Interview Prep
Career
GenAI
Prompt Engg
ChatGPT
LLM
Langchain
RAG
AI Agents
Machine Learning
Deep Learning
GenAI Tools
LLMOps
Python
NLP
SQL
AIML Projects

Reading list

Machine Learning Basics for a Newbie
6 Steps of Machine learning Lifecycle Introduction to Predictive Modeling
Introduction to Exploratory Data Analysis & Data Insights Descriptive Statistics Inferential Statistics How to Understand Population Distributions?
Reading Data Files into Python Different Variable Datatypes
Probability for Data Science Basic Concepts of Probability Axioms of Probability Conditional Probability
Central Tendencies for Continuous Variables Spread of Data KDE plots for Continuous Variable Overview of Distribution for Continuous variables Normal Distribution Skewed Distribution Skeweness and Kurtosis Distribution for Continuous Variable
Central Tendencies for Categorical Variables Understanding Discrete Distributions Performing EDA on Categorical Variables
Dealing with Missing Values Understanding Outliers Identifying Outliers in Data Outlier Detection in Python Outliers Detection Using IQR, Z-score, LOF and DBSCAN
Sample and Population Central Limit Theorem Confidence Interval and Margin of Error
Bivariate Analysis Introduction
Covariance Pearson Correlation Spearman's Correlation & Kendall's Tau Correlation versus Causation Tabular and Graphical methods for Bivariate Analysis Performing Bivariate Analysis on Continuous-Continuous Variables
Tabular and Graphical methods for Continuous-Categorical Variables Introduction to Hypothesis Testing P-value Two sample Z-test T-test T-test vs Z-test Performing Bivariate Analysis on Continuous-Catagorical variables
Chi-Squares Test Bivariate Analysis on Categorical Categorical Variables
Multivariate Analysis A Comprehensive Guide to Data Exploration The Data Science behind IPL
Supervised Learning vs Unsupervised Learning Reinforcement Learning Generative and Descriminative Models Parametric and Non Parametric model
Machine Learning Pipeline Preparing Dataset Build a Benchmark Model: Regression Build a Benchmark Model: Classification
Evaluation Metrics for Machine Learning Everyone should know Confusion Matrix Accuracy Precision and Recall AUC-ROC Log Loss R2 and Adjusted R2
Dealing with Missing Values Replacing Missing Values Imputing Missing Values in Data Working with Categorical Variables Working with Outliers Preprocessing Data for Model Building
Understanding Cost Function Understanding Gradient Descent Math Behind Gradient Descent Assumptions of Linear Regression Implement Linear Regression from Scratch Train Linear Regression in Python Implementing Linear Regression in R Diagnosing Residual Plots in Linear Regression Models Generalized Linear Models Introduction to Logistic Regression Odds Ratio Implementing Logistic Regression from Scratch Introduction to Scikit-learn in Python Train Logistic Regression in python Multiclass using Logistic Regression How to use Multinomial and Ordinal Logistic Regression in R ? Challenges with Linear Regression Introduction to Regularisation Implementing Regularisation Ridge Regression Lasso Regression
Introduction to K Nearest Neighbours Determining the Right Value of K in KNN Implement KNN from Scratch Implement KNN in Python
Bias Variance Tradeoff Introduction to Overfitting and Underfitting Visualizing Overfitting and Underfitting Selecting the Right Model What is Validation? Hold-Out Validation Understanding K Fold Cross Validation
Introduction to Feature Selection Feature Selection Algorithms Missing Value Ratio Low Variance Filter High Correlation Filter Backward Feature Elimination Forward Feature Selection Implement Feature Selection in Python Implement Feature Selection in R
Introduction to Decision Tree Purity in Decision Tree Terminologies Related to Decision Tree How to Select Best Split Point in Decision Tree? Chi-Squares Information Gain Reduction in Variance Optimizing Performance of Decision Tree Train Decision Tree using Scikit Learn Pruning of Decision Trees
Introduction to Feature Engineering Feature Transformation Feature Scaling Feature Engineering Frequency Encoding Automated Feature Engineering: Feature Tools
Introduction to Naive Bayes Conditional Probability and Bayes Theorem Introduction to Bayesian Adjustment Rating: The Incredible Concept Behind Online Ratings! Working of Naive Bayes Math behind Naive Bayes Types of Naive Bayes Implementation of Naive Bayes
Understanding how to solve Multiclass and Multilabled Classification Problem Evaluation Metrics: Multi Class Classification
Introduction to Ensemble Techniques Basic Ensemble Techniques Implementing Basic Ensemble Techniques Finding Optimal Weights of Ensemble Learner using Neural Network Why Ensemble Models Work well?
Introduction to Stacking Implementing Stacking Variants of Stacking Implementing Variants of Stacking Introduction to Blending Bootstrap Sampling Introduction to Random Sampling Hyper-parameters of Random Forest Implementing Random Forest Out-of-Bag (OOB) Score in the Random Forest IPL Team Win Prediction Project Using Machine Learning Introduction to Boosting Gradient Boosting Algorithm Math behind GBM Implementing GBM in python Regularized Greedy Forests Extreme Gradient Boosting Implementing XGBM in python Tuning Hyperparameters of XGBoost in Python Implement XGBM in R/H2O Adaptive Boosting Implementing Adaptive Boosing LightGBM Implementing LightGBM in Python Catboost Implementing Catboost in Python
Different Hyperparameter Tuning methods Implementing Different Hyperparameter Tuning methods GridsearchCV RandomizedsearchCV Bayesian Optimization for Hyperparameter Tuning Hyperopt
Understanding SVM Algorithm SVM Kernels In-depth Intuition and Practical Implementation SVM Kernel Tricks Kernels and Hyperparameters in SVM Implementing SVM from Scratch in Python and R
Introduction to Principal Component Analysis Steps to Perform Principal Compound Analysis Computation of Covariance Matrix Finding Eigenvectors and Eigenvalues Implementing PCA in python Visualizing PCA A Brief Introduction to Linear Discriminant Analysis Introduction to Factor Analysis
Introduction to Clustering Applications of Clustering Evaluation Metrics for Clustering Understanding K-Means Implementation of K-Means in Python Implementation of K-Means in R Choosing Right Value for K Profiling Market Segments using K-Means Clustering Hierarchical Clustering Implementation of Hierarchial Clustering DBSCAN Defining Similarity between clusters Build Better and Accurate Clusters with Gaussian Mixture Models
Understand Basics of Recommendation Engine with Case Study
8 Ways to Improve Accuracy of Machine Learning Models
Introduction to Dask Working with CuML
Introduction to Machine Learning Interpretability Framework and Interpretable Models model Agnostic Methods for Interpretability Implementing Interpretable Model Understanding SHAP Out-of-Core ML Introduction to Interpretable Machine Learning Models Model Agnostic Methods for Interpretability Game Theory & Shapley Values
Introduction to Machine Learning Interpretability Framework and Interpretable Models model Agnostic Methods for Interpretability Implementing Interpretable Model Understanding SHAP Out-of-Core ML Introduction to Interpretable Machine Learning Models Model Agnostic Methods for Interpretability Game Theory & Shapley Values
Introduction to AutoML Implementation of MLBox Introduction to PyCaret TPOT Auto-Sklearn EvalML
Pickle and Joblib Introduction to Model Deployment
Deploying Machine Learning Model using Streamlit Deploying ML Models in Docker Deploy Using Streamlit Deploy on Heroku Deploy Using Netlify Introduction to Amazon Sagemaker Setting up Amazon SageMaker Using SageMaker Endpoint to Generate Inference Deploy on Microsoft Azure Cloud Introduction to Flask for Model Deploying ML model using Flask
Model Deployment in Android Model Deployment in Iphone

Deploying Machine learning Application on AWS Fargate

Deepak
Deepak Last Updated : 26 Jun, 2021
8 min read

This article was published as a part of the Data Science Blogathon

Overview

In this article, we will learn how to run/deploy containerized machine learning application on AWS Fargate, serverless service of AWS cloud

Prerequisites

  • Basic Command-Line Knowledge( I will use Linux )
  • Machine learning
  • Basic knowledge of AWS cloud and AWS cloud account
  • Docker and containerization

Note: Please refer to this article to learn about docker and how to containerize machine learning workflow. We will use the same machine learning workflow and flask app that we have built in the article.

Introduction

We have come a long way in technology, with advancements now if we need to deploy our websites or application we don’t have to worry about the infrastructure, servers, and networking management or to scale infrastructure up or down based on network traffic.

We can leverage the concept of cloud computing.

What is Cloud Computing?

Cloud Computing is the on-demand delivery of services such as computing power, servers, databases, software to users over the internet with pay-as-per-use pricing.

Now we don’t have to buy and maintain physical data centers and
servers, we can access technology services, such as computing power,
storage, and databases, on an as-needed basis from a various cloud provider like
Amazon Web Services (AWS), Cloud Cloud Platform(GCP), or Azure Cloud.

Types of Cloud Computing Models

Infrastructure as a Service (IaaS)

IaaS provides access to networking features, computers (virtual or on dedicated hardware), and data storage space. It provides flexibility and we have full control over resources. Example: AWS EC2

Platform as a Service (PaaS)

With the PaaS model, we don’t have to manage the underlying infrastructure
(usually hardware and operating systems) and can just focus on development. Example: AWS Elastic Beanstalk

Software as a Service (SaaS)

SaaS provides us with a complete product that is run and managed by the service provider. Example: Gmail

Advantages of Cloud Computing

  • Flexible access: Enables access to cloud services from anywhere over the internet
  • High availability: Ensures resource availability based on consumers requirement, enables fault tolerance
  • Flexible scaling: Enables scaling of resources to meet demand, manual or automatic resource scaling
  • Reduce IT cost: Reduces upfront capital expenditure, improves resource utilization, reduces energy and space consumption with a pay-as-per-use pricing model
  • Business continuity: Reduces the impact of downtime

AWS

Amazon Web Services(AWS) offers reliable, scalable, and cost-effective cloud computing services. It provides Infrastructure as a service(IaaS), Platform as a Service(PaaS), Software as a Service(SaaS) also a new model known as Function as a Service(FaaS) eg. AWS Lambda which is a serverless entity.

Before going further, if you don’t have an AWS account please create one to follow along with the hands-on.

Amazon Elastic Container Service(ECS)

Amazon ECS is a container orchestration platform developed by Amazon, it is similar to Kubernetes.

Amazon Elastic Container Service (ECS) helps schedule and orchestrate containers across a group of servers.

Amazon ecs | aws fargate

Source: AWS ECR

The two major ECS components are Tasks and Services.

A Task is one or more containers that are to be scheduled together by ECS.

A Service is like an Auto Scaling group for tasks. It defines the number of tasks to run across the cluster, where they should be running, automatically associates them with a load balancer, and horizontally scales based on metrics that you define like memory utilization, etc.

Another important AWS service is Elastic Container Registry(ECR), It is a registry to store, manage our container images.

What is Fargate?

AWS Fargate is a serverless compute engine for Amazon ECS that runs containers without requiring us to worrying about the underlying infrastructure. With Fargate, we specify an image present in ECR to deploy and the amount of CPU and memory it requires. Fargate handles the updating and securing of the underlying Linux OS, Docker daemon, and ECS agent as well as all the infrastructure capacity management and scaling.

Let’s get our hands working on the AWS cloud.

Steps to Deploy Application on AWS Fargate

Step1: The first step is login to your AWS management console and searches for ECR

deploy app on aws fargate

Source: Author

Step2: Click on ‘Get started’ on the landing page, it will ask you to create a repository. Fill in the details as per your need. You can create a Private or Public repository, give a repository name and click ‘Create repository’

create repository

Source: Author

Step3: Your ECR repository is ready, click on the repository radio button, and a ‘View push commands’ button will be visible

ecr repository

Source: Author

Step4: Now click on the ‘View push commands’, It will pop up the commands to upload a docker image to the Elastic container registry(ECR)

Note: You should have a docker image in place to push to ECR If not, follow my previous part to create one or have your own application docker image ready

You can check for available images using the docker images command, Here I have my app docker image ready which I want to deploy so I will push it to ECR.

docker images | aws fargate

Source: Author

Before running AWS commands we need to install AWS CLI, follow this to install it in your system.

AWS Command Line Interface(CLI) is a command-line tool to manage AWS.

instaliing aws cli

 Source: AWS

I have a Linux system, so I will use the following command to install the CLI. Refer to this blog.

commands aws fargate

Source: Author

We can check if the installation is successful or not using the ‘aws –version’ command.

Now we have to configure it with AWS account credentials to execute AWS commands. Click on your account and click on ‘My Security Credentials‘ and then click on create. The credentials will be created and you can download them.

 

credentials | aws fargate

Source: Author

Now, on the terminal run ‘aws configure command to configure your credentials, specify your credentials, and set any region and for the output format, you can press enter (or use json as the output format).

 

aws configure

Source: Author

Now we are all set to push our docker image to ECR.

Step5: Follow the commands based on the Operating system you are working on, run commands on your local terminal. If you get permission denied error executing the commands then use sudo before docker commands.

login

Source: Author

If you have already created the docker image then don’t run the build command and if not created then go to the directory where you have the Dockerfile and run the specified commands.

pushed

Source: Author

Great, we have pushed our docker image to ECR, you can verify from the console.

sentiment analysis | aws fargate

Source: Author

Copy the image URI for further reference.

Step6: Now we need to create a cluster. Check the left panel for Clusters and click on it. On the redirected page click on ‘Create Cluster’. Select ‘Networking only‘ and click next to configure the cluster. Assign a name to cluster and add tags to it (It is useful when you work in an organization to differentiate between projects and to take note of billing) and click create.

create cluster | aws fargate

Source: Author

Step7: Now we need to create ‘Task Definition’. Click on the ‘View cluster’ and on the left side you will ‘Task Definitions’ option, click on it. After that click on ‘Create new Task Definition‘ and select Fargate as launch type and click next to configure it.

view cluster

Source: Author

Now configure the Task Definition, give it a name, and now specify task Memory and CPU needed to run the task.

create new task definition
task size

Source: Author

Now click on Add container, to add the container that we have pushed to ECR. Provide a name and image URI that we have copied in the previous step and specify the port mappings to 5000 as it will allow containers to access the port on the host container to send or receive traffic. Click Add and then click Create.

 

add container

Source: Author

We can now view our ‘Task Definition‘

launch status | aws fargate

Source: Author

Step8: Click on Actions and Run Task, select launch type as Fargate 

run task

Source: Author

Select the VPC and subnet from the dropdown and click Run Task

security groups

Source: Author

Step9: Our Task is created successfully, now we need to add an inbound rule to the security group to access our application on port 5000.

Click on the created task and on the next page click on ENI Id under the Network section also note the Public IP.

cerated task | aws fargate
task

Source: Author

It will redirect to the network interface page, click on the check box, and then on the security group under the Details section.

network interface

Source: Author

Now click on Edit inbound rules and click Add rule. Add a custom TCP rule with port 5000 and source to be 0.0.0.0/0 (to make the application accessible through all IPs) and click Save rules.

edit inbound rules

Source: Author

Now we can access our application using Public IP under Network section and port 5000

app
result

Source: Author

You did a great job, so give yourself a pat on the back!!!

Note: Before Wrapping up, I want to mention an important thing, to delete all your created  AWS resources so that you don’t incur any extra cost.

First, you can stop the running Task and then delete the Cluster

stop task | aws fargate
stop cluster

Source: Author

End Notes

In this article, we have learned about Cloud Computing and AWS Cloud. How to set up AWS CLI and how to push our docker image to ECR and run our containerized application using AWS Fargate.

Reference

https://aws.amazon.com/what-is-cloud-computing/

https://aws.amazon.com/blogs/compute/building-deploying-and-operating-containerized-applications-with-aws-fargate/

 

About me

I am a Machine Learning Engineer, Solving challenging business problems through Data, Machine Learning, and Cloud.

Connect with me: Linkedin

The media shown in this article are not owned by Analytics Vidhya and are used at the Author’s discretion.

Deepak
Deepak

Free Courses

Generative AI 4.7

Generative AI - A Way of Life

Explore Generative AI for beginners: create text and images, use top AI tools, learn practical skills, and ethics.
Large Language Models 4.5

Getting Started with Large Language Models

Master Large Language Models (LLMs) with this course, offering clear guidance in NLP and model training made simple.
Prompt Engineering 4.6

Building LLM Applications using Prompt Engineering

This free course guides you on building LLM apps, mastering prompt engineering, and developing chatbots with enterprise data.
LlamaIndex 4.8

Improving Real World RAG Systems: Key Challenges & Practical Solutions

Explore practical solutions, advanced retrieval strategies, and agentic RAG systems to improve context, relevance, and accuracy in AI-driven applications.
RAG systems using LlamaIndex 4.7

Microsoft Excel: Formulas & Functions

Master MS Excel for data analysis with key formulas, functions, and LookUp tools in this comprehensive course.

Recommended Articles

Responses From Readers

Clear

Write for us

Write, captivate, and earn accolades and rewards for your work
  • Reach a Global Audience
  • Get Expert Feedback
  • Build Your Brand & Audience
  • Cash In on Your Knowledge
  • Join a Thriving Community
  • Level Up Your Data Science Game
imag

We use cookies essential for this site to function well. Please click to help us improve its usefulness with additional cookies. Learn about our use of cookies in our Privacy Policy & Cookies Policy.

Show details