[SPARK-19345][ML][DOC] Add doc for "coldStartStrategy" usage in ALS

[SPARK-14489](https://issues.apache.org/jira/browse/SPARK-14489) added the ability to skip `NaN` predictions during `ALSModel.transform`. This PR adds documentation for the `coldStartStrategy` param to the ALS user guide, and add code to the examples to illustrate usage.

## How was this patch tested?

Doc and example change only. Build HTML doc locally and verified example code builds, and runs in shell for Scala/Python.

Author: Nick Pentreath <nickp@za.ibm.com>

Closes #17102 from MLnick/SPARK-19345-coldstart-doc.

3 files changed, 7 insertions, 1 deletions

diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaALSExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaALSExample.java
index 33ba668b32..81970b7c81 100644
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaALSExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaALSExample.java
@@ -103,6 +103,8 @@ public class JavaALSExample {
     ALSModel model = als.fit(training);
 
     // Evaluate the model by computing the RMSE on the test data
+    // Note we set cold start strategy to 'drop' to ensure we don't get NaN evaluation metrics
+    model.setColdStartStrategy("drop");
     Dataset<Row> predictions = model.transform(test);
 
     RegressionEvaluator evaluator = new RegressionEvaluator()
diff --git a/examples/src/main/python/ml/als_example.py b/examples/src/main/python/ml/als_example.py
index 1a979ff5b5..2e7214ed56 100644
--- a/examples/src/main/python/ml/als_example.py
+++ b/examples/src/main/python/ml/als_example.py
@@ -44,7 +44,9 @@ if __name__ == "__main__":
     (training, test) = ratings.randomSplit([0.8, 0.2])
 
     # Build the recommendation model using ALS on the training data
-    als = ALS(maxIter=5, regParam=0.01, userCol="userId", itemCol="movieId", ratingCol="rating")
+    # Note we set cold start strategy to 'drop' to ensure we don't get NaN evaluation metrics
+    als = ALS(maxIter=5, regParam=0.01, userCol="userId", itemCol="movieId", ratingCol="rating",
+              coldStartStrategy="drop")
     model = als.fit(training)
 
     # Evaluate the model by computing the RMSE on the test data
diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/ALSExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/ALSExample.scala
index bb5d163608..868f49b16f 100644
--- a/examples/src/main/scala/org/apache/spark/examples/ml/ALSExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/ALSExample.scala
@@ -65,6 +65,8 @@ object ALSExample {
     val model = als.fit(training)
 
     // Evaluate the model by computing the RMSE on the test data
+    // Note we set cold start strategy to 'drop' to ensure we don't get NaN evaluation metrics
+    model.setColdStartStrategy("drop")
     val predictions = model.transform(test)
 
     val evaluator = new RegressionEvaluator()