Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/7029#discussion_r33435601 --- Diff: docs/mllib-feature-extraction.md --- @@ -451,19 +452,20 @@ JavaRDD<LabeledPoint> points = MLUtils.loadLibSVMFile(sc.sc(), "data/mllib/sample_libsvm_data.txt").toJavaRDD().cache(); // Discretize data in 16 equal bins since ChiSqSelector requires categorical features +// Even though features are doubles, the ChiSqSelector treats each unique value as a category JavaRDD<LabeledPoint> discretizedData = points.map( new Function<LabeledPoint, LabeledPoint>() { @Override public LabeledPoint call(LabeledPoint lp) { final double[] discretizedFeatures = new double[lp.features().size()]; for (int i = 0; i < lp.features().size(); ++i) { - discretizedFeatures[i] = lp.features().apply(i) / 16; + discretizedFeatures[i] = Math.floor(lp.features().apply(i) / 16); } return new LabeledPoint(lp.label(), Vectors.dense(discretizedFeatures)); } }); -// Create ChiSqSelector that will select 50 features +// Create ChiSqSelector that will select top 50 of 692 features --- End diff -- remove the extra space after `50`
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org