Merge pull request #311 from frx/streaming_vw

StreamingStringFeatures improvements
shogun-toolbox · Aug 26, 2011 · 58b557f · 58b557f
2 parents 4a4d755 + 1d81f89
commit 58b557f
Show file tree

Hide file tree

Showing 4 changed files with 354 additions and 288 deletions.
diff --git a/examples/undocumented/libshogun/streaming_stringfeatures.cpp b/examples/undocumented/libshogun/streaming_stringfeatures.cpp
@@ -0,0 +1,52 @@
+// This example simply demonstrates the use/working of StreamingStringFeatures
+
+#include <shogun/io/StreamingAsciiFile.h>
+#include <shogun/features/StreamingStringFeatures.h>
+
+using namespace shogun;
+
+void display_vector(const SGString<char> &vec)
+{
+	printf("\nNew Vector\n------------------\n");
+	printf("Length=%d.\n", vec.slen);
+	for (int32_t i=0; i<vec.slen; i++)
+	{
+		printf("%c", vec.string[i]);
+	}
+	printf("\n");
+}
+
+int main(int argc, char **argv)
+{
+	init_shogun_with_defaults();
+
+	// Create a StreamingAsciiFile from our input file
+	CStreamingAsciiFile* file = new CStreamingAsciiFile("../data/fm_train_dna.dat");
+
+	// This file contains unlabelled data, so the second arg is `false'.
+	CStreamingStringFeatures<char>* feat = new CStreamingStringFeatures<char>(file, false, 1024);
+	// Alphabet to use is DNA
+	feat->use_alphabet(DNA);
+
+	// Loop over all examples and simply display each example
+	feat->start_parser();
+	while (feat->get_next_example())
+	{
+		SGString<char> vec = feat->get_vector();
+		display_vector(vec);
+		feat->release_example();
+	}
+	feat->end_parser();
+
+	// Get the alphabet and display the histogram
+	CAlphabet* alpha = feat->get_alphabet();
+	printf("\nThe histogram is:\n");
+	alpha->print_histogram();
+	SG_UNREF(alpha);
+
+	SG_UNREF(feat);
+	SG_UNREF(file);
+
+	exit_shogun();
+	return 0;
+}
diff --git a/src/shogun/features/StreamingStringFeatures.h b/src/shogun/features/StreamingStringFeatures.h
@@ -69,7 +69,7 @@ template <class T> class CStreamingStringFeatures : public CStreamingFeatures
 	~CStreamingStringFeatures()
 	{
 		parser.end_parser();
-		SG_FREE(current_string);
+		SG_UNREF(alphabet);
 	}
 
 	/** 
@@ -102,6 +102,8 @@ template <class T> class CStreamingStringFeatures : public CStreamingFeatures
 	 */
 	void use_alphabet(EAlphabet alpha)
 	{
+		SG_UNREF(alphabet);
+
 		alphabet=new CAlphabet(alpha);
 		SG_REF(alphabet);
 		num_symbols=alphabet->get_num_symbols();
@@ -115,6 +117,8 @@ template <class T> class CStreamingStringFeatures : public CStreamingFeatures
 	 */
 	void use_alphabet(CAlphabet* alpha)
 	{
+		SG_UNREF(alphabet);
+
 		alphabet=new CAlphabet(alpha);
 		SG_REF(alphabet);
 		num_symbols=alphabet->get_num_symbols();
@@ -375,7 +379,7 @@ void CStreamingStringFeatures<T>::init()
 {
 	working_file=NULL;
 	alphabet=new CAlphabet();
-	
+
 	current_string=NULL;
 	current_length=-1;
 	current_sgstring.string=current_string;
@@ -391,6 +395,8 @@ void CStreamingStringFeatures<T>::init(CStreamingFile* file,
 	has_labels=is_labelled;
 	working_file=file;
 	parser.init(file, is_labelled, size);
+	parser.set_free_vector_after_release(false);
+	parser.set_free_vectors_on_destruct(false);
 }
 
 template <class T>