[SYSTEMDS-2756] Improved scale built-in function
Closes #1123.
diff --git a/scripts/builtin/scale.dml b/scripts/builtin/scale.dml
index 7f371cd..4fc3ef4 100644
--- a/scripts/builtin/scale.dml
+++ b/scripts/builtin/scale.dml
@@ -19,22 +19,29 @@
#
#-------------------------------------------------------------
-m_scale = function(Matrix[Double] X, Boolean center, Boolean scale) return (Matrix[Double] Y) {
- # This function centers scales and performs z-score on the input matrix X
+# Scale and center individual features in the input matrix
+# (column-wise) using z-score to scale the values.
+# -----------------------------------------------------------------------------
+# NAME TYPE DEFAULT MEANING
+# -----------------------------------------------------------------------------
+# X Matrix --- Input feature matrix
+# center Boolean TRUE Indicates whether or not to center the feature matrix
+# scale Boolean TRUE Indicates whether or not to scale the feature matrix
+# -----------------------------------------------------------------------------
+# Y Matrix --- Output feature matrix with K columns
+# -----------------------------------------------------------------------------
+m_scale = function(Matrix[Double] X, Boolean center, Boolean scale) return (Matrix[Double] Y) {
if( center )
X = X - colMeans(X);
if (scale) {
- N = nrow(X);
- if( center )
- cvars = (colSums(X^2) - N*(colMeans(X)^2))/(N-1);
- else
- cvars = colSums(X^2)/(N-1);
+ cvars = colSums(X^2)/(nrow(X)-1);
#scale by std-dev and replace NaNs with 0's
X = replace(target=X/sqrt(cvars),
pattern=NaN, replacement=0);
}
+
Y = X;
}
