public static void main(String[] args) {
SparkConf conf = new SparkConf().setAppName("JavaStandardScalerExample");
JavaSparkContext jsc = new JavaSparkContext(conf);
SQLContext jsql = new SQLContext(jsc);
DataFrame dataFrame = jsql.read().format("libsvm").load("data/mllib/sample_libsvm_data.txt");
StandardScaler scaler = new StandardScaler()
.setInputCol("features")
.setOutputCol("scaledFeatures")
.setWithStd(true)
.setWithMean(false);
StandardScalerModel scalerModel = scaler.fit(dataFrame);
DataFrame scaledData = scalerModel.transform(dataFrame);
scaledData.show();
jsc.stop();
}
|