Book Image

Getting Started with Streamlit for Data Science

By : Tyler Richards
Book Image

Getting Started with Streamlit for Data Science

By: Tyler Richards

Overview of this book

Streamlit shortens the development time for the creation of data-focused web applications, allowing data scientists to create web app prototypes using Python in hours instead of days. Getting Started with Streamlit for Data Science takes a hands-on approach to helping you learn the tips and tricks that will have you up and running with Streamlit in no time. You'll start with the fundamentals of Streamlit by creating a basic app and gradually build on the foundation by producing high-quality graphics with data visualization and testing machine learning models. As you advance through the chapters, you’ll walk through practical examples of both personal data projects and work-related data-focused web applications, and get to grips with more challenging topics such as using Streamlit Components, beautifying your apps, and quick deployment of your new apps. By the end of this book, you’ll be able to create dynamic web apps in Streamlit quickly and effortlessly using the power of Python.
Table of Contents (17 chapters)
Section 1: Creating Basic Streamlit Applications
Section 2: Advanced Streamlit Applications
Section 3: Streamlit Use Cases

Using Streamlit for proof of skill data projects

Proving to others that you are a skilled data scientist is notoriously difficult. Anyone can put Python or machine learning on their résumé or even work in a research group at a university that might do some machine learning. But often, recruiters, professors you want to work with, and data science managers rely on things on your résumé that are proxies for competence, such as having attended the "right" university or already having a fancy data science internship or job. 

Prior to Streamlit, there were not many effective solutions to this problem. If you put a Python file or Jupyter Notebook on your GitHub profile, the time it would take for someone to understand whether the work was impressive or not was too much of a risk to take. If the recruiter has to click on the right repository in your GitHub profile and then click through numerous files until they find the Jupyter notebook with unreadable...