Merge pull request #209 from jecisc/speedup-data-encoding

Speedup data preprocessing a lot

Author: jecisc

src/DataFrame/DataFrame.class.st

@@ -852,6 +852,18 @@ DataFrame >> crossTabulate: colName1 with: colName2 [
 	^ col1 crossTabulateWith: col2
 ]
 
+{ #category : #copying }
+DataFrame >> dataPreProcessingEncodeWith: anEncoder [
+	"This method is here to speed up pharo-ai/data-preprocessing algos without coupling both projects."
+
+	| copy |
+	copy := self copy.
+	self columns doWithIndex: [ :dataSerie :columnIndex |
+		dataSerie doWithIndex: [ :element :rowIndex | copy at: rowIndex at: columnIndex put: ((anEncoder categories at: columnIndex) indexOf: element) ] ].
+
+	^ copy
+]
+
 { #category : #'data-types' }
 DataFrame >> dataTypeOfColumn: aColumnName [
 	"Given a column name of the DataFrame, it returns the data type of that column"