Section 2: Data Ingestion, Preparation, Feature Engineering, and Pipelining
In this section, we will learn how to load and store data in Azure and how to manage this data from an Azure Machine Learning workspace. We will then investigate techniques to preprocess and visualize our data and how we can get insights from a high-dimensional dataset. From there on, we will concentrate on how to optimize our given dataset through creating and converting features and creating labels for supervised modeling. We will use this knowledge to perform advanced feature extraction for natural-language processing by using complex semantic word embeddings. Finally, we will incorporate what we learned into an automated preprocessing and training pipeline using Azure Machine Learning pipelines.
This section comprises the following chapters:
- Chapter 4, Ingesting Data and Managing Datasets
- Chapter 5, Performing Data Analysis and Visualization
- Chapter 6, Feature Engineering and Labeling...