FRCAWS-23AWS

Practical Data Science with Amazon SageMaker

Name: Practical Data Science with Amazon SageMaker
Price: 650.00 USD
Availability: InStock

Duration · 1 dayVirtual + In-PersonInstructor-Led

$650

Course Description

This one-day instructor-led course provides hands-on experience using Amazon SageMaker to perform practical data science workflows, including data preparation, exploratory data analysis, feature engineering, model training, tuning, deployment, and evaluation. Participants learn how to accelerate machine learning development using managed AWS services and industry best practices.

— Be First in Line —

Register Your Interest

We're finalizing the schedule for Practical Data Science with Amazon SageMaker. Add your details below and we'll notify you the moment a session opens for registration — no payment or commitment required.

Audience Profile

This course is intended for:

Data Scientists
Machine Learning Engineers
Data Analysts
AI Developers
Software Developers
Cloud Engineers
Technical Professionals transitioning into machine learning

Prerequisites

Before enrolling, you should have:

Basic understanding of machine learning concepts
Familiarity with Python programming
Basic knowledge of statistics and data analysis
General understanding of AWS core services
Experience working with datasets is recommended

— What You'll Learn —

Learning Objectives

In this course, you will learn to:

1Navigate and use Amazon SageMaker Studio
2Prepare and transform data for machine learning
3Perform exploratory data analysis (EDA)
4Build and train machine learning models
5Optimize models using hyperparameter tuning
6Evaluate model performance using industry metrics
7Deploy models for real-time and batch inference
8Monitor and manage machine learning workflows on AWS
9Apply practical MLOps and operational ML concepts

— Day-by-Day —

Course Outline

Module 1

Introduction to Practical Data Science on AWS

Topics

Introduction to data science workflows
Machine learning lifecycle overview
Overview of Amazon SageMaker
Benefits of managed ML services
Understanding SageMaker Studio
AWS AI/ML ecosystem overview
Practical use cases for machine learning
AWS Services Covered
Amazon SageMaker Studio
Amazon S3
AWS IAM

Hands-On Lab

Access and configure SageMaker Studio
Create notebook environments
Upload datasets into Amazon S3

Module 2

Data Preparation and Exploratory Data Analysis

Topics

Importing and accessing datasets
Data cleansing and preprocessing
Handling missing and inconsistent data
Exploratory Data Analysis (EDA)
Data visualization techniques
Feature identification and transformation
Preparing training and validation datasets
AWS Services Covered
SageMaker Data Wrangler
Amazon Athena
Amazon S3

Hands-On Lab

Import and analyze datasets
Perform data cleansing operations
Visualize and transform data using SageMaker tools

Module 3

Feature Engineering and Model Training

Topics

Feature engineering strategies
Selecting features for machine learning
Understanding supervised learning workflows
Training machine learning models in SageMaker
Built-in algorithms overview
Using XGBoost for predictive modeling
Configuring SageMaker training jobs
AWS Services Covered
SageMaker Training Jobs
SageMaker Processing
SageMaker Feature Store

Hands-On Lab

Engineer features for a predictive model
Train a machine learning model
Analyze training metrics and outputs

Module 4

Model Optimization and Evaluation

Topics

Model evaluation fundamentals
Accuracy, precision, recall, and F1-score
Confusion matrices and validation strategies
Hyperparameter optimization techniques
Avoiding overfitting and underfitting
Comparing model performance
AWS Services Covered
SageMaker Automatic Model Tuning
SageMaker Experiments

Hands-On Lab

Perform automated hyperparameter tuning
Compare and evaluate model performance results

Module 5

Deploying and Using Machine Learning Models

Topics

Real-time inference concepts
Batch inference concepts
Deploying models to SageMaker endpoints
Scaling and securing inference workloads
Monitoring deployed models
Introduction to model drift concepts
AWS Services Covered
SageMaker Endpoints
SageMaker Batch Transform
Amazon CloudWatch

Hands-On Lab

Deploy a model endpoint
Generate predictions using real-time inference
Perform batch prediction jobs

Module 6

End-to-End Practical Data Science Workflow

Topics

Building repeatable ML workflows
Managing experiments and artifacts
Introduction to MLOps concepts
Cost optimization for ML workloads
Operational best practices for SageMaker
Governance and security considerations
Capstone Hands-On Lab
Participants complete a practical machine learning workflow that includes:
Data ingestion
Data preparation
Feature engineering
Model training
Hyperparameter tuning
Model deployment
Prediction validation
Course Wrap-Up
Final Review
Review of key data science workflows
AWS best practices for machine learning
Common implementation challenges
Production deployment considerations
Knowledge Validation
Practical lab review
Interactive Q&A
Scenario-based discussions
Next Steps
Advanced SageMaker learning paths
MLOps and production ML training recommendations
AWS certification pathways
AWS Services Covered
Amazon SageMaker Studio
SageMaker Data Wrangler
SageMaker Training Jobs
SageMaker Feature Store
SageMaker Processing
SageMaker Automatic Model Tuning
SageMaker Experiments
SageMaker Endpoints
SageMaker Batch Transform
Amazon S3
Amazon Athena
AWS IAM
Amazon CloudWatch

Note: Course outlines are provided as a general guide. Content, pacing, labs, and instructional emphasis may vary based on instructor expertise, student experience levels, and customer-specific learning objectives.

— Keep Exploring —

Need a different angle?

Browse the full AWS catalog or chat with an advisor about a custom training plan for your team.