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
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
|
/*
* 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.recommendation
import java.io.IOException
import java.lang.{Integer => JavaInteger}
import org.apache.hadoop.fs.Path
import org.jblas.DoubleMatrix
import org.apache.spark.{Logging, SparkContext}
import org.apache.spark.api.java.{JavaPairRDD, JavaRDD}
import org.apache.spark.mllib.util.{Loader, Saveable}
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.{Row, SQLContext}
import org.apache.spark.storage.StorageLevel
/**
* Model representing the result of matrix factorization.
*
* Note: If you create the model directly using constructor, please be aware that fast prediction
* requires cached user/product features and their associated partitioners.
*
* @param rank Rank for the features in this model.
* @param userFeatures RDD of tuples where each tuple represents the userId and
* the features computed for this user.
* @param productFeatures RDD of tuples where each tuple represents the productId
* and the features computed for this product.
*/
class MatrixFactorizationModel(
val rank: Int,
val userFeatures: RDD[(Int, Array[Double])],
val productFeatures: RDD[(Int, Array[Double])])
extends Saveable with Serializable with Logging {
require(rank > 0)
validateFeatures("User", userFeatures)
validateFeatures("Product", productFeatures)
/** Validates factors and warns users if there are performance concerns. */
private def validateFeatures(name: String, features: RDD[(Int, Array[Double])]): Unit = {
require(features.first()._2.size == rank,
s"$name feature dimension does not match the rank $rank.")
if (features.partitioner.isEmpty) {
logWarning(s"$name factor does not have a partitioner. "
+ "Prediction on individual records could be slow.")
}
if (features.getStorageLevel == StorageLevel.NONE) {
logWarning(s"$name factor is not cached. Prediction could be slow.")
}
}
/** Predict the rating of one user for one product. */
def predict(user: Int, product: Int): Double = {
val userVector = new DoubleMatrix(userFeatures.lookup(user).head)
val productVector = new DoubleMatrix(productFeatures.lookup(product).head)
userVector.dot(productVector)
}
/**
* Predict the rating of many users for many products.
* The output RDD has an element per each element in the input RDD (including all duplicates)
* unless a user or product is missing in the training set.
*
* @param usersProducts RDD of (user, product) pairs.
* @return RDD of Ratings.
*/
def predict(usersProducts: RDD[(Int, Int)]): RDD[Rating] = {
val users = userFeatures.join(usersProducts).map{
case (user, (uFeatures, product)) => (product, (user, uFeatures))
}
users.join(productFeatures).map {
case (product, ((user, uFeatures), pFeatures)) =>
val userVector = new DoubleMatrix(uFeatures)
val productVector = new DoubleMatrix(pFeatures)
Rating(user, product, userVector.dot(productVector))
}
}
/**
* Java-friendly version of [[MatrixFactorizationModel.predict]].
*/
def predict(usersProducts: JavaPairRDD[JavaInteger, JavaInteger]): JavaRDD[Rating] = {
predict(usersProducts.rdd.asInstanceOf[RDD[(Int, Int)]]).toJavaRDD()
}
/**
* Recommends products to a user.
*
* @param user the user to recommend products to
* @param num how many products to return. The number returned may be less than this.
* @return [[Rating]] objects, each of which contains the given user ID, a product ID, and a
* "score" in the rating field. Each represents one recommended product, and they are sorted
* by score, decreasing. The first returned is the one predicted to be most strongly
* recommended to the user. The score is an opaque value that indicates how strongly
* recommended the product is.
*/
def recommendProducts(user: Int, num: Int): Array[Rating] =
recommend(userFeatures.lookup(user).head, productFeatures, num)
.map(t => Rating(user, t._1, t._2))
/**
* Recommends users to a product. That is, this returns users who are most likely to be
* interested in a product.
*
* @param product the product to recommend users to
* @param num how many users to return. The number returned may be less than this.
* @return [[Rating]] objects, each of which contains a user ID, the given product ID, and a
* "score" in the rating field. Each represents one recommended user, and they are sorted
* by score, decreasing. The first returned is the one predicted to be most strongly
* recommended to the product. The score is an opaque value that indicates how strongly
* recommended the user is.
*/
def recommendUsers(product: Int, num: Int): Array[Rating] =
recommend(productFeatures.lookup(product).head, userFeatures, num)
.map(t => Rating(t._1, product, t._2))
protected override val formatVersion: String = "1.0"
override def save(sc: SparkContext, path: String): Unit = {
MatrixFactorizationModel.SaveLoadV1_0.save(this, path)
}
private def recommend(
recommendToFeatures: Array[Double],
recommendableFeatures: RDD[(Int, Array[Double])],
num: Int): Array[(Int, Double)] = {
val recommendToVector = new DoubleMatrix(recommendToFeatures)
val scored = recommendableFeatures.map { case (id,features) =>
(id, recommendToVector.dot(new DoubleMatrix(features)))
}
scored.top(num)(Ordering.by(_._2))
}
}
object MatrixFactorizationModel extends Loader[MatrixFactorizationModel] {
import org.apache.spark.mllib.util.Loader._
override def load(sc: SparkContext, path: String): MatrixFactorizationModel = {
val (loadedClassName, formatVersion, metadata) = loadMetadata(sc, path)
val classNameV1_0 = SaveLoadV1_0.thisClassName
(loadedClassName, formatVersion) match {
case (className, "1.0") if className == classNameV1_0 =>
SaveLoadV1_0.load(sc, path)
case _ =>
throw new IOException("MatrixFactorizationModel.load did not recognize model with" +
s"(class: $loadedClassName, version: $formatVersion). Supported:\n" +
s" ($classNameV1_0, 1.0)")
}
}
private[recommendation]
object SaveLoadV1_0 {
private val thisFormatVersion = "1.0"
private[recommendation]
val thisClassName = "org.apache.spark.mllib.recommendation.MatrixFactorizationModel"
/**
* Saves a [[MatrixFactorizationModel]], where user features are saved under `data/users` and
* product features are saved under `data/products`.
*/
def save(model: MatrixFactorizationModel, path: String): Unit = {
val sc = model.userFeatures.sparkContext
val sqlContext = new SQLContext(sc)
import sqlContext.implicits.createDataFrame
val metadata = (thisClassName, thisFormatVersion, model.rank)
val metadataRDD = sc.parallelize(Seq(metadata), 1).toDataFrame("class", "version", "rank")
metadataRDD.toJSON.saveAsTextFile(metadataPath(path))
model.userFeatures.toDataFrame("id", "features").saveAsParquetFile(userPath(path))
model.productFeatures.toDataFrame("id", "features").saveAsParquetFile(productPath(path))
}
def load(sc: SparkContext, path: String): MatrixFactorizationModel = {
val sqlContext = new SQLContext(sc)
val (className, formatVersion, metadata) = loadMetadata(sc, path)
assert(className == thisClassName)
assert(formatVersion == thisFormatVersion)
val rank = metadata.select("rank").first().getInt(0)
val userFeatures = sqlContext.parquetFile(userPath(path))
.map { case Row(id: Int, features: Seq[Double]) =>
(id, features.toArray)
}
val productFeatures = sqlContext.parquetFile(productPath(path))
.map { case Row(id: Int, features: Seq[Double]) =>
(id, features.toArray)
}
new MatrixFactorizationModel(rank, userFeatures, productFeatures)
}
private def userPath(path: String): String = {
new Path(dataPath(path), "user").toUri.toString
}
private def productPath(path: String): String = {
new Path(dataPath(path), "product").toUri.toString
}
}
}
|
