Web Calculators With Machine Learning Models In Python

[BaDshaH]

Published 8/2024
MP4 | Video: h264, 1920x1080 | Audio: AAC, 44.1 KHz
Language: English | Size: 367.88 MB | Duration: 0h 41m

Development of web applications with Machine Learning models in Python using the Streamlit and Scikit-Learn libraries.

What you'll learn
Build an ML-powered smart calculator in a web application (end-to-end)
Don't leave your ML model in the notebook; put it to work in a web application
Add a complete project to your portfolio
Build sklearn pipelines to dynamically populate the ML input form

Requirements
We will explain everything step by step, starting from blank notebooks.
No prior experience is required. However, if you already know Python or Machine Learning, you will feel more comfortable.
You will receive the solved exercises to learn comfortably on your own.

Description
This comprehensive course is designed for data enthusiasts, job seekers, students, and professionals who want to take their data analysis skills to the next level by developing web applications that showcase their machine learning models.In this course, we start from the basics, ensuring that even beginners can follow along comfortably. You will learn how to train and export machine learning models using Scikit-Learn, one of the most popular libraries in the Python ecosystem. We will guide you through loading these models and simulating a backend to make your web applications dynamic and interactive.Our journey begins with an introduction to training, exporting, and simulating the backend of machine learning models. Next, you will learn how to create intuitive web calculators using Streamlit, a powerful framework that simplifies the development of data applications. We cover everything from basic setup to deploying your applications on Streamlit Share, making your work accessible to a broader audience.Then, we dive into SHAP (Shapley Additive exPlanations), where you'll explore various visualization techniques to explain your model's predictions. You'll learn how to simulate backend processes, handle dynamic default values based on variable averages, and follow coding best practices like DRY (Don't Repeat Yourself).In the final section, we focus on building robust pipelines for preprocessing and modeling. You will gain practical experience processing input values to make your forms more dynamic and simulating backend processes with pipelines. By the end of this course, you will have the skills to develop and deploy complete web applications that leverage machine learning models, giving a significant boost to your portfolio and professional capabilities.Join us and transform your data science projects into fully functional web applications with Streamlit and Scikit-Learn.

Overview
Section 1: Preparation
Lecture 1 Materials
Lecture 2 Working with local programs
Section 2: Machine Learning Calculator in Web Application
Lecture 3 Train and export Machine Learning model
Lecture 4 Load Machine Learning model simulate backend
Lecture 5 Create calculator in web application with Streamlit
Lecture 6 Publish app on Streamlit Share
Lecture 7 File path not found
Section 3: SHAP (Shapley Additive exPlanations)
Lecture 8 Possible visualizations to explain predictions
Lecture 9 Simulate backend process with SHAP
Lecture 10 Dynamic default values according to variable averages
Lecture 11 DRY: Don't Repeat Yourself
Section 4: Pipeline to Preprocess and Model Data
Lecture 12 Preprocessing and modeling pipeline
Lecture 13 Process possible input values to dynamize form
Lecture 14 Simulate backend process with Pipeline
Lecture 15 Build input form with dynamic values based on JSON
Data enthusiasts who want to take a step further by developing data applications to showcase their findings, rather than leaving visualizations in a notebook.,Job seekers who want to add end-to-end projects to their portfolio.,Students who want to learn with practical exercises and applied projects.,Professionals who want to automate their data reports programmatically with Python.

Homepage

[To see links please register or login]

[To see links please register or login]