Merge pull request #21034 from v-rajagt/dacoelho

Link fixed.

Author: PRMerger12

docs/big-data-cluster/spark-create-machine-learning-model.md

@@ -56,12 +56,12 @@ The data is first read into Spark and split into training and testing data sets.
 
 ## Model scoring with SQL Server
 
-Now that the Spark ML pipeline model is in a common serialization [MLeap bundle](http://mleap-docs.combust.ml/core-concepts/mleap-bundles.html) format, you can score the model in Java without the presence of Spark.
+Now that the Spark ML pipeline model is in a common serialization [MLeap bundle](https://github.com/combust/mleap-docs/blob/master/core-concepts/mleap-bundles.md) format, you can score the model in Java without the presence of Spark.
 
 This sample uses the [Java Language Extension](../language-extensions/language-extensions-overview.md) in SQL Server. In order to score the model in SQL Server, you first need to build a Java application that can load the model into Java and score it. You can find the sample code for this Java application in the [mssql-mleap-app folder](https://github.com/microsoft/sql-server-samples/blob/master/samples/features/sql-big-data-cluster/spark/sparkml/mssql-mleap-app).
 
 After building the sample, you can use Transact-SQL to call the Java application and score the model with a database table. This can be seen in thee [mleap_sql_test/mleap_sql_tests.py](https://github.com/microsoft/sql-server-samples/blob/master/samples/features/sql-big-data-cluster/spark/sparkml/mleap_sql_test/mleap_sql_tests.py) source file.
 
 ## Next steps
 
-For more information about big data clusters, see [How to deploy [!INCLUDE[big-data-clusters-2019](../includes/ssbigdataclusters-ss-nover.md)] on Kubernetes](deployment-guidance.md)
+For more information about big data clusters, see [How to deploy [!INCLUDE[big-data-clusters-2019](../includes/ssbigdataclusters-ss-nover.md)] on Kubernetes](deployment-guidance.md)