better way of generating mean samples

shogun-toolbox · Jul 22, 2012 · 3d23819 · 3d23819
1 parent f1232bc
commit 3d23819
Show file tree

Hide file tree

Showing 2 changed files with 25 additions and 10 deletions.
diff --git a/src/shogun/features/DataGenerator.cpp b/src/shogun/features/DataGenerator.cpp
@@ -27,16 +27,29 @@ void CDataGenerator::init()
 }
 
 SGMatrix<float64_t> CDataGenerator::generate_mean_data(index_t m,
-		index_t dim, float64_t mean_shift)
+		index_t dim, float64_t mean_shift, float64_t* target_data)
 {
-	SGMatrix<float64_t> result(dim, m);
+	/* evtl use pre-allocated space */
+	SGMatrix<float64_t> result;
 
-	for (index_t i=0; i<m; ++i)
+	if (target_data)
+	{
+		result.matrix=target_data;
+		result.num_rows=dim;
+		result.num_cols=2*m;
+	}
+	else
+		result=SGMatrix<float64_t>(dim, 2*m);
+
+	/* fill matrix with normal data */
+	for (index_t i=0; i<2*m; ++i)
 	{
 		for (index_t j=0; j<dim; ++j)
 			result(j,i)=CMath::randn_double();
 
-		result(0,i)+=mean_shift;
+		/* mean shift for second half */
+		if (i>=m)
+			result(0,i)+=mean_shift;
 	}
 
 	return result;

diff --git a/src/shogun/features/DataGenerator.h b/src/shogun/features/DataGenerator.h
@@ -26,17 +26,19 @@ class CDataGenerator: public CSGObject
 
 	virtual ~CDataGenerator();
 
-	/** produces a set of vectors, where each dimension is standard normally
-	 * distributed and the mean of the first dimension is shifted by a
-	 * provided value
+	/** Takes each m samples from two distributions p and q, where each element
+	 * is standard normally distributed, except for the first dimension of q,
+	 * where the mean is shifted by a specified value.
 	 *
 	 * @param m number of samples to generate
 	 * @param dim dimension of generated samples
 	 * @param mean_shift is added mean of first dimension
-	 * @return matrix with samples
+	 * @target_data if non-NULL then this is used as matrix data storage. Make
+	 * sure that its dimensions fit
+	 * @return matrix with concatenated samples,first p then q
 	 */
-	SGMatrix<float64_t> generate_mean_data(index_t m, index_t dim,
-			float64_t mean_shift);
+	static SGMatrix<float64_t> generate_mean_data(index_t m, index_t dim,
+			float64_t mean_shift, float64_t* target_data=NULL);
 
 	inline virtual const char* get_name() const { return "DataGenerator"; }