diff options
Diffstat (limited to 'docs/ml-guide.md')
| -rw-r--r-- | docs/ml-guide.md | 10 |
1 files changed, 2 insertions, 8 deletions
diff --git a/docs/ml-guide.md b/docs/ml-guide.md index c293e71d28..be18a05361 100644 --- a/docs/ml-guide.md +++ b/docs/ml-guide.md @@ -867,10 +867,9 @@ The `ParamMap` which produces the best evaluation metric is selected as the best import org.apache.spark.ml.evaluation.RegressionEvaluator import org.apache.spark.ml.regression.LinearRegression import org.apache.spark.ml.tuning.{ParamGridBuilder, TrainValidationSplit} -import org.apache.spark.mllib.util.MLUtils // Prepare training and test data. -val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt").toDF() +val data = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt") val Array(training, test) = data.randomSplit(Array(0.9, 0.1), seed = 12345) val lr = new LinearRegression() @@ -911,14 +910,9 @@ import org.apache.spark.ml.evaluation.RegressionEvaluator; import org.apache.spark.ml.param.ParamMap; import org.apache.spark.ml.regression.LinearRegression; import org.apache.spark.ml.tuning.*; -import org.apache.spark.mllib.regression.LabeledPoint; -import org.apache.spark.mllib.util.MLUtils; -import org.apache.spark.rdd.RDD; import org.apache.spark.sql.DataFrame; -DataFrame data = sqlContext.createDataFrame( - MLUtils.loadLibSVMFile(jsc.sc(), "data/mllib/sample_libsvm_data.txt"), - LabeledPoint.class); +DataFrame data = jsql.read().format("libsvm").load("data/mllib/sample_libsvm_data.txt"); // Prepare training and test data. DataFrame[] splits = data.randomSplit(new double[] {0.9, 0.1}, 12345); |