/datascience

Template for data science projects (R-based) which includes a few useful utilities.

Primary LanguageRGNU General Public License v3.0GPL-3.0

Common R functions for data science

This project contains several useful stuffs for doing data science with R.

What you can find (under src/util directory):

  • List of frequently used R packages (in R_package_install_file.R)

  • Interactions with AWS S3 and Redshift using PostgreSQL (in redshift_s3.R)

  • Statistical tests (in tests.R)

  • Training of regression and classification models with hyperparameters optimisation via gridsearch and the caret package (in train-classifiers.R and train-regressors.R)

  • Common plots for evaluating a binary classification model (in validate.R)

  • Example of doing forecasting (in forecast.Rmd)

  • Example of creating notebook with R markdown (in forecast.Rmd)