Review SPARK-6528 #2
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,114 @@ | ||
| /* | ||
| * 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._ | ||
| import org.apache.spark.ml.param._ | ||
| import org.apache.spark.ml.param.shared._ | ||
| import org.apache.spark.ml.util.SchemaUtils | ||
| import org.apache.spark.mllib.feature | ||
| import org.apache.spark.mllib.linalg.{Vector, VectorUDT} | ||
| import org.apache.spark.sql._ | ||
| import org.apache.spark.sql.functions._ | ||
| import org.apache.spark.sql.types.StructType | ||
|
|
||
| /** | ||
| * Params for [[IDF]] and [[IDFModel]]. | ||
| */ | ||
| private[feature] trait IDFBase extends Params with HasInputCol with HasOutputCol { | ||
|
|
||
| /** | ||
| * The minimum of documents in which a term should appear. | ||
| * @group param | ||
| */ | ||
| final val minDocFreq = new IntParam( | ||
| this, "minDocFreq", "minimum of documents in which a term should appear for filtering") | ||
|
|
||
| /** @group getParam */ | ||
| def getMinDocFreq: Int = getOrDefault(minDocFreq) | ||
|
|
||
| /** @group setParam */ | ||
| def setMinDocFreq(value: Int): this.type = set(minDocFreq, value) | ||
|
|
||
| /** | ||
| * Validate and transform the input schema. | ||
| */ | ||
| protected def validateAndTransformSchema(schema: StructType, paramMap: ParamMap): StructType = { | ||
| val map = extractParamMap(paramMap) | ||
| SchemaUtils.checkColumnType(schema, map(inputCol), new VectorUDT) | ||
| SchemaUtils.appendColumn(schema, map(outputCol), new VectorUDT) | ||
| } | ||
| } | ||
|
|
||
| /** | ||
| * :: AlphaComponent :: | ||
| * Compute the Inverse Document Frequency (IDF) given a collection of documents. | ||
| */ | ||
| @AlphaComponent | ||
| final class IDF extends Estimator[IDFModel] with IDFBase { | ||
|
|
||
| /** @group setParam */ | ||
| def setInputCol(value: String): this.type = set(inputCol, value) | ||
|
|
||
| /** @group setParam */ | ||
| def setOutputCol(value: String): this.type = set(outputCol, value) | ||
|
|
||
| override def fit(dataset: DataFrame, paramMap: ParamMap): IDFModel = { | ||
| transformSchema(dataset.schema, paramMap, logging = true) | ||
| val map = extractParamMap(paramMap) | ||
| val input = dataset.select(map(inputCol)).map { case Row(v: Vector) => v } | ||
| val idf = new feature.IDF(getMinDocFreq).fit(input) | ||
| val model = new IDFModel(this, map, idf) | ||
| Params.inheritValues(map, this, model) | ||
| model | ||
| } | ||
|
|
||
| override def transformSchema(schema: StructType, paramMap: ParamMap): StructType = { | ||
| validateAndTransformSchema(schema, paramMap) | ||
| } | ||
| } | ||
|
|
||
| /** | ||
| * :: AlphaComponent :: | ||
| * Model fitted by [[IDF]]. | ||
| */ | ||
| @AlphaComponent | ||
| class IDFModel private[ml] ( | ||
| override val parent: IDF, | ||
| override val fittingParamMap: ParamMap, | ||
| idfModel: feature.IDFModel) | ||
| extends Model[IDFModel] with IDFBase { | ||
|
|
||
| /** @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 idf = udf { vec: Vector => idfModel.transform(vec) } | ||
|
||
| dataset.withColumn(map(outputCol), idf(col(map(inputCol)))) | ||
| } | ||
|
|
||
| override def transformSchema(schema: StructType, paramMap: ParamMap): StructType = { | ||
| validateAndTransformSchema(schema, paramMap) | ||
| } | ||
| } | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,112 @@ | ||
| /* | ||
| * 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.linalg.{DenseVector, SparseVector, Vector, Vectors} | ||
| import org.apache.spark.mllib.util.MLlibTestSparkContext | ||
| import org.apache.spark.mllib.util.TestingUtils._ | ||
| import org.apache.spark.sql.{DataFrame, Row, SQLContext} | ||
|
|
||
| class IDFSuite extends FunSuite with MLlibTestSparkContext { | ||
|
|
||
| @transient var sqlContext: SQLContext = _ | ||
|
|
||
| override def beforeAll(): Unit = { | ||
| super.beforeAll() | ||
| sqlContext = new SQLContext(sc) | ||
| } | ||
|
|
||
| def getResultFromDF(result: DataFrame): Array[Vector] = { | ||
| result.select("idf_value").collect().map { | ||
| case Row(features: Vector) => features | ||
| } | ||
| } | ||
|
|
||
| def assertValues(lhs: Array[Vector], rhs: Array[Vector]): Unit = { | ||
| assert((lhs, rhs).zipped.forall { (vector1, vector2) => | ||
| vector1 ~== vector2 absTol 1E-5 | ||
| }, "The vector value is not correct after IDF.") | ||
| } | ||
|
|
||
| def getResultFromVector(dataSet: Array[Vector], model: Vector): Array[Vector] = { | ||
| dataSet.map { | ||
| case data: DenseVector => | ||
| val res = data.toArray.zip(model.toArray).map { case (x, y) => x * y } | ||
| Vectors.dense(res) | ||
| case data: SparseVector => | ||
| val res = data.indices.zip(data.values).map { case (id, value) => | ||
| (id, value * model(id)) | ||
| } | ||
| Vectors.sparse(data.size, res) | ||
| } | ||
| } | ||
|
|
||
| test("Normalization with default parameter") { | ||
| val numOfFeatures = 4 | ||
| val data = Array( | ||
| Vectors.sparse(numOfFeatures, Array(1, 3), Array(1.0, 2.0)), | ||
| Vectors.dense(0.0, 1.0, 2.0, 3.0), | ||
| Vectors.sparse(numOfFeatures, Array(1), Array(1.0))) | ||
| val numOfData = data.length | ||
| val idf = Vectors.dense(Array(0, 3, 1, 2).map { x => | ||
| math.log((numOfData + 1.0) / (x + 1.0)) | ||
| }) | ||
| val expected = getResultFromVector(data, idf) | ||
|
|
||
| val df = sqlContext.createDataFrame(data.zip(expected)).toDF("features", "expected") | ||
|
|
||
| val idfModel = new IDF() | ||
| .setInputCol("features") | ||
| .setOutputCol("idf_value") | ||
| .fit(df) | ||
|
|
||
| idfModel.transform(df).select("idf_value", "expected").collect().foreach { | ||
| case Row(x: Vector, y: Vector) => | ||
| assert(x ~== y absTol 1e-5) | ||
| } | ||
| } | ||
|
|
||
| test("Normalization with setter") { | ||
| val numOfFeatures = 4 | ||
| val data = Array( | ||
| Vectors.sparse(numOfFeatures, Array(1, 3), Array(1.0, 2.0)), | ||
| Vectors.dense(0.0, 1.0, 2.0, 3.0), | ||
| Vectors.sparse(numOfFeatures, Array(1), Array(1.0))) | ||
| val numOfData = data.length | ||
|
|
||
| val sqlContext = new SQLContext(sc) | ||
| import sqlContext.implicits._ | ||
| val dataFrame = sc.parallelize(data, 2).map(Tuple1.apply).toDF("features") | ||
|
|
||
| val idfModel = new IDF() | ||
| .setInputCol("features") | ||
| .setOutputCol("idf_value") | ||
| .setMinDocFreq(1) | ||
| .fit(dataFrame) | ||
|
|
||
| val expectedModel = Vectors.dense(Array(0, 3, 1, 2).map { x => | ||
| if (x > 0) math.log((numOfData + 1.0) / (x + 1.0)) else 0 | ||
| }) | ||
|
|
||
| assertValues( | ||
| getResultFromDF(idfModel.transform(dataFrame)), | ||
| getResultFromVector(data, expectedModel)) | ||
| } | ||
| } |
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
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.
Should add