Overview
Sparkflows is now integrated with H2O. It has 8 processors for H2O which can be immediately used.
Distributed Random Forest
Gradient Boostes Machine ( GBM )
Generalized Linear Model ( GLM )
Isolation Forest
K- Means
Naive Bayes
Neural Networks
Principal Component Analysis (PCA)
The above processors include clustering, regression, classification and scoring.
Workflow
Below is a workflow in sparkflows in using H2O. It uses H2O GBM to predict the number of bike rentals at any day and hour.
