Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/8884#discussion_r41899983
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/regression/LinearRegressionSuite.scala
---
@@ -93,525 +94,559 @@ class LinearRegressionSuite extends SparkFunSuite
with MLlibTestSparkContext {
}
test("linear regression with intercept without regularization") {
- val trainer1 = new LinearRegression
- // The result should be the same regardless of standardization without
regularization
- val trainer2 = (new LinearRegression).setStandardization(false)
- val model1 = trainer1.fit(dataset)
- val model2 = trainer2.fit(dataset)
-
- /*
- Using the following R code to load the data and train the model
using glmnet package.
-
- library("glmnet")
- data <- read.csv("path", header=FALSE, stringsAsFactors=FALSE)
- features <- as.matrix(data.frame(as.numeric(data$V2),
as.numeric(data$V3)))
- label <- as.numeric(data$V1)
- weights <- coef(glmnet(features, label, family="gaussian", alpha =
0, lambda = 0))
- > weights
- 3 x 1 sparse Matrix of class "dgCMatrix"
- s0
- (Intercept) 6.298698
- as.numeric.data.V2. 4.700706
- as.numeric.data.V3. 7.199082
- */
- val interceptR = 6.298698
- val weightsR = Vectors.dense(4.700706, 7.199082)
-
- assert(model1.intercept ~== interceptR relTol 1E-3)
- assert(model1.weights ~= weightsR relTol 1E-3)
- assert(model2.intercept ~== interceptR relTol 1E-3)
- assert(model2.weights ~= weightsR relTol 1E-3)
-
-
- model1.transform(dataset).select("features",
"prediction").collect().foreach {
- case Row(features: DenseVector, prediction1: Double) =>
- val prediction2 =
- features(0) * model1.weights(0) + features(1) *
model1.weights(1) + model1.intercept
- assert(prediction1 ~== prediction2 relTol 1E-5)
- }
+ Seq("auto", "l-bfgs", "normal").foreach { solver => {
+ val trainer1 = new LinearRegression().setSolver(solver)
+ // The result should be the same regardless of standardization
without regularization
+ val trainer2 = (new
LinearRegression).setStandardization(false).setSolver(solver)
+ val model1 = trainer1.fit(dataset)
+ val model2 = trainer2.fit(dataset)
+
+ /*
+ Using the following R code to load the data and train the model
using glmnet package.
+
+ library("glmnet")
+ data <- read.csv("path", header=FALSE, stringsAsFactors=FALSE)
+ features <- as.matrix(data.frame(as.numeric(data$V2),
as.numeric(data$V3)))
+ label <- as.numeric(data$V1)
+ weights <- coef(glmnet(features, label, family="gaussian", alpha
= 0, lambda = 0))
+ > weights
+ 3 x 1 sparse Matrix of class "dgCMatrix"
+ s0
+ (Intercept) 6.298698
+ as.numeric.data.V2. 4.700706
+ as.numeric.data.V3. 7.199082
+ */
+ val interceptR = 6.298698
+ val weightsR = Vectors.dense(4.700706, 7.199082)
+
+ assert(model1.intercept ~== interceptR relTol 1E-3)
+ assert(model1.weights ~= weightsR relTol 1E-3)
+ assert(model2.intercept ~== interceptR relTol 1E-3)
+ assert(model2.weights ~= weightsR relTol 1E-3)
+
+ model1.transform(dataset).select("features",
"prediction").collect().foreach {
+ case Row(features: DenseVector, prediction1: Double) =>
+ val prediction2 =
+ features(0) * model1.weights(0) + features(1) *
model1.weights(1) + model1.intercept
+ assert(prediction1 ~== prediction2 relTol 1E-5)
+ }
+ }}
}
test("linear regression without intercept without regularization") {
- val trainer1 = (new LinearRegression).setFitIntercept(false)
- // Without regularization the results should be the same
- val trainer2 = (new
LinearRegression).setFitIntercept(false).setStandardization(false)
- val model1 = trainer1.fit(dataset)
- val modelWithoutIntercept1 = trainer1.fit(datasetWithoutIntercept)
- val model2 = trainer2.fit(dataset)
- val modelWithoutIntercept2 = trainer2.fit(datasetWithoutIntercept)
-
-
- /*
- weights <- coef(glmnet(features, label, family="gaussian", alpha =
0, lambda = 0,
- intercept = FALSE))
- > weights
- 3 x 1 sparse Matrix of class "dgCMatrix"
- s0
- (Intercept) .
- as.numeric.data.V2. 6.995908
- as.numeric.data.V3. 5.275131
- */
- val weightsR = Vectors.dense(6.995908, 5.275131)
-
- assert(model1.intercept ~== 0 absTol 1E-3)
- assert(model1.weights ~= weightsR relTol 1E-3)
- assert(model2.intercept ~== 0 absTol 1E-3)
- assert(model2.weights ~= weightsR relTol 1E-3)
-
- /*
- Then again with the data with no intercept:
- > weightsWithoutIntercept
- 3 x 1 sparse Matrix of class "dgCMatrix"
- s0
- (Intercept) .
- as.numeric.data3.V2. 4.70011
- as.numeric.data3.V3. 7.19943
- */
- val weightsWithoutInterceptR = Vectors.dense(4.70011, 7.19943)
-
- assert(modelWithoutIntercept1.intercept ~== 0 absTol 1E-3)
- assert(modelWithoutIntercept1.weights ~= weightsWithoutInterceptR
relTol 1E-3)
- assert(modelWithoutIntercept2.intercept ~== 0 absTol 1E-3)
- assert(modelWithoutIntercept2.weights ~= weightsWithoutInterceptR
relTol 1E-3)
+ Seq("auto", "l-bfgs", "normal").foreach { solver => {
+ val trainer1 = (new
LinearRegression).setFitIntercept(false).setSolver(solver)
+ // Without regularization the results should be the same
+ val trainer2 = (new
LinearRegression).setFitIntercept(false).setStandardization(false)
+ .setSolver(solver)
+ val model1 = trainer1.fit(dataset)
+ val modelWithoutIntercept1 = trainer1.fit(datasetWithoutIntercept)
+ val model2 = trainer2.fit(dataset)
+ val modelWithoutIntercept2 = trainer2.fit(datasetWithoutIntercept)
+
+ /*
+ weights <- coef(glmnet(features, label, family="gaussian", alpha
= 0, lambda = 0,
+ intercept = FALSE))
+ > weights
+ 3 x 1 sparse Matrix of class "dgCMatrix"
+ s0
+ (Intercept) .
+ as.numeric.data.V2. 6.995908
+ as.numeric.data.V3. 5.275131
+ */
+ val weightsR = Vectors.dense(6.995908, 5.275131)
+
+ assert(model1.intercept ~== 0 absTol 1E-3)
+ assert(model1.weights ~= weightsR relTol 1E-3)
+ assert(model2.intercept ~== 0 absTol 1E-3)
+ assert(model2.weights ~= weightsR relTol 1E-3)
+
+ /*
+ Then again with the data with no intercept:
+ > weightsWithoutIntercept
+ 3 x 1 sparse Matrix of class "dgCMatrix"
+ s0
+ (Intercept) .
+ as.numeric.data3.V2. 4.70011
+ as.numeric.data3.V3. 7.19943
+ */
+ val weightsWithoutInterceptR = Vectors.dense(4.70011, 7.19943)
+
+ assert(modelWithoutIntercept1.intercept ~== 0 absTol 1E-3)
+ assert(modelWithoutIntercept1.weights ~= weightsWithoutInterceptR
relTol 1E-3)
+ assert(modelWithoutIntercept2.intercept ~== 0 absTol 1E-3)
+ assert(modelWithoutIntercept2.weights ~= weightsWithoutInterceptR
relTol 1E-3)
+ }}
}
test("linear regression with intercept with L1 regularization") {
- val trainer1 = (new
LinearRegression).setElasticNetParam(1.0).setRegParam(0.57)
- val trainer2 = (new
LinearRegression).setElasticNetParam(1.0).setRegParam(0.57)
- .setStandardization(false)
- val model1 = trainer1.fit(dataset)
- val model2 = trainer2.fit(dataset)
-
- /*
- weights <- coef(glmnet(features, label, family="gaussian", alpha =
1.0, lambda = 0.57))
- > weights
- 3 x 1 sparse Matrix of class "dgCMatrix"
- s0
- (Intercept) 6.24300
- as.numeric.data.V2. 4.024821
- as.numeric.data.V3. 6.679841
- */
- val interceptR1 = 6.24300
- val weightsR1 = Vectors.dense(4.024821, 6.679841)
-
- assert(model1.intercept ~== interceptR1 relTol 1E-3)
- assert(model1.weights ~= weightsR1 relTol 1E-3)
-
- /*
- weights <- coef(glmnet(features, label, family="gaussian", alpha =
1.0, lambda = 0.57,
- standardize=FALSE))
- > weights
- 3 x 1 sparse Matrix of class "dgCMatrix"
- s0
- (Intercept) 6.416948
- as.numeric.data.V2. 3.893869
- as.numeric.data.V3. 6.724286
- */
- val interceptR2 = 6.416948
- val weightsR2 = Vectors.dense(3.893869, 6.724286)
-
- assert(model2.intercept ~== interceptR2 relTol 1E-3)
- assert(model2.weights ~= weightsR2 relTol 1E-3)
-
-
- model1.transform(dataset).select("features",
"prediction").collect().foreach {
- case Row(features: DenseVector, prediction1: Double) =>
- val prediction2 =
- features(0) * model1.weights(0) + features(1) *
model1.weights(1) + model1.intercept
- assert(prediction1 ~== prediction2 relTol 1E-5)
- }
+ Seq("auto").foreach { solver => {
+ val trainer1 = (new
LinearRegression).setElasticNetParam(1.0).setRegParam(0.57)
+ .setSolver(solver)
+ val trainer2 = (new
LinearRegression).setElasticNetParam(1.0).setRegParam(0.57)
+ .setSolver(solver).setStandardization(false)
+ val model1 = trainer1.fit(dataset)
+ val model2 = trainer2.fit(dataset)
+
+ /*
+ weights <- coef(glmnet(features, label, family="gaussian", alpha
= 1.0, lambda = 0.57))
+ > weights
+ 3 x 1 sparse Matrix of class "dgCMatrix"
+ s0
+ (Intercept) 6.24300
+ as.numeric.data.V2. 4.024821
+ as.numeric.data.V3. 6.679841
+ */
+ val interceptR1 = 6.24300
+ val weightsR1 = Vectors.dense(4.024821, 6.679841)
+ assert(model1.intercept ~== interceptR1 relTol 1E-3)
+ assert(model1.weights ~= weightsR1 relTol 1E-3)
+
+ /*
+ weights <- coef(glmnet(features, label, family="gaussian", alpha
= 1.0, lambda = 0.57,
+ standardize=FALSE))
+ > weights
+ 3 x 1 sparse Matrix of class "dgCMatrix"
+ s0
+ (Intercept) 6.416948
+ as.numeric.data.V2. 3.893869
+ as.numeric.data.V3. 6.724286
+ */
+ val interceptR2 = 6.416948
+ val weightsR2 = Vectors.dense(3.893869, 6.724286)
+
+ assert(model2.intercept ~== interceptR2 relTol 1E-3)
+ assert(model2.weights ~= weightsR2 relTol 1E-3)
+
+ model1.transform(dataset).select("features",
"prediction").collect().foreach {
+ case Row(features: DenseVector, prediction1: Double) =>
+ val prediction2 =
+ features(0) * model1.weights(0) + features(1) *
model1.weights(1) + model1.intercept
+ assert(prediction1 ~== prediction2 relTol 1E-5)
+ }
+ }}
}
test("linear regression without intercept with L1 regularization") {
- val trainer1 = (new
LinearRegression).setElasticNetParam(1.0).setRegParam(0.57)
- .setFitIntercept(false)
- val trainer2 = (new
LinearRegression).setElasticNetParam(1.0).setRegParam(0.57)
- .setFitIntercept(false).setStandardization(false)
- val model1 = trainer1.fit(dataset)
- val model2 = trainer2.fit(dataset)
-
- /*
- weights <- coef(glmnet(features, label, family="gaussian", alpha =
1.0, lambda = 0.57,
- intercept=FALSE))
- > weights
- 3 x 1 sparse Matrix of class "dgCMatrix"
- s0
- (Intercept) .
- as.numeric.data.V2. 6.299752
- as.numeric.data.V3. 4.772913
- */
- val interceptR1 = 0.0
- val weightsR1 = Vectors.dense(6.299752, 4.772913)
-
- assert(model1.intercept ~== interceptR1 absTol 1E-3)
- assert(model1.weights ~= weightsR1 relTol 1E-3)
-
- /*
- weights <- coef(glmnet(features, label, family="gaussian", alpha =
1.0, lambda = 0.57,
- intercept=FALSE, standardize=FALSE))
- > weights
- 3 x 1 sparse Matrix of class "dgCMatrix"
- s0
- (Intercept) .
- as.numeric.data.V2. 6.232193
- as.numeric.data.V3. 4.764229
- */
- val interceptR2 = 0.0
- val weightsR2 = Vectors.dense(6.232193, 4.764229)
-
- assert(model2.intercept ~== interceptR2 absTol 1E-3)
- assert(model2.weights ~= weightsR2 relTol 1E-3)
-
-
- model1.transform(dataset).select("features",
"prediction").collect().foreach {
- case Row(features: DenseVector, prediction1: Double) =>
- val prediction2 =
- features(0) * model1.weights(0) + features(1) *
model1.weights(1) + model1.intercept
- assert(prediction1 ~== prediction2 relTol 1E-5)
- }
+ Seq("auto").foreach { solver => {
+ val trainer1 = (new
LinearRegression).setElasticNetParam(1.0).setRegParam(0.57)
+ .setFitIntercept(false).setSolver(solver)
+ val trainer2 = (new
LinearRegression).setElasticNetParam(1.0).setRegParam(0.57)
+ .setFitIntercept(false).setStandardization(false).setSolver(solver)
+
+ val model1 = trainer1.fit(dataset)
+ val model2 = trainer2.fit(dataset)
+
+ /*
+ weights <- coef(glmnet(features, label, family="gaussian", alpha
= 1.0, lambda = 0.57,
+ intercept=FALSE))
+ > weights
+ 3 x 1 sparse Matrix of class "dgCMatrix"
+ s0
+ (Intercept) .
+ as.numeric.data.V2. 6.299752
+ as.numeric.data.V3. 4.772913
+ */
+ val interceptR1 = 0.0
+ val weightsR1 = Vectors.dense(6.299752, 4.772913)
+
+ assert(model1.intercept ~== interceptR1 absTol 1E-3)
+ assert(model1.weights ~= weightsR1 relTol 1E-3)
+
+ /*
+ weights <- coef(glmnet(features, label, family="gaussian", alpha
= 1.0, lambda = 0.57,
+ intercept=FALSE, standardize=FALSE))
+ > weights
+ 3 x 1 sparse Matrix of class "dgCMatrix"
+ s0
+ (Intercept) .
+ as.numeric.data.V2. 6.232193
+ as.numeric.data.V3. 4.764229
+ */
+ val interceptR2 = 0.0
+ val weightsR2 = Vectors.dense(6.232193, 4.764229)
+
+ assert(model2.intercept ~== interceptR2 absTol 1E-3)
+ assert(model2.weights ~= weightsR2 relTol 1E-3)
+
+ model1.transform(dataset).select("features",
"prediction").collect().foreach {
+ case Row(features: DenseVector, prediction1: Double) =>
+ val prediction2 =
+ features(0) * model1.weights(0) + features(1) *
model1.weights(1) + model1.intercept
+ assert(prediction1 ~== prediction2 relTol 1E-5)
+ }
+ }}
}
test("linear regression with intercept with L2 regularization") {
- val trainer1 = (new
LinearRegression).setElasticNetParam(0.0).setRegParam(2.3)
- val trainer2 = (new
LinearRegression).setElasticNetParam(0.0).setRegParam(2.3)
- .setStandardization(false)
- val model1 = trainer1.fit(dataset)
- val model2 = trainer2.fit(dataset)
-
- /*
- weights <- coef(glmnet(features, label, family="gaussian", alpha =
0.0, lambda = 2.3))
- > weights
- 3 x 1 sparse Matrix of class "dgCMatrix"
- s0
- (Intercept) 5.269376
- as.numeric.data.V2. 3.736216
- as.numeric.data.V3. 5.712356)
- */
- val interceptR1 = 5.269376
- val weightsR1 = Vectors.dense(3.736216, 5.712356)
-
- assert(model1.intercept ~== interceptR1 relTol 1E-3)
- assert(model1.weights ~= weightsR1 relTol 1E-3)
-
- /*
- weights <- coef(glmnet(features, label, family="gaussian", alpha =
0.0, lambda = 2.3,
- standardize=FALSE))
- > weights
- 3 x 1 sparse Matrix of class "dgCMatrix"
- s0
- (Intercept) 5.791109
- as.numeric.data.V2. 3.435466
- as.numeric.data.V3. 5.910406
- */
- val interceptR2 = 5.791109
- val weightsR2 = Vectors.dense(3.435466, 5.910406)
-
- assert(model2.intercept ~== interceptR2 relTol 1E-3)
- assert(model2.weights ~= weightsR2 relTol 1E-3)
-
- model1.transform(dataset).select("features",
"prediction").collect().foreach {
- case Row(features: DenseVector, prediction1: Double) =>
- val prediction2 =
- features(0) * model1.weights(0) + features(1) *
model1.weights(1) + model1.intercept
- assert(prediction1 ~== prediction2 relTol 1E-5)
- }
+ Seq("auto", "l-bfgs", "normal").foreach { solver => {
+ val trainer1 = (new
LinearRegression).setElasticNetParam(0.0).setRegParam(2.3)
+ .setSolver(solver)
+ val trainer2 = (new
LinearRegression).setElasticNetParam(0.0).setRegParam(2.3)
+ .setStandardization(false).setSolver(solver)
+ val model1 = trainer1.fit(dataset)
+ val model2 = trainer2.fit(dataset)
+
+ /*
+ weights <- coef(glmnet(features, label, family="gaussian", alpha
= 0.0, lambda = 2.3))
+ > weights
+ 3 x 1 sparse Matrix of class "dgCMatrix"
+ s0
+ (Intercept) 5.269376
+ as.numeric.data.V2. 3.736216
+ as.numeric.data.V3. 5.712356)
+ */
+ val interceptR1 = 5.269376
+ val weightsR1 = Vectors.dense(3.736216, 5.712356)
+
+ assert(model1.intercept ~== interceptR1 relTol 1E-3)
+ assert(model1.weights ~= weightsR1 relTol 1E-3)
+
+ /*
+ weights <- coef(glmnet(features, label, family="gaussian", alpha
= 0.0, lambda = 2.3,
+ standardize=FALSE))
+ > weights
+ 3 x 1 sparse Matrix of class "dgCMatrix"
+ s0
+ (Intercept) 5.791109
+ as.numeric.data.V2. 3.435466
+ as.numeric.data.V3. 5.910406
+ */
+ val interceptR2 = 5.791109
+ val weightsR2 = Vectors.dense(3.435466, 5.910406)
+
+ assert(model2.intercept ~== interceptR2 relTol 1E-3)
+ assert(model2.weights ~= weightsR2 relTol 1E-3)
+
+ model1.transform(dataset).select("features",
"prediction").collect().foreach {
+ case Row(features: DenseVector, prediction1: Double) =>
+ val prediction2 =
+ features(0) * model1.weights(0) + features(1) *
model1.weights(1) + model1.intercept
+ assert(prediction1 ~== prediction2 relTol 1E-5)
+ }
+ }}
}
test("linear regression without intercept with L2 regularization") {
- val trainer1 = (new
LinearRegression).setElasticNetParam(0.0).setRegParam(2.3)
- .setFitIntercept(false)
- val trainer2 = (new
LinearRegression).setElasticNetParam(0.0).setRegParam(2.3)
- .setFitIntercept(false).setStandardization(false)
- val model1 = trainer1.fit(dataset)
- val model2 = trainer2.fit(dataset)
-
- /*
- weights <- coef(glmnet(features, label, family="gaussian", alpha =
0.0, lambda = 2.3,
- intercept = FALSE))
- > weights
- 3 x 1 sparse Matrix of class "dgCMatrix"
- s0
- (Intercept) .
- as.numeric.data.V2. 5.522875
- as.numeric.data.V3. 4.214502
- */
- val interceptR1 = 0.0
- val weightsR1 = Vectors.dense(5.522875, 4.214502)
-
- assert(model1.intercept ~== interceptR1 absTol 1E-3)
- assert(model1.weights ~= weightsR1 relTol 1E-3)
-
- /*
- weights <- coef(glmnet(features, label, family="gaussian", alpha =
0.0, lambda = 2.3,
- intercept = FALSE, standardize=FALSE))
- > weights
- 3 x 1 sparse Matrix of class "dgCMatrix"
- s0
- (Intercept) .
- as.numeric.data.V2. 5.263704
- as.numeric.data.V3. 4.187419
- */
- val interceptR2 = 0.0
- val weightsR2 = Vectors.dense(5.263704, 4.187419)
-
- assert(model2.intercept ~== interceptR2 absTol 1E-3)
- assert(model2.weights ~= weightsR2 relTol 1E-3)
-
- model1.transform(dataset).select("features",
"prediction").collect().foreach {
- case Row(features: DenseVector, prediction1: Double) =>
- val prediction2 =
- features(0) * model1.weights(0) + features(1) *
model1.weights(1) + model1.intercept
- assert(prediction1 ~== prediction2 relTol 1E-5)
- }
+ Seq("auto", "l-bfgs", "normal").foreach { solver => {
+ val trainer1 = (new
LinearRegression).setElasticNetParam(0.0).setRegParam(2.3)
+ .setFitIntercept(false).setSolver(solver)
+ val trainer2 = (new
LinearRegression).setElasticNetParam(0.0).setRegParam(2.3)
+ .setFitIntercept(false).setStandardization(false).setSolver(solver)
+ val model1 = trainer1.fit(dataset)
+ val model2 = trainer2.fit(dataset)
+
+ /*
+ weights <- coef(glmnet(features, label, family="gaussian", alpha
= 0.0, lambda = 2.3,
+ intercept = FALSE))
+ > weights
+ 3 x 1 sparse Matrix of class "dgCMatrix"
+ s0
+ (Intercept) .
+ as.numeric.data.V2. 5.522875
+ as.numeric.data.V3. 4.214502
+ */
+ val interceptR1 = 0.0
+ val weightsR1 = Vectors.dense(5.522875, 4.214502)
+
+ assert(model1.intercept ~== interceptR1 absTol 1E-3)
+ assert(model1.weights ~= weightsR1 relTol 1E-3)
+
+ /*
+ weights <- coef(glmnet(features, label, family="gaussian", alpha
= 0.0, lambda = 2.3,
+ intercept = FALSE, standardize=FALSE))
+ > weights
+ 3 x 1 sparse Matrix of class "dgCMatrix"
+ s0
+ (Intercept) .
+ as.numeric.data.V2. 5.263704
+ as.numeric.data.V3. 4.187419
+ */
+ val interceptR2 = 0.0
+ val weightsR2 = Vectors.dense(5.263704, 4.187419)
+
+ assert(model2.intercept ~== interceptR2 absTol 1E-3)
+ assert(model2.weights ~= weightsR2 relTol 1E-3)
+
+ model1.transform(dataset).select("features",
"prediction").collect().foreach {
+ case Row(features: DenseVector, prediction1: Double) =>
+ val prediction2 =
+ features(0) * model1.weights(0) + features(1) *
model1.weights(1) + model1.intercept
+ assert(prediction1 ~== prediction2 relTol 1E-5)
+ }
+ }}
}
test("linear regression with intercept with ElasticNet regularization") {
- val trainer1 = (new
LinearRegression).setElasticNetParam(0.3).setRegParam(1.6)
- val trainer2 = (new
LinearRegression).setElasticNetParam(0.3).setRegParam(1.6)
- .setStandardization(false)
- val model1 = trainer1.fit(dataset)
- val model2 = trainer2.fit(dataset)
-
- /*
- weights <- coef(glmnet(features, label, family="gaussian", alpha =
0.3, lambda = 1.6))
- > weights
- 3 x 1 sparse Matrix of class "dgCMatrix"
- s0
- (Intercept) 6.324108
- as.numeric.data.V2. 3.168435
- as.numeric.data.V3. 5.200403
- */
- val interceptR1 = 5.696056
- val weightsR1 = Vectors.dense(3.670489, 6.001122)
-
- assert(model1.intercept ~== interceptR1 relTol 1E-3)
- assert(model1.weights ~= weightsR1 relTol 1E-3)
-
- /*
- weights <- coef(glmnet(features, label, family="gaussian", alpha =
0.3, lambda = 1.6
- standardize=FALSE))
- > weights
- 3 x 1 sparse Matrix of class "dgCMatrix"
- s0
- (Intercept) 6.114723
- as.numeric.data.V2. 3.409937
- as.numeric.data.V3. 6.146531
- */
- val interceptR2 = 6.114723
- val weightsR2 = Vectors.dense(3.409937, 6.146531)
-
- assert(model2.intercept ~== interceptR2 relTol 1E-3)
- assert(model2.weights ~= weightsR2 relTol 1E-3)
-
- model1.transform(dataset).select("features",
"prediction").collect().foreach {
- case Row(features: DenseVector, prediction1: Double) =>
- val prediction2 =
- features(0) * model1.weights(0) + features(1) *
model1.weights(1) + model1.intercept
- assert(prediction1 ~== prediction2 relTol 1E-5)
- }
+ Seq("auto").foreach { solver => {
+ val trainer1 = (new
LinearRegression).setElasticNetParam(0.3).setRegParam(1.6)
+ .setSolver(solver)
+ val trainer2 = (new
LinearRegression).setElasticNetParam(0.3).setRegParam(1.6)
+ .setStandardization(false).setSolver(solver)
+ val model1 = trainer1.fit(dataset)
+ val model2 = trainer2.fit(dataset)
+
+ /*
+ weights <- coef(glmnet(features, label, family="gaussian", alpha
= 0.3, lambda = 1.6))
+ > weights
+ 3 x 1 sparse Matrix of class "dgCMatrix"
+ s0
+ (Intercept) 6.324108
+ as.numeric.data.V2. 3.168435
+ as.numeric.data.V3. 5.200403
+ */
+ val interceptR1 = 5.696056
+ val weightsR1 = Vectors.dense(3.670489, 6.001122)
+
+ assert(model1.intercept ~== interceptR1 relTol 1E-3)
+ assert(model1.weights ~= weightsR1 relTol 1E-3)
+
+ /*
+ weights <- coef(glmnet(features, label, family="gaussian", alpha
= 0.3, lambda = 1.6
+ standardize=FALSE))
+ > weights
+ 3 x 1 sparse Matrix of class "dgCMatrix"
+ s0
+ (Intercept) 6.114723
+ as.numeric.data.V2. 3.409937
+ as.numeric.data.V3. 6.146531
+ */
+ val interceptR2 = 6.114723
+ val weightsR2 = Vectors.dense(3.409937, 6.146531)
+
+ assert(model2.intercept ~== interceptR2 relTol 1E-3)
+ assert(model2.weights ~= weightsR2 relTol 1E-3)
+
+ model1.transform(dataset).select("features",
"prediction").collect().foreach {
+ case Row(features: DenseVector, prediction1: Double) =>
+ val prediction2 =
+ features(0) * model1.weights(0) + features(1) *
model1.weights(1) + model1.intercept
+ assert(prediction1 ~== prediction2 relTol 1E-5)
+ }
+ }}
}
test("linear regression without intercept with ElasticNet
regularization") {
- val trainer1 = (new
LinearRegression).setElasticNetParam(0.3).setRegParam(1.6)
- .setFitIntercept(false)
- val trainer2 = (new
LinearRegression).setElasticNetParam(0.3).setRegParam(1.6)
- .setFitIntercept(false).setStandardization(false)
- val model1 = trainer1.fit(dataset)
- val model2 = trainer2.fit(dataset)
-
- /*
- weights <- coef(glmnet(features, label, family="gaussian", alpha =
0.3, lambda = 1.6,
- intercept=FALSE))
- > weights
- 3 x 1 sparse Matrix of class "dgCMatrix"
- s0
- (Intercept) .
- as.numeric.dataM.V2. 5.673348
- as.numeric.dataM.V3. 4.322251
- */
- val interceptR1 = 0.0
- val weightsR1 = Vectors.dense(5.673348, 4.322251)
-
- assert(model1.intercept ~== interceptR1 absTol 1E-3)
- assert(model1.weights ~= weightsR1 relTol 1E-3)
-
- /*
- weights <- coef(glmnet(features, label, family="gaussian", alpha =
0.3, lambda = 1.6,
- intercept=FALSE, standardize=FALSE))
- > weights
- 3 x 1 sparse Matrix of class "dgCMatrix"
- s0
- (Intercept) .
- as.numeric.data.V2. 5.477988
- as.numeric.data.V3. 4.297622
- */
- val interceptR2 = 0.0
- val weightsR2 = Vectors.dense(5.477988, 4.297622)
-
- assert(model2.intercept ~== interceptR2 absTol 1E-3)
- assert(model2.weights ~= weightsR2 relTol 1E-3)
-
- model1.transform(dataset).select("features",
"prediction").collect().foreach {
- case Row(features: DenseVector, prediction1: Double) =>
- val prediction2 =
- features(0) * model1.weights(0) + features(1) *
model1.weights(1) + model1.intercept
- assert(prediction1 ~== prediction2 relTol 1E-5)
- }
+ Seq("auto").foreach { solver => {
+ val trainer1 = (new
LinearRegression).setElasticNetParam(0.3).setRegParam(1.6)
+ .setFitIntercept(false).setSolver(solver)
+ val trainer2 = (new
LinearRegression).setElasticNetParam(0.3).setRegParam(1.6)
+ .setFitIntercept(false).setStandardization(false).setSolver(solver)
+ val model1 = trainer1.fit(dataset)
+ val model2 = trainer2.fit(dataset)
+
+ /*
+ weights <- coef(glmnet(features, label, family="gaussian", alpha
= 0.3, lambda = 1.6,
+ intercept=FALSE))
+ > weights
+ 3 x 1 sparse Matrix of class "dgCMatrix"
+ s0
+ (Intercept) .
+ as.numeric.dataM.V2. 5.673348
+ as.numeric.dataM.V3. 4.322251
+ */
+ val interceptR1 = 0.0
+ val weightsR1 = Vectors.dense(5.673348, 4.322251)
+
+ assert(model1.intercept ~== interceptR1 absTol 1E-3)
+ assert(model1.weights ~= weightsR1 relTol 1E-3)
+
+ /*
+ weights <- coef(glmnet(features, label, family="gaussian", alpha
= 0.3, lambda = 1.6,
+ intercept=FALSE, standardize=FALSE))
+ > weights
+ 3 x 1 sparse Matrix of class "dgCMatrix"
+ s0
+ (Intercept) .
+ as.numeric.data.V2. 5.477988
+ as.numeric.data.V3. 4.297622
+ */
+ val interceptR2 = 0.0
+ val weightsR2 = Vectors.dense(5.477988, 4.297622)
+
+ assert(model2.intercept ~== interceptR2 absTol 1E-3)
+ assert(model2.weights ~= weightsR2 relTol 1E-3)
+
+ model1.transform(dataset).select("features",
"prediction").collect().foreach {
+ case Row(features: DenseVector, prediction1: Double) =>
+ val prediction2 =
+ features(0) * model1.weights(0) + features(1) *
model1.weights(1) + model1.intercept
+ assert(prediction1 ~== prediction2 relTol 1E-5)
+ }
+ }}
}
test("linear regression model training summary") {
- val trainer = new LinearRegression
- val model = trainer.fit(dataset)
- val trainerNoPredictionCol = trainer.setPredictionCol("")
- val modelNoPredictionCol = trainerNoPredictionCol.fit(dataset)
-
-
- // Training results for the model should be available
- assert(model.hasSummary)
- assert(modelNoPredictionCol.hasSummary)
-
- // Schema should be a superset of the input dataset
- assert((dataset.schema.fieldNames.toSet + "prediction").subsetOf(
- model.summary.predictions.schema.fieldNames.toSet))
- // Validate that we re-insert a prediction column for evaluation
- val modelNoPredictionColFieldNames =
modelNoPredictionCol.summary.predictions.schema.fieldNames
- assert((dataset.schema.fieldNames.toSet).subsetOf(
- modelNoPredictionColFieldNames.toSet))
- assert(modelNoPredictionColFieldNames.exists(s =>
s.startsWith("prediction_")))
-
- // Residuals in [[LinearRegressionResults]] should equal those
manually computed
- val expectedResiduals = dataset.select("features", "label")
- .map { case Row(features: DenseVector, label: Double) =>
- val prediction =
- features(0) * model.weights(0) + features(1) * model.weights(1) +
model.intercept
- label - prediction
- }
- .zip(model.summary.residuals.map(_.getDouble(0)))
- .collect()
- .foreach { case (manualResidual: Double, resultResidual: Double) =>
- assert(manualResidual ~== resultResidual relTol 1E-5)
- }
+ Seq("l-bfgs").foreach { solver => {
+ val trainer = new LinearRegression().setSolver(solver)
+ val model = trainer.fit(dataset)
+ val trainerNoPredictionCol = trainer.setPredictionCol("")
+ val modelNoPredictionCol = trainerNoPredictionCol.fit(dataset)
+
+
+ // Training results for the model should be available
+ assert(model.hasSummary)
+ assert(modelNoPredictionCol.hasSummary)
+
+ // Schema should be a superset of the input dataset
+ assert((dataset.schema.fieldNames.toSet + "prediction").subsetOf(
+ model.summary.predictions.schema.fieldNames.toSet))
+ // Validate that we re-insert a prediction column for evaluation
+ val modelNoPredictionColFieldNames
+ = modelNoPredictionCol.summary.predictions.schema.fieldNames
+ assert((dataset.schema.fieldNames.toSet).subsetOf(
+ modelNoPredictionColFieldNames.toSet))
+ assert(modelNoPredictionColFieldNames.exists(s =>
s.startsWith("prediction_")))
+
+ // Residuals in [[LinearRegressionResults]] should equal those
manually computed
+ val expectedResiduals = dataset.select("features", "label")
+ .map { case Row(features: DenseVector, label: Double) =>
+ val prediction =
+ features(0) * model.weights(0) + features(1) * model.weights(1)
+ model.intercept
+ label - prediction
+ }
+ .zip(model.summary.residuals.map(_.getDouble(0)))
+ .collect()
+ .foreach { case (manualResidual: Double, resultResidual: Double) =>
+ assert(manualResidual ~== resultResidual relTol 1E-5)
+ }
- /*
- Use the following R code to generate model training results.
-
- predictions <- predict(fit, newx=features)
- residuals <- label - predictions
- > mean(residuals^2) # MSE
- [1] 0.009720325
- > mean(abs(residuals)) # MAD
- [1] 0.07863206
- > cor(predictions, label)^2# r^2
- [,1]
- s0 0.9998749
- */
- assert(model.summary.meanSquaredError ~== 0.00972035 relTol 1E-5)
- assert(model.summary.meanAbsoluteError ~== 0.07863206 relTol 1E-5)
- assert(model.summary.r2 ~== 0.9998749 relTol 1E-5)
-
- // Objective function should be monotonically decreasing for linear
regression
- assert(
- model.summary
- .objectiveHistory
- .sliding(2)
- .forall(x => x(0) >= x(1)))
+ /*
+ Use the following R code to generate model training results.
+
+ predictions <- predict(fit, newx=features)
+ residuals <- label - predictions
+ > mean(residuals^2) # MSE
+ [1] 0.009720325
+ > mean(abs(residuals)) # MAD
+ [1] 0.07863206
+ > cor(predictions, label)^2# r^2
+ [,1]
+ s0 0.9998749
+ */
+ assert(model.summary.meanSquaredError ~== 0.00972035 relTol 1E-5)
+ assert(model.summary.meanAbsoluteError ~== 0.07863206 relTol 1E-5)
+ assert(model.summary.r2 ~== 0.9998749 relTol 1E-5)
+
+ // Normal solver uses "WeightedLeastSquares". This algorithm does
not generate
+ // objective history because it does not run through iterations.
+ if (solver == "l-bfgs") {
+ // Objective function should be monotonically decreasing for
linear regression
+ assert(
+ model.summary
+ .objectiveHistory
+ .sliding(2)
+ .forall(x => x(0) >= x(1)))
+ }
+ }}
}
test("linear regression model testset evaluation summary") {
- val trainer = new LinearRegression
- val model = trainer.fit(dataset)
-
- // Evaluating on training dataset should yield results summary equal
to training summary
- val testSummary = model.evaluate(dataset)
- assert(model.summary.meanSquaredError ~== testSummary.meanSquaredError
relTol 1E-5)
- assert(model.summary.r2 ~== testSummary.r2 relTol 1E-5)
- model.summary.residuals.select("residuals").collect()
- .zip(testSummary.residuals.select("residuals").collect())
- .forall { case (Row(r1: Double), Row(r2: Double)) => r1 ~== r2
relTol 1E-5 }
+ Seq("auto", "l-bfgs", "normal").foreach { solver => {
+ val trainer = new LinearRegression().setSolver(solver)
+ val model = trainer.fit(dataset)
+
+ // Evaluating on training dataset should yield results summary equal
to training summary
+ val testSummary = model.evaluate(dataset)
+ assert(model.summary.meanSquaredError ~==
testSummary.meanSquaredError relTol 1E-5)
+ assert(model.summary.r2 ~== testSummary.r2 relTol 1E-5)
+ model.summary.residuals.select("residuals").collect()
+ .zip(testSummary.residuals.select("residuals").collect())
+ .forall { case (Row(r1: Double), Row(r2: Double)) => r1 ~== r2
relTol 1E-5 }
+ }}
}
test("linear regression with weighted samples"){
- val (data, weightedData) = {
- val activeData = LinearDataGenerator.generateLinearInput(
- 6.3, Array(4.7, 7.2), Array(0.9, -1.3), Array(0.7, 1.2), 500, 1,
0.1)
-
- val rnd = new Random(8392)
- val signedData = activeData.map { case p: LabeledPoint =>
- (rnd.nextGaussian() > 0.0, p)
- }
-
- val data1 = signedData.flatMap {
- case (true, p) => Iterator(p, p)
- case (false, p) => Iterator(p)
- }
-
- val weightedSignedData = signedData.flatMap {
- case (true, LabeledPoint(label, features)) =>
- Iterator(
- Instance(label, weight = 1.2, features),
- Instance(label, weight = 0.8, features)
- )
- case (false, LabeledPoint(label, features)) =>
- Iterator(
- Instance(label, weight = 0.3, features),
- Instance(label, weight = 0.1, features),
- Instance(label, weight = 0.6, features)
- )
+ Seq("auto", "l-bfgs").foreach { solver => {
--- End diff --
Can you add a simple test testing that it will match for only L2? Or just
make this test to L2 should be good for me.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
