fixing merge

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2018 Dainis Boumber
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -1 +1,5 @@
-# complexity
+# complexity
+Authors: Ricardo Vilalta, Dainis Boumber, Michael Meskhi.
+
+Current work on estimating complexity of a distribution.
+

complexity.py

@@ -7,6 +7,7 @@
 
 import modules.complexity_estimator as ce
 import modules.util as u
+from modules import mnist
 from modules.oracle import Oracle
 from nd_boundary_plot.plots import nd_boundary_plot
 
@@ -119,9 +120,12 @@ def main():
 
     # experiments.append('moons')
     # datasets.append((u.hastie(1000), u.hastie(1000)))
-    datasets.append((make_gaussian_quantiles(cov=0.5, n_samples=50, n_features=10, n_classes=2),
-                     make_gaussian_quantiles(n_samples=50, n_features=10, n_classes=2)))
-    experiments.append('gauus')
+
+    # datasets.append((make_gaussian_quantiles(n_samples=500, n_features=10, n_classes=3),
+    #                 make_gaussian_quantiles(n_samples=500, n_features=10, n_classes=3)))
+    # experiments.append('gauus')
+    datasets.append((mnist.load_mnist(), mnist.load_mnist_rotated()))
+    experiments.append('MNIST_vs_MNIST_Rotated')
 
     active(classifiers=clfs, datasets=datasets, experiments=experiments)
 

modules/mnist.py

@@ -0,0 +1,59 @@
+import numpy as np
+import pandas as pd
+from scipy import ndimage
+import matplotlib.pyplot as plt
+from sklearn.utils import shuffle
+
+
+# Import data and preprocess 
+mnist = pd.read_csv('./data/mnist/train_src_100.csv') # Using 100 samples only for this test run
+labels = mnist.as_matrix(columns=['label'])
+dataset = mnist.drop('label', axis = 1).as_matrix()
+dataset[dataset > 0] = 1 # Convert each pixel either 0 for white and 1 for black for better classification
+
+
+def load_mnist():
+
+    rows = 100
+    columns = 784
+    index = 1
+    X = []
+    for image in dataset[:rows*columns]:
+        img = np.reshape(image, [28, 28])
+        X.append(img)
+        index += 1
+    X = np.array(X).reshape(rows, -1)
+    mnist = pd.DataFrame(X)
+    mnist = mnist.as_matrix()
+    y = labels.flatten()
+
+    print("Completed with X shape: ", mnist.shape)
+    print("Flattened y shape: ", y.shape)
+
+    mnist, y = shuffle(X, y, random_state = 5)
+    return mnist, y
+
+
+def load_mnist_rotated():
+
+    rows = 100
+    columns = 784
+    indx = 1
+    X = []
+    for image in dataset[:rows*columns]:
+        img = np.reshape(image, [28, 28])
+        rotated = ndimage.rotate(img, 90) # Rotate the images by 90 degrees
+        X.append(rotated)
+        indx += 1
+    X = np.array(X).reshape(rows, -1)
+
+    mnist_rotated = pd.DataFrame(X)
+    # mnist_rotated.to_csv('./data/mnist_rotated/minst_rotated_21000.csv', index=False, header=False)
+    mnist_rotated = mnist_rotated.as_matrix()
+
+    y = labels.flatten()
+    print("Completed with X shape: ", mnist_rotated.shape)
+    print("Flattened y shape: ", y.shape)
+
+    mnist_rotated, y = shuffle(X, y, random_state = 15)
+    return mnist_rotated, y