Metadata-Version: 2.1
Name: DecisionTreeConstraints
Version: 0.1
Summary: Building Decision Trees with Constraints
Home-page: https://github.com/valiro21/DecisionTreeConstraints
Author: Valentin Rosca
Author-email: rosca.valentin2012@gmail.com
License: UNKNOWN
Description: # Decision Tree Constraints 
        
        This is a sample code of the `PruneToSizeK` method for sklearn [Decision Tree Classifier](https://scikit-learn.org/stable/modules/tree.html).
        
        Usage:
        ```
        from sklearn.datasets import load_iris
        from sklearn import tree
        from DecisionTreeConstraints import SizeConstraintPruning
        
        iris = load_iris()
        clf = tree.DecisionTreeClassifier()
        clf = clf.fit(iris.data, iris.target)
        
        MAX_SIZE=6
        SizeConstraintPruning(MAX_SIZE).pruneToSizeK(clf)
        
        accuracy = clf.score(iris.data, iris.target)
        print('Training accuracy for max size %s: %.3f' % (MAX_SIZE, accuracy))
        ```
        
        Garofalakis, M., Hyun, D., Rastogi, R. et al. Data Mining and Knowledge Discovery (2003) 7: 187. [doi:10.1023](https://doi.org/10.1023/A:1022445500761).
        
Keywords: decision trees classifier pruning constraints
Platform: UNKNOWN
Classifier: Development Status :: 3 - Alpha
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Intended Audience :: Science/Research
Classifier: Intended Audience :: Developers
Description-Content-Type: text/markdown
