XGBoost and HyperParameter Optimization

Dask can be used with many different machine learning workflows. Two that we see commonly are the following: - XGBoost or LightGBM for gradient boosted trees - HyperParameter Optimization with Optuna This demo goes through two examples combining these two libraries: Fitting hyper-parameters for XGBoost models that fit in one machine with Optuna and Dask Fitting large XGBoost models with the xgboost.dask integration For these notebooks and others see https://github.com/coiled/examples and https://github.com/coiled/dask-xgboost-nyctaxi Key Moments 00:00 Intro 00:53 Optuna 02:03 Optuna + Dask 04:27 XGBoost + Dask 07:11 Summary --- Scale Your Python Workloads with Dask and Coiled. Coiled is a Dask company. With Coiled's rock-solid infrastructure, you can quickly and securely create Dask clusters in your cloud account. Learn more about Coiled and get started for free https://coiled.io/start More content on our blog: https://coiled.io/blog