From 2d4f9b84e7ccfd7e96db08601d00c533828f6447 Mon Sep 17 00:00:00 2001 From: JeremyNixon Date: Fri, 12 Feb 2016 12:52:10 -0800 Subject: [PATCH 1/2] use correct regression data in train-validation-split example --- docs/ml-guide.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/ml-guide.md b/docs/ml-guide.md index 5aafd53b584e..33193959c622 100644 --- a/docs/ml-guide.md +++ b/docs/ml-guide.md @@ -870,7 +870,7 @@ import org.apache.spark.ml.regression.LinearRegression import org.apache.spark.ml.tuning.{ParamGridBuilder, TrainValidationSplit} // Prepare training and test data. -val data = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt") +val data = sqlContext.read.format("libsvm").load("data/mllib/sample_linear_regression_data.txt") val Array(training, test) = data.randomSplit(Array(0.9, 0.1), seed = 12345) val lr = new LinearRegression() From 5d399e36af59e682023c54efb8889aee1229e42b Mon Sep 17 00:00:00 2001 From: JeremyNixon Date: Sat, 13 Feb 2016 19:08:32 -0800 Subject: [PATCH 2/2] update java train-validation-split example in ml-guide --- docs/ml-guide.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/ml-guide.md b/docs/ml-guide.md index 33193959c622..1d28ba084015 100644 --- a/docs/ml-guide.md +++ b/docs/ml-guide.md @@ -913,7 +913,7 @@ import org.apache.spark.ml.regression.LinearRegression; import org.apache.spark.ml.tuning.*; import org.apache.spark.sql.DataFrame; -DataFrame data = jsql.read().format("libsvm").load("data/mllib/sample_libsvm_data.txt"); +DataFrame data = jsql.read().format("libsvm").load("data/mllib/sample_linear_regression_data.txt"); // Prepare training and test data. DataFrame[] splits = data.randomSplit(new double[] {0.9, 0.1}, 12345);