• Module 1: Get started with data science in Microsoft Fabric
  • Objective: Introduce the data science capabilities within Microsoft Fabric and understand the overall data science process.
  • Key Topics:
    • Understanding the data science process lifecycle.
    • Introduction to the data science experience in Microsoft Fabric.
    • Managing data science artifacts (notebooks, experiments, models) in Fabric.
    • Collaborating with other data professionals.
• Module 2: Explore data for data science with notebooks in Microsoft Fabric
  • Objective: Learn how to use notebooks within Microsoft Fabric for data exploration and initial analysis.
  • Key Topics:
    • Working with Fabric notebooks.
    • Loading data into notebooks from various sources (e.g., Lakehouse).
    • Understanding data distribution and summary statistics.
    • Handling missing data and outliers.
    • Applying data exploration techniques.
    • Visualizing data using charts and graphs within notebooks.
• Module 3: Preprocess data with Data Wrangler in Microsoft Fabric
  • Objective: Utilize the Data Wrangler tool in Microsoft Fabric for efficient data cleaning and transformation.
  • Key Topics:
    • Introduction to Data Wrangler and its capabilities.
    • Performing data exploration within Data Wrangler.
    • Handling missing values and errors.
    • Transforming and cleaning data using built-in operations.
    • Generating code from Data Wrangler steps.
• Module 4: Train and track machine learning models with MLflow in Microsoft Fabric
  • Objective: Learn how to train machine learning models in Fabric notebooks and track experiments using MLflow.
  • Key Topics:
    • Understanding the process of training machine learning models.
    • Using MLflow for experiment tracking, logging parameters, and metrics.
    • Managing different model runs and versions within experiments.
    • Registering and managing models in the Microsoft Fabric model registry.
• Module 5: Generate batch predictions using a deployed model in Microsoft Fabric
  • Objective: Deploy trained machine learning models and generate batch predictions on new data within Microsoft Fabric.
  • Key Topics:
    • Understanding model deployment concepts in Fabric.
    • Preparing new data for scoring.
    • Generating predictions using a deployed model.
    • Saving prediction results back to a Lakehouse or other storage.

This training is ideal for:

• Data Scientists
• Data Analysts 
• Data Engineers
• AI/ML Enthusiasts
• Business Intelligence Professionals
• Students and Career Starters in Data & AI

Participants should be familiar with basic data concepts and terminology.

Upon successful completion of the training, participants will be able to:

• Ingest and explore data using notebooks in Microsoft Fabric.
• Preprocess and clean data using Data Wrangler.
• Train and evaluate machine learning models with MLflow.
• Deploy models and generate batch predictions.
• Integrate predictive insights into business intelligence tools like Power BI.