Summary: The caret package was developed by Max Kuhn and contains a handful of great functions that help with parameter tuning. Purpose of the caret Package The caret package lets you quickly automate model tuning. Using a training and holdout sample, the caret package trains a model you provide and returns the optimal model based […]
Summary: Keep analyses organized with a directory that supports exploratory and production results (scripts, visualizations, and models) and keep data immutable. Use a tool like CookieCutter Data Science to automatically build a directory structure.
Summary: The best training sessions gather information on the audience before and after by using a survey. There are no surprises in the class because handouts detail everything that is taught. Lastly, analogies are used and students participate in order to cement the knowledge.
Summary: Kaggle competitors spend their time exploring the data, building training set samples to build their models on representative data, explore data leaks, and use tools like Python, R, XGBoost, and Multi-Level Models.
Summary: R offers a handful of packages to automate building models. rpart, randomForest, MASS, and forecast packages help you search through a hypothesis space. The caret package helps crawl through the hyper parameter space.