"This course, Feature Engineering - Locales, is intended for non-English learners. If you want to take this course in English, please enroll in Feature Engineering." Want to know about Vertex AI Feature Store? Want to know how you can improve the accuracy of your ML models? What about how to find which data columns make the most useful features? Welcome to Feature Engineering, where we discuss good versus bad features and how you can preprocess and transform them for optimal use in your models. This course includes content and labs on feature engineering using BigQuery ML, Keras, and TensorFlow
Overview
Syllabus
- Introduction
- Course introduction
- Introduction to Vertex AI Feature Store
- Introduction
- Feature Store benefits
- Feature Store terminology and concepts
- The Feature Store data model
- Creating a Feature Store
- Serving features: Batch and online
- (Optional) Lab intro: Using Feature Store
- Using Feature Store
- Quiz: Introduction to Vertex AI Feature Store
- Raw Data to Features
- Introduction
- Overview of feature engineering
- Raw data to features
- Good features versus bad features
- Features should be known at prediction-time
- Features should be numeric
- Features should have enough examples
- Bringing human insight
- Representing features
- Quiz: Raw Data to Features
- Feature Engineering
- Introduction
- Machine learning versus statistics
- Basic feature engineering
- Lab intro: Performing Basic Feature Engineering in BigQuery ML
- Performing Basic Feature Engineering in BQML
- Advanced feature engineering: Feature crosses
- Bucketize and Transform Functions
- (Optional) Lab intro: Advanced Feature Engineering BigQuery ML
- Performing Advanced Feature Engineering in BQML
- Predict housing prices
- Estimate taxi fare
- Temporal and geolocation features
- Lab intro: Basic Feature Engineering in Keras
- Performing Basic Feature Engineering in Keras
- Lab intro: Advanced Feature Engineering in Keras
- Performing Advanced Feature Engineering in Keras
- Quiz: Feature Engineering
- Preprocessing and Feature Creation
- Introduction
- Apache Beam and Dataflow
- Dataflow terms and concepts
- Quiz: Preprocessing and Feature Creation
- Feature Crosses - TensorFlow Playground
- Introduction
- What is a feature cross
- Discretization
- Lab intro: TensorFlow Playground: Use feature crosses to create a good classifier
- Lab intro: TensorFlow Playground: Too much of a good thing
- Quiz: Feature Crosses - TensorFlow Playground
- Introduction to TensorFlow Transform
- Introduction
- TensorFlow Transform
- Analyze phase
- Transform phase
- Supporting serving
- Lab Intro: Exploring tf.transform
- Exploring tf.transform
- Quiz: Introduction to TensorFlow Transform
- Summary
- Summary
- Resource: All quiz questions
- Resource: All readings
- Resource: All slides
