Merge pull request #1954 from PirosB3/feature/1868

Looks good.

applications/classification/evaluate_multiclass_labels.py

@@ -0,0 +1,72 @@
+#!/usr/bin/env python
+
+#  Copyright (c) The Shogun Machine Learning Toolbox
+#  Written (w) 2014 Daniel Pyrathon
+#  All rights reserved.
+#  
+#  Redistribution and use in source and binary forms, with or without
+#  modification, are permitted provided that the following conditions are met:
+#  
+#  1. Redistributions of source code must retain the above copyright notice, this
+#     list of conditions and the following disclaimer.
+#  2. Redistributions in binary form must reproduce the above copyright notice,
+#     this list of conditions and the following disclaimer in the documentation
+#     and/or other materials provided with the distribution.
+#  
+#  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
+#  ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+#  WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+#  DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
+#  ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+#  (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+#  LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+#  ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+#  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+#  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+#  
+#  The views and conclusions contained in the software and documentation are those
+#  of the authors and should not be interpreted as representing official policies,
+#  either expressed or implied, of the Shogun Development Team.
+
+
+import argparse
+import logging
+import numpy as np
+from modshogun import (LibSVMFile, MulticlassLabels, MulticlassAccuracy)
+from utils import get_features_and_labels
+
+LOGGER = logging.getLogger(__file__)
+
+def parse_arguments():
+	parser = argparse.ArgumentParser(description="Evaluate predicted \
+					labels againsy bare truth")
+	parser.add_argument('--actual', required=True, type=str,
+					help='Path to LibSVM dataset.')
+	parser.add_argument('--predicted', required=True, type=str,
+					help='Path to serialized predicted labels')
+	return parser.parse_args()
+
+
+def main(actual, predicted):
+	LOGGER.info("SVM Multiclass evaluator")
+
+	# Load SVMLight dataset
+	feats, labels = get_features_and_labels(LibSVMFile(actual))
+
+	# Load predicted labels
+	with open(predicted, 'r') as f:
+		predicted_labels_arr = np.array([float(l) for l in f])
+		predicted_labels = MulticlassLabels(predicted_labels_arr)
+
+	# Evaluate accuracy
+	multiclass_measures = MulticlassAccuracy()
+	LOGGER.info("Accuracy = %s" % multiclass_measures.evaluate(
+		labels, predicted_labels))
+	LOGGER.info("Confusion matrix:")
+	res = multiclass_measures.get_confusion_matrix(labels, predicted_labels)
+	print res
+
+
+if __name__ == '__main__':
+	args = parse_arguments()
+	main(args.actual, args.predicted)

applications/classification/predict_multiclass_svm.py

@@ -0,0 +1,75 @@
+#!/usr/bin/env python
+
+#  Copyright (c) The Shogun Machine Learning Toolbox
+#  Written (w) 2014 Daniel Pyrathon
+#  All rights reserved.
+#  
+#  Redistribution and use in source and binary forms, with or without
+#  modification, are permitted provided that the following conditions are met:
+#  
+#  1. Redistributions of source code must retain the above copyright notice, this
+#     list of conditions and the following disclaimer.
+#  2. Redistributions in binary form must reproduce the above copyright notice,
+#     this list of conditions and the following disclaimer in the documentation
+#     and/or other materials provided with the distribution.
+#  
+#  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
+#  ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+#  WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+#  DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
+#  ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+#  (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+#  LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+#  ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+#  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+#  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+#  
+#  The views and conclusions contained in the software and documentation are those
+#  of the authors and should not be interpreted as representing official policies,
+#  either expressed or implied, of the Shogun Development Team.
+
+
+import argparse
+import logging
+from contextlib import closing
+from modshogun import (LibSVMFile, SparseRealFeatures, MulticlassLabels,
+											MulticlassLibSVM, SerializableHdf5File,
+											MulticlassAccuracy)
+from utils import get_features_and_labels
+
+LOGGER = logging.getLogger(__file__)
+
+def parse_arguments():
+	parser = argparse.ArgumentParser(description="Test a serialized SVM \
+					classifier agains a SVMLight test file")
+	parser.add_argument('--classifier', required=True, type=str,
+					help='Path to training dataset in LibSVM format.')
+	parser.add_argument('--testset', required=True, type=str,
+					help='Path to the SVMLight test file')
+	parser.add_argument('--output', required=True, type=str,
+					help='File path to write predicted labels')
+	return parser.parse_args()
+
+
+def main(classifier, testset, output):
+	LOGGER.info("SVM Multiclass evaluation")
+
+	svm = MulticlassLibSVM()
+	serialized_classifier = SerializableHdf5File(classifier, 'r')
+	with closing(serialized_classifier):
+		svm.load_serializable(serialized_classifier)
+
+	test_feats, test_labels = get_features_and_labels(LibSVMFile(testset))
+	predicted_labels = svm.apply(test_feats)
+
+	with open(output, 'w') as f:
+		for cls in predicted_labels.get_labels():
+			f.write("%s\n" % int(cls))
+
+	LOGGER.info("Predicted labels saved in: '%s'" % output)
+
+
+if __name__ == '__main__':
+	args = parse_arguments()
+	main(args.classifier, args.testset, args.output)
+

applications/classification/train_multiclass_svm.py

@@ -0,0 +1,98 @@
+#!/usr/bin/env python
+
+#  Copyright (c) The Shogun Machine Learning Toolbox
+#  Written (w) 2014 Daniel Pyrathon
+#  All rights reserved.
+#  
+#  Redistribution and use in source and binary forms, with or without
+#  modification, are permitted provided that the following conditions are met:
+#  
+#  1. Redistributions of source code must retain the above copyright notice, this
+#     list of conditions and the following disclaimer.
+#  2. Redistributions in binary form must reproduce the above copyright notice,
+#     this list of conditions and the following disclaimer in the documentation
+#     and/or other materials provided with the distribution.
+#  
+#  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
+#  ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+#  WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+#  DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
+#  ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+#  (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+#  LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+#  ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+#  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+#  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+#  
+#  The views and conclusions contained in the software and documentation are those
+#  of the authors and should not be interpreted as representing official policies,
+#  either expressed or implied, of the Shogun Development Team.
+
+
+import argparse
+import logging
+from contextlib import contextmanager, closing
+from modshogun import (LibSVMFile, GaussianKernel, MulticlassLibSVM,
+																SerializableHdf5File, LinearKernel)
+from utils import get_features_and_labels, track_execution
+
+LOGGER = logging.getLogger(__file__)
+
+KERNELS = {
+	'linear': lambda feats, width: LinearKernel(feats, feats),
+	'gaussian': lambda feats, width: GaussianKernel(feats, feats, width),
+}
+
+def parse_arguments():
+	parser = argparse.ArgumentParser(description="Train a multiclass SVM \
+					stored in libsvm format")
+	parser.add_argument('--dataset', required=True, type=str,
+					help='Path to training dataset in LibSVM format.')
+	parser.add_argument('--capacity', default=1.0, type=float,
+					help='SVM capacity parameter')
+	parser.add_argument('--width', default=2.1, type=float,
+					help='Width of the Gaussian Kernel to approximate')
+	parser.add_argument('--epsilon', default=0.01, type=float,
+					help='SVMOcas epsilon parameter')
+	parser.add_argument('--kernel', type=str, default='linear',
+					choices=['linear', 'gaussian'],
+					help='Optionally specify a kernel type. \
+					Only Linear or Gaussian')
+	parser.add_argument('--output', required=True, type=str,
+					help='Destination path for the output serialized \
+					classifier')
+	return parser.parse_args()
+
+
+def main(dataset, output, epsilon, capacity, width, kernel_type):
+
+	LOGGER.info("SVM Multiclass classifier")
+	LOGGER.info("Epsilon: %s" % epsilon)
+	LOGGER.info("Capacity: %s" % capacity)
+	LOGGER.info("Gaussian width: %s" % width)
+
+	# Get features
+	feats, labels = get_features_and_labels(LibSVMFile(dataset))
+
+	# Create kernel
+	try:
+		kernel = KERNELS[kernel_type](feats, width)
+	except KeyError:
+		LOGGER.error("Kernel %s not available. try Gaussian or Linear" % kernel_type)
+
+	# Initialize and train Multiclass SVM
+	svm = MulticlassLibSVM(capacity, kernel, labels)
+	svm.set_epsilon(epsilon)
+	with track_execution():
+		svm.train()
+
+	# Serialize to file
+	writable_file = SerializableHdf5File(output, 'w')
+	with closing(writable_file):
+		svm.save_serializable(writable_file)
+	LOGGER.info("Serialized classifier saved in: '%s'" % output)
+
+
+if __name__ == '__main__':
+	args = parse_arguments()
+	main(args.dataset, args.output, args.epsilon, args.capacity, args.width, args.kernel)

applications/classification/utils.py

@@ -0,0 +1,51 @@
+#!/usr/bin/env python
+
+#  Copyright (c) The Shogun Machine Learning Toolbox
+#  Written (w) 2014 Daniel Pyrathon
+#  All rights reserved.
+#  
+#  Redistribution and use in source and binary forms, with or without
+#  modification, are permitted provided that the following conditions are met:
+#  
+#  1. Redistributions of source code must retain the above copyright notice, this
+#     list of conditions and the following disclaimer.
+#  2. Redistributions in binary form must reproduce the above copyright notice,
+#     this list of conditions and the following disclaimer in the documentation
+#     and/or other materials provided with the distribution.
+#  
+#  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
+#  ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+#  WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+#  DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
+#  ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+#  (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+#  LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+#  ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+#  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+#  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+#  
+#  The views and conclusions contained in the software and documentation are those
+#  of the authors and should not be interpreted as representing official policies,
+#  either expressed or implied, of the Shogun Development Team.
+
+import logging
+from contextlib import contextmanager
+from modshogun import MulticlassLabels, SparseRealFeatures, Time
+
+
+logging.basicConfig(level=logging.INFO, format='[%(asctime)-15s %(module)s] %(message)s')
+LOGGER = logging.getLogger(__file__)
+
+def get_features_and_labels(input_file):
+	feats = SparseRealFeatures()
+	label_array = feats.load_with_labels(input_file)
+	labels = MulticlassLabels(label_array)
+	return feats, labels
+
+@contextmanager
+def track_execution():
+	LOGGER.info('Starting training.')
+	timer = Time()
+	yield
+	timer.stop()
+	LOGGER.info('Training completed, took {0:.2f}s.'.format(timer.time_diff_sec()))