Diveplane Reactor ™# Diveplane Reactor ™ is an instance based machine learning platform that creates powerful decision-making models that are fully explainable, auditable, and editable.

User Guide#. The User Guide will cover how to setup and use the Diveplane Machine Learning and Artificial Intelligence products. You will learn about terminology that is unique to Diveplane, and see how Diveplane approaches some Machine Learning …

Scikit Example#. An example to demonstrate the usage of Diveplane in “traditional” ML ways. The diveplane python package extends the scikit-learn Estimator via the following classes:. diveplane.scikit.DiveplaneEstimator

Terminology# Concepts#. Diveplane’s technology operates a little differently than traditional machine learning (ML) systems and thus certain terminology is specific to Diveplane.

License Acceptance#. In order to use Diveplane Reactor you must first accept the end user license agreement.. To accept this license, you may either run the following command in your python environment terminal:

partial_features are important because they allow IFA to correctly specify the bounds. For example, imagine a nominal feature of US zip codes (90016, 91334, etc.). IFA may infer these values to be continuous and the resulting dictionary will include min and max bounds. You can edit the type to be nominal post calling IFA, but the continuous bounds may cause an issue …

Scikit Package. DiveplaneClassifier. DiveplaneClassifier.__init__() DiveplaneClassifier.fit() DiveplaneClassifier.load() DiveplaneClassifier.partial_fit()

SendSafely Redirect - send.diveplane.com

Datasets#. Below are datasets used throughout this documentation as well as in our examples for reference. PMLB#. The following datasets are sourced from the Penn Machine Learning Benchmarks (PMLB) repository.

next. Scikit Example. On this page Jupyter Notebook Recipes; Python Examples