Archit Datar
Research Investigator and Data Scientist at Celanese Corporation (former DuPont)
PhD, Chemical Engineering, Graduate Minor in Statistical Machine Learning
Sessions
TL;DR
Learn how to turn your Python functions into interactive web applications using open-source tools. By the end, each of us will have deployed a portfolio (or store) with multiple web applications and learned how to reproduce it easily later on.
Tell me more
Work not shown is work lost. Many excellent scientists and engineers are not always adept at showcasing their work. This results in many interesting scientific ideas that have never been brought to light.
However, using today's tools, one no longer has to leave the Python ecosystem to create classy, complete prototypes using modern data visualization and web development tools. With over five years of experience building and presenting data solutions at huge science companies, we show it doesn't have to be challenging. We provide a walkthrough of the primary web application frameworks and showcase Fast Dash, an open-source Python library that we built to address specific prototyping needs.
This tutorial is designed for all data professionals who value the ability to quickly convert their scientific code into web applications. Participants will learn about the leading frameworks, their strengths and limitations, and a decision flowchart for picking the best one for a given task. We will go through some day-to-day applications and hands-on Python coding throughout the session. Whether you bring your use-cases and datasets, or pick from our suggestions, you'll have a reproducible portfolio (app store) of deployed web applications by the end!
Estimating uncertainty in machine learning (ML) models enables users to estimate the precision of their predictions which is crucial to their implementation. Yet, the process of estimating uncertainty in machine learning predictions remains tedious; the field lacks software packages that can easily estimate uncertainties in models and predictions. To address this, the Machine Learning Uncertainty package—built on top of SciPy and Scikit-Learn—provides an interface to estimate uncertainties in ML predictions and where possible, model parameters. Moreover, the techniques used exploit the underlying statistics of the models making them computationally inexpensive and suitable to real-world use cases with small amounts of available data.