Official Google Cloud Certified Professional Machine Learning Engineer Study Guide

Chapter 3Feature Engineering

GOOGLE CLOUD PROFESSIONAL MACHINE LEARNING ENGINEER EXAM OBJECTIVES COVERED IN THIS CHAPTER:

• 2.1 Exploring and preprocessing organization‐wide data (e.g., Cloud Storage, BigQuery, Cloud Spanner, Cloud SQL, Apache Spark, Apache Hadoop). Considerations include:
  • Data preprocessing (e.g., Dataflow, TensorFlow Extended [TFX], BigQuery)
• 5.1 Developing end‐to‐end ML pipelines. Considerations include:
  • Data and model validation
  • Ensuring consistent data pre‐processing between training and serving

In the previous chapter, we discussed why it's important to have quality data. We covered some of the ways to get quality data such as removing missing values, removing outliers, and using data normalization. In this chapter, we will cover feature‐engineering techniques. We will also cover encoded structured data type, class imbalance, feature cross, and TensorFlow Transform to perform feature engineering.

Feature engineering is the process of transforming raw data coming from various sources such as log files and weather readings to useful features for model training. The features can be numerical or categorical. Let's understand the primary reasons for data transformation.

• Transforming for Data Compatibility Data consists of both numeric features ...