diff options
author | sethah <seth.hendrickson16@gmail.com> | 2016-10-14 20:21:03 +0000 |
---|---|---|
committer | DB Tsai <dbtsai@login.dbtsai.com> | 2016-10-14 20:21:03 +0000 |
commit | de1c1ca5c9d6064d3b7b3711e3bfb08fa018abe8 (patch) | |
tree | 004af65ec7d17f7a6c60311ca0fdab960d745b63 /mllib | |
parent | 05800b4b4e7873ebc445dfcd020b76d7539686e1 (diff) | |
download | spark-de1c1ca5c9d6064d3b7b3711e3bfb08fa018abe8.tar.gz spark-de1c1ca5c9d6064d3b7b3711e3bfb08fa018abe8.tar.bz2 spark-de1c1ca5c9d6064d3b7b3711e3bfb08fa018abe8.zip |
[SPARK-17941][ML][TEST] Logistic regression tests should use sample weights.
## What changes were proposed in this pull request?
The sample weight testing for logistic regressions is not robust. Logistic regression suite already has many test cases comparing results to R glmnet. Since both libraries support sample weights, we should use sample weights in the test to increase coverage for sample weighting. This patch doesn't really add any code and makes the testing more complete.
Also fixed some errors with the R code that was referenced in the test suit. Changed `standardization=T` to `standardize=T` since the former is invalid.
## How was this patch tested?
Existing unit tests are modified. No non-test code is touched.
Author: sethah <seth.hendrickson16@gmail.com>
Closes #15488 from sethah/logreg_weight_tests.
Diffstat (limited to 'mllib')
-rw-r--r-- | mllib/src/test/scala/org/apache/spark/ml/classification/LogisticRegressionSuite.scala | 1493 |
1 files changed, 748 insertions, 745 deletions
diff --git a/mllib/src/test/scala/org/apache/spark/ml/classification/LogisticRegressionSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/classification/LogisticRegressionSuite.scala index 42b56754e0..bc631dc6d3 100644 --- a/mllib/src/test/scala/org/apache/spark/ml/classification/LogisticRegressionSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/ml/classification/LogisticRegressionSuite.scala @@ -25,14 +25,14 @@ import scala.util.control.Breaks._ import org.apache.spark.{SparkException, SparkFunSuite} import org.apache.spark.ml.attribute.NominalAttribute import org.apache.spark.ml.classification.LogisticRegressionSuite._ -import org.apache.spark.ml.feature.LabeledPoint +import org.apache.spark.ml.feature.{Instance, LabeledPoint} import org.apache.spark.ml.linalg.{DenseMatrix, Matrices, SparseMatrix, SparseVector, Vector, Vectors} import org.apache.spark.ml.param.ParamsSuite import org.apache.spark.ml.util.{DefaultReadWriteTest, MLTestingUtils} import org.apache.spark.ml.util.TestingUtils._ import org.apache.spark.mllib.util.MLlibTestSparkContext import org.apache.spark.sql.{Dataset, Row} -import org.apache.spark.sql.functions.{col, lit} +import org.apache.spark.sql.functions.{col, lit, rand} import org.apache.spark.sql.types.LongType class LogisticRegressionSuite @@ -40,6 +40,7 @@ class LogisticRegressionSuite import testImplicits._ + private val seed = 42 @transient var smallBinaryDataset: Dataset[_] = _ @transient var smallMultinomialDataset: Dataset[_] = _ @transient var binaryDataset: Dataset[_] = _ @@ -49,7 +50,7 @@ class LogisticRegressionSuite override def beforeAll(): Unit = { super.beforeAll() - smallBinaryDataset = generateLogisticInput(1.0, 1.0, nPoints = 100, seed = 42).toDF() + smallBinaryDataset = generateLogisticInput(1.0, 1.0, nPoints = 100, seed = seed).toDF() smallMultinomialDataset = { val nPoints = 100 @@ -61,7 +62,7 @@ class LogisticRegressionSuite val xVariance = Array(0.6856, 0.1899) val testData = generateMultinomialLogisticInput( - coefficients, xMean, xVariance, addIntercept = true, nPoints, 42) + coefficients, xMean, xVariance, addIntercept = true, nPoints, seed) val df = sc.parallelize(testData, 4).toDF() df.cache() @@ -76,9 +77,9 @@ class LogisticRegressionSuite val testData = generateMultinomialLogisticInput(coefficients, xMean, xVariance, - addIntercept = true, nPoints, 42) + addIntercept = true, nPoints, seed) - sc.parallelize(testData, 4).toDF() + sc.parallelize(testData, 4).toDF().withColumn("weight", rand(seed)) } multinomialDataset = { @@ -91,9 +92,9 @@ class LogisticRegressionSuite val xVariance = Array(0.6856, 0.1899, 3.116, 0.581) val testData = generateMultinomialLogisticInput( - coefficients, xMean, xVariance, addIntercept = true, nPoints, 42) + coefficients, xMean, xVariance, addIntercept = true, nPoints, seed) - val df = sc.parallelize(testData, 4).toDF() + val df = sc.parallelize(testData, 4).toDF().withColumn("weight", rand(seed)) df.cache() df } @@ -104,11 +105,11 @@ class LogisticRegressionSuite * so we can validate the training accuracy compared with R's glmnet package. */ ignore("export test data into CSV format") { - binaryDataset.rdd.map { case Row(label: Double, features: Vector) => - label + "," + features.toArray.mkString(",") + binaryDataset.rdd.map { case Row(label: Double, features: Vector, weight: Double) => + label + "," + weight + "," + features.toArray.mkString(",") }.repartition(1).saveAsTextFile("target/tmp/LogisticRegressionSuite/binaryDataset") - multinomialDataset.rdd.map { case Row(label: Double, features: Vector) => - label + "," + features.toArray.mkString(",") + multinomialDataset.rdd.map { case Row(label: Double, features: Vector, weight: Double) => + label + "," + weight + "," + features.toArray.mkString(",") }.repartition(1).saveAsTextFile("target/tmp/LogisticRegressionSuite/multinomialDataset") } @@ -519,31 +520,35 @@ class LogisticRegressionSuite test("binary logistic regression with intercept without regularization") { val trainer1 = (new LogisticRegression).setFitIntercept(true).setStandardization(true) + .setWeightCol("weight") val trainer2 = (new LogisticRegression).setFitIntercept(true).setStandardization(false) + .setWeightCol("weight") val model1 = trainer1.fit(binaryDataset) val model2 = trainer2.fit(binaryDataset) /* - Using the following R code to load the data and train the model using glmnet package. - - library("glmnet") - data <- read.csv("path", header=FALSE) - label = factor(data$V1) - features = as.matrix(data.frame(data$V2, data$V3, data$V4, data$V5)) - coefficients = coef(glmnet(features,label, family="binomial", alpha = 0, lambda = 0)) - coefficients + Use the following R code to load the data and train the model using glmnet package. + library("glmnet") + data <- read.csv("path", header=FALSE) + label = factor(data$V1) + w = data$V2 + features = as.matrix(data.frame(data$V3, data$V4, data$V5, data$V6)) + coefficients = coef(glmnet(features, label, weights=w, family="binomial", alpha = 0, + lambda = 0)) + coefficients + $`0` + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + (Intercept) 2.7355261 + data.V3 -0.5734389 + data.V4 0.8911736 + data.V5 -0.3878645 + data.V6 -0.8060570 - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - (Intercept) 2.8366423 - data.V2 -0.5895848 - data.V3 0.8931147 - data.V4 -0.3925051 - data.V5 -0.7996864 */ - val interceptR = 2.8366423 - val coefficientsR = Vectors.dense(-0.5895848, 0.8931147, -0.3925051, -0.7996864) + val coefficientsR = Vectors.dense(-0.5734389, 0.8911736, -0.3878645, -0.8060570) + val interceptR = 2.7355261 assert(model1.intercept ~== interceptR relTol 1E-3) assert(model1.coefficients ~= coefficientsR relTol 1E-3) @@ -555,413 +560,374 @@ class LogisticRegressionSuite test("binary logistic regression without intercept without regularization") { val trainer1 = (new LogisticRegression).setFitIntercept(false).setStandardization(true) + .setWeightCol("weight") val trainer2 = (new LogisticRegression).setFitIntercept(false).setStandardization(false) + .setWeightCol("weight") val model1 = trainer1.fit(binaryDataset) val model2 = trainer2.fit(binaryDataset) /* - Using the following R code to load the data and train the model using glmnet package. + Use the following R code to load the data and train the model using glmnet package. - library("glmnet") - data <- read.csv("path", header=FALSE) - label = factor(data$V1) - features = as.matrix(data.frame(data$V2, data$V3, data$V4, data$V5)) - coefficients = - coef(glmnet(features,label, family="binomial", alpha = 0, lambda = 0, intercept=FALSE)) - coefficients + library("glmnet") + data <- read.csv("path", header=FALSE) + label = factor(data$V1) + w = data$V2 + features = as.matrix(data.frame(data$V3, data$V4, data$V5, data$V6)) + coefficients = coef(glmnet(features, label, weights=w, family="binomial", alpha = 0, + lambda = 0, intercept=FALSE)) + coefficients + $`0` + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + (Intercept) . + data.V3 -0.3448461 + data.V4 1.2776453 + data.V5 -0.3539178 + data.V6 -0.7469384 - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - (Intercept) . - data.V2 -0.3534996 - data.V3 1.2964482 - data.V4 -0.3571741 - data.V5 -0.7407946 */ - val interceptR = 0.0 - val coefficientsR = Vectors.dense(-0.3534996, 1.2964482, -0.3571741, -0.7407946) + val coefficientsR = Vectors.dense(-0.3448461, 1.2776453, -0.3539178, -0.7469384) - assert(model1.intercept ~== interceptR relTol 1E-3) + assert(model1.intercept ~== 0.0 relTol 1E-3) assert(model1.coefficients ~= coefficientsR relTol 1E-2) // Without regularization, with or without standardization should converge to the same solution. - assert(model2.intercept ~== interceptR relTol 1E-3) + assert(model2.intercept ~== 0.0 relTol 1E-3) assert(model2.coefficients ~= coefficientsR relTol 1E-2) } test("binary logistic regression with intercept with L1 regularization") { val trainer1 = (new LogisticRegression).setFitIntercept(true) - .setElasticNetParam(1.0).setRegParam(0.12).setStandardization(true) + .setElasticNetParam(1.0).setRegParam(0.12).setStandardization(true).setWeightCol("weight") val trainer2 = (new LogisticRegression).setFitIntercept(true) - .setElasticNetParam(1.0).setRegParam(0.12).setStandardization(false) + .setElasticNetParam(1.0).setRegParam(0.12).setStandardization(false).setWeightCol("weight") val model1 = trainer1.fit(binaryDataset) val model2 = trainer2.fit(binaryDataset) /* - Using the following R code to load the data and train the model using glmnet package. + Use the following R code to load the data and train the model using glmnet package. - library("glmnet") - data <- read.csv("path", header=FALSE) - label = factor(data$V1) - features = as.matrix(data.frame(data$V2, data$V3, data$V4, data$V5)) - coefficients = coef(glmnet(features,label, family="binomial", alpha = 1, lambda = 0.12)) - coefficients + library("glmnet") + data <- read.csv("path", header=FALSE) + label = factor(data$V1) + w = data$V2 + features = as.matrix(data.frame(data$V3, data$V4, data$V5, data$V6)) + coefficients = coef(glmnet(features, label, weights=w, family="binomial", alpha = 1, + lambda = 0.12, standardize=T)) + coefficients + $`0` + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + (Intercept) -0.06775980 + data.V3 . + data.V4 . + data.V5 -0.03933146 + data.V6 -0.03047580 - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - (Intercept) -0.05627428 - data.V2 . - data.V3 . - data.V4 -0.04325749 - data.V5 -0.02481551 */ - val interceptR1 = -0.05627428 - val coefficientsR1 = Vectors.dense(0.0, 0.0, -0.04325749, -0.02481551) + val coefficientsRStd = Vectors.dense(0.0, 0.0, -0.03933146, -0.03047580) + val interceptRStd = -0.06775980 - assert(model1.intercept ~== interceptR1 relTol 1E-2) - assert(model1.coefficients ~= coefficientsR1 absTol 2E-2) + assert(model1.intercept ~== interceptRStd relTol 1E-2) + assert(model1.coefficients ~= coefficientsRStd absTol 2E-2) /* - Using the following R code to load the data and train the model using glmnet package. + Use the following R code to load the data and train the model using glmnet package. - library("glmnet") - data <- read.csv("path", header=FALSE) - label = factor(data$V1) - features = as.matrix(data.frame(data$V2, data$V3, data$V4, data$V5)) - coefficients = coef(glmnet(features,label, family="binomial", alpha = 1, lambda = 0.12, - standardize=FALSE)) - coefficients + library("glmnet") + data <- read.csv("path", header=FALSE) + label = factor(data$V1) + w = data$V2 + features = as.matrix(data.frame(data$V3, data$V4, data$V5, data$V6)) + coefficients = coef(glmnet(features, label, weights=w, family="binomial", alpha = 1, + lambda = 0.12, standardize=F)) + coefficients + $`0` + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + (Intercept) 0.3544768 + data.V3 . + data.V4 . + data.V5 -0.1626191 + data.V6 . - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - (Intercept) 0.3722152 - data.V2 . - data.V3 . - data.V4 -0.1665453 - data.V5 . */ - val interceptR2 = 0.3722152 - val coefficientsR2 = Vectors.dense(0.0, 0.0, -0.1665453, 0.0) + val coefficientsR = Vectors.dense(0.0, 0.0, -0.1626191, 0.0) + val interceptR = 0.3544768 - assert(model2.intercept ~== interceptR2 relTol 1E-2) - assert(model2.coefficients ~== coefficientsR2 absTol 1E-3) + assert(model2.intercept ~== interceptR relTol 1E-2) + assert(model2.coefficients ~== coefficientsR absTol 1E-3) // TODO: move this to a standalone test of compression after SPARK-17471 assert(model2.coefficients.isInstanceOf[SparseVector]) } test("binary logistic regression without intercept with L1 regularization") { val trainer1 = (new LogisticRegression).setFitIntercept(false) - .setElasticNetParam(1.0).setRegParam(0.12).setStandardization(true) + .setElasticNetParam(1.0).setRegParam(0.12).setStandardization(true).setWeightCol("weight") val trainer2 = (new LogisticRegression).setFitIntercept(false) - .setElasticNetParam(1.0).setRegParam(0.12).setStandardization(false) + .setElasticNetParam(1.0).setRegParam(0.12).setStandardization(false).setWeightCol("weight") val model1 = trainer1.fit(binaryDataset) val model2 = trainer2.fit(binaryDataset) /* - Using the following R code to load the data and train the model using glmnet package. - - library("glmnet") - data <- read.csv("path", header=FALSE) - label = factor(data$V1) - features = as.matrix(data.frame(data$V2, data$V3, data$V4, data$V5)) - coefficients = coef(glmnet(features,label, family="binomial", alpha = 1, lambda = 0.12, - intercept=FALSE)) - coefficients - - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - (Intercept) . - data.V2 . - data.V3 . - data.V4 -0.05189203 - data.V5 -0.03891782 - */ - val interceptR1 = 0.0 - val coefficientsR1 = Vectors.dense(0.0, 0.0, -0.05189203, -0.03891782) - - assert(model1.intercept ~== interceptR1 relTol 1E-3) - assert(model1.coefficients ~= coefficientsR1 absTol 1E-3) + Use the following R code to load the data and train the model using glmnet package. - /* - Using the following R code to load the data and train the model using glmnet package. + library("glmnet") + data <- read.csv("path", header=FALSE) + label = factor(data$V1) + w = data$V2 + features = as.matrix(data.frame(data$V3, data$V4, data$V5, data$V6)) + coefficientsStd = coef(glmnet(features, label, weights=w, family="binomial", alpha = 1, + lambda = 0.12, intercept=F, standardize=T)) + coefficients = coef(glmnet(features, label, weights=w, family="binomial", alpha = 1, + lambda = 0.12, intercept=F, standardize=F)) + coefficientsStd + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + (Intercept) . + data.V3 . + data.V4 . + data.V5 -0.04967635 + data.V6 -0.04757757 - library("glmnet") - data <- read.csv("path", header=FALSE) - label = factor(data$V1) - features = as.matrix(data.frame(data$V2, data$V3, data$V4, data$V5)) - coefficients = coef(glmnet(features,label, family="binomial", alpha = 1, lambda = 0.12, - intercept=FALSE, standardize=FALSE)) - coefficients + coefficients + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + (Intercept) . + data.V3 . + data.V4 . + data.V5 -0.08433195 + data.V6 . - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - (Intercept) . - data.V2 . - data.V3 . - data.V4 -0.08420782 - data.V5 . */ - val interceptR2 = 0.0 - val coefficientsR2 = Vectors.dense(0.0, 0.0, -0.08420782, 0.0) + val coefficientsRStd = Vectors.dense(0.0, 0.0, -0.04967635, -0.04757757) - assert(model2.intercept ~== interceptR2 absTol 1E-3) - assert(model2.coefficients ~= coefficientsR2 absTol 1E-3) + val coefficientsR = Vectors.dense(0.0, 0.0, -0.08433195, 0.0) + + assert(model1.intercept ~== 0.0 absTol 1E-3) + assert(model1.coefficients ~= coefficientsRStd absTol 1E-3) + assert(model2.intercept ~== 0.0 absTol 1E-3) + assert(model2.coefficients ~= coefficientsR absTol 1E-3) } test("binary logistic regression with intercept with L2 regularization") { val trainer1 = (new LogisticRegression).setFitIntercept(true) - .setElasticNetParam(0.0).setRegParam(1.37).setStandardization(true) + .setElasticNetParam(0.0).setRegParam(1.37).setStandardization(true).setWeightCol("weight") val trainer2 = (new LogisticRegression).setFitIntercept(true) - .setElasticNetParam(0.0).setRegParam(1.37).setStandardization(false) + .setElasticNetParam(0.0).setRegParam(1.37).setStandardization(false).setWeightCol("weight") val model1 = trainer1.fit(binaryDataset) val model2 = trainer2.fit(binaryDataset) /* - Using the following R code to load the data and train the model using glmnet package. - - library("glmnet") - data <- read.csv("path", header=FALSE) - label = factor(data$V1) - features = as.matrix(data.frame(data$V2, data$V3, data$V4, data$V5)) - coefficients = coef(glmnet(features,label, family="binomial", alpha = 0, lambda = 1.37)) - coefficients - - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - (Intercept) 0.15021751 - data.V2 -0.07251837 - data.V3 0.10724191 - data.V4 -0.04865309 - data.V5 -0.10062872 - */ - val interceptR1 = 0.15021751 - val coefficientsR1 = Vectors.dense(-0.07251837, 0.10724191, -0.04865309, -0.10062872) - - assert(model1.intercept ~== interceptR1 relTol 1E-3) - assert(model1.coefficients ~= coefficientsR1 relTol 1E-3) + Use the following R code to load the data and train the model using glmnet package. - /* - Using the following R code to load the data and train the model using glmnet package. + library("glmnet") + data <- read.csv("path", header=FALSE) + label = factor(data$V1) + w = data$V2 + features = as.matrix(data.frame(data$V3, data$V4, data$V5, data$V6)) + coefficientsStd = coef(glmnet(features, label, weights=w, family="binomial", alpha = 0, + lambda = 1.37, standardize=T)) + coefficients = coef(glmnet(features, label, weights=w, family="binomial", alpha = 0, + lambda = 1.37, standardize=F)) + coefficientsStd + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + (Intercept) 0.12707703 + data.V3 -0.06980967 + data.V4 0.10803933 + data.V5 -0.04800404 + data.V6 -0.10165096 - library("glmnet") - data <- read.csv("path", header=FALSE) - label = factor(data$V1) - features = as.matrix(data.frame(data$V2, data$V3, data$V4, data$V5)) - coefficients = coef(glmnet(features,label, family="binomial", alpha = 0, lambda = 1.37, - standardize=FALSE)) - coefficients + coefficients + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + (Intercept) 0.46613016 + data.V3 -0.04944529 + data.V4 0.02326772 + data.V5 -0.11362772 + data.V6 -0.06312848 - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - (Intercept) 0.48657516 - data.V2 -0.05155371 - data.V3 0.02301057 - data.V4 -0.11482896 - data.V5 -0.06266838 */ - val interceptR2 = 0.48657516 - val coefficientsR2 = Vectors.dense(-0.05155371, 0.02301057, -0.11482896, -0.06266838) + val coefficientsRStd = Vectors.dense(-0.06980967, 0.10803933, -0.04800404, -0.10165096) + val interceptRStd = 0.12707703 + val coefficientsR = Vectors.dense(-0.04944529, 0.02326772, -0.11362772, -0.06312848) + val interceptR = 0.46613016 - assert(model2.intercept ~== interceptR2 relTol 1E-3) - assert(model2.coefficients ~= coefficientsR2 relTol 1E-3) + assert(model1.intercept ~== interceptRStd relTol 1E-3) + assert(model1.coefficients ~= coefficientsRStd relTol 1E-3) + assert(model2.intercept ~== interceptR relTol 1E-3) + assert(model2.coefficients ~= coefficientsR relTol 1E-3) } test("binary logistic regression without intercept with L2 regularization") { val trainer1 = (new LogisticRegression).setFitIntercept(false) - .setElasticNetParam(0.0).setRegParam(1.37).setStandardization(true) + .setElasticNetParam(0.0).setRegParam(1.37).setStandardization(true).setWeightCol("weight") val trainer2 = (new LogisticRegression).setFitIntercept(false) - .setElasticNetParam(0.0).setRegParam(1.37).setStandardization(false) + .setElasticNetParam(0.0).setRegParam(1.37).setStandardization(false).setWeightCol("weight") val model1 = trainer1.fit(binaryDataset) val model2 = trainer2.fit(binaryDataset) /* - Using the following R code to load the data and train the model using glmnet package. + Use the following R code to load the data and train the model using glmnet package. - library("glmnet") - data <- read.csv("path", header=FALSE) - label = factor(data$V1) - features = as.matrix(data.frame(data$V2, data$V3, data$V4, data$V5)) - coefficients = coef(glmnet(features,label, family="binomial", alpha = 0, lambda = 1.37, - intercept=FALSE)) - coefficients + library("glmnet") + data <- read.csv("path", header=FALSE) + label = factor(data$V1) + w = data$V2 + features = as.matrix(data.frame(data$V3, data$V4, data$V5, data$V6)) + coefficientsStd = coef(glmnet(features, label, weights=w, family="binomial", alpha = 0, + lambda = 1.37, intercept=F, standardize=T)) + coefficients = coef(glmnet(features, label, weights=w, family="binomial", alpha = 0, + lambda = 1.37, intercept=F, standardize=F)) + coefficientsStd + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + (Intercept) . + data.V3 -0.06000152 + data.V4 0.12598737 + data.V5 -0.04669009 + data.V6 -0.09941025 - 5 x 1 sparse Matrix of class "dgCMatrix" + coefficients + 5 x 1 sparse Matrix of class "dgCMatrix" s0 - (Intercept) . - data.V2 -0.06099165 - data.V3 0.12857058 - data.V4 -0.04708770 - data.V5 -0.09799775 - */ - val interceptR1 = 0.0 - val coefficientsR1 = Vectors.dense(-0.06099165, 0.12857058, -0.04708770, -0.09799775) - - assert(model1.intercept ~== interceptR1 absTol 1E-3) - assert(model1.coefficients ~= coefficientsR1 relTol 1E-2) - - /* - Using the following R code to load the data and train the model using glmnet package. - - library("glmnet") - data <- read.csv("path", header=FALSE) - label = factor(data$V1) - features = as.matrix(data.frame(data$V2, data$V3, data$V4, data$V5)) - coefficients = coef(glmnet(features,label, family="binomial", alpha = 0, lambda = 1.37, - intercept=FALSE, standardize=FALSE)) - coefficients + (Intercept) . + data.V3 -0.005482255 + data.V4 0.048106338 + data.V5 -0.093411640 + data.V6 -0.054149798 - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - (Intercept) . - data.V2 -0.005679651 - data.V3 0.048967094 - data.V4 -0.093714016 - data.V5 -0.053314311 */ - val interceptR2 = 0.0 - val coefficientsR2 = Vectors.dense(-0.005679651, 0.048967094, -0.093714016, -0.053314311) + val coefficientsRStd = Vectors.dense(-0.06000152, 0.12598737, -0.04669009, -0.09941025) + val coefficientsR = Vectors.dense(-0.005482255, 0.048106338, -0.093411640, -0.054149798) - assert(model2.intercept ~== interceptR2 absTol 1E-3) - assert(model2.coefficients ~= coefficientsR2 relTol 1E-2) + assert(model1.intercept ~== 0.0 absTol 1E-3) + assert(model1.coefficients ~= coefficientsRStd relTol 1E-2) + assert(model2.intercept ~== 0.0 absTol 1E-3) + assert(model2.coefficients ~= coefficientsR relTol 1E-2) } test("binary logistic regression with intercept with ElasticNet regularization") { - val trainer1 = (new LogisticRegression).setFitIntercept(true) - .setElasticNetParam(0.38).setRegParam(0.21).setStandardization(true) + val trainer1 = (new LogisticRegression).setFitIntercept(true).setMaxIter(200) + .setElasticNetParam(0.38).setRegParam(0.21).setStandardization(true).setWeightCol("weight") val trainer2 = (new LogisticRegression).setFitIntercept(true) - .setElasticNetParam(0.38).setRegParam(0.21).setStandardization(false) + .setElasticNetParam(0.38).setRegParam(0.21).setStandardization(false).setWeightCol("weight") val model1 = trainer1.fit(binaryDataset) val model2 = trainer2.fit(binaryDataset) /* - Using the following R code to load the data and train the model using glmnet package. - - library("glmnet") - data <- read.csv("path", header=FALSE) - label = factor(data$V1) - features = as.matrix(data.frame(data$V2, data$V3, data$V4, data$V5)) - coefficients = coef(glmnet(features,label, family="binomial", alpha = 0.38, lambda = 0.21)) - coefficients - - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - (Intercept) 0.57734851 - data.V2 -0.05310287 - data.V3 . - data.V4 -0.08849250 - data.V5 -0.15458796 - */ - val interceptR1 = 0.57734851 - val coefficientsR1 = Vectors.dense(-0.05310287, 0.0, -0.08849250, -0.15458796) - - assert(model1.intercept ~== interceptR1 relTol 6E-3) - assert(model1.coefficients ~== coefficientsR1 absTol 5E-3) + Use the following R code to load the data and train the model using glmnet package. - /* - Using the following R code to load the data and train the model using glmnet package. + library("glmnet") + data <- read.csv("path", header=FALSE) + label = factor(data$V1) + w = data$V2 + features = as.matrix(data.frame(data$V3, data$V4, data$V5, data$V6)) + coefficientsStd = coef(glmnet(features, label, weights=w, family="binomial", alpha = 0.38, + lambda = 0.21, standardize=T)) + coefficients = coef(glmnet(features, label, weights=w, family="binomial", alpha = 0.38, + lambda = 0.21, standardize=F)) + coefficientsStd + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + (Intercept) 0.49991996 + data.V3 -0.04131110 + data.V4 . + data.V5 -0.08585233 + data.V6 -0.15875400 - library("glmnet") - data <- read.csv("path", header=FALSE) - label = factor(data$V1) - features = as.matrix(data.frame(data$V2, data$V3, data$V4, data$V5)) - coefficients = coef(glmnet(features,label, family="binomial", alpha = 0.38, lambda = 0.21, - standardize=FALSE)) - coefficients + coefficients + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + (Intercept) 0.5024256 + data.V3 . + data.V4 . + data.V5 -0.1846038 + data.V6 -0.0559614 - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - (Intercept) 0.51555993 - data.V2 . - data.V3 . - data.V4 -0.18807395 - data.V5 -0.05350074 */ - val interceptR2 = 0.51555993 - val coefficientsR2 = Vectors.dense(0.0, 0.0, -0.18807395, -0.05350074) - - assert(model2.intercept ~== interceptR2 relTol 6E-3) - assert(model2.coefficients ~= coefficientsR2 absTol 1E-3) + val coefficientsRStd = Vectors.dense(-0.04131110, 0.0, -0.08585233, -0.15875400) + val interceptRStd = 0.49991996 + val coefficientsR = Vectors.dense(0.0, 0.0, -0.1846038, -0.0559614) + val interceptR = 0.5024256 + + assert(model1.intercept ~== interceptRStd relTol 6E-3) + assert(model1.coefficients ~== coefficientsRStd absTol 5E-3) + assert(model2.intercept ~== interceptR relTol 6E-3) + assert(model2.coefficients ~= coefficientsR absTol 1E-3) } test("binary logistic regression without intercept with ElasticNet regularization") { val trainer1 = (new LogisticRegression).setFitIntercept(false) - .setElasticNetParam(0.38).setRegParam(0.21).setStandardization(true) + .setElasticNetParam(0.38).setRegParam(0.21).setStandardization(true).setWeightCol("weight") val trainer2 = (new LogisticRegression).setFitIntercept(false) - .setElasticNetParam(0.38).setRegParam(0.21).setStandardization(false) + .setElasticNetParam(0.38).setRegParam(0.21).setStandardization(false).setWeightCol("weight") val model1 = trainer1.fit(binaryDataset) val model2 = trainer2.fit(binaryDataset) /* - Using the following R code to load the data and train the model using glmnet package. - - library("glmnet") - data <- read.csv("path", header=FALSE) - label = factor(data$V1) - features = as.matrix(data.frame(data$V2, data$V3, data$V4, data$V5)) - coefficients = coef(glmnet(features,label, family="binomial", alpha = 0.38, lambda = 0.21, - intercept=FALSE)) - coefficients - - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - (Intercept) . - data.V2 -0.001005743 - data.V3 0.072577857 - data.V4 -0.081203769 - data.V5 -0.142534158 - */ - val interceptR1 = 0.0 - val coefficientsR1 = Vectors.dense(-0.001005743, 0.072577857, -0.081203769, -0.142534158) - - assert(model1.intercept ~== interceptR1 relTol 1E-3) - assert(model1.coefficients ~= coefficientsR1 absTol 1E-2) + Use the following R code to load the data and train the model using glmnet package. - /* - Using the following R code to load the data and train the model using glmnet package. + library("glmnet") + data <- read.csv("path", header=FALSE) + label = factor(data$V1) + w = data$V2 + features = as.matrix(data.frame(data$V3, data$V4, data$V5, data$V6)) + coefficientsStd = coef(glmnet(features, label, weights=w, family="binomial", alpha = 0.38, + lambda = 0.21, intercept=FALSE, standardize=T)) + coefficients = coef(glmnet(features, label, weights=w, family="binomial", alpha = 0.38, + lambda = 0.21, intercept=FALSE, standardize=F)) + coefficientsStd + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + (Intercept) . + data.V3 . + data.V4 0.06859390 + data.V5 -0.07900058 + data.V6 -0.14684320 - library("glmnet") - data <- read.csv("path", header=FALSE) - label = factor(data$V1) - features = as.matrix(data.frame(data$V2, data$V3, data$V4, data$V5)) - coefficients = coef(glmnet(features,label, family="binomial", alpha = 0.38, lambda = 0.21, - intercept=FALSE, standardize=FALSE)) - coefficients + coefficients + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + (Intercept) . + data.V3 . + data.V4 0.03060637 + data.V5 -0.11126742 + data.V6 . - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - (Intercept) . - data.V2 . - data.V3 0.03345223 - data.V4 -0.11304532 - data.V5 . */ - val interceptR2 = 0.0 - val coefficientsR2 = Vectors.dense(0.0, 0.03345223, -0.11304532, 0.0) + val coefficientsRStd = Vectors.dense(0.0, 0.06859390, -0.07900058, -0.14684320) + val coefficientsR = Vectors.dense(0.0, 0.03060637, -0.11126742, 0.0) - assert(model2.intercept ~== interceptR2 absTol 1E-3) - assert(model2.coefficients ~= coefficientsR2 absTol 1E-3) + assert(model1.intercept ~== 0.0 relTol 1E-3) + assert(model1.coefficients ~= coefficientsRStd absTol 1E-2) + assert(model2.intercept ~== 0.0 absTol 1E-3) + assert(model2.coefficients ~= coefficientsR absTol 1E-3) } test("binary logistic regression with intercept with strong L1 regularization") { - val trainer1 = (new LogisticRegression).setFitIntercept(true) + val trainer1 = (new LogisticRegression).setFitIntercept(true).setWeightCol("weight") .setElasticNetParam(1.0).setRegParam(6.0).setStandardization(true) - val trainer2 = (new LogisticRegression).setFitIntercept(true) + val trainer2 = (new LogisticRegression).setFitIntercept(true).setWeightCol("weight") .setElasticNetParam(1.0).setRegParam(6.0).setStandardization(false) val model1 = trainer1.fit(binaryDataset) val model2 = trainer2.fit(binaryDataset) - val histogram = binaryDataset.rdd.map { case Row(label: Double, features: Vector) => label } + val histogram = binaryDataset.as[Instance].rdd.map { i => (i.label, i.weight)} .treeAggregate(new MultiClassSummarizer)( seqOp = (c, v) => (c, v) match { - case (classSummarizer: MultiClassSummarizer, label: Double) => classSummarizer.add(label) + case (classSummarizer: MultiClassSummarizer, (label: Double, weight: Double)) => + classSummarizer.add(label, weight) }, combOp = (c1, c2) => (c1, c2) match { case (classSummarizer1: MultiClassSummarizer, classSummarizer2: MultiClassSummarizer) => @@ -989,25 +955,26 @@ class LogisticRegressionSuite assert(model2.coefficients ~= coefficientsTheory absTol 1E-6) /* - TODO: why is this needed? The correctness of L1 regularization is already checked elsewhere Using the following R code to load the data and train the model using glmnet package. library("glmnet") data <- read.csv("path", header=FALSE) label = factor(data$V1) - features = as.matrix(data.frame(data$V2, data$V3, data$V4, data$V5)) - coefficients = coef(glmnet(features,label, family="binomial", alpha = 1.0, lambda = 6.0)) + w = data$V2 + features = as.matrix(data.frame(data$V3, data$V4, data$V5, data$V6)) + coefficients = coef(glmnet(features, label, weights=w, family="binomial", alpha = 1.0, + lambda = 6.0)) coefficients 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - (Intercept) -0.2480643 - data.V2 0.0000000 - data.V3 . - data.V4 . - data.V5 . + s0 + (Intercept) -0.2516986 + data.V3 0.0000000 + data.V4 . + data.V5 . + data.V6 . */ - val interceptR = -0.248065 + val interceptR = -0.2516986 val coefficientsR = Vectors.dense(0.0, 0.0, 0.0, 0.0) assert(model1.intercept ~== interceptR relTol 1E-5) @@ -1015,9 +982,9 @@ class LogisticRegressionSuite } test("multinomial logistic regression with intercept with strong L1 regularization") { - val trainer1 = (new LogisticRegression).setFitIntercept(true) + val trainer1 = (new LogisticRegression).setFitIntercept(true).setWeightCol("weight") .setElasticNetParam(1.0).setRegParam(6.0).setStandardization(true) - val trainer2 = (new LogisticRegression).setFitIntercept(true) + val trainer2 = (new LogisticRegression).setFitIntercept(true).setWeightCol("weight") .setElasticNetParam(1.0).setRegParam(6.0).setStandardization(false) val sqlContext = multinomialDataset.sqlContext @@ -1025,16 +992,17 @@ class LogisticRegressionSuite val model1 = trainer1.fit(multinomialDataset) val model2 = trainer2.fit(multinomialDataset) - val histogram = multinomialDataset.as[LabeledPoint].rdd.map(_.label) + val histogram = multinomialDataset.as[Instance].rdd.map(i => (i.label, i.weight)) .treeAggregate(new MultiClassSummarizer)( seqOp = (c, v) => (c, v) match { - case (classSummarizer: MultiClassSummarizer, label: Double) => classSummarizer.add(label) + case (classSummarizer: MultiClassSummarizer, (label: Double, weight: Double)) => + classSummarizer.add(label, weight) }, combOp = (c1, c2) => (c1, c2) match { case (classSummarizer1: MultiClassSummarizer, classSummarizer2: MultiClassSummarizer) => classSummarizer1.merge(classSummarizer2) }).histogram - val numFeatures = multinomialDataset.as[LabeledPoint].first().features.size + val numFeatures = multinomialDataset.as[Instance].first().features.size val numClasses = histogram.length /* @@ -1068,52 +1036,58 @@ class LogisticRegressionSuite test("multinomial logistic regression with intercept without regularization") { val trainer1 = (new LogisticRegression).setFitIntercept(true) - .setElasticNetParam(0.0).setRegParam(0.0).setStandardization(true).setMaxIter(100) + .setElasticNetParam(0.0).setRegParam(0.0).setStandardization(true).setWeightCol("weight") val trainer2 = (new LogisticRegression).setFitIntercept(true) - .setElasticNetParam(0.0).setRegParam(0.0).setStandardization(false) + .setElasticNetParam(0.0).setRegParam(0.0).setStandardization(false).setWeightCol("weight") val model1 = trainer1.fit(multinomialDataset) val model2 = trainer2.fit(multinomialDataset) /* - Using the following R code to load the data and train the model using glmnet package. - > library("glmnet") - > data <- read.csv("path", header=FALSE) - > label = as.factor(data$V1) - > features = as.matrix(data.frame(data$V2, data$V3, data$V4, data$V5)) - > coefficients = coef(glmnet(features, label, family="multinomial", alpha = 0, lambda = 0)) - > coefficients - $`0` - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - -2.24493379 - V2 0.25096771 - V3 -0.03915938 - V4 0.14766639 - V5 0.36810817 - $`1` - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - 0.3778931 - V2 -0.3327489 - V3 0.8893666 - V4 -0.2306948 - V5 -0.4442330 - $`2` - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - 1.86704066 - V2 0.08178121 - V3 -0.85020722 - V4 0.08302840 - V5 0.07612480 - */ + Use the following R code to load the data and train the model using glmnet package. + library("glmnet") + data <- read.csv("path", header=FALSE) + label = as.factor(data$V1) + w = data$V2 + features = as.matrix(data.frame(data$V3, data$V4, data$V5, data$V6)) + coefficients = coef(glmnet(features, label, weights=w, family="multinomial", + alpha = 0, lambda = 0)) + coefficients + $`0` + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + -2.10320093 + data.V3 0.24337896 + data.V4 -0.05916156 + data.V5 0.14446790 + data.V6 0.35976165 + + $`1` + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + 0.3394473 + data.V3 -0.3443375 + data.V4 0.9181331 + data.V5 -0.2283959 + data.V6 -0.4388066 + + $`2` + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + 1.76375361 + data.V3 0.10095851 + data.V4 -0.85897154 + data.V5 0.08392798 + data.V6 0.07904499 + + + */ val coefficientsR = new DenseMatrix(3, 4, Array( - 0.2509677, -0.0391594, 0.1476664, 0.3681082, - -0.3327489, 0.8893666, -0.2306948, -0.4442330, - 0.0817812, -0.8502072, 0.0830284, 0.0761248), isTransposed = true) - val interceptsR = Vectors.dense(-2.2449338, 0.3778931, 1.8670407) + 0.24337896, -0.05916156, 0.14446790, 0.35976165, + -0.3443375, 0.9181331, -0.2283959, -0.4388066, + 0.10095851, -0.85897154, 0.08392798, 0.07904499), isTransposed = true) + val interceptsR = Vectors.dense(-2.10320093, 0.3394473, 1.76375361) assert(model1.coefficientMatrix ~== coefficientsR relTol 0.05) assert(model1.coefficientMatrix.toArray.sum ~== 0.0 absTol eps) @@ -1128,52 +1102,57 @@ class LogisticRegressionSuite test("multinomial logistic regression without intercept without regularization") { val trainer1 = (new LogisticRegression).setFitIntercept(false) - .setElasticNetParam(0.0).setRegParam(0.0).setStandardization(true) + .setElasticNetParam(0.0).setRegParam(0.0).setStandardization(true).setWeightCol("weight") val trainer2 = (new LogisticRegression).setFitIntercept(false) - .setElasticNetParam(0.0).setRegParam(0.0).setStandardization(false) + .setElasticNetParam(0.0).setRegParam(0.0).setStandardization(false).setWeightCol("weight") val model1 = trainer1.fit(multinomialDataset) val model2 = trainer2.fit(multinomialDataset) /* - Using the following R code to load the data and train the model using glmnet package. - library("glmnet") - data <- read.csv("path", header=FALSE) - label = as.factor(data$V1) - features = as.matrix(data.frame(data$V2, data$V3, data$V4, data$V5)) - coefficients = coef(glmnet(features, label, family="multinomial", alpha = 0, lambda = 0, - intercept=F)) - > coefficients - $`0` - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - . - V2 0.06992464 - V3 -0.36562784 - V4 0.12142680 - V5 0.32052211 - $`1` - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - . - V2 -0.3036269 - V3 0.9449630 - V4 -0.2271038 - V5 -0.4364839 - $`2` - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - . - V2 0.2337022 - V3 -0.5793351 - V4 0.1056770 - V5 0.1159618 - */ + Use the following R code to load the data and train the model using glmnet package. + + library("glmnet") + data <- read.csv("path", header=FALSE) + label = as.factor(data$V1) + w = data$V2 + features = as.matrix(data.frame(data$V3, data$V4, data$V5, data$V6)) + coefficients = coef(glmnet(features, label, weights=w, family="multinomial", alpha = 0, + lambda = 0, intercept=F)) + coefficients + $`0` + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + . + data.V3 0.07276291 + data.V4 -0.36325496 + data.V5 0.12015088 + data.V6 0.31397340 + + $`1` + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + . + data.V3 -0.3180040 + data.V4 0.9679074 + data.V5 -0.2252219 + data.V6 -0.4319914 + $`2` + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + . + data.V3 0.2452411 + data.V4 -0.6046524 + data.V5 0.1050710 + data.V6 0.1180180 + + + */ val coefficientsR = new DenseMatrix(3, 4, Array( - 0.0699246, -0.3656278, 0.1214268, 0.3205221, - -0.3036269, 0.9449630, -0.2271038, -0.4364839, - 0.2337022, -0.5793351, 0.1056770, 0.1159618), isTransposed = true) + 0.07276291, -0.36325496, 0.12015088, 0.31397340, + -0.3180040, 0.9679074, -0.2252219, -0.4319914, + 0.2452411, -0.6046524, 0.1050710, 0.1180180), isTransposed = true) assert(model1.coefficientMatrix ~== coefficientsR relTol 0.05) assert(model1.coefficientMatrix.toArray.sum ~== 0.0 absTol eps) @@ -1190,92 +1169,95 @@ class LogisticRegressionSuite // use tighter constraints because OWL-QN solver takes longer to converge val trainer1 = (new LogisticRegression).setFitIntercept(true) .setElasticNetParam(1.0).setRegParam(0.05).setStandardization(true) - .setMaxIter(300).setTol(1e-10) + .setMaxIter(300).setTol(1e-10).setWeightCol("weight") val trainer2 = (new LogisticRegression).setFitIntercept(true) .setElasticNetParam(1.0).setRegParam(0.05).setStandardization(false) - .setMaxIter(300).setTol(1e-10) + .setMaxIter(300).setTol(1e-10).setWeightCol("weight") val model1 = trainer1.fit(multinomialDataset) val model2 = trainer2.fit(multinomialDataset) /* - Use the following R code to load the data and train the model using glmnet package. - library("glmnet") - data <- read.csv("path", header=FALSE) - label = as.factor(data$V1) - features = as.matrix(data.frame(data$V2, data$V3, data$V4, data$V5)) - coefficientsStd = coef(glmnet(features, label, family="multinomial", alpha = 1, - lambda = 0.05, standardization=T)) - coefficients = coef(glmnet(features, label, family="multinomial", alpha = 1, lambda = 0.05, - standardization=F)) - > coefficientsStd - $`0` - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - -0.68988825 - V2 . - V3 . - V4 . - V5 0.09404023 - - $`1` - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - -0.2303499 - V2 -0.1232443 - V3 0.3258380 - V4 -0.1564688 - V5 -0.2053965 - - $`2` - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - 0.9202381 - V2 . - V3 -0.4803856 - V4 . - V5 . - - > coefficients - $`0` - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - -0.44893320 - V2 . - V3 . - V4 0.01933812 - V5 0.03666044 - - $`1` - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - 0.7376760 - V2 -0.0577182 - V3 . - V4 -0.2081718 - V5 -0.1304592 - - $`2` - 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - -0.2887428 - V2 . - V3 . - V4 . - V5 . - */ + Use the following R code to load the data and train the model using glmnet package. - val coefficientsRStd = new DenseMatrix(3, 4, Array( - 0.0, 0.0, 0.0, 0.09404023, - -0.1232443, 0.3258380, -0.1564688, -0.2053965, - 0.0, -0.4803856, 0.0, 0.0), isTransposed = true) - val interceptsRStd = Vectors.dense(-0.68988825, -0.2303499, 0.9202381) + library("glmnet") + data <- read.csv("path", header=FALSE) + label = as.factor(data$V1) + w = data$V2 + features = as.matrix(data.frame(data$V3, data$V4, data$V5, data$V6)) + coefficientsStd = coef(glmnet(features, label, weights=w, family="multinomial", + alpha = 1, lambda = 0.05, standardize=T)) + coefficients = coef(glmnet(features, label, weights=w, family="multinomial", alpha = 1, + lambda = 0.05, standardize=F)) + coefficientsStd + $`0` + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + -0.62244703 + data.V3 . + data.V4 . + data.V5 . + data.V6 0.08419825 + $`1` + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + -0.2804845 + data.V3 -0.1336960 + data.V4 0.3717091 + data.V5 -0.1530363 + data.V6 -0.2035286 + + $`2` + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + 0.9029315 + data.V3 . + data.V4 -0.4629737 + data.V5 . + data.V6 . + + + coefficients + $`0` + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + -0.44215290 + data.V3 . + data.V4 . + data.V5 0.01767089 + data.V6 0.02542866 + + $`1` + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + 0.76308326 + data.V3 -0.06818576 + data.V4 . + data.V5 -0.20446351 + data.V6 -0.13017924 + + $`2` + 5 x 1 sparse Matrix of class "dgCMatrix" + s0 + -0.3209304 + data.V3 . + data.V4 . + data.V5 . + data.V6 . + + + */ + val coefficientsRStd = new DenseMatrix(3, 4, Array( + 0.0, 0.0, 0.0, 0.08419825, + -0.1336960, 0.3717091, -0.1530363, -0.2035286, + 0.0, -0.4629737, 0.0, 0.0), isTransposed = true) + val interceptsRStd = Vectors.dense(-0.62244703, -0.2804845, 0.9029315) val coefficientsR = new DenseMatrix(3, 4, Array( - 0.0, 0.0, 0.01933812, 0.03666044, - -0.0577182, 0.0, -0.2081718, -0.1304592, + 0.0, 0.0, 0.01767089, 0.02542866, + -0.06818576, 0.0, -0.20446351, -0.13017924, 0.0, 0.0, 0.0, 0.0), isTransposed = true) - val interceptsR = Vectors.dense(-0.44893320, 0.7376760, -0.2887428) + val interceptsR = Vectors.dense(-0.44215290, 0.76308326, -0.3209304) assert(model1.coefficientMatrix ~== coefficientsRStd absTol 0.02) assert(model1.interceptVector ~== interceptsRStd relTol 0.1) @@ -1287,87 +1269,91 @@ class LogisticRegressionSuite test("multinomial logistic regression without intercept with L1 regularization") { val trainer1 = (new LogisticRegression).setFitIntercept(false) - .setElasticNetParam(1.0).setRegParam(0.05).setStandardization(true) + .setElasticNetParam(1.0).setRegParam(0.05).setStandardization(true).setWeightCol("weight") val trainer2 = (new LogisticRegression).setFitIntercept(false) - .setElasticNetParam(1.0).setRegParam(0.05).setStandardization(false) + .setElasticNetParam(1.0).setRegParam(0.05).setStandardization(false).setWeightCol("weight") val model1 = trainer1.fit(multinomialDataset) val model2 = trainer2.fit(multinomialDataset) /* Use the following R code to load the data and train the model using glmnet package. + library("glmnet") data <- read.csv("path", header=FALSE) label = as.factor(data$V1) - features = as.matrix(data.frame(data$V2, data$V3, data$V4, data$V5)) - coefficientsStd = coef(glmnet(features, label, family="multinomial", alpha = 1, - lambda = 0.05, intercept=F, standardization=T)) - coefficients = coef(glmnet(features, label, family="multinomial", alpha = 1, lambda = 0.05, - intercept=F, standardization=F)) - > coefficientsStd + w = data$V2 + features = as.matrix(data.frame(data$V3, data$V4, data$V5, data$V6)) + coefficientsStd = coef(glmnet(features, label, weights=w, family="multinomial", alpha = 1, + lambda = 0.05, intercept=F, standardize=T)) + coefficients = coef(glmnet(features, label, weights=w, family="multinomial", alpha = 1, + lambda = 0.05, intercept=F, standardize=F)) + coefficientsStd $`0` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - . - V2 . - V3 . - V4 . - V5 0.01525105 + s0 + . + data.V3 . + data.V4 . + data.V5 . + data.V6 0.01144225 $`1` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - . - V2 -0.1502410 - V3 0.5134658 - V4 -0.1601146 - V5 -0.2500232 + s0 + . + data.V3 -0.1678787 + data.V4 0.5385351 + data.V5 -0.1573039 + data.V6 -0.2471624 $`2` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - . - V2 0.003301875 - V3 . - V4 . - V5 . - - > coefficients + s0 + . + data.V3 . + data.V4 . + data.V5 . + data.V6 . + + + coefficients $`0` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - . - V2 . - V3 . - V4 . - V5 . + s0 + . + data.V3 . + data.V4 . + data.V5 . + data.V6 . $`1` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - . - V2 . - V3 0.1943624 - V4 -0.1902577 - V5 -0.1028789 + s0 + . + data.V3 . + data.V4 0.1929409 + data.V5 -0.1889121 + data.V6 -0.1010413 $`2` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - . - V2 . - V3 . - V4 . - V5 . - */ + s0 + . + data.V3 . + data.V4 . + data.V5 . + data.V6 . + + */ val coefficientsRStd = new DenseMatrix(3, 4, Array( - 0.0, 0.0, 0.0, 0.01525105, - -0.1502410, 0.5134658, -0.1601146, -0.2500232, - 0.003301875, 0.0, 0.0, 0.0), isTransposed = true) + 0.0, 0.0, 0.0, 0.01144225, + -0.1678787, 0.5385351, -0.1573039, -0.2471624, + 0.0, 0.0, 0.0, 0.0), isTransposed = true) val coefficientsR = new DenseMatrix(3, 4, Array( 0.0, 0.0, 0.0, 0.0, - 0.0, 0.1943624, -0.1902577, -0.1028789, + 0.0, 0.1929409, -0.1889121, -0.1010413, 0.0, 0.0, 0.0, 0.0), isTransposed = true) assert(model1.coefficientMatrix ~== coefficientsRStd absTol 0.01) @@ -1380,92 +1366,95 @@ class LogisticRegressionSuite test("multinomial logistic regression with intercept with L2 regularization") { val trainer1 = (new LogisticRegression).setFitIntercept(true) - .setElasticNetParam(0.0).setRegParam(0.1).setStandardization(true) + .setElasticNetParam(0.0).setRegParam(0.1).setStandardization(true).setWeightCol("weight") val trainer2 = (new LogisticRegression).setFitIntercept(true) - .setElasticNetParam(0.0).setRegParam(0.1).setStandardization(false) + .setElasticNetParam(0.0).setRegParam(0.1).setStandardization(false).setWeightCol("weight") val model1 = trainer1.fit(multinomialDataset) val model2 = trainer2.fit(multinomialDataset) /* Use the following R code to load the data and train the model using glmnet package. + library("glmnet") data <- read.csv("path", header=FALSE) label = as.factor(data$V1) - features = as.matrix(data.frame(data$V2, data$V3, data$V4, data$V5)) - coefficientsStd = coef(glmnet(features, label, family="multinomial", alpha = 0, - lambda = 0.1, intercept=T, standardization=T)) - coefficients = coef(glmnet(features, label, family="multinomial", alpha = 0, - lambda = 0.1, intercept=T, standardization=F)) - > coefficientsStd + w = data$V2 + features = as.matrix(data.frame( data$V3, data$V4, data$V5, data$V6)) + coefficientsStd = coef(glmnet(features, label, weights=w, family="multinomial", + alpha = 0, lambda = 0.1, intercept=T, standardize=T)) + coefficients = coef(glmnet(features, label, weights=w, family="multinomial", alpha = 0, + lambda = 0.1, intercept=T, standardize=F)) + coefficientsStd $`0` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - -1.70040424 - V2 0.17576070 - V3 0.01527894 - V4 0.10216108 - V5 0.26099531 + s0 + -1.5898288335 + data.V3 0.1691226336 + data.V4 0.0002983651 + data.V5 0.1001732896 + data.V6 0.2554575585 $`1` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - 0.2438590 - V2 -0.2238875 - V3 0.5967610 - V4 -0.1555496 - V5 -0.3010479 + s0 + 0.2125746 + data.V3 -0.2304586 + data.V4 0.6153492 + data.V5 -0.1537017 + data.V6 -0.2975443 $`2` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - 1.45654525 - V2 0.04812679 - V3 -0.61203992 - V4 0.05338850 - V5 0.04005258 - - > coefficients + s0 + 1.37725427 + data.V3 0.06133600 + data.V4 -0.61564761 + data.V5 0.05352840 + data.V6 0.04208671 + + + coefficients $`0` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - -1.65488543 - V2 0.15715048 - V3 0.01992903 - V4 0.12428858 - V5 0.22130317 + s0 + -1.5681088 + data.V3 0.1508182 + data.V4 0.0121955 + data.V5 0.1217930 + data.V6 0.2162850 $`1` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - 1.1297533 - V2 -0.1974768 - V3 0.2776373 - V4 -0.1869445 - V5 -0.2510320 + s0 + 1.1217130 + data.V3 -0.2028984 + data.V4 0.2862431 + data.V5 -0.1843559 + data.V6 -0.2481218 $`2` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - 0.52513212 - V2 0.04032627 - V3 -0.29756637 - V4 0.06265594 - V5 0.02972883 - */ + s0 + 0.44639579 + data.V3 0.05208012 + data.V4 -0.29843864 + data.V5 0.06256289 + data.V6 0.03183676 - val coefficientsRStd = new DenseMatrix(3, 4, Array( - 0.17576070, 0.01527894, 0.10216108, 0.26099531, - -0.2238875, 0.5967610, -0.1555496, -0.3010479, - 0.04812679, -0.61203992, 0.05338850, 0.04005258), isTransposed = true) - val interceptsRStd = Vectors.dense(-1.70040424, 0.2438590, 1.45654525) + */ + val coefficientsRStd = new DenseMatrix(3, 4, Array( + 0.1691226336, 0.0002983651, 0.1001732896, 0.2554575585, + -0.2304586, 0.6153492, -0.1537017, -0.2975443, + 0.06133600, -0.61564761, 0.05352840, 0.04208671), isTransposed = true) + val interceptsRStd = Vectors.dense(-1.5898288335, 0.2125746, 1.37725427) val coefficientsR = new DenseMatrix(3, 4, Array( - 0.15715048, 0.01992903, 0.12428858, 0.22130317, - -0.1974768, 0.2776373, -0.1869445, -0.2510320, - 0.04032627, -0.29756637, 0.06265594, 0.02972883), isTransposed = true) - val interceptsR = Vectors.dense(-1.65488543, 1.1297533, 0.52513212) + 0.1508182, 0.0121955, 0.1217930, 0.2162850, + -0.2028984, 0.2862431, -0.1843559, -0.2481218, + 0.05208012, -0.29843864, 0.06256289, 0.03183676), isTransposed = true) + val interceptsR = Vectors.dense(-1.5681088, 1.1217130, 0.44639579) - assert(model1.coefficientMatrix ~== coefficientsRStd relTol 0.05) + assert(model1.coefficientMatrix ~== coefficientsRStd absTol 0.001) assert(model1.interceptVector ~== interceptsRStd relTol 0.05) assert(model1.interceptVector.toArray.sum ~== 0.0 absTol eps) assert(model2.coefficientMatrix ~== coefficientsR relTol 0.05) @@ -1475,86 +1464,92 @@ class LogisticRegressionSuite test("multinomial logistic regression without intercept with L2 regularization") { val trainer1 = (new LogisticRegression).setFitIntercept(false) - .setElasticNetParam(0.0).setRegParam(0.1).setStandardization(true) + .setElasticNetParam(0.0).setRegParam(0.1).setStandardization(true).setWeightCol("weight") val trainer2 = (new LogisticRegression).setFitIntercept(false) - .setElasticNetParam(0.0).setRegParam(0.1).setStandardization(false) + .setElasticNetParam(0.0).setRegParam(0.1).setStandardization(false).setWeightCol("weight") val model1 = trainer1.fit(multinomialDataset) val model2 = trainer2.fit(multinomialDataset) /* Use the following R code to load the data and train the model using glmnet package. + library("glmnet") data <- read.csv("path", header=FALSE) label = as.factor(data$V1) - features = as.matrix(data.frame(data$V2, data$V3, data$V4, data$V5)) - coefficientsStd = coef(glmnet(features, label, family="multinomial", alpha = 0, - lambda = 0.1, intercept=F, standardization=T)) - coefficients = coef(glmnet(features, label, family="multinomial", alpha = 0, - lambda = 0.1, intercept=F, standardization=F)) - > coefficientsStd + w = data$V2 + features = as.matrix(data.frame(data$V3, data$V4, data$V5, data$V6)) + coefficientsStd = coef(glmnet(features, label, weights=w, family="multinomial", alpha = 0, + lambda = 0.1, intercept=F, standardize=T)) + coefficients = coef(glmnet(features, label, weights=w, family="multinomial", alpha = 0, + lambda = 0.1, intercept=F, standardize=F)) + coefficientsStd $`0` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - . - V2 0.03904171 - V3 -0.23354322 - V4 0.08288096 - V5 0.22706393 + s0 + . + data.V3 0.04048126 + data.V4 -0.23075758 + data.V5 0.08228864 + data.V6 0.22277648 $`1` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - . - V2 -0.2061848 - V3 0.6341398 - V4 -0.1530059 - V5 -0.2958455 + s0 + . + data.V3 -0.2149745 + data.V4 0.6478666 + data.V5 -0.1515158 + data.V6 -0.2930498 $`2` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - . - V2 0.16714312 - V3 -0.40059658 - V4 0.07012496 - V5 0.06878158 - > coefficients + s0 + . + data.V3 0.17449321 + data.V4 -0.41710901 + data.V5 0.06922716 + data.V6 0.07027332 + + + coefficients $`0` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - . - V2 -0.005704542 - V3 -0.144466409 - V4 0.092080736 - V5 0.182927657 + s0 + . + data.V3 -0.003949652 + data.V4 -0.142982415 + data.V5 0.091439598 + data.V6 0.179286241 $`1` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - . - V2 -0.08469036 - V3 0.38996748 - V4 -0.16468436 - V5 -0.22522976 + s0 + . + data.V3 -0.09071124 + data.V4 0.39752531 + data.V5 -0.16233832 + data.V6 -0.22206059 $`2` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - . - V2 0.09039490 - V3 -0.24550107 - V4 0.07260362 - V5 0.04230210 + s0 + . + data.V3 0.09466090 + data.V4 -0.25454290 + data.V5 0.07089872 + data.V6 0.04277435 + + */ val coefficientsRStd = new DenseMatrix(3, 4, Array( - 0.03904171, -0.23354322, 0.08288096, 0.2270639, - -0.2061848, 0.6341398, -0.1530059, -0.2958455, - 0.16714312, -0.40059658, 0.07012496, 0.06878158), isTransposed = true) + 0.04048126, -0.23075758, 0.08228864, 0.22277648, + -0.2149745, 0.6478666, -0.1515158, -0.2930498, + 0.17449321, -0.41710901, 0.06922716, 0.07027332), isTransposed = true) val coefficientsR = new DenseMatrix(3, 4, Array( - -0.005704542, -0.144466409, 0.092080736, 0.182927657, - -0.08469036, 0.38996748, -0.16468436, -0.22522976, - 0.0903949, -0.24550107, 0.07260362, 0.0423021), isTransposed = true) + -0.003949652, -0.142982415, 0.091439598, 0.179286241, + -0.09071124, 0.39752531, -0.16233832, -0.22206059, + 0.09466090, -0.25454290, 0.07089872, 0.04277435), isTransposed = true) assert(model1.coefficientMatrix ~== coefficientsRStd absTol 0.01) assert(model1.interceptVector.toArray === Array.fill(3)(0.0)) @@ -1565,10 +1560,10 @@ class LogisticRegressionSuite } test("multinomial logistic regression with intercept with elasticnet regularization") { - val trainer1 = (new LogisticRegression).setFitIntercept(true) + val trainer1 = (new LogisticRegression).setFitIntercept(true).setWeightCol("weight") .setElasticNetParam(0.5).setRegParam(0.1).setStandardization(true) .setMaxIter(300).setTol(1e-10) - val trainer2 = (new LogisticRegression).setFitIntercept(true) + val trainer2 = (new LogisticRegression).setFitIntercept(true).setWeightCol("weight") .setElasticNetParam(0.5).setRegParam(0.1).setStandardization(false) .setMaxIter(300).setTol(1e-10) @@ -1576,82 +1571,85 @@ class LogisticRegressionSuite val model2 = trainer2.fit(multinomialDataset) /* Use the following R code to load the data and train the model using glmnet package. + library("glmnet") data <- read.csv("path", header=FALSE) label = as.factor(data$V1) - features = as.matrix(data.frame(data$V2, data$V3, data$V4, data$V5)) - coefficientsStd = coef(glmnet(features, label, family="multinomial", alpha = 0.5, - lambda = 0.1, intercept=T, standardization=T)) - coefficients = coef(glmnet(features, label, family="multinomial", alpha = 0.5, - lambda = 0.1, intercept=T, standardization=F)) - > coefficientsStd + w = data$V2 + features = as.matrix(data.frame(data$V3, data$V4, data$V5, data$V6)) + coefficientsStd = coef(glmnet(features, label, weights=w, family="multinomial", alpha = 0.5, + lambda = 0.1, intercept=T, standardize=T)) + coefficients = coef(glmnet(features, label, weights=w, family="multinomial", alpha = 0.5, + lambda = 0.1, intercept=T, standardize=F)) + coefficientsStd $`0` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - -0.5521819483 - V2 0.0003092611 - V3 . - V4 . - V5 0.0913818490 + s0 + -0.50133383 + data.V3 . + data.V4 . + data.V5 . + data.V6 0.08351653 $`1` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - -0.27531989 - V2 -0.09790029 - V3 0.28502034 - V4 -0.12416487 - V5 -0.16513373 + s0 + -0.3151913 + data.V3 -0.1058702 + data.V4 0.3183251 + data.V5 -0.1212969 + data.V6 -0.1629778 $`2` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - 0.8275018 - V2 . - V3 -0.4044859 - V4 . - V5 . - - > coefficients + s0 + 0.8165252 + data.V3 . + data.V4 -0.3943069 + data.V5 . + data.V6 . + + + coefficients $`0` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - -0.39876213 - V2 . - V3 . - V4 0.02547520 - V5 0.03893991 + s0 + -0.38857157 + data.V3 . + data.V4 . + data.V5 0.02384198 + data.V6 0.03127749 $`1` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - 0.61089869 - V2 -0.04224269 - V3 . - V4 -0.18923970 - V5 -0.09104249 + s0 + 0.62492165 + data.V3 -0.04949061 + data.V4 . + data.V5 -0.18584462 + data.V6 -0.08952455 $`2` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - -0.2121366 - V2 . - V3 . - V4 . - V5 . - */ + s0 + -0.2363501 + data.V3 . + data.V4 . + data.V5 . + data.V6 . - val coefficientsRStd = new DenseMatrix(3, 4, Array( - 0.0003092611, 0.0, 0.0, 0.091381849, - -0.09790029, 0.28502034, -0.12416487, -0.16513373, - 0.0, -0.4044859, 0.0, 0.0), isTransposed = true) - val interceptsRStd = Vectors.dense(-0.5521819483, -0.27531989, 0.8275018) + */ + val coefficientsRStd = new DenseMatrix(3, 4, Array( + 0.0, 0.0, 0.0, 0.08351653, + -0.1058702, 0.3183251, -0.1212969, -0.1629778, + 0.0, -0.3943069, 0.0, 0.0), isTransposed = true) + val interceptsRStd = Vectors.dense(-0.50133383, -0.3151913, 0.8165252) val coefficientsR = new DenseMatrix(3, 4, Array( - 0.0, 0.0, 0.0254752, 0.03893991, - -0.04224269, 0.0, -0.1892397, -0.09104249, + 0.0, 0.0, 0.02384198, 0.03127749, + -0.04949061, 0.0, -0.18584462, -0.08952455, 0.0, 0.0, 0.0, 0.0), isTransposed = true) - val interceptsR = Vectors.dense(-0.39876213, 0.61089869, -0.2121366) + val interceptsR = Vectors.dense(-0.38857157, 0.62492165, -0.2363501) assert(model1.coefficientMatrix ~== coefficientsRStd absTol 0.01) assert(model1.interceptVector ~== interceptsRStd absTol 0.01) @@ -1662,10 +1660,10 @@ class LogisticRegressionSuite } test("multinomial logistic regression without intercept with elasticnet regularization") { - val trainer1 = (new LogisticRegression).setFitIntercept(false) + val trainer1 = (new LogisticRegression).setFitIntercept(false).setWeightCol("weight") .setElasticNetParam(0.5).setRegParam(0.1).setStandardization(true) .setMaxIter(300).setTol(1e-10) - val trainer2 = (new LogisticRegression).setFitIntercept(false) + val trainer2 = (new LogisticRegression).setFitIntercept(false).setWeightCol("weight") .setElasticNetParam(0.5).setRegParam(0.1).setStandardization(false) .setMaxIter(300).setTol(1e-10) @@ -1673,78 +1671,83 @@ class LogisticRegressionSuite val model2 = trainer2.fit(multinomialDataset) /* Use the following R code to load the data and train the model using glmnet package. + library("glmnet") data <- read.csv("path", header=FALSE) label = as.factor(data$V1) - features = as.matrix(data.frame(data$V2, data$V3, data$V4, data$V5)) - coefficientsStd = coef(glmnet(features, label, family="multinomial", alpha = 0.5, - lambda = 0.1, intercept=F, standardization=T)) - coefficients = coef(glmnet(features, label, family="multinomial", alpha = 0.5, - lambda = 0.1, intercept=F, standardization=F)) - > coefficientsStd + w = data$V2 + features = as.matrix(data.frame(data$V3, data$V4, data$V5, data$V6)) + coefficientsStd = coef(glmnet(features, label, weights=w, family="multinomial", alpha = 0.5, + lambda = 0.1, intercept=F, standardize=T)) + coefficients = coef(glmnet(features, label, weights=w, family="multinomial", alpha = 0.5, + lambda = 0.1, intercept=F, standardize=F)) + coefficientsStd $`0` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - . - V2 . - V3 . - V4 . - V5 0.03543706 + s0 + . + data.V3 . + data.V4 . + data.V5 . + data.V6 0.03238285 $`1` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - . - V2 -0.1187387 - V3 0.4025482 - V4 -0.1270969 - V5 -0.1918386 + s0 + . + data.V3 -0.1328284 + data.V4 0.4219321 + data.V5 -0.1247544 + data.V6 -0.1893318 $`2` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - . - V2 0.00774365 - V3 . - V4 . - V5 . - - > coefficients + s0 + . + data.V3 0.004572312 + data.V4 . + data.V5 . + data.V6 . + + + coefficients $`0` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - . - V2 . - V3 . - V4 . - V5 . + s0 + . + data.V3 . + data.V4 . + data.V5 . + data.V6 . $`1` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - . - V2 . - V3 0.14666497 - V4 -0.16570638 - V5 -0.05982875 + s0 + . + data.V3 . + data.V4 0.14571623 + data.V5 -0.16456351 + data.V6 -0.05866264 $`2` 5 x 1 sparse Matrix of class "dgCMatrix" - s0 - . - V2 . - V3 . - V4 . - V5 . + s0 + . + data.V3 . + data.V4 . + data.V5 . + data.V6 . + + */ val coefficientsRStd = new DenseMatrix(3, 4, Array( - 0.0, 0.0, 0.0, 0.03543706, - -0.1187387, 0.4025482, -0.1270969, -0.1918386, - 0.0, 0.0, 0.0, 0.00774365), isTransposed = true) + 0.0, 0.0, 0.0, 0.03238285, + -0.1328284, 0.4219321, -0.1247544, -0.1893318, + 0.004572312, 0.0, 0.0, 0.0), isTransposed = true) val coefficientsR = new DenseMatrix(3, 4, Array( 0.0, 0.0, 0.0, 0.0, - 0.0, 0.14666497, -0.16570638, -0.05982875, + 0.0, 0.14571623, -0.16456351, -0.05866264, 0.0, 0.0, 0.0, 0.0), isTransposed = true) assert(model1.coefficientMatrix ~== coefficientsRStd absTol 0.01) |