- Overview of a use case - Sentiment analysis
- Introduction - Using Jupyter Notebook & AWS SageMaker
- Setup New Project
- Setup and Run the Build CI/CD Pipeline
- Setup the Release Pipeline
- Test Build and Release Pipelines
- Testing the deployed solution
- Examining deployed model performance
3. Varun Kumar
Senior Consultant,
Cloud Engineering
Background
Varun Kumar is a Senior Consultant with Deloitte SEA & AWS APN Ambassador. He is a
cloud professional over 8 plus years of diversified experience in DevOps.
• Varun is also a Research Scholar, published three research papers, including IEEE. His
research area & topic was virtualization and Hypervisors.
• He is a Technical Blogger, wrote many blogs about AWS cloud, DevOps. DevSecOps,
MLOps and in general cloud computing topics.
• He is a professional cloud trainer, delivered many training across the globe and share
his knowledge toward community which includes collage students, fresher's and
Corporate professionals.
Please find more details:
• https://www.linkedin.com/in/vkmanik/
• https://medium.com/@varunmanik1
• https://www.facebook.com/cloudvirtualization/
• https://twitter.com/varunkmanik/
• https://www.youtube.com/channel/UCcuMPYJ4Osax4528rgqQWrw
4. Qualifications and Professional Affiliations
Qualification:
• Master Degree in Computer Science.
Professional Certificate:
• AWS Certified Solutions Architect - Professional
• AWS Certified Developer – Associate
• AWS Certified SysOps - Associate
• AWS Certified Solution Architect – Associate
• AWS Certified Practitioner
• Red Hat Certificate of Expertise in Ansible Automation
5. Notable Recent Experiences
• Cloud migration lead at a large media company based in South East Asia, providing ongoing
consulting, improvement feedback, and cloud expertise to this team for implementation of
DevOps practices and migration of their CRM/billing systems to cloud.
• Building DevOps, DevSecOps, MLOps capabilities and Automation labs within the organization
by implementing various tools for Continuous Integration (CI), Continuous Deployment (CD)
and Continuous Assessment (CA) for multiple accounts.
• Lead the automation team, Automate daily Cloud tasks in DevOps Tools, Create & configure
automation of AWS resources with DevOps best practice to enhance the CICD (Continuous
Integration and Continuous Delivery) process for the organization.
• Built the DevOps, DevSecOps, DevFinOps practice within the organization and enabled a
DevOps champion in every product team, leading to cohesive standards and capabilities in
these areas.
6. Index
- Introduction of Machine learning
• Using Jupyter Notebook 15 min
• AWS SageMaker 15 min
• Sentiment analysis 15 min
• Break 10 min
- Overview of a Use case
• Model Deployment 15 min
• Examining deployed model performance 10 min
- Setup New Project Copilot
• Setup and Run the Build CI/CD Pipeline 15 min
• Setup the Release Pipeline 15 min
• Break 10 min
• Test Build and Release Pipelines 15 min
• Testing the deployed solution 15 min
7. What is ML….?
• What are the different types in machine learning?
• What are the different algorithms available for developing machine learning models?
• What tools are available for developing these models?
• What are the programming language choices?
• What platforms support development and deployment of Machine Learning applications?
• How to quickly upgrade your skills in this important area?
8. Applications of Machines Learning
Machine Learning is the most rapidly growing technology and according to researchers we are in the
golden year of AI and ML. It is used to solve many real-world complex problems which cannot be
solved with traditional approach. Following are some real-world applications of ML −
• Emotion analysis
• Sentiment analysis
• Error detection and prevention
9. Applications of Machines Learning
• Weather forecasting and prediction
• Stock market analysis and forecasting
• Speech synthesis
• Speech recognition
• Customer segmentation
• Object recognition
• Fraud detection
• Fraud prevention
• Recommendation of products to customer in online shopping
10. Types of Machine Learning
Machine Learning
Supervised
Learning
Unsupervised
Learning
Reinforcement
Learning
Deep Learning
Deep Reinforcement
Learning
11. Algorithms for Supervised Learning
There are several algorithms available for supervised learning. Some of the widely used algorithms of
supervised learning are as shown below :
• k-Nearest Neighbours
• Decision Trees
• Naive Bayes
• Logistic Regression
• Support Vector Machine
12. Sentiment Analysis by Amazon Comprehend
Analyze text in real time by using built-in or custom models. With built-in models, you can recognize
entities, extract key phrases, detect dominant languages, detect PII, determine sentiment, or analyze
syntax. With custom models, you can detect entities that you define, or you can classify documents
using your own categories or labels.
16. AWS Sagemaker
SageMaker Studio, a machine learning Integrated Development Environment (IDE) for building, training, and
debugging models, tracking experiments, deploying models, and monitoring their performance.
18. SageMaker Benefits and features
• Labeling raw data with active learning
• Highly accurate training datasets
• Fully-managed notebook instances
• Highly-optimized machine learning algorithms
• One-click training
• Deployment without engineering effort
21. Jupyter Notebook
• Jupyter Lab
• Note book Creation
• File Option
• Code vs Markdown
• File Upload down load
22. Machine Learning Use case
• Machine Learning (and in mathematics) there are often three values that interests us:
Mean - The average value
Median - The mid point value
Mode - The most common value
• Random Data Distributions
• Linear Regression
• Polynomial Regression
25. Deep Learning uses ANN
Applications
Deep Learning has shown a lot of success in several areas of machine learning applications.
Self-driving Cars − The autonomous self-driving cars use deep learning techniques. They generally adapt to
the ever changing traffic situations and get better and better at driving over a period of time.
Speech Recognition − Another interesting application of Deep Learning is speech recognition. All of us use
several mobile apps today that are capable of recognizing our speech. Apple’s Siri, Amazon’s Alexa, Microsoft’s
Cortena and Google’s Assistant – all these use deep learning techniques.
Mobile Apps − We use several web-based and mobile apps for organizing our photos. Face detection, face ID,
face tagging, identifying objects in an image – all these use deep learning.
26. ML Platform & tools
Language Choice
• Python
• R
• Matlab
• Octave
• Julia
• C++
• C
IDEs
• AWS Sagemaker
• R Studio
• Pycharm
• iPython/Jupyter Notebook
• Julia
• Spyder
• Anaconda
• Rodeo
• Google –Colab
Platforms
• Amazon
• IBM
• Microsoft Azure
• Google Cloud
• Mlflow
30. What is Copilot…?
• The AWS Copilot command-line interface (CLI) provides application-first, high-level commands to simplify
modeling, creating, releasing, and managing production-ready containerized applications on Amazon ECS
from a local development environment.
• Provisioned with application templates, infrastructure as code, and CI/CD pipeline options, the AWS
Copilot CLI aligns with application workflows that support modern application best practices.
36. Services
• Creating a Service
• Choosing a Service Type
• Load Balanced Web
Service
• Backend Service
• Config and the Manifest
• Deploying a Service
• Digging into your Service
• What's in your service?
• What's your service
status?
• Where are my service
37. Environment
• Creating an Environment
• Deploying a Service
• Environment Infrastructure
• VPC and Networking
• Load Balancers and DNS
• Customize your Environment
• Digging into your Environment
• What's in your environment?
38. Application
• Creating an App
• Additional App Configurations
• App Infrastructure
• ECR Repositories
• Release Infrastructure
• Digging into your App
• What's in my application?
40. Pipeline
• Pipeline structure
• GitHub Source
• Build Stage
• Deploy Stages
• Creating a Pipeline in 3 steps
• Preparing the pipeline structure.
• Committing the generated buildspec.yml.
• Creating the actual CodePipeline.
41.
42. Final Deployment Test and Validation
1. Push the new version of code in code
commit
2. It will automatically deploy the new
task with new version
3. At last you can run the DNS ALB on
your browser