Creating ML model with Swift & CreateML

Click for: original source

We know machine learning is so popular in mobile and desktop applications. Therefore we need basic ML skills to follow this trend. By Oguz Kayra.

CreateML is a programming framework, to create apps with ML in IOS, macOS, and IpadOS (Apple Ecosystem). CreateML is facilitating using ML on projects for non-data scientists. ML power can spread many apps.

The article then does a good job explaining:

  • Machine learning workflow
  • Step by step: Create ML models with CreateML
    • Determine your dataset
    • Import CreateML and foundation modules
    • Create data table with CSV table
    • Separating relevant data from DataTable
    • Dividing DataTable as test and training
    • Creating model and train the model
    • Test your regression
    • Saving machine learning model

Basically, machine learning workflow is simple, get data, train models with these data, test your model, update your model, use this model in a real application.

You can find code and dataset on author’s GitHub account in this Github repository. Good read!

[Read More]

Tags machine-learning big-data how-to swiftlang app-development