Implement a Data Science and Machine Learning Solution for AI with Microsoft Fabric (DP-604)
1 DAY COURSE

This learning path explores the end-to-end data science process in Microsoft Fabric, from data exploration and preparation to machine learning model training and deployment. Learners gain hands-on experience using notebooks, Data Wrangler, MLflow, and Fabric-native tools to build, track, and operationalize machine learning solutions for AI-driven analytics.

Implement a Data Science and Machine Learning Solution for AI with Microsoft Fabric (DP-604) Benefits

• In this course, you will learn how to:

  • Load and manage data in a Lakehouse within Microsoft Fabric.
  • Utilize notebooks for comprehensive data exploration.
  • Preprocess data using Microsoft Fabric's Data Wrangler for optimized model training.
  • Train and manage machine learning models with MLflow, tracking experiments effectively.
  • Generate batch predictions to apply AI in practical scenarios.

• Prerequisites

  • Familiarity with basic data concepts and terminology.

DP-604 Course Outline

Learning Objectives

1. Introduction to End-to-End Analytics Using Microsoft Fabric

• Overview of Microsoft Fabric and unified analytics
• End-to-end analytics architecture
• Data teams and collaboration in Fabric
• Enabling and using Microsoft Fabric

2. Get Started with Data Science in Microsoft Fabric

• Understanding the data science lifecycle
• Exploring and processing data in Fabric
• Training and scoring models
• Hands-on: Explore data science workflows in Fabric

3. Explore Data for Data Science with Notebooks

• Using Fabric notebooks for data exploration
• Loading and analyzing datasets
• Understanding data distribution and missing values
• Applying advanced exploration techniques
• Visualizing data with charts
• Hands-on: Perform data exploration using notebooks

4. Preprocess Data with Data Wrangler

• Understanding Data Wrangler capabilities
• Performing exploratory data analysis
• Handling missing and inconsistent data
• Transforming features with operators
• Hands-on: Preprocess data for machine learning

5. Train and Track Machine Learning Models with MLflow

• Training machine learning models in notebooks
• Tracking experiments with MLflow
• Managing models in Microsoft Fabric
• Hands-on: Train and track a machine learning model

6. Generate Batch Predictions Using Deployed Models

• Customizing models for batch scoring
• Preparing data for predictions
• Generating and storing predictions in Delta tables
• Hands-on: Generate and save batch predictions