1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
|
/*
* 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
import org.apache.spark.sql.functions.col
// $example off$
import org.apache.spark.sql.SparkSession
/**
* An example demonstrating BucketedRandomProjectionLSH.
* Run with:
* bin/run-example ml.BucketedRandomProjectionLSHExample
*/
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", "features")
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", "features")
val key = Vectors.dense(1.0, 0.0)
val brp = new BucketedRandomProjectionLSH()
.setBucketLength(2.0)
.setNumHashTables(3)
.setInputCol("features")
.setOutputCol("hashes")
val model = brp.fit(dfA)
// Feature Transformation
println("The hashed dataset where hashed values are stored in the column 'hashes':")
model.transform(dfA).show()
// Compute the locality sensitive hashes for the input rows, then perform approximate
// similarity join.
// We could avoid computing hashes by passing in the already-transformed dataset, e.g.
// `model.approxSimilarityJoin(transformedA, transformedB, 1.5)`
println("Approximately joining dfA and dfB on Euclidean distance smaller than 1.5:")
model.approxSimilarityJoin(dfA, dfB, 1.5, "EuclideanDistance")
.select(col("datasetA.id").alias("idA"),
col("datasetB.id").alias("idB"),
col("EuclideanDistance")).show()
// Compute the locality sensitive hashes for the input rows, then perform approximate nearest
// neighbor search.
// We could avoid computing hashes by passing in the already-transformed dataset, e.g.
// `model.approxNearestNeighbors(transformedA, key, 2)`
println("Approximately searching dfA for 2 nearest neighbors of the key:")
model.approxNearestNeighbors(dfA, key, 2).show()
// $example off$
spark.stop()
}
}
// scalastyle:on println
|