Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/16699#discussion_r100574976
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/regression/GeneralizedLinearRegressionSuite.scala
---
@@ -798,77 +798,160 @@ class GeneralizedLinearRegressionSuite
}
}
- test("glm summary: gaussian family with weight") {
+ test("generalized linear regression with offset") {
/*
- R code:
+ R code:
+ library(statmod)
- A <- matrix(c(0, 1, 2, 3, 5, 7, 11, 13), 4, 2)
- b <- c(17, 19, 23, 29)
- w <- c(1, 2, 3, 4)
- df <- as.data.frame(cbind(A, b))
- */
- val datasetWithWeight = Seq(
- Instance(17.0, 1.0, Vectors.dense(0.0, 5.0).toSparse),
- Instance(19.0, 2.0, Vectors.dense(1.0, 7.0)),
- Instance(23.0, 3.0, Vectors.dense(2.0, 11.0)),
- Instance(29.0, 4.0, Vectors.dense(3.0, 13.0))
+ df <- as.data.frame(matrix(c(
+ 0.2, 1.0, 2.0, 0.0, 5.0,
+ 0.5, 2.1, 0.5, 1.0, 2.0,
+ 0.9, 0.4, 1.0, 2.0, 1.0,
+ 0.7, 0.7, 0.0, 3.0, 3.0), 4, 5, byrow = TRUE))
+ families <- list(gaussian, binomial, poisson, Gamma, tweedie(1.5))
+ 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] 0.5169222 -0.3344444
+ [1] 0.9419107 -0.6864404
+ [1] 0.1812436 -0.6568422
+ [1] -0.2869094 0.7857710
+ [1] 0.1055254 0.2979113
+ [1] -0.05990345 0.53188982 -0.32118415
+ [1] -0.2147117 0.9911750 -0.6356096
+ [1] -1.5616130 0.6646470 -0.3192581
+ [1] 0.3390397 -0.3406099 0.6870259
+ [1] 0.3665034 0.1039416 0.1484616
+ */
+ val dataset = Seq(
+ OffsetInstance(0.2, 1.0, 2.0, Vectors.dense(0.0, 5.0)),
+ OffsetInstance(0.5, 2.1, 0.5, Vectors.dense(1.0, 2.0)),
+ OffsetInstance(0.9, 0.4, 1.0, Vectors.dense(2.0, 1.0)),
+ OffsetInstance(0.7, 0.7, 0.0, Vectors.dense(3.0, 3.0))
).toDF()
+
+ val expected = Seq(
+ Vectors.dense(0, 0.5169222, -0.3344444),
+ Vectors.dense(0, 0.9419107, -0.6864404),
+ Vectors.dense(0, 0.1812436, -0.6568422),
+ Vectors.dense(0, -0.2869094, 0.785771),
+ Vectors.dense(0, 0.1055254, 0.2979113),
+ Vectors.dense(-0.05990345, 0.53188982, -0.32118415),
+ Vectors.dense(-0.2147117, 0.991175, -0.6356096),
+ Vectors.dense(-1.561613, 0.664647, -0.3192581),
+ Vectors.dense(0.3390397, -0.3406099, 0.6870259),
+ Vectors.dense(0.3665034, 0.1039416, 0.1484616))
+
+ import GeneralizedLinearRegression._
+
+ var idx = 0
+
+ for (fitIntercept <- Seq(false, true)) {
+ for (family <- Seq("gaussian", "binomial", "poisson", "gamma",
"tweedie")) {
--- End diff --
What do you think about changing this to:
`for (family <- GeneralizedLinearRegression.supportedFamilyNames)` ?
That way we are being sure that we include all the families. I realize that
this would break the ordering and therefore require changing up some of the
code. I'd be quite alright doing that in a different PR.
---
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
