Return to page

Gradient Boosting Machine with H2O

May 2020: Seventh Edition

Contents

SectionTitlePage
1Introduction4
2What is H2O?4
3Installation5
3.1Installation in R5
3.2Installation in Python6
3.3Pointing to a Different H2O Cluster7
3.4Example Code7
3.5Citation7
4Overview8
4.1Summary of Features8
4.2Theory and Framework9
4.3Distributed Trees10
4.4Treatment of Factors11
4.5Key Parameters12
4.5.1Convergence-based Early Stopping13
4.5.2Time-based Early Stopping13
4.5.3Stochastic GBM13
4.5.4Distributions and Loss Functions14
5Use Case: Airline Data Classificationon
5.1Loading Data15
5.2Performing a Trial Run16
5.3Extracting and Handling the Results19
5.4Web Interface20
5.5Variable Importances20
5.6Supported Output20
5.7Java Models21
5.8Grid Search for Model Comparison21
5.8.1Cartesian Grid Search21
5.8.2Random Grid Search23
6Model Parameters24
7Acknowledgments28
8References29
9Authors30

To read the eBook, click the download link above.