Fixed GNB zero variance handling

shogun-toolbox · Jun 1, 2012 · e915d01 · e915d01
1 parent f100cae
commit e915d01
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 13 deletions.
diff --git a/src/shogun/multiclass/GaussianNaiveBayes.cpp b/src/shogun/multiclass/GaussianNaiveBayes.cpp
@@ -215,10 +215,12 @@ float64_t CGaussianNaiveBayes::apply_one(int32_t idx)
 		}
 		else
 			m_rates.vector[i] = CMath::log(m_label_prob.vector[i]);
-
+	
 		// product all conditional gaussian probabilities
 		for (k=0; k<m_dim; k++)
-			m_rates.vector[i]+= CMath::log(normal_exp(feature_vector.vector[k],i,k)/CMath::sqrt(m_variances(k, i)));
+			if (m_variances(k,i)!=0.0)
+				m_rates.vector[i]+= CMath::log(0.39894228/CMath::sqrt(m_variances(k, i))) - 
+					0.5*CMath::sq(feature_vector.vector[k]-m_means(k, i))/(m_variances(k, i));
 	}
 
 	// find label with maximum rate

diff --git a/src/shogun/multiclass/GaussianNaiveBayes.h b/src/shogun/multiclass/GaussianNaiveBayes.h
@@ -117,17 +117,6 @@ class CGaussianNaiveBayes : public CNativeMulticlassMachine
 	/// a priori probabilities of labels
 	SGVector<float64_t> m_label_prob;
 
-	/** computes gaussian exponent by x, indexes, m_means and m_variances
-	 * @param x feature value
-	 * @param l_idx index of label
-	 * @param f_idx index of feature
-	 * @return exponent value
-	 */
-	float64_t inline normal_exp(float64_t x, int32_t l_idx, int32_t f_idx)
-	{
-		return CMath::exp(-CMath::sq(x-m_means(f_idx, l_idx))/(2*m_variances(f_idx, l_idx)));
-	}
-
 	/// label rates
 	SGVector<float64_t> m_rates;
 };