change libsvm read format

Author: yinxusen

examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeClassifierExample.java

@@ -42,8 +42,7 @@ public static void main(String[] args) {
 
     // $example on$
     // Load and parse the data file, converting it to a DataFrame.
-    RDD<LabeledPoint> rdd = MLUtils.loadLibSVMFile(jsc.sc(), "data/mllib/sample_libsvm_data.txt");
-    DataFrame data = sqlContext.createDataFrame(rdd, LabeledPoint.class);
+    DataFrame data = sqlContext.read().format("libsvm").load("data/mllib/sample_libsvm_data.txt");
 
     // Index labels, adding metadata to the label column.
     // Fit on whole dataset to include all labels in index.

examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeRegressorExample.java

@@ -43,8 +43,7 @@ public static void main(String[] args) {
 
     // $example on$
     // Load and parse the data file, converting it to a DataFrame.
-    RDD<LabeledPoint> rdd = MLUtils.loadLibSVMFile(jsc.sc(), "data/mllib/sample_libsvm_data.txt");
-    DataFrame data = sqlContext.createDataFrame(rdd, LabeledPoint.class);
+    DataFrame data = sqlContext.read().format("libsvm").load("data/mllib/sample_libsvm_data.txt");
 
     // Automatically identify categorical features, and index them.
     // Set maxCategories so features with > 4 distinct values are treated as continuous.

examples/src/main/java/org/apache/spark/examples/ml/JavaRandomForestClassifierExample.java

@@ -42,8 +42,7 @@ public static void main(String[] args) {
 
     // $example on$
     // Load and parse the data file, converting it to a DataFrame.
-    RDD<LabeledPoint> rdd = MLUtils.loadLibSVMFile(jsc.sc(), "data/mllib/sample_libsvm_data.txt");
-    DataFrame data = sqlContext.createDataFrame(rdd, LabeledPoint.class);
+    DataFrame data = sqlContext.read().format("libsvm").load("data/mllib/sample_libsvm_data.txt");
 
     // Index labels, adding metadata to the label column.
     // Fit on whole dataset to include all labels in index.

examples/src/main/java/org/apache/spark/examples/ml/JavaRandomForestRegressorExample.java

@@ -43,8 +43,7 @@ public static void main(String[] args) {
 
     // $example on$
     // Load and parse the data file, converting it to a DataFrame.
-    RDD<LabeledPoint> rdd = MLUtils.loadLibSVMFile(jsc.sc(), "data/mllib/sample_libsvm_data.txt");
-    DataFrame data = sqlContext.createDataFrame(rdd, LabeledPoint.class);
+    DataFrame data = sqlContext.read().format("libsvm").load("data/mllib/sample_libsvm_data.txt");
 
     // Automatically identify categorical features, and index them.
     // Set maxCategories so features with > 4 distinct values are treated as continuous.

examples/src/main/python/ml/gradient_boosted_tree_classifier_example.py

@@ -37,7 +37,7 @@
 
     # $example on$
     # Load and parse the data file, converting it to a DataFrame.
-    data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt").toDF()
+    data = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
 
     # Index labels, adding metadata to the label column.
     # Fit on whole dataset to include all labels in index.

examples/src/main/python/ml/gradient_boosted_tree_regressor_example.py

@@ -37,7 +37,7 @@
 
     # $example on$
     # Load and parse the data file, converting it to a DataFrame.
-    data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt").toDF()
+    data = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
 
     # Automatically identify categorical features, and index them.
     # Set maxCategories so features with > 4 distinct values are treated as continuous.

examples/src/main/python/ml/random_forest_classifier_example.py

@@ -37,7 +37,7 @@
 
     # $example on$
     # Load and parse the data file, converting it to a DataFrame.
-    data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt").toDF()
+    data = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
 
     # Index labels, adding metadata to the label column.
     # Fit on whole dataset to include all labels in index.

examples/src/main/python/ml/random_forest_regressor_example.py

@@ -37,7 +37,7 @@
 
     # $example on$
     # Load and parse the data file, converting it to a DataFrame.
-    data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt").toDF()
+    data = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
 
     # Automatically identify categorical features, and index them.
     # Set maxCategories so features with > 4 distinct values are treated as continuous.

examples/src/main/scala/org/apache/spark/examples/ml/GradientBoostedTreeClassifierExample.scala

@@ -33,11 +33,10 @@ object GradientBoostedTreeClassifierExample {
     val conf = new SparkConf().setAppName("GradientBoostedTreeClassifierExample")
     val sc = new SparkContext(conf)
     val sqlContext = new SQLContext(sc)
-    import sqlContext.implicits._
 
     // $example on$
     // Load and parse the data file, converting it to a DataFrame.
-    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")
 
     // Index labels, adding metadata to the label column.
     // Fit on whole dataset to include all labels in index.

examples/src/main/scala/org/apache/spark/examples/ml/GradientBoostedTreeRegressorExample.scala

@@ -33,11 +33,10 @@ object GradientBoostedTreeRegressorExample {
     val conf = new SparkConf().setAppName("GradientBoostedTreeRegressorExample")
     val sc = new SparkContext(conf)
     val sqlContext = new SQLContext(sc)
-    import sqlContext.implicits._
 
     // $example on$
     // Load and parse the data file, converting it to a DataFrame.
-    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")
 
     // Automatically identify categorical features, and index them.
     // Set maxCategories so features with > 4 distinct values are treated as continuous.