Box 1: StandardScaler

The StandardScaler assumes your data is normally distributed within each feature and will scale them such that the distribution is now centred around 0, with a standard deviation of 1.

Example:

All features are now on the same scale relative to one another.

Box 2: Min Max Scaler

Notice that the skewness of the distribution is maintained but the 3 distributions are brought into the same scale so that they overlap.

Box 3: Normalizer

Use the Convert to ARFF module in Azure Machine Learning Studio, to convert datasets and results in Azure Machine Learning to the attribute-relation file format used by the Weka toolset. This format is known as ARFF.

The ARFF data specification for Weka supports multiple machine learning tasks, including data preprocessing, classification, and feature selection. In this format, data is organized by entites and their attributes, and is contained in a single text file.

Box 1: Local web service

The Local web service compute target is used for testing/debugging. Use it for limited testing and troubleshooting. Hardware acceleration depends on use of libraries in the local system.

Box 2: Azure Kubernetes Service (AKS)

Azure Kubernetes Service (AKS) is used for Real-time inference.

Recommended for production workloads.

Use it for high-scale production deployments. Provides fast response time and autoscaling of the deployed service