Merge pull request #1803 from iglesias/develop

Small refactoring and gitignore update

.gitignore

@@ -130,3 +130,6 @@ examples/undocumented/python_modular/*
 CMakeCache.txt
 /build
 /third_party
+
+# protobuf
+src/shogun/io/protobuf/*.pb.*

examples/undocumented/python_modular/structure_discrete_hmsvm_bmrm.py

@@ -9,10 +9,8 @@
 parameter_list=[[data_dict]]
 
 def structure_discrete_hmsvm_bmrm (m_data_dict=data_dict):
-	from modshogun   import RealMatrixFeatures
-	from modshogun  import SequenceLabels, HMSVMModel, Sequence, TwoStateModel, SMT_TWO_STATE
-	from modshogun import StructuredAccuracy
-	from modshogun  import DualLibQPBMSOSVM
+	from modshogun import RealMatrixFeatures, SequenceLabels, HMSVMModel, Sequence, TwoStateModel
+	from modshogun import StructuredAccuracy, DualLibQPBMSOSVM, SMT_TWO_STATE
 
 	labels_array = m_data_dict['label'][0]
 

examples/undocumented/python_modular/structure_discrete_hmsvm_mosek.py

@@ -9,9 +9,8 @@
 parameter_list=[[data_dict]]
 
 def structure_discrete_hmsvm_mosek (m_data_dict=data_dict):
-	from modshogun   import RealMatrixFeatures
-	from modshogun  import SequenceLabels, HMSVMModel, Sequence, TwoStateModel, SMT_TWO_STATE
-	from modshogun import StructuredAccuracy
+	from modshogun import RealMatrixFeatures, SequenceLabels, HMSVMModel, Sequence, TwoStateModel
+	from modshogun import StructuredAccuracy, SMT_TWO_STATE
 
 	try:
 		from modshogun import PrimalMosekSOSVM

examples/undocumented/python_modular/structure_plif_hmsvm_bmrm.py

@@ -3,9 +3,7 @@
 parameter_list=[[100, 250, 10, 2]]
 
 def structure_plif_hmsvm_bmrm (num_examples, example_length, num_features, num_noise_features):
-	from modshogun   import RealMatrixFeatures
-	from modshogun  import TwoStateModel, DualLibQPBMSOSVM
-	from modshogun import StructuredAccuracy
+	from modshogun import RealMatrixFeatures, TwoStateModel, DualLibQPBMSOSVM, StructuredAccuracy
 
 	model = TwoStateModel.simulate_data(num_examples, example_length, num_features, num_noise_features)
 	sosvm = DualLibQPBMSOSVM(model, model.get_labels(), 5000.0)

examples/undocumented/python_modular/structure_plif_hmsvm_mosek.py

@@ -3,9 +3,7 @@
 parameter_list=[[100, 250, 10, 2]]
 
 def structure_plif_hmsvm_mosek (num_examples, example_length, num_features, num_noise_features):
-	from modshogun   import RealMatrixFeatures
-	from modshogun  import TwoStateModel
-	from modshogun import StructuredAccuracy
+	from modshogun import RealMatrixFeatures, TwoStateModel, StructuredAccuracy
 
 	try:
 		from modshogun import PrimalMosekSOSVM

src/shogun/distributions/Distribution.h

@@ -43,6 +43,8 @@ class CDistribution : public CSGObject
 	public:
 		/** default constructor */
 		CDistribution();
+
+		/** destructor */
 		virtual ~CDistribution();
 
 		/** learn distribution
@@ -72,7 +74,7 @@ class CDistribution : public CSGObject
 
 		/** get model parameter (logarithmic)
 		 *
-		 * abstrac base method
+		 * abstract base method
 		 *
 		 * @return model parameter (logarithmic)
 		 */

src/shogun/evaluation/StructuredAccuracy.cpp

@@ -69,10 +69,8 @@ float64_t CStructuredAccuracy::evaluate_real(CStructuredLabels* predicted,
 
 	for ( int32_t i = 0 ; i < length ; ++i )
 	{
-		CRealNumber* truth =
-			CRealNumber::obtain_from_generic(ground_truth->get_label(i));
-		CRealNumber* pred =
-			CRealNumber::obtain_from_generic(predicted->get_label(i));
+		CRealNumber* truth = CRealNumber::obtain_from_generic(ground_truth->get_label(i));
+		CRealNumber* pred = CRealNumber::obtain_from_generic(predicted->get_label(i));
 
 		num_equal += truth->value == pred->value;
 
@@ -93,10 +91,8 @@ float64_t CStructuredAccuracy::evaluate_sequence(CStructuredLabels* predicted,
 
 	for ( int32_t i = 0 ; i < length ; ++i )
 	{
-		CSequence* true_seq =
-			CSequence::obtain_from_generic(ground_truth->get_label(i));
-		CSequence* pred_seq =
-			CSequence::obtain_from_generic(predicted->get_label(i));
+		CSequence* true_seq = CSequence::obtain_from_generic(ground_truth->get_label(i));
+		CSequence* pred_seq = CSequence::obtain_from_generic(predicted->get_label(i));
 
 		SGVector<int32_t> true_seq_data = true_seq->get_data();
 		SGVector<int32_t> pred_seq_data = pred_seq->get_data();

src/shogun/evaluation/StructuredAccuracy.h

@@ -48,11 +48,16 @@ class CStructuredAccuracy : public CEvaluation
 		 */
 		static SGMatrix<int32_t> get_confusion_matrix(CLabels* predicted, CLabels* ground_truth);
 
+		/** whether the evaluation criterion has to be maximimed or minimized
+		*
+		* @return maximize evaluation criterion
+		*/
 		inline EEvaluationDirection get_evaluation_direction() const
 		{
 			return ED_MAXIMIZE;
 		}
 
+		/** @return name of SGSerializable */
 		virtual const char* get_name() const { return "StructuredAccuracy"; }
 
 	private:

src/shogun/structure/HMSVMModel.cpp

@@ -335,10 +335,8 @@ CResultSet* CHMSVMModel::argmax(
 	if ( training )
 	{
 		ret->delta     = CStructuredModel::delta_loss(feat_idx, ypred);
-		ret->psi_truth = CStructuredModel::get_joint_feature_vector(
-					feat_idx, feat_idx);
-		ret->score    -= SGVector< float64_t >::dot(w.vector,
-					ret->psi_truth.vector, dim);
+		ret->psi_truth = CStructuredModel::get_joint_feature_vector(feat_idx, feat_idx);
+		ret->score    -= SGVector< float64_t >::dot(w.vector, ret->psi_truth.vector, dim);
 	}
 
 	return ret;

src/shogun/structure/PrimalMosekSOSVM.cpp

@@ -76,13 +76,7 @@ bool CPrimalMosekSOSVM::train_machine(CFeatures* data)
 	// Interface with MOSEK
 	CMosek* mosek = new CMosek(0, M+num_aux+N);
 	SG_REF(mosek);
-	if ( mosek->get_rescode() != MSK_RES_OK )
-	{
-		SG_PRINT("Mosek object could not be properly created..."
-			 "aborting training of PrimalMosekSOSVM\n");
-
-		return false;
-	}
+	REQUIRE(mosek->get_rescode() == MSK_RES_OK, "Mosek object could not be properly created in PrimalMosekSOSVM training.\n");
 
 	// Initialize the terms of the optimization problem
 	SGMatrix< float64_t > A, B, C;
@@ -92,11 +86,8 @@ bool CPrimalMosekSOSVM::train_machine(CFeatures* data)
 	SG_DEBUG("Regularization used in PrimalMosekSOSVM equal to %.2f.\n", m_regularization);
 
 	// Input terms of the problem that do not change between iterations
-	if ( mosek->init_sosvm(M, N, num_aux, num_aux_con, C, lb, ub, A, b) != MSK_RES_OK )
-	{
-		// MOSEK error took place
-		return false;
-	}
+	REQUIRE(mosek->init_sosvm(M, N, num_aux, num_aux_con, C, lb, ub, A, b) == MSK_RES_OK,
+		"Mosek error in PrimalMosekSOSVM initializing SO-SVM.\n")
 
 	// Initialize the weight vector
 	m_w = SGVector< float64_t >(M);
@@ -119,11 +110,6 @@ bool CPrimalMosekSOSVM::train_machine(CFeatures* data)
 	// Initialize variables used in the loop
 	int32_t     num_con     = num_aux_con;	// number of constraints
 	int32_t     old_num_con = num_con;
-	float64_t   slack       = 0.0;
-	float64_t   max_slack   = 0.0;
-	CResultSet* result      = NULL;
-	CResultSet* cur_res     = NULL;
-	CList*      cur_list    = NULL;
 	bool        exception   = false;
 	index_t     iteration   = 0;
 
@@ -142,24 +128,23 @@ bool CPrimalMosekSOSVM::train_machine(CFeatures* data)
 		for ( int32_t i = 0 ; i < N ; ++i )
 		{
 			// Predict the result of the ith training example (loss-aug)
-			result = m_model->argmax(m_w, i);
+			CResultSet* result = m_model->argmax(m_w, i);
 
 			// Compute the loss associated with the prediction (surrogate loss, max(0, \tilde{H}))
-			slack = CHingeLoss().loss( compute_loss_arg(result) );
-			cur_list = (CList*) results->get_element(i);
+			float64_t slack = CHingeLoss().loss( compute_loss_arg(result) );
+			CList* cur_list = (CList*) results->get_element(i);
 
 			// Update the list of constraints
 			if ( cur_list->get_num_elements() > 0 )
 			{
 				// Find the maximum loss within the elements of
 				// the list of constraints
-				cur_res = (CResultSet*) cur_list->get_first_element();
-				max_slack = -CMath::INFTY;
+				CResultSet* cur_res = (CResultSet*) cur_list->get_first_element();
+				float64_t max_slack = -CMath::INFTY;
 
 				while ( cur_res != NULL )
 				{
-					max_slack = CMath::max(max_slack,
-							CHingeLoss().loss( compute_loss_arg(cur_res) ));
+					max_slack = CMath::max(max_slack, CHingeLoss().loss( compute_loss_arg(cur_res) ));
 
 					SG_UNREF(cur_res);
 					cur_res = (CResultSet*) cur_list->get_next_element();

src/shogun/structure/SequenceLabels.h

@@ -59,7 +59,6 @@ class CSequence : public CStructuredData
 	SGVector<int32_t> get_data() const { return data; }
 
 protected:
-
 	/** data sequence */
 	SGVector< int32_t > data;