blob: c93ed64183ad69a6e399b6c74024cce14d8416b4 (
plain) (
blame)
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
|
/*
* 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.
*/
package org.apache.spark.mllib.feature
import java.lang.{Iterable => JavaIterable}
import scala.collection.JavaConverters._
import scala.collection.mutable
import org.apache.spark.annotation.Since
import org.apache.spark.api.java.JavaRDD
import org.apache.spark.mllib.linalg.{Vector, Vectors}
import org.apache.spark.rdd.RDD
import org.apache.spark.util.Utils
/**
* Maps a sequence of terms to their term frequencies using the hashing trick.
*
* @param numFeatures number of features (default: 2^20^)
*/
@Since("1.1.0")
class HashingTF(val numFeatures: Int) extends Serializable {
/**
*/
@Since("1.1.0")
def this() = this(1 << 20)
/**
* Returns the index of the input term.
*/
@Since("1.1.0")
def indexOf(term: Any): Int = Utils.nonNegativeMod(term.##, numFeatures)
/**
* Transforms the input document into a sparse term frequency vector.
*/
@Since("1.1.0")
def transform(document: Iterable[_]): Vector = {
val termFrequencies = mutable.HashMap.empty[Int, Double]
document.foreach { term =>
val i = indexOf(term)
termFrequencies.put(i, termFrequencies.getOrElse(i, 0.0) + 1.0)
}
Vectors.sparse(numFeatures, termFrequencies.toSeq)
}
/**
* Transforms the input document into a sparse term frequency vector (Java version).
*/
@Since("1.1.0")
def transform(document: JavaIterable[_]): Vector = {
transform(document.asScala)
}
/**
* Transforms the input document to term frequency vectors.
*/
@Since("1.1.0")
def transform[D <: Iterable[_]](dataset: RDD[D]): RDD[Vector] = {
dataset.map(this.transform)
}
/**
* Transforms the input document to term frequency vectors (Java version).
*/
@Since("1.1.0")
def transform[D <: JavaIterable[_]](dataset: JavaRDD[D]): JavaRDD[Vector] = {
dataset.rdd.map(this.transform).toJavaRDD()
}
}
|
