classification-algorithm ensemble-learning Python Machine learning
Need help with DeepSuperLearner?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.


DeepSuperLearner - Python implementation of the deep ensemble algorithm

126 Stars 21 Forks MIT License 8 Commits 3 Opened issues

Services available

Need anything else?

DeepSuperLearner (2018) in Python

This is a sklearn implementation of the machine-learning DeepSuperLearner algorithm, A Deep Ensemble method for Classification Problems.

For details about DeepSuperLearner please refer to the Deep Super Learner: A Deep Ensemble for Classification Problems by Steven Young, Tamer Abdou, and Ayse Bener.

Installation and demo

  1. Clone this repository

    git clone
  2. Install the python library

    cd DeepSuperLearner
    python install


    ERT_learner = ExtremeRandomizedTrees(n_estimators=200, max_depth=None, max_features=1)
    kNN_learner = kNearestNeighbors(n_neighbors=11)
    LR_learner = LogisticRegression()
    RFC_learner = RandomForestClassifier(n_estimators=200, max_depth=None)
    XGB_learner = XGBClassifier(n_estimators=200, max_depth=3, learning_rate=1.)
    Base_learners = {'ExtremeRandomizedTrees':ERT_learner, 'kNearestNeighbors':kNN_learner, 'LogisticRegression':LR_learner,
                     'RandomForestClassifier':RFC_learner, 'XGBClassifier':XGB_learner}    
    X, y = datasets.make_classification(n_samples=1000, n_features=12,
                                        n_informative=2, n_redundant=6)
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
    DSL_learner = DeepSuperLearner(Base_learners), y_train)
    DSL_learner.get_precision_recall(X_test, y_test, show_graphs=True)    

See deepSuperLearner/ for full example.

Alt text


  1. For running example you need to install the XGB python lib as it is used as a base learner just as done in the paper.
  2. Although the algorithm is implemented for classification problems, it can be modified to perform on regression problems aswell.


  • [x] Train on some sklearn data.
  • [ ] Restore paper classification results.

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.