Merge pull request #480 from karlnapf/master

Implement the new SubsetStack system
shogun-toolbox · Apr 22, 2012 · 4328d97 · 4328d97
2 parents e4ab8a1 + 1144ae8
commit 4328d97
Show file tree

Hide file tree

Showing 33 changed files with 677 additions and 459 deletions.
diff --git a/examples/undocumented/libshogun/Makefile b/examples/undocumented/libshogun/Makefile
@@ -40,6 +40,7 @@ TARGETS = basic_minimal \
 		  modelselection_grid_search_linear features_subset_labels \
 		  modelselection_grid_search_kernel \
 		  modelselection_grid_search_string_kernel \
+		  features_subset_stack \
 		  features_subset_simple_features \
 		  features_subset_sparse_features \
 		  features_copy_subset_simple_features \

diff --git a/examples/undocumented/libshogun/evaluation_cross_validation_classification.cpp b/examples/undocumented/libshogun/evaluation_cross_validation_classification.cpp
@@ -104,7 +104,7 @@ void test_cross_validation()
 	CCrossValidation* cross=new CCrossValidation(svm, features, labels,
 			splitting, eval_crit);
 
-	cross->set_num_runs(100);
+	cross->set_num_runs(10);
 	cross->set_conf_int_alpha(0.05);
 
 	/* actual evaluation */
@@ -122,6 +122,8 @@ int main(int argc, char **argv)
 {
 	init_shogun(&print_message, &print_message, &print_message);
 
+	sg_io->set_loglevel(MSG_DEBUG);
+
 	test_cross_validation();
 
 	exit_shogun();

diff --git a/examples/undocumented/libshogun/evaluation_cross_validation_locked_comparison.cpp b/examples/undocumented/libshogun/evaluation_cross_validation_locked_comparison.cpp
@@ -5,7 +5,6 @@
  * (at your option) any later version.
  *
  * Written (W) 2012 Heiko Strathmann
- * Copyright (C) 2012 Berlin Institute of Technology and Max-Planck-Society
  */
 
 #include <shogun/base/init.h>
@@ -29,8 +28,8 @@ void print_message(FILE* target, const char* str)
 void test_cross_validation()
 {
 	/* data matrix dimensions */
-	index_t num_vectors=500;
-	index_t num_features=50;
+	index_t num_vectors=50;
+	index_t num_features=5;
 
 	/* data means -1, 1 in all components, std deviation of sigma */
 	SGVector<float64_t> mean_1(num_features);
@@ -93,19 +92,19 @@ void test_cross_validation()
 	ASSERT(eval_result<2);
 
 	/* splitting strategy */
-	index_t n_folds=5;
+	index_t n_folds=3;
 	CStratifiedCrossValidationSplitting* splitting=
 			new CStratifiedCrossValidationSplitting(labels, n_folds);
 
 	/* cross validation instance, 10 runs, 95% confidence interval */
 	CCrossValidation* cross=new CCrossValidation(svm, features, labels,
 			splitting, eval_crit);
 
-	cross->set_num_runs(10);
+	cross->set_num_runs(5);
 	cross->set_conf_int_alpha(0.05);
 
 	/* no locking */
-	index_t repetitions=3;
+	index_t repetitions=5;
 	SG_SPRINT("unlocked x-val\n");
 	kernel->init(features, features);
 	cross->set_autolock(false);

diff --git a/examples/undocumented/libshogun/features_copy_subset_simple_features.cpp b/examples/undocumented/libshogun/features_copy_subset_simple_features.cpp
@@ -4,7 +4,7 @@
  * the Free Software Foundation; either version 3 of the License, or
  * (at your option) any later version.
  *
- * Written (W) 2011 Heiko Strathmann
+ * Written (W) 2011-2012 Heiko Strathmann
  * Copyright (C) 2011 Berlin Institute of Technology and Max-Planck-Society
  */
 
@@ -36,7 +36,7 @@ int main(int argc, char **argv)
 	CMath::display_vector(feature_subset.vector, feature_subset.vlen,
 			"feature subset");
 
-	f->add_subset(new CSubset(feature_subset));
+	f->add_subset(feature_subset);
 	SG_SPRINT("feature vectors after setting subset on original data:\n");
 	for (index_t i=0; i<f->get_num_vectors(); ++i)
 	{
@@ -70,7 +70,8 @@ int main(int argc, char **argv)
 
 	SG_UNREF(f);
 	SG_UNREF(subset_copy);
-	SG_FREE(feature_copy_subset.vector);
+	feature_copy_subset.destroy_vector();
+	feature_subset.destroy_vector();
 
 	SG_SPRINT("\nEND\n");
 	exit_shogun();

diff --git a/examples/undocumented/libshogun/features_copy_subset_sparse_features.cpp b/examples/undocumented/libshogun/features_copy_subset_sparse_features.cpp
@@ -4,7 +4,7 @@
  * the Free Software Foundation; either version 3 of the License, or
  * (at your option) any later version.
  *
- * Written (W) 2011 Heiko Strathmann
+ * Written (W) 2011-2012 Heiko Strathmann
  * Copyright (C) 2011 Berlin Institute of Technology and Max-Planck-Society
  */
 
@@ -64,7 +64,7 @@ int main(int argc, char **argv)
 			"feature subset");
 
 	/* set subset and print data */
-	f->add_subset(new CSubset(feature_subset));
+	f->add_subset(feature_subset);
 	SG_SPRINT("feature vectors after setting subset on original data:\n");
 	for (index_t i=0; i<f->get_num_vectors(); ++i)
 	{
@@ -125,6 +125,7 @@ int main(int argc, char **argv)
 	SG_UNREF(f);
 	SG_UNREF(subset_copy);
 	feature_copy_subset.destroy_vector();
+	feature_subset.destroy_vector();
 
 	exit_shogun();
 

diff --git a/examples/undocumented/libshogun/features_copy_subset_string_features.cpp b/examples/undocumented/libshogun/features_copy_subset_string_features.cpp
@@ -4,7 +4,7 @@
  * the Free Software Foundation; either version 3 of the License, or
  * (at your option) any later version.
  *
- * Written (W) 2011 Heiko Strathmann
+ * Written (W) 2011-2012 Heiko Strathmann
  * Copyright (C) 2011 Berlin Institute of Technology and Max-Planck-Society
  */
 
@@ -63,7 +63,7 @@ int main(int argc, char **argv)
 	CMath::display_vector(feature_subset.vector, feature_subset.vlen,
 			"feature subset");
 
-	f->add_subset(new CSubset(feature_subset));
+	f->add_subset(feature_subset);
 	SG_SPRINT("feature vectors after setting subset on original data:\n");
 	for (index_t i=0; i<f->get_num_vectors(); ++i)
 	{
@@ -117,7 +117,8 @@ int main(int argc, char **argv)
 
 	SG_UNREF(f);
 	SG_UNREF(subset_copy);
-	SG_FREE(feature_copy_subset.vector);
+	feature_copy_subset.destroy_vector();
+	feature_subset.destroy_vector();
 
 	exit_shogun();
 

diff --git a/examples/undocumented/libshogun/features_subset_labels.cpp b/examples/undocumented/libshogun/features_subset_labels.cpp
@@ -4,7 +4,7 @@
  * the Free Software Foundation; either version 3 of the License, or
  * (at your option) any later version.
  *
- * Written (W) 2011 Heiko Strathmann
+ * Written (W) 2011-2012 Heiko Strathmann
  * Copyright (C) 2011 Berlin Institute of Technology and Max-Planck-Society
  */
 
@@ -49,7 +49,7 @@ int main(int argc, char **argv)
 	SG_SPRINT("\n\n-------------------\n"
 			"applying subset to features\n"
 			"-------------------\n");
-	labels->set_subset(new CSubset(subset_idx));
+	labels->add_subset(subset_idx);
 
 	/* do some stuff do check and output */
 	ASSERT(labels->get_num_labels()==num_subset_idx);
@@ -59,13 +59,13 @@ int main(int argc, char **argv)
 	{
 		float64_t label=labels->get_label(i);
 		SG_SPRINT("label %f:\n", label);
-		ASSERT(label==labels_data.vector[labels->subset_idx_conversion(i)]);
+		ASSERT(label==labels_data.vector[subset_idx.vector[i]]);
 	}
 
 	/* remove features subset */SG_SPRINT("\n\n-------------------\n"
 			"removing subset from features\n"
 			"-------------------\n");
-	labels->remove_subset();
+	labels->remove_all_subsets();
 
 	ASSERT(labels->get_num_labels()==num_labels);
 	SG_SPRINT("labels->get_num_labels(): %d\n", labels->get_num_labels());
@@ -77,9 +77,11 @@ int main(int argc, char **argv)
 		ASSERT(label==labels_data.vector[i]);
 	}
 	SG_UNREF(labels);
+	subset_idx.destroy_vector();
 
 	SG_SPRINT("\nEND\n");
 	exit_shogun();
 
 	return 0;
 }
+
diff --git a/examples/undocumented/libshogun/features_subset_simple_features.cpp b/examples/undocumented/libshogun/features_subset_simple_features.cpp
@@ -4,7 +4,7 @@
  * the Free Software Foundation; either version 3 of the License, or
  * (at your option) any later version.
  *
- * Written (W) 2011 Heiko Strathmann
+ * Written (W) 2011-2012 Heiko Strathmann
  * Copyright (C) 2011 Berlin Institute of Technology and Max-Planck-Society
  */
 
@@ -80,7 +80,7 @@ int main(int argc, char **argv)
 	SG_SPRINT("\n\n-------------------\n"
 			"applying subset to features\n"
 			"-------------------\n");
-	features->add_subset(new CSubset(subset_idx));
+	features->add_subset(subset_idx);
 
 	/* do some stuff do check and output */
 	ASSERT(features->get_num_vectors()==num_subset_idx);
@@ -99,8 +99,7 @@ int main(int argc, char **argv)
 		CMath::display_vector(vec.vector, vec.vlen);
 
 		for (index_t j=0; j<dim_features; ++j)
-			ASSERT(vec.vector[j]==data.matrix[features->subset_idx_conversion(
-					i)*num_vectors+j]);
+			ASSERT(vec.vector[j]==data.matrix[subset_idx.vector[i]*num_vectors+j]);
 
 		/* not necessary since feature matrix is in memory. for documentation */
 		features->free_feature_vector(vec, i);
@@ -128,17 +127,16 @@ int main(int argc, char **argv)
 		CMath::display_vector(vec.vector, vec.vlen);
 
 		for (index_t j=0; j<dim_features; ++j)
-			ASSERT(vec.vector[j]==data.matrix[features->subset_idx_conversion(i)
-					*num_vectors+j]);
+			ASSERT(vec.vector[j]==data.matrix[i*num_vectors+j]);
 
 		/* not necessary since feature matrix is in memory. for documentation */
 		features->free_feature_vector(vec, i);
 	}
 
 
 	SG_UNREF(features);
+	subset_idx.destroy_vector();
 
-	SG_SPRINT("\nEND\n");
 	exit_shogun();
 
 	return 0;

diff --git a/examples/undocumented/libshogun/features_subset_sparse_features.cpp b/examples/undocumented/libshogun/features_subset_sparse_features.cpp
@@ -4,7 +4,7 @@
  * the Free Software Foundation; either version 3 of the License, or
  * (at your option) any later version.
  *
- * Written (W) 2011 Heiko Strathmann
+ * Written (W) 2011-2012 Heiko Strathmann
  * Copyright (C) 2011 Berlin Institute of Technology and Max-Planck-Society
  */
 
@@ -75,7 +75,7 @@ int main(int argc, char **argv)
 	SG_SPRINT("\n-------------------\n"
 	"applying subset to features\n"
 	"-------------------\n");
-	features->add_subset(new CSubset(subset_idx));
+	features->add_subset(subset_idx);
 
 	/* do some stuff do check and output */
 	ASSERT(features->get_num_vectors()==num_subset_idx);
@@ -102,7 +102,7 @@ int main(int argc, char **argv)
 		for (index_t j=0; j<vec.num_feat_entries; ++j)
 		{
 			int32_t a=vec.features[j].entry;
-			index_t ind=features->subset_idx_conversion(i)*num_vectors+j;
+			index_t ind=subset_idx.vector[i]*num_vectors+j;
 			int32_t	b=data.matrix[ind];
 			ASSERT(a==b);
 		}
@@ -145,7 +145,9 @@ int main(int argc, char **argv)
 	}
 
 	SG_UNREF(features);
-	SG_FREE(data.matrix);
+	data.destroy_matrix();
+	subset_idx.destroy_vector();
+
 
 	exit_shogun();
 

diff --git a/examples/undocumented/libshogun/features_subset_stack.cpp b/examples/undocumented/libshogun/features_subset_stack.cpp
@@ -0,0 +1,65 @@
+/*
+ * This program 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.
+ *
+ * Written (W) 2012 Heiko Strathmann
+ */
+
+#include <shogun/base/init.h>
+#include <shogun/features/SubsetStack.h>
+
+using namespace shogun;
+
+void print_message(FILE* target, const char* str)
+{
+	fprintf(target, "%s", str);
+}
+
+int main(int argc, char **argv)
+{
+	init_shogun(&print_message, &print_message, &print_message);
+
+	CSubsetStack* stack=new CSubsetStack();
+	SG_REF(stack);
+
+	/* subset indices, each set is shifted by one */
+	SGVector<index_t> subset_a(10);
+	SGVector<index_t> subset_b(4);
+	subset_a.range_fill(1);
+	subset_b.range_fill(1);
+
+	/* add and remove subsets a couple of times */
+	stack->add_subset(subset_a);
+	stack->remove_subset();
+	stack->add_subset(subset_b);
+	stack->remove_subset();
+
+	/* add and remove subsets a couple of times, different order */
+	stack->add_subset(subset_a);
+	stack->add_subset(subset_b);
+	stack->remove_subset();
+	stack->remove_subset();
+
+	/** add two subsets and check if index mapping works */
+	stack->add_subset(subset_a);
+	stack->add_subset(subset_b);
+
+	/* remember, offset of one for each index set */
+	for (index_t i=0; i<subset_b.vlen; ++i)
+		ASSERT(stack->subset_idx_conversion(i)==i+2);
+
+	stack->remove_subset();
+	stack->remove_subset();
+
+	/* clean up */
+	SG_UNREF(stack);
+	subset_a.destroy_vector();
+	subset_b.destroy_vector();
+
+	exit_shogun();
+
+	return 0;
+}
+
diff --git a/src/shogun/base/DynArray.h b/src/shogun/base/DynArray.h
@@ -104,6 +104,15 @@ template <class T> class DynArray
 			return array[index];
 		}
 
+		/** gets last array element
+		 *
+		 * @return array element at last index
+		 */
+		inline T get_last_element() const
+		{
+			return array[last_element_idx];
+		}
+
 		/** get array element at index as pointer
 		 *
 		 * (does NOT do bounds checking)