THIS IS A TEST INSTANCE. ALL YOUR CHANGES WILL BE LOST!!!!
Some potential roadmap items for 2018+ below. For more details please see the JIRAs.
Predictive models
- Multi-class SVM
- Mixed effects modeling
- Gradient boosted machines
- Gaussian Mixture Model using Expectation Maximization (EM) algorithm
- Hierarchical clustering
- Deep learning
Graph
- Personalized PageRank
- Betweenness centrality
- Graph cut
- Triangle counting
- Minimum spanning tree
- Eigenvector centrality
Utilities
- Balanced datasets
Summary - add more statistics - Anonymization MADLIB-911
- URI tools MADLIB-910
Usability
- Expand coverage for PivotalR
- Expand coverage for PMML export??? (or perhaps switch to PFA???)
- Interface improvement and consistency for 2.0 release (does not need to be backward compatible)
- Implement an interface using named parameters
- Python API
Performance and scalability
- Work around PostgreSQL 1 GB field size limit MADLIB-991
- GPU support
- Improve decision tree and random forest performance for run-time and memory usage
MADLIB-1057MADLIB-976
Platform
Support for PostgreSQL 9.5 and 9.6 MADLIB-944- Tensorflow support, or another deep learning framework