In continuation of my earlier blog post related to Azure ML studio, I would like to describe some additional components that can be used while setting up an experiment. One of the main components available in the Experiment designer is called Statistical functions. This section has a set of multiple functions to choose from, they range from Elementary Statistics to Hypothesis testing. These components would typically used once the dataset has been cleansed to an extent so that one can accurate readings of the data from the experiment. Please see the image below. In this example after executing an R-Script the output is fed to an Descriptive Statistics module.
The Descriptive statistics module typically can include Counts, Range, Statistical Summaries and Percentiles. Once the descriptive statistics is completed, the output can be stored on a variety of formats and this is provided by the writer component. Please see the image below. The Data destination can be
Azure (SQL Database, blob storage, table), Hive Query. Each format has its own advantages and for more info, one can refer to the link here:
https://msdn.microsoft.com/library/azure/7a391181-b6a7-4ad4-b82d-e419c0d6522c
No comments:
Post a Comment