Basics of Machine Learning with R

In order to use data for machine learning, it is first necessary to import it as raw data from a source. Subsequently, the data must be prepared or processed for the subsequent analysis as part of a transformation. A data transformation includes, among other things, the selection of the data required for the analysis, validation, fusion with other data, reshaping, supplementation, and summarization. Once the data is cleaned, it is necessary to better understand, analyze, and identify peculiarities with the help of visualizations. At this point, it can also be determined how to deal with outliers and missing data in further analyses. After these preparatory activities, the methods and models of machine learning can be applied and their suitability evaluated before finally communicating the resulting insights. In addition to modeling, the formation of samples, the division of data into training and test data, and resampling are also presented. In addition to model selection and model training, parameter tuning is also explained.