Cleanup string preprocessors and rename init to fit

shogun-toolbox · Jun 8, 2018 · cb0f95c · cb0f95c
1 parent 4784e33
commit cb0f95c
Show file tree

Hide file tree

Showing 7 changed files with 13 additions and 48 deletions.
diff --git a/src/shogun/preprocessor/DecompressString.cpp b/src/shogun/preprocessor/DecompressString.cpp
@@ -24,13 +24,6 @@ CDecompressString<ST>::~CDecompressString()
 	delete compressor;
 }
 
-template <class ST>
-bool CDecompressString<ST>::init(CFeatures* f)
-{
-	ASSERT(f->get_feature_class()==C_STRING)
-	return true;
-}
-
 template <class ST>
 void CDecompressString<ST>::cleanup()
 {
@@ -56,22 +49,19 @@ template <class ST>
 bool CDecompressString<ST>::apply_to_string_features(CFeatures* f)
 {
 	int32_t i;
-	int32_t num_vec=((CStringFeatures<ST>*)f)->get_num_vectors();
+	auto sf = f->as<CStringFeatures<ST>>();
+	int32_t num_vec = sf->get_num_vectors();
 
 	for (i=0; i<num_vec; i++)
 	{
 		int32_t len=0;
 		bool free_vec;
-		ST* vec=((CStringFeatures<ST>*)f)->
-			get_feature_vector(i, len, free_vec);
+		ST* vec = sf->get_feature_vector(i, len, free_vec);
 
 		ST* decompressed=apply_to_string(vec, len);
-		((CStringFeatures<ST>*)f)->
-			free_feature_vector(vec, i, free_vec);
-		((CStringFeatures<ST>*)f)->
-			cleanup_feature_vector(i);
-		((CStringFeatures<ST>*)f)->
-			set_feature_vector(i, decompressed, len);
+		sf->free_feature_vector(vec, i, free_vec);
+		sf->cleanup_feature_vector(i);
+		sf->set_feature_vector(i, decompressed, len);
 	}
 	return true;
 }

diff --git a/src/shogun/preprocessor/DecompressString.h b/src/shogun/preprocessor/DecompressString.h
@@ -43,9 +43,6 @@ template <class ST> class CDecompressString : public CStringPreprocessor<ST>
 		/** destructor */
 		virtual ~CDecompressString();
 
-		/// initialize preprocessor from features
-		virtual bool init(CFeatures* f);
-
 		/// cleanup
 		virtual void cleanup();
 

diff --git a/src/shogun/preprocessor/SortUlongString.cpp b/src/shogun/preprocessor/SortUlongString.cpp
@@ -20,15 +20,6 @@ CSortUlongString::~CSortUlongString()
 {
 }
 
-/// initialize preprocessor from features
-bool CSortUlongString::init(CFeatures* f)
-{
-	ASSERT(f->get_feature_class()==C_STRING)
-	ASSERT(f->get_feature_type()==F_ULONG)
-
-	return true;
-}
-
 /// clean up allocated memory
 void CSortUlongString::cleanup()
 {
@@ -56,14 +47,14 @@ bool CSortUlongString::save(FILE* f)
 bool CSortUlongString::apply_to_string_features(CFeatures* f)
 {
 	int32_t i;
-	int32_t num_vec=((CStringFeatures<uint64_t>*)f)->get_num_vectors();
+	auto sf = f->as<CStringFeatures<uint64_t>>();
+	int32_t num_vec = sf->get_num_vectors();
 
 	for (i=0; i<num_vec; i++)
 	{
 		int32_t len=0;
 		bool free_vec;
-		uint64_t* vec=((CStringFeatures<uint64_t>*)f)->
-			get_feature_vector(i, len, free_vec);
+		uint64_t* vec = sf->get_feature_vector(i, len, free_vec);
 		ASSERT(!free_vec) // won't work with non-in-memory string features
 
 		SG_DEBUG("sorting string of length %i\n", len)

diff --git a/src/shogun/preprocessor/SortUlongString.h b/src/shogun/preprocessor/SortUlongString.h
@@ -31,8 +31,6 @@ class CSortUlongString : public CStringPreprocessor<uint64_t>
 	/** destructor */
 	virtual ~CSortUlongString();
 
-	/// initialize preprocessor from features
-	virtual bool init(CFeatures* f);
 	/// cleanup
 	virtual void cleanup();
 	/// initialize preprocessor from file

diff --git a/src/shogun/preprocessor/SortWordString.cpp b/src/shogun/preprocessor/SortWordString.cpp
@@ -20,15 +20,6 @@ CSortWordString::~CSortWordString()
 {
 }
 
-/// initialize preprocessor from features
-bool CSortWordString::init(CFeatures* f)
-{
-	ASSERT(f->get_feature_class()==C_STRING)
-	ASSERT(f->get_feature_type()==F_WORD)
-
-	return true;
-}
-
 /// clean up allocated memory
 void CSortWordString::cleanup()
 {
@@ -56,13 +47,14 @@ bool CSortWordString::save(FILE* f)
 bool CSortWordString::apply_to_string_features(CFeatures* f)
 {
 	int32_t i;
-	int32_t num_vec=((CStringFeatures<uint16_t>*)f)->get_num_vectors() ;
+	auto sf = f->as<CStringFeatures<uint16_t>>();
+	int32_t num_vec = sf->get_num_vectors();
 
 	for (i=0; i<num_vec; i++)
 	{
 		int32_t len = 0 ;
 		bool free_vec;
-		uint16_t* vec = ((CStringFeatures<uint16_t>*)f)->get_feature_vector(i, len, free_vec);
+		uint16_t* vec = sf->get_feature_vector(i, len, free_vec);
 		ASSERT(!free_vec) // won't work with non-in-memory string features
 
 		//CMath::qsort(vec, len);

diff --git a/src/shogun/preprocessor/SortWordString.h b/src/shogun/preprocessor/SortWordString.h
@@ -32,9 +32,6 @@ class CSortWordString : public CStringPreprocessor<uint16_t>
 	/** destructor */
 	virtual ~CSortWordString();
 
-	/// initialize preprocessor from features
-	virtual bool init(CFeatures* f);
-
 	/// cleanup
 	virtual void cleanup();
 	/// initialize preprocessor from file

diff --git a/tests/unit/kernel/CommUlongStringKernel_unittest.cc b/tests/unit/kernel/CommUlongStringKernel_unittest.cc
@@ -37,7 +37,7 @@ TEST(CommUlongStringKernel, kernel_matrix)
 	CStringFeatures<uint64_t>* l_feats = new CStringFeatures<uint64_t>(alphabet);
 	l_feats->obtain_from_char(s_feats, 5-1, 5, 0, false);
 	CSortUlongString* preproc = new CSortUlongString();
-	preproc->init(l_feats);
+	preproc->fit(l_feats);
 	l_feats->add_preprocessor(preproc);
 	l_feats->apply_preprocessor();
 	CCommUlongStringKernel* kernel = new CCommUlongStringKernel(l_feats, l_feats);