AOCL-Data Analytics

The AOCL-Data Analytics Library (AOCL-DA) provides optimized building blocks for data analysis and classical machine learning. APIs are available in C, C++, and Python. There is also a patch to enable scikit-learn users to benefit from the performance of AOCL-DA with minimal code changes.

AOCL-Data Analytics provides ability to:

• Load data from CSV files
• Preprocess data by standardizing, removing missing values and extracting subsets
• Process data using a variety of algorithms, including linear models, clustering methods, decompositions, decision forest and nearest neighbor algorithms

Highlights of AOCL-Data Analytics 5.1

• New APIs for DBSCAN clustering, support vector machines and pairwise distances
• Dynamic dispatch: multiple Zen generation code paths compiled in a single binary, with appropriate code path selected at runtime
• Performance improvements to decision trees, random forest and k-nearest neighbors algorithms

Documentation

• Source code: GitHub
  
• AOCL-DA API Guide

Downloads