,
+                                   tile_height=height,
+                                   num_tiles_x=width,
+                                   num_tiles_y=height,
+                                   border_size=1,
+                                   normalized=True)
+vis.imshow_matrix(matrix=ica_filters,
+                  windowtitle='Filters learned by ICA')
+
+# Show all windows.
+vis.show()

pydeep/misc/io.py

@@ -4,8 +4,10 @@
         - Save/Load arbitrary objects.
         - Save/Load images.
         - Load MNIST.
-        - Load CIFAR.
         - Load Caltech.
+        - Load CIFAR.
+        - load Natural image patches
+        - load olivetti face images
 
     :Version:
         1.1.0
@@ -344,9 +346,46 @@ def load_natural_image_patches(path):
     print('-> loading data ... ')
     try:
         # https://zenodo.org/record/167823/files/NaturalImage.mat
-        data = numx.random.permutation(scipy.io.loadmat(path)['rawImages'].T)
+        data = scipy.io.loadmat(path)['rawImages'].T
+        print('-> done!')
+    except:
+        raise Exception('-> File reading Error: ')
+    data = numx.array(data, dtype=numx.double)
+    return data
+
+def load_olivetti_faces(path, correct_orientation=True):
+    """ Loads the Olivetti face dataset 400 images, size 64x64
+
+    :param path: Path and name of the file to load.
+    :type path: string
+
+    :param correct_orientation: Corrects the orientation of the images.
+    :type correct_orientation: bool
+
+    :return: Olivetti face dataset
+    :rtype: numpy array
+    """
+    if not os.path.isfile(path):
+        print('-> File not existing: ' + path)
+        try:
+            download_file('http://www.cs.nyu.edu/~roweis/data/olivettifaces.mat', path, buffer_size=10 * 1024 ** 2)
+        except:
+            try:
+                download_file('https://github.com/probml/pmtk3/tree/master/bigData/facesOlivetti/facesOlivetti.mat',
+                              path, buffer_size=10 * 1024 ** 2)
+            except:
+                raise Exception('Download failed, make sure you have internet connection!')
+    print('-> loading data ... ')
+    try:
+        data = scipy.io.loadmat(path)['faces'].T
+        if correct_orientation:
+            import pydeep.base.numpyextension as npext
+            for i in range(data.shape[0]):
+                data[i] = npext.rotate(data[i].reshape(64,64),270).reshape(64*64)
+            print('-> orientation corrected!')
         print('-> done!')
     except:
         raise Exception('-> File reading Error: ')
     data = numx.array(data, dtype=numx.double)
     return data
+

pydeep/misc/visualization.py

@@ -5,6 +5,7 @@
         - Tile a matrix rows
         - Tile a matrix columns
         - Show a matrix
+        - Show plot
         - Show a histogram
 
         - Plot data
@@ -171,6 +172,20 @@ def imshow_matrix(matrix, windowtitle, interpolation='nearest'):
     imshow(np.array(matrix, np.float64), interpolation=interpolation)
 
 
+def imshow_plot(matrix, windowtitle):
+    """ Plots the colums of a matrix.
+
+    :param matrix: Data to plot
+    :type matrix: numpy array
+
+    :param windowtitle: Figure title
+    :type windowtitle: string
+    """
+    figure().suptitle(windowtitle)
+    gray()
+    plot(np.array(matrix, np.float64))
+
+
 def imshow_histogram(matrix,
                      windowtitle,
                      num_bins=10,

pydeep/rbm/dbn.py

@@ -59,7 +59,7 @@ def forward_propagate(self, input_data, sample=False):
         :return: Output of the network.
         :rtype: numpy array [batchsize x output dim]
         """
-        if input_data.shape[1] != self._input_dim:
+        if input_data.shape[1] != self.input_dim:
             raise Exception("Input dimensionality has to match dbn.input_dim!")
         self.states[0] = input_data
         for l in range(len(self._layers)):
@@ -80,7 +80,7 @@ def backward_propagate(self, output_data, sample=False):
         :return: Input of the network.
         :rtype: numpy array [batchsize x input dim]
         """
-        if output_data.shape[1] != self._output_dim:
+        if output_data.shape[1] != self.output_dim:
             raise Exception("Output dimensionality has to match dbn.output_dim!")
         self.states[len(self._layers)] = output_data
         for l in range(len(self._layers), 0, -1):