Repository: incubator-systemml Updated Branches: refs/heads/master 66ea6f0c6 -> ba6f1e60a
[DOC] Add comments to `RDDConverterUtilsExt.addIDToDataFrame` to explain that it uses 1-based indexing. Closes #154. Project: http://git-wip-us.apache.org/repos/asf/incubator-systemml/repo Commit: http://git-wip-us.apache.org/repos/asf/incubator-systemml/commit/ba6f1e60 Tree: http://git-wip-us.apache.org/repos/asf/incubator-systemml/tree/ba6f1e60 Diff: http://git-wip-us.apache.org/repos/asf/incubator-systemml/diff/ba6f1e60 Branch: refs/heads/master Commit: ba6f1e60ad7d603fe520de93f376d7e65d98b5e2 Parents: 66ea6f0 Author: Tommy YU <[email protected]> Authored: Mon May 16 12:19:06 2016 -0700 Committer: Mike Dusenberry <[email protected]> Committed: Mon May 16 12:19:06 2016 -0700 ---------------------------------------------------------------------- .../instructions/spark/utils/RDDConverterUtilsExt.java | 8 ++++++++ 1 file changed, 8 insertions(+) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/incubator-systemml/blob/ba6f1e60/src/main/java/org/apache/sysml/runtime/instructions/spark/utils/RDDConverterUtilsExt.java ---------------------------------------------------------------------- diff --git a/src/main/java/org/apache/sysml/runtime/instructions/spark/utils/RDDConverterUtilsExt.java b/src/main/java/org/apache/sysml/runtime/instructions/spark/utils/RDDConverterUtilsExt.java index f949f74..ccdc927 100644 --- a/src/main/java/org/apache/sysml/runtime/instructions/spark/utils/RDDConverterUtilsExt.java +++ b/src/main/java/org/apache/sysml/runtime/instructions/spark/utils/RDDConverterUtilsExt.java @@ -346,6 +346,14 @@ public class RDDConverterUtilsExt } } + + /** + * Add element indices as new column to DataFrame + * Note: Element indices start from 1 + * @param df input data frame + * @param nameOfCol name of index column + * @return new data frame + */ public static DataFrame addIDToDataFrame(DataFrame df, SQLContext sqlContext, String nameOfCol) { StructField[] oldSchema = df.schema().fields(); StructField[] newSchema = new StructField[oldSchema.length + 1];
