Getting useful results from machine learning is a process of experimentation, fine-tuning, and trying multiple models and algorithms. Each type of estimator has its own set of hyperparameters, which must be exhaustively searched and cross-validated. This process can take a while, even on a machine with lots of cores and memory.
In this Free Code Friday, we will check out a code example with scikit-learn and Spark that does just that.
- [GitHub Repo] - https://github.com/mapr-demos/spark-sklearn-airbnb-predict
- [Training] - MapR online training