In the first part of the series, we were introduced to danfo.js, a new JavaScript package that provides fast, flexible, and expressive data structures designed to make working with “relational” or “labeled” data easier and more intuitive.

In part 2, we’ll sail on to actually building our ML model and evaluating it with TensorFlow.js and danfo.js in an Observable notebook.

source: Danfo.Js official

What you will learn

• Data preparation and format for modeling (part 2)
• Model building and evaluation with TensorFlow.js (part 2)
• Converting Observable notebook to a script for browser-side deployment (part 3)
• Train and perform inference in the browser (part 3)

Data preparation and format for modeling

In part 1, we analyzed our data to spot trends that can be very useful for feature engineering, model building, and interpretation. If we check the dataset, we can see that the features have all been converted into numerical features, and there’s little or no need for feature engineering without a base model. Therefore, we can start with the normalization of the dataset.

#tensorflowjs #tensorflow #machine-learning #data-science #heartbeat