SimpleLogistic (original) (raw)

Classifier for building linear logistic regression models. LogitBoost with simple regression functions as base learners is used for fitting the logistic models. The optimal number of LogitBoost iterations to perform is cross-validated, which leads to automatic attribute selection. For more information see:
Niels Landwehr, Mark Hall, Eibe Frank (2005). Logistic Model Trees.

Marc Sumner, Eibe Frank, Mark Hall: Speeding up Logistic Model Tree Induction. In: 9th European Conference on Principles and Practice of Knowledge Discovery in Databases, 675-683, 2005.

BibTeX:

@article{Landwehr2005, author = {Niels Landwehr and Mark Hall and Eibe Frank}, booktitle = {Machine Learning}, number = {1-2}, pages = {161-205}, title = {Logistic Model Trees}, volume = {95}, year = {2005} }

@inproceedings{Sumner2005, author = {Marc Sumner and Eibe Frank and Mark Hall}, booktitle = {9th European Conference on Principles and Practice of Knowledge Discovery in Databases}, pages = {675-683}, publisher = {Springer}, title = {Speeding up Logistic Model Tree Induction}, year = {2005} }

Valid options are:

-I Set fixed number of iterations for LogitBoost

-S Use stopping criterion on training set (instead of cross-validation)

-P Use error on probabilities (rmse) instead of misclassification error for stopping criterion

-M Set maximum number of boosting iterations

-H Set parameter for heuristic for early stopping of LogitBoost. If enabled, the minimum is selected greedily, stopping if the current minimum has not changed for iter iterations. By default, heuristic is enabled with value 50. Set to zero to disable heuristic.

-W Set beta for weight trimming for LogitBoost. Set to 0 for no weight trimming.

-A The AIC is used to choose the best iteration (instead of CV or training error).