Github user yanboliang commented on a diff in the pull request:
https://github.com/apache/spark/pull/16344#discussion_r94764683
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala
---
@@ -397,32 +432,121 @@ object GeneralizedLinearRegression extends
DefaultParamsReadable[GeneralizedLine
/** Trim the fitted value so that it will be in valid range. */
def project(mu: Double): Double = mu
+
}
private[regression] object Family {
/**
- * Gets the [[Family]] object from its name.
+ * Gets the [[Family]] object based on family and variancePower.
+ * 1) retrieve object based on family name
+ * 2) if family name is tweedie, retrieve object based on variancePower
*
- * @param name family name: "gaussian", "binomial", "poisson" or
"gamma".
+ * @param params the parameter map containing family name and variance
power
*/
- def fromName(name: String): Family = {
- name match {
- case Gaussian.name => Gaussian
- case Binomial.name => Binomial
- case Poisson.name => Poisson
- case Gamma.name => Gamma
+ def fromParams(params: GeneralizedLinearRegressionBase): Family = {
+ params.getFamily match {
+ case "gaussian" => Gaussian
+ case "binomial" => Binomial
+ case "poisson" => Poisson
+ case "gamma" => Gamma
+ case "tweedie" =>
+ params.getVariancePower match {
+ case 0.0 => Gaussian
+ case 1.0 => Poisson
+ case 2.0 => Gamma
+ case default => new Tweedie(default)
+ }
+ }
+ }
+ }
+
+ /**
+ * Tweedie exponential family distribution.
+ * This includes the special cases of Gaussian, Poisson and Gamma.
+ */
+ private[regression] class Tweedie(private val variancePower: Double)
+ extends Family("tweedie") {
+
+ /*
+ The canonical link is 1 - variancePower, which becomes Identity for
Gaussian,
+ Log for Poisson, and Inverse for Gamma. Except for these special
cases,
+ the canonical link is rarely used. For example, the canonical link
is 1/Sqrt
+ when variancePower = 1.5. We set Log as the default link, which may
be overridden
+ in subclasses.
+ */
+ override val defaultLink: Link = Log
+
+ override def initialize(y: Double, weight: Double): Double = {
+ if (variancePower >= 1.0 && variancePower < 2.0) {
+ require(y >= 0.0, s"The response variable of $name($variancePower)
family " +
+ s"should be non-negative, but got $y")
+ } else if (variancePower >= 2.0) {
+ require(y > 0.0, s"The response variable of $name($variancePower)
family " +
+ s"should be non-negative, but got $y")
--- End diff --
```y > 0.0``` means ```positive``` rather than ```non-negative```.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
