Machine Learning Model Deployment with Streamlit

Focused View

Marco Peixeiro

7:13:23

28 View

1. Introduction to Streamlit

1. Welcome!.html

2. Installation and setup.mp4

03:35

3. Overview of Streamlit and its features.mp4

04:11

4.1 Source code on GitHub.html

4. Creating a basic Streamlit app.mp4

05:40

2. Streamlit fundamentals

1.1 Source code on GitHub.html

1. Text elements in Streamlit.mp4

09:08

2.1 Source code on GitHub.html

2. Data display elements.mp4

07:40

3.1 Source code on GitHub.html

3. Charting elements.mp4

09:44

4.1 Source code on GitHub.html

4. Input widgets - Part 1.mp4

09:36

5.1 Source code on GitHub.html

5. Input widgets - Part 2.mp4

12:12

6.1 Source code on GitHub.html

6. Forms in Streamlit.mp4

11:14

7.1 Source code on GitHub.html

7. Customize the layout.mp4

11:25

8.1 Starter file on GitHub.html

8. Capstone project - Build an interactive dashboard.mp4

07:06

9.1 Source code on GitHub.html

9. Capstone project - Build an interactive dashboard - Solution.mp4

28:13

3. Caching

1. Basics of caching in Streamlit.mp4

03:42

2.1 Source code on GitHub.html

2. Code - Basics of caching.mp4

09:19

3.1 Source code on GitHub.html

3. Refactor our dashboard with caching.mp4

10:09

4. Advanced caching in Streamlit.mp4

06:58

5.1 Source code on GitHub.html

5. Capstone project - Deploy a classification model with caching.mp4

19:20

6.1 Source code on GitHub.html

6. Improving our last capstone.mp4

10:14

4. Session state management

1. Basics of state mangement.mp4

03:56

2.1 Source code on GitHub.html

2. Code - State management.mp4

07:13

3. Advanced state management.mp4

04:42

4.1 Source code on GitHub.html

4. Code - Advanced state management.mp4

14:56

5.1 Source code on GitHub.html

5. Build a temperature conversion calculator.mp4

18:36

6.1 Source code on GitHub.html

6. Capstone project - Deploy a regression model with state management.mp4

20:14

5. Multipage applications

1. Basics of multipage applications.mp4

04:21

2.1 Source code on GitHub.html

2. Code - Build your first multipage app.mp4

11:36

3. Widget state mangement in multipage apps.mp4

01:55

4.1 Source code on GitHub.html

4. Code - Implement a workaround for multipage apps.mp4

06:44

5.1 Source code on GitHub.html

5. Capstone project - Train and rank different classification models.mp4

25:06

6. Authentication

1. Basic authentication.mp4

01:34

2.1 Source code on GitHub.html

2. Code - Basic authentication.mp4

14:15

3. Streamlit-Authenticator.mp4

02:07

4.1 Source code on GitHub.html

4. Code - Streamlit-Authenticator.mp4

13:35

5.1 Source code on GitHub.html

5. Capstone project - Clustering for a marketing campaign.mp4

19:42

7. Connect to data sources

1. Connect to data sources.mp4

03:20

2.1 Source code on GitHub.html

2. Code - Connect to a database (Supabase).mp4

17:24

3.1 Source code on GitHub.html

3. Code - Make API calls.mp4

14:39

4.1 Article - Forecasting Intermittent Time Series in Python.html

4.2 Source code on GitHub.html

4. Capstone project - Deploy a demand forecasting model.mp4

14:13

8. Deploy to production

1. Deployment process.mp4

04:59

2. Deploy a Streamlit app.mp4

12:01

3. Advanced deployment concepts.mp4

03:15

4. Deploy a Streamlit app with secrets.mp4

10:44

5. Next steps.mp4

02:50

Description

Deploy ML models with Streamlit and share your data science work with the world

What You'll Learn?

Understand the core concepts and features of Streamlit
Build interactive data-driven web applications to deploy your model
Master the advanced features and integrations in Streamlit
Apply the best practices and optimization techniques for Streamlit
Connect your Streamlit app to data sources
Deploy your Streamlit app for free

Who is this for?

Data scientists and machine learning engineers looking to deploy ML models and dashboards.

What You Need to Know?

A working knowledge of Python and machine learning is required.

This course focuses only on deploying models using Streamlit. We will not spend time explaining how the models work or how they are developed and trained.

A computer with Anaconda installed.

Your favourite text editor installed (I use VSCode)

More details

Description
The complete course to deploy machine learning models using Streamlit. Build web applications powered by ML and AI and deploy them to share them with the world.

This course will take you from the basics to deploying scalable applications powered by machine learning. To put your knowledge to the test, I have designed more than six capstone projects with full guided solutions.

This course covers:

Basics of Streamlit
Add interactive elements, like buttons, forms, sliders, input elements, etc.
Display charts
Customize the layout of your application
Capstone project: build an interactive dashboard
Caching
Performance enhancement with caching
Basic and advanced usage of caching
Capstone project: deploy a classification model
Session state management
Add more interactivity and boost performance with session state management
Basic and advanced usage of session state
Capstone project: deploy a regression model
Multipage applications
Build large apps with multiple pages
Capstone project: train and rank classification models
Authentication
Add a security layer with authentication
Add login/logout components
Advanced authentication with user management, reset password, etc.
Capstone project: deploy a clustering model for marketing
Connect to data sources
Connect to databases
Access data through APIs
Capstone project: Deploy a sales demand model
Deployment
Deploy aÂ Streamlit app for free
Advanced deployment process with secrets management and environment variables
Who this course is for:
Data scientists and machine learning engineers looking to deploy ML models and dashboards.

User Reviews

Rating

average 0

Total votes0

Focused display

Machine Learning

Marco Peixeiro

Instructor's Courses

Experience as a data scientistI completed a bachelor degree in a field that did not interest me. Instead, I started learning web development on the side and landed my first job as a web developer.I went on to teach myself data science, as I was very curious about the idea of machines learning by themselves. I proceeded to land another job as a professional data scientist, even though I do not have a masters or a PhD.As a self-taught data scientist and web developer, I know what it feels like to dive in a completely new field. I know the hard parts, and I know what must be taught to land a professional job and gain new skills with a real impact on our career.Experience as an instructorAs far I can remember, I was always the person explaining to my peers. Through tutoring, blog articles, and courses, I have a passion for sharing my knowledge and teaching. I strive to have an impact on my students and see them become better and more knowledgeable.

Udemy

View courses Udemy

Students take courses primarily to improve job-related skills.Some courses generate credit toward technical certification. Udemy has made a special effort to attract corporate trainers seeking to create coursework for employees of their company.