- author = "Randal S. Olson and Jason H. Moore",
- title = "{TPOT}: A Tree-Based Pipeline Optimization Tool for Automating Machine Learning",
- booktitle = "Automated Machine Learning: Methods, Systems, Challenges",
- publisher = "Springer",
- year = "2019",
- editor = "Frank Hutter and Lars Kotthoff and Joaquin Vanschoren",
- chapter = "8",
- pages = "151--160",
- keywords = "genetic algorithms, genetic programming, TPOT",
- isbn13 = "978-3-030-05318-5",
-
URL = "
https://www.automl.org/wp-content/uploads/2018/12/tpot.pdf",
-
DOI = "
doi:10.1007/978-3-030-05318-5_8",
-
video_url = "
https://www.youtube.com/watch?v=25lQ-JbN6Mw",
-
code_url = "https://github.com/EpistasisLab/tpot",
-
code_url = "https://github.com/EpistasisLab/penn-ml-benchmarks",
- size = "11 pages",
- abstract = "As data science becomes increasingly mainstream, there will be an ever-growing demand for data science tools that are more accessible, flexible, and scalable. In response to this demand, automated machine learning (AutoML) researchers have begun building systems that automate the process of designing and optimizing machine learning pipelines. In this chapter we present TPOT v0.3, an open source genetic programming-based AutoML system that optimizes a series of feature preprocessors and machine learning models with the goal of maximizing classification accuracy on a supervised classification task. We benchmark TPOT on a series of 150 supervised classification tasks and find that it significantly outperforms a basic machine learning analysis in 21 of them, while experiencing minimal degradation in accuracy on 4 of the benchmarks, all without any domain knowledge nor human input. As such, genetic programming-based AutoML systems show considerable promise in the AutoML domain.",
-
notes = "'This chapter is an extended version of our 2016 paper
introducing TPOT,presented at the 2016 ICML Workshop on
AutoML' \cite{Olson:2016:autoML}.
https://sites.google.com/site/automl2016/
https://github.com/EpistasisLab/tpot https://www.youtube.com/watch?v=25lQ-JbN6Mw
Penn Machine Learning Benchmark (PMLB) https://github.com/EpistasisLab/penn-ml-benchmarks https://arxiv.org/abs/1703.00512
KNN, Random Forest, DecisionTree, RandomForest, eXtreme Gradient Boosting Classifier XGBoost, LogisticRegression, KNearestNeighborClassifier. StandardScaler, RobustScaler, MinMaxScaler, MaxAbsScaler, RandomizedPCA, Binarizer, PolynomialFeature.",
