-
Notifications
You must be signed in to change notification settings - Fork 17
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
0a008a2
commit 4f7d34c
Showing
1,007 changed files
with
234,227 additions
and
40 deletions.
There are no files selected for viewing
This file contains 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 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 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 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
93 changes: 93 additions & 0 deletions
93
ml-accelerator/src/main/scala/org/apache/spark/ml/stat/Correlation.scala
This file contains 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 +1,93 @@ | ||
| // scalastyle:off header.matches | ||
| /* | ||
| * Copyright (C) 2021. Huawei Technologies Co., Ltd. | ||
| * This program is distributed in the hope that it will be useful, | ||
| * but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
| * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. | ||
| * */ | ||
| /* | ||
| * 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.stat | ||
|
|
||
| import scala.collection.JavaConverters._ | ||
|
|
||
| import org.apache.spark.annotation.{Experimental, Since} | ||
| import org.apache.spark.ml.linalg.{SQLDataTypes, Vector} | ||
| import org.apache.spark.mllib.linalg.{Vectors => OldVectors} | ||
| import org.apache.spark.mllib.stat.{Statistics => OldStatistics} | ||
| import org.apache.spark.sql.{DataFrame, Dataset, Row} | ||
| import org.apache.spark.sql.types.{StructField, StructType} | ||
|
|
||
| /** | ||
| * API for correlation functions in MLlib, compatible with DataFrames and Datasets. | ||
| * | ||
| * The functions in this package generalize the functions in [[org.apache.spark.sql.Dataset#stat]] | ||
| * to spark.ml's Vector types. | ||
| */ | ||
| @Since("2.2.0") | ||
| @Experimental | ||
| object Correlation { | ||
|
|
||
| /** | ||
| * :: Experimental :: | ||
| * Compute the correlation matrix for the input Dataset of Vectors using the specified method. | ||
| * Methods currently supported: `pearson` (default), `spearman`. | ||
| * | ||
| * @param dataset A dataset or a dataframe | ||
| * @param column The name of the column of vectors for which the correlation coefficient needs | ||
| * to be computed. This must be a column of the dataset, and it must contain | ||
| * Vector objects. | ||
| * @param method String specifying the method to use for computing correlation. | ||
| * Supported: `pearson` (default), `spearman` | ||
| * @return A dataframe that contains the correlation matrix of the column of vectors. This | ||
| * dataframe contains a single row and a single column of name | ||
| * '$METHODNAME($COLUMN)'. | ||
| * @throws IllegalArgumentException if the column is not a valid column in the dataset, or if | ||
| * the content of this column is not of type Vector. | ||
| * | ||
| * Here is how to access the correlation coefficient: | ||
| * {{{ | ||
| * val data: Dataset[Vector] = ... | ||
| * val Row(coeff: Matrix) = Correlation.corr(data, "value").head | ||
| * // coeff now contains the Pearson correlation matrix. | ||
| * }}} | ||
| * | ||
| * @note For Spearman, a rank correlation, we need to create an RDD[Double] for each column | ||
| * and sort it in order to retrieve the ranks and then join the columns back into an RDD[Vector], | ||
| * which is fairly costly. Cache the input Dataset before calling corr with `method = "spearman"` | ||
| * to avoid recomputing the common lineage. | ||
| */ | ||
| @Since("2.2.0") | ||
| def corr(dataset: Dataset[_], column: String, method: String): DataFrame = { | ||
| val rdd = dataset.select(column).rdd.map { | ||
| case Row(v: Vector) => OldVectors.fromML(v) | ||
| } | ||
| val oldM = OldStatistics.corr(rdd, method) | ||
| val name = s"$method($column)" | ||
| val schema = StructType(Array(StructField(name, SQLDataTypes.MatrixType, nullable = false))) | ||
| dataset.sparkSession.createDataFrame(Seq(Row(oldM.asML)).asJava, schema) | ||
| } | ||
|
|
||
| /** | ||
| * Compute the Pearson correlation matrix for the input Dataset of Vectors. | ||
| */ | ||
| @Since("2.2.0") | ||
| def corr(dataset: Dataset[_], column: String): DataFrame = { | ||
| corr(dataset, column, "pearson") | ||
| } | ||
| } |
This file contains 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 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 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
103 changes: 103 additions & 0 deletions
103
ml-accelerator/src/main/scala/org/apache/spark/mllib/stat/correlation/Correlation.scala
This file contains 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 +1,103 @@ | ||
| // scalastyle:off header.matches | ||
| /* | ||
| * Copyright (C) 2021. Huawei Technologies Co., Ltd. | ||
| * This program is distributed in the hope that it will be useful, | ||
| * but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
| * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. | ||
| * */ | ||
| /* | ||
| * 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.stat.correlation | ||
|
|
||
| import org.apache.spark.mllib.linalg.{DenseVector, Matrix, Vector} | ||
| import org.apache.spark.rdd.RDD | ||
|
|
||
| /** | ||
| * Trait for correlation algorithms. | ||
| */ | ||
| private[stat] trait Correlation { | ||
|
|
||
| /** | ||
| * Compute correlation for two datasets. | ||
| */ | ||
| def computeCorrelation(x: RDD[Double], y: RDD[Double]): Double | ||
|
|
||
| /** | ||
| * Compute the correlation matrix S, for the input matrix, where S(i, j) is the correlation | ||
| * between column i and j. S(i, j) can be NaN if the correlation is undefined for column i and j. | ||
| */ | ||
| def computeCorrelationMatrix(X: RDD[Vector]): Matrix | ||
|
|
||
| /** | ||
| * Combine the two input RDD[Double]s into an RDD[Vector] and compute the correlation using the | ||
| * correlation implementation for RDD[Vector]. Can be NaN if correlation is undefined for the | ||
| * input vectors. | ||
| */ | ||
| def computeCorrelationWithMatrixImpl(x: RDD[Double], y: RDD[Double]): Double = { | ||
| val mat: RDD[Vector] = x.zip(y).map { case (xi, yi) => new DenseVector(Array(xi, yi)) } | ||
| computeCorrelationMatrix(mat)(0, 1) | ||
| } | ||
|
|
||
| } | ||
|
|
||
| /** | ||
| * Delegates computation to the specific correlation object based on the input method name. | ||
| */ | ||
| private[stat] object Correlations { | ||
|
|
||
| def corr(x: RDD[Double], | ||
| y: RDD[Double], | ||
| method: String = CorrelationNames.defaultCorrName): Double = { | ||
| val correlation = getCorrelationFromName(method) | ||
| correlation.computeCorrelation(x, y) | ||
| } | ||
|
|
||
| def corrMatrix(X: RDD[Vector], | ||
| method: String = CorrelationNames.defaultCorrName): Matrix = { | ||
| val correlation = getCorrelationFromName(method) | ||
| correlation.computeCorrelationMatrix(X) | ||
| } | ||
|
|
||
| // Match input correlation name with a known name via simple string matching. | ||
| def getCorrelationFromName(method: String): Correlation = { | ||
| try { | ||
| CorrelationNames.nameToObjectMap(method) | ||
| } catch { | ||
| case nse: NoSuchElementException => | ||
| throw new IllegalArgumentException("Unrecognized method name. Supported correlations: " | ||
| + CorrelationNames.nameToObjectMap.keys.mkString(", ")) | ||
| } | ||
| } | ||
| } | ||
|
|
||
| /** | ||
| * Maintains supported and default correlation names. | ||
| * | ||
| * Currently supported correlations: `pearson`, `spearman`. | ||
| * Current default correlation: `pearson`. | ||
| * | ||
| * After new correlation algorithms are added, please update the documentation here and in | ||
| * Statistics.scala for the correlation APIs. | ||
| */ | ||
| private[mllib] object CorrelationNames { | ||
|
|
||
| // Note: after new types of correlations are implemented, please update this map. | ||
| val nameToObjectMap = Map(("pearson", PearsonCorrelation), ("spearman", SpearmanCorrelation)) | ||
| val defaultCorrName: String = "pearson" | ||
|
|
||
| } |
Oops, something went wrong.