Skip to main content

Data Preparation for Machine Learning

This course teaches the fundamentals of preparing data for traditional machine learning on Databricks. Learners load data into Delta tables governed by Unity Catalog and explore it with notebooks, built-in visualizations, and Genie Code. They then clean data, handle missing values and outliers, split and sample it without data leakage, and build reproducible Spark ML pipelines for imputation, encoding, and standardization. Finally, they store, govern, and reuse features with Feature Engineering in Unity Catalog. This includes point-in-time lookups for leakage-free training sets and an introduction to online feature serving with Lakebase-backed Online Feature Stores. Each module combines lectures with hands-on demos and a lab that run on serverless compute. Model training, serving, and monitoring are not covered; they are taught in the Machine Learning Model Development and Machine Learning Model Deployment courses. This course is designed for associate-level data scientists and machine learning practitioners who want a solid foundation in data preparation on Databricks.


Languages Available: English | 日本語 | Português BR | 한국어

Skill Level
Associate
Duration
4h
Prerequisites

In this course, the content was developed for participants with these skills/knowledge/abilities: 

• Databricks basics. Completion of Get Started with Databricks for Machine Learning, or equivalent experience.

    - Learners should be able to navigate the workspace, create and run notebooks, and attach a notebook to compute, including serverless compute. They should also understand the basic machine learning workflow on Databricks.

• Intermediate Python.

    - Learners should be comfortable writing Python for data manipulation. Experience with pandas is useful. Basic familiarity with PySpark DataFrames is helpful but not required, because the course uses Spark DataFrames and Spark ML for all distributed work.

• Basic SQL.

    - Learners should be able to read and write simple SELECT, CREATE TABLE, and GRANT statements. Several demos and labs use SQL cells.

• Machine learning fundamentals.

    - Learners should be familiar with features and labels, training, validation, and test sets, and the idea of data leakage. Model training itself is not taught in this course.

• Data formats and lakehouse concepts.

    - Learners should be familiar with common formats such as CSV, JSON, and Parquet, and have introductory knowledge of Delta Lake and the lakehouse architecture.

• Exploratory data analysis and basic statistics.

    - Learners should understand distributions, mean, median, and standard deviation, missing values, outliers, and simple charts used to assess data quality.

Outline

Managing and Exploring Data

• Managing and Exploring Data

• Demo: Load and Explore Data

• Lab: Load and Explore Data


Data Preparation and Feature Engineering

• Fundamentals of Data Preparation and Feature Engineering

• Data Imputation

• Data Encoding

• Data Standardization

• Demo: Data Imputation and Transformation Pipeline

• Demo: Build a Feature Engineering Pipeline with Embeddings

• Lab: Build a Feature Engineering Pipeline


Feature Store

• Introduction to Feature Store

• Demo: Using Feature Store for Feature Engineering

• Lab: Feature Engineering with Feature Store


Upcoming Public Classes

Date
Time
Your Local Time
Language
Price
Dec 01
09 AM - 01 PM (America/New_York)
-
English
$750.00
Jan 05
09 AM - 01 PM (Asia/Singapore)
-
English
$750.00
Jan 05
09 AM - 01 PM (Europe/Paris)
-
English
$750.00
Jan 05
01 PM - 05 PM (America/New_York)
-
English
$750.00

Public Class Registration

If your company has purchased success credits or has a learning subscription, please fill out the Training Request form. Otherwise, you can register below.

Private Class Request

If your company is interested in private training, please submit a request.

See all our registration options

Registration options

Databricks has a delivery method for wherever you are on your learning journey

Runtime

Self-Paced

Custom-fit learning paths for data, analytics, and AI roles and career paths through on-demand videos

Register now

Instructors

Instructor-Led

Public and private courses taught by expert instructors across half-day to two-day courses

Register now

Learning

Blended Learning

Self-paced and weekly instructor-led sessions for every style of learner to optimize course completion and knowledge retention. Go to Subscriptions Catalog tab to purchase

Purchase now

Scale

Skills@Scale

Comprehensive training offering for large scale customers that includes learning elements for every style of learning. Inquire with your account executive for details

Upcoming Public Classes

Questions?

If you have any questions, please refer to our Frequently Asked Questions page.