Merge pull request #225 from karlnapf/master

implementation of copy_subset

examples/undocumented/libshogun/Makefile

@@ -24,7 +24,8 @@ TARGETS = basic_minimal classifier_libsvm classifier_minimal_svm \
 		  modelselection_grid_search_simple features_subset_labels \
 		  features_subset_simple_features \
 		  features_subset_sparse_features \
-		  mathematics_confidence_intervals
+		  mathematics_confidence_intervals \
+		  features_copy_subset_simple_features
 
 
 all: $(TARGETS)

examples/undocumented/libshogun/features_copy_subset_simple_features.cpp

@@ -0,0 +1,80 @@
+/*
+ * 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) 2011 Heiko Strathmann
+ * Copyright (C) 2011 Berlin Institute of Technology and Max-Planck-Society
+ */
+
+#include <shogun/base/init.h>
+#include <shogun/features/SimpleFeatures.h>
+#include <shogun/features/Subset.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);
+
+	SGMatrix<float64_t> data(3, 10);
+	CSimpleFeatures<float64_t>* f=new CSimpleFeatures<float64_t>(data);
+	CMath::range_fill_vector(data.matrix, data.num_cols*data.num_rows, 1.0);
+	CMath::display_matrix(data.matrix, data.num_rows, data.num_cols,
+			"original feature data");
+
+	index_t offset_subset=1;
+	SGVector<index_t> feature_subset(8);
+	CMath::range_fill_vector(feature_subset.vector, feature_subset.vlen,
+			offset_subset);
+	CMath::display_vector(feature_subset.vector, feature_subset.vlen,
+			"feature subset");
+
+	f->set_subset(new CSubset(feature_subset));
+	SG_SPRINT("feature vectors after setting subset on original data:\n");
+	for (index_t i=0; i<f->get_num_vectors(); ++i)
+	{
+		SGVector<float64_t> vec=f->get_feature_vector(i);
+		SG_SPRINT("%i: ", i);
+		CMath::display_vector(vec.vector, vec.vlen);
+		f->free_feature_vector(vec, i);
+	}
+
+	index_t offset_copy=2;
+	SGVector<index_t> feature_copy_subset(4);
+	CMath::range_fill_vector(feature_copy_subset.vector,
+			feature_copy_subset.vlen, offset_copy);
+	CMath::display_vector(feature_copy_subset.vector, feature_copy_subset.vlen,
+			"indices that are to be copied");
+
+	CSimpleFeatures<float64_t>* subset_copy=
+			(CSimpleFeatures<float64_t>*)f->copy_subset(feature_copy_subset);
+
+	SGMatrix<float64_t> subset_copy_matrix=subset_copy->get_feature_matrix();
+	CMath::display_matrix(subset_copy_matrix.matrix,
+			subset_copy_matrix.num_rows, subset_copy_matrix.num_cols,
+			"copy matrix");
+
+	index_t num_its=subset_copy_matrix.num_rows*subset_copy_matrix.num_cols;
+	for (index_t i=0; i<num_its; ++i)
+	{
+		index_t idx=i+(offset_copy+offset_subset)*subset_copy_matrix.num_rows;
+		ASSERT(subset_copy_matrix.matrix[i]==data.matrix[idx]);
+	}
+
+	SG_UNREF(f);
+	SG_UNREF(subset_copy);
+	delete[] feature_copy_subset.vector;
+
+	SG_SPRINT("\nEND\n");
+	exit_shogun();
+
+	return 0;
+}
+

src/shogun/features/SimpleFeatures.h

@@ -918,6 +918,27 @@ template<class ST> class CSimpleFeatures: public CDotFeatures {
 		delete[] it;
 	}
 
+	/** Creates a new CFeatures instance containing copies of the elements
+	 * which are specified by the provided indices.
+	 *
+	 * @param indices indices of feature elements to copy
+	 * @return new CFeatures instance with copies of feature data
+	 */
+	virtual CFeatures* copy_subset(SGVector<index_t> indices) const
+	{
+		SGMatrix<ST> feature_matrix_copy(num_features, indices.vlen);
+
+		for (index_t i=0; i<indices.vlen; ++i)
+		{
+			index_t real_idx=subset_idx_conversion(indices.vector[i]);
+			memcpy(&feature_matrix_copy.matrix[i*num_features],
+					&feature_matrix[real_idx*num_features],
+					num_features*sizeof(ST));
+		}
+
+		return new CSimpleFeatures(feature_matrix_copy);
+	}
+
 	/** @return object name */
 	inline virtual const char* get_name() const {
 		return "SimpleFeatures";
@@ -937,6 +958,7 @@ template<class ST> class CSimpleFeatures: public CDotFeatures {
 	 */
 	virtual ST* compute_feature_vector(int32_t num, int32_t& len, ST* target =
 			NULL) {
+		SG_NOTIMPLEMENTED;
 		len = 0;
 		return NULL;
 	}