diff options
Diffstat (limited to 'examples/src/main/scala/org/apache/spark/examples/ml/BucketedRandomProjectionLSHExample.scala')
-rw-r--r-- | examples/src/main/scala/org/apache/spark/examples/ml/BucketedRandomProjectionLSHExample.scala | 80 |
1 files changed, 80 insertions, 0 deletions
diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/BucketedRandomProjectionLSHExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/BucketedRandomProjectionLSHExample.scala new file mode 100644 index 0000000000..686cc39d3b --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/BucketedRandomProjectionLSHExample.scala @@ -0,0 +1,80 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.ml + +// $example on$ +import org.apache.spark.ml.feature.BucketedRandomProjectionLSH +import org.apache.spark.ml.linalg.Vectors +// $example off$ +import org.apache.spark.sql.SparkSession + +object BucketedRandomProjectionLSHExample { + def main(args: Array[String]): Unit = { + // Creates a SparkSession + val spark = SparkSession + .builder + .appName("BucketedRandomProjectionLSHExample") + .getOrCreate() + + // $example on$ + val dfA = spark.createDataFrame(Seq( + (0, Vectors.dense(1.0, 1.0)), + (1, Vectors.dense(1.0, -1.0)), + (2, Vectors.dense(-1.0, -1.0)), + (3, Vectors.dense(-1.0, 1.0)) + )).toDF("id", "keys") + + val dfB = spark.createDataFrame(Seq( + (4, Vectors.dense(1.0, 0.0)), + (5, Vectors.dense(-1.0, 0.0)), + (6, Vectors.dense(0.0, 1.0)), + (7, Vectors.dense(0.0, -1.0)) + )).toDF("id", "keys") + + val key = Vectors.dense(1.0, 0.0) + + val brp = new BucketedRandomProjectionLSH() + .setBucketLength(2.0) + .setNumHashTables(3) + .setInputCol("keys") + .setOutputCol("values") + + val model = brp.fit(dfA) + + // Feature Transformation + model.transform(dfA).show() + // Cache the transformed columns + val transformedA = model.transform(dfA).cache() + val transformedB = model.transform(dfB).cache() + + // Approximate similarity join + model.approxSimilarityJoin(dfA, dfB, 1.5).show() + model.approxSimilarityJoin(transformedA, transformedB, 1.5).show() + // Self Join + model.approxSimilarityJoin(dfA, dfA, 2.5).filter("datasetA.id < datasetB.id").show() + + // Approximate nearest neighbor search + model.approxNearestNeighbors(dfA, key, 2).show() + model.approxNearestNeighbors(transformedA, key, 2).show() + // $example off$ + + spark.stop() + } +} +// scalastyle:on println |