A common requirement when creating a data model is to transform the data after it is loaded from the source and before it is loaded into the data model. For example, you may need to group, pivot, replace, or expand the data. In a traditional data warehouse implementation this is performed using an ETL (Extraction, Transform and Load) tool such as SQL Server Integration Server (SSIS). While SSIS is a great tool for developers it is not meant for Business Analysts implementing self-service BI. To enable self-service ETL Microsoft has created a great tool – Power Query. Power Query lets the user create robust transformations using an intuitive interface and then loading the results into a Power Pivot Model. This session guides you through the process of using Power Query to extract, transform and load data into your data model from a variety of sources.
While Machine Learning is not new, it has never been easy to implement. Azure Machine Learning (AML) aims to provide a set of tools that are easier to use and once a model is created easier to consume by client applications. At the core of AML is ML Studio. ML Studio provides an easy to use graphical tool that allows you to control the process from pre-processing the data, to applying learning algorithms, testing the model, and finally deploying the model for use by client applications. This session guides you through the process of creating and deploying a ML model. In addition it will demonstrate how client applications can easily use the model once it is deployed.