Github user yanboliang commented on a diff in the pull request:
https://github.com/apache/spark/pull/16699#discussion_r124271108
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/regression/GeneralizedLinearRegressionSuite.scala
---
@@ -578,6 +578,79 @@ class GeneralizedLinearRegressionSuite
}
}
+ test("generalized linear regression with offset") {
+ /*
+ R code:
+ df <- as.data.frame(matrix(c(
+ 1.0, 1.0, 2.0, 0.0, 5.0,
+ 2.0, 2.0, 0.5, 1.0, 2.0,
+ 1.0, 3.0, 1.0, 2.0, 1.0,
+ 2.0, 4.0, 0.0, 3.0, 3.0), 4, 5, byrow = TRUE))
+ families <- c(gaussian, poisson, Gamma)
+ f1 <- V1 ~ -1 + V4 + V5
+ f2 <- V1 ~ V4 + V5
+ for (f in c(f1, f2)) {
+ for (fam in families) {
+ model <- glm(f, df, family = fam, weights = V2, offset = V3)
+ print(as.vector(coef(model)))
+ }
+ }
+
+ [1] 0.535040431 0.005390836
+ [1] 0.1968355 -0.2061711
+ [1] 0.307996 -0.153579
+ [1] -0.8800000 0.7342857 0.1714286
+ [1] -1.9991044 0.7247511 0.1424392
+ [1] -0.27378146 0.31599396 -0.06204946
+ */
+ val dataset = Seq(
+ OffsetInstance(1.0, 1.0, 2.0, Vectors.dense(0.0, 5.0)),
+ OffsetInstance(2.0, 2.0, 0.5, Vectors.dense(1.0, 2.0)),
+ OffsetInstance(1.0, 3.0, 1.0, Vectors.dense(2.0, 1.0)),
+ OffsetInstance(2.0, 4.0, 0.0, Vectors.dense(3.0, 3.0))
+ ).toDF()
+
+ val expected = Seq(
+ Vectors.dense(0.0, 0.535040431, 0.005390836),
+ Vectors.dense(0.0, 0.1968355, -0.2061711),
+ Vectors.dense(0.0, 0.307996, -0.153579),
+ Vectors.dense(-0.88, 0.7342857, 0.1714286),
+ Vectors.dense(-1.9991044, 0.7247511, 0.1424392),
+ Vectors.dense(-0.27378146, 0.31599396, -0.06204946))
+
+ import GeneralizedLinearRegression._
+
+ var idx = 0
+ for (fitIntercept <- Seq(false, true)) {
+ for (family <- Seq("gaussian", "poisson", "gamma")) {
+ val trainer = new GeneralizedLinearRegression().setFamily(family)
+ .setFitIntercept(fitIntercept).setOffsetCol("offset")
+ .setWeightCol("weight").setLinkPredictionCol("linkPrediction")
+ val model = trainer.fit(dataset)
+ val actual = Vectors.dense(model.intercept, model.coefficients(0),
model.coefficients(1))
+ assert(actual ~= expected(idx) absTol 1e-4, s"Model mismatch: GLM
with family = $family," +
+ s" and fitIntercept = $fitIntercept.")
+
+ val familyObj = Family.fromName(family)
+ val familyLink = new FamilyAndLink(familyObj, familyObj.defaultLink)
+ model.transform(dataset).select("features", "offset", "prediction",
"linkPrediction")
+ .collect().foreach {
+ case Row(features: DenseVector, offset: Double, prediction1:
Double,
+ linkPrediction1: Double) =>
+ val eta = BLAS.dot(features, model.coefficients) +
model.intercept + offset
+ val prediction2 = familyLink.fitted(eta)
+ val linkPrediction2 = eta
+ assert(prediction1 ~= prediction2 relTol 1E-5, "Prediction
mismatch: GLM with " +
--- End diff --
Here we use ```~=``` intentionally, since we need to handle exception
information by ourselves to make it more clear by printing out family name and
whether to fit with intercept.
---
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
