The idea of this project is to create a very simple open source library to help iOS developers integrate machine learning into any iOS application.
To implement this library I have used a powerful and innovative platform named BigML. This platform provides the funcionality necessary to handle easily resources such as data sources, datasets, models and predictions.
This library is licensed under the Apache License, Version 2.0.
To use this library there are two main options:
-
Add the source code to your project
-
Generate the library and add to your project the generate file ML4iOS.a. Also don't forget to add to your project the header files placed in the include folder.
I have included three .csv example files under the data folder of the testing application.
The project ML4iOSTests implements a test case that shows a basic usage of the library. It creates a data source from a sample .csv file. Once the data source is created it is created a dataset from the data source, a model from the dataset and a prediction based on the model created.
If you find any bug or issue please report it to me on ML4iOS issue tracker
If you have any question, doubt or problem with the API feel free to contact them. They provide very good support for developers.
Requires iOS 5.0 and later.
In order to use the library you need to have a BigML account. You can apply for an invitation on their web site.
Please feel free to contribute to this library. My idea was to publish it under Apache License in order to allow that anybody interested can contribute to the project. I am sure that it could help iOS developers that want to integrate machine learning functionalities on their applications.
The recommended steps to follow for any contribution are:
- Fork it
- Create your feature branch (
git checkout -b my-new-feature) - Commit your changes (
git commit -am 'Added some feature') - Push to the branch (
git push origin my-new-feature) - Create new Pull Request