-
Notifications
You must be signed in to change notification settings - Fork 28.1k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[SPARK-5891][ML] Add Binarizer ML Transformer #5699
Changes from 3 commits
1682f8c
7564c63
cc4f03c
bc397f2
1a0b9a4
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,82 @@ | ||
/* | ||
* 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.ml.feature | ||
|
||
import org.apache.spark.annotation.AlphaComponent | ||
import org.apache.spark.ml.Transformer | ||
import org.apache.spark.ml.attribute.BinaryAttribute | ||
import org.apache.spark.ml.param._ | ||
import org.apache.spark.ml.param.shared._ | ||
import org.apache.spark.ml.util.SchemaUtils | ||
import org.apache.spark.sql._ | ||
import org.apache.spark.sql.functions._ | ||
import org.apache.spark.sql.types.{DoubleType, StructType} | ||
|
||
/** | ||
* :: AlphaComponent :: | ||
* Binarize a column of continuous features given a threshold. | ||
*/ | ||
@AlphaComponent | ||
final class Binarizer extends Transformer with HasInputCol with HasOutputCol { | ||
|
||
/** | ||
* Param for threshold used to binarize continuous features. | ||
* The features greater than the threshold, will be binarized to 1.0. | ||
* The features equal to or less than the threshold, will be binarized to 0.0. | ||
* @group param | ||
*/ | ||
val threshold: DoubleParam = | ||
new DoubleParam(this, "threshold", "threshold used to binarize continuous features") | ||
|
||
/** @group getParam */ | ||
def getThreshold: Double = getOrDefault(threshold) | ||
|
||
/** @group setParam */ | ||
def setThreshold(value: Double): this.type = set(threshold, value) | ||
|
||
setDefault(threshold -> 0.0) | ||
|
||
/** @group setParam */ | ||
def setInputCol(value: String): this.type = set(inputCol, value) | ||
|
||
/** @group setParam */ | ||
def setOutputCol(value: String): this.type = set(outputCol, value) | ||
|
||
override def transform(dataset: DataFrame, paramMap: ParamMap): DataFrame = { | ||
transformSchema(dataset.schema, paramMap, logging = true) | ||
val map = extractParamMap(paramMap) | ||
val td = map(threshold) | ||
val binarizer = udf { in: Double => if (in > td) 1.0 else 0.0 } | ||
dataset.withColumn(map(outputCol), binarizer(col(map(inputCol)))) | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. |
||
} | ||
|
||
override def transformSchema(schema: StructType, paramMap: ParamMap): StructType = { | ||
val map = extractParamMap(paramMap) | ||
SchemaUtils.checkColumnType(schema, map(inputCol), DoubleType) | ||
|
||
val inputFields = schema.fields | ||
val outputColName = map(outputCol) | ||
|
||
require(inputFields.forall(_.name != outputColName), | ||
s"Output column $outputColName already exists.") | ||
|
||
val attr = BinaryAttribute.defaultAttr.withName(map(outputCol)) | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more.
|
||
val outputFields = inputFields :+ attr.toStructField() | ||
StructType(outputFields) | ||
} | ||
} |
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,76 @@ | ||
/* | ||
* 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.ml.feature | ||
|
||
import org.scalatest.FunSuite | ||
|
||
import org.apache.spark.mllib.util.MLlibTestSparkContext | ||
import org.apache.spark.mllib.util.TestingUtils._ | ||
import org.apache.spark.sql.{DataFrame, Row, SQLContext} | ||
|
||
|
||
class BinarizerSuite extends FunSuite with MLlibTestSparkContext { | ||
|
||
@transient var data: Array[Double] = _ | ||
@transient var dataFrame: DataFrame = _ | ||
@transient var binarizer: Binarizer = _ | ||
@transient val threshold = 0.2 | ||
@transient var defaultBinarized: Array[Double] = _ | ||
@transient var thresholdBinarized: Array[Double] = _ | ||
|
||
override def beforeAll(): Unit = { | ||
super.beforeAll() | ||
|
||
data = Array(0.1, -0.5, 0.2, -0.3, 0.8, 0.7, -0.1, -0.4) | ||
defaultBinarized = data.map(x => if (x > 0.0) 1.0 else 0.0) | ||
thresholdBinarized = data.map(x => if (x > threshold) 1.0 else 0.0) | ||
|
||
val sqlContext = new SQLContext(sc) | ||
dataFrame = sqlContext.createDataFrame(sc.parallelize(data, 2).map(BinarizerSuite.FeatureData)) | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. It is not required to use case classes. sqlContext.createDataFrame(data.map(Tuple1.apply)).toDF("feature") If we pair input and expected output before and my comment below. |
||
binarizer = new Binarizer() | ||
.setInputCol("feature") | ||
.setOutputCol("binarized_feature") | ||
} | ||
|
||
def collectResult(result: DataFrame): Array[Double] = { | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. The risk is that if the DataFrame has multiple partitions, |
||
result.select("binarized_feature").collect().map { | ||
case Row(feature: Double) => feature | ||
} | ||
} | ||
|
||
def assertValues(lhs: Array[Double], rhs: Array[Double]): Unit = { | ||
assert((lhs, rhs).zipped.forall { (x1, x2) => | ||
x1 === x2 | ||
}, "The feature value is not correct after binarization.") | ||
} | ||
|
||
test("Binarize continuous features with default parameter") { | ||
val result = collectResult(binarizer.transform(dataFrame)) | ||
assertValues(result, defaultBinarized) | ||
} | ||
|
||
test("Binarize continuous features with setter") { | ||
binarizer.setThreshold(threshold) | ||
val result = collectResult(binarizer.transform(dataFrame)) | ||
assertValues(result, thresholdBinarized) | ||
} | ||
} | ||
|
||
private object BinarizerSuite { | ||
case class FeatureData(feature: Double) | ||
} |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Only
HasInputCol
andHasOutputCol
are used. So this could be more explicit.