From the course: Advanced Data Processing: Batch, Real-Time, and Cloud Architectures for AI
Join today to access over 24,900 courses taught by industry experts.
Feature engineering
From the course: Advanced Data Processing: Batch, Real-Time, and Cloud Architectures for AI
Feature engineering
- [Instructor] Let's dive deeper into feature engineering functions in LM in this video. What is feature engineering? Raw input for machine learning is acquired from various source systems. Feature engineering is the process of cleansing, extracting, and transforming such raw data to a form that is suitable for machine learning and inference. It is a crucial piece of the puzzle that can determine the success or failure of the ML process. There are several tasks that may be performed in feature engineering. A single feature engineering pipeline may implement one or more of these tasks. We begin with data cleansing tasks. What are the popular data cleansing tasks? Quality checks ensure that the incoming data meets the requirements for the use case. This is especially needed when the data is acquired from external sources that are not trusted. Deduplication eliminates duplicate data from the datasets. Missing values pmputation provides replacement values for attributes when they are…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.
