Data is perceived as the oil of the 21st century and programming skills for processing data are becoming core qualifications in many job descriptions and vacancies. By getting introduced to the programming language R in regards to machine learning applications the participants of the training are taking their first steps to master data science workplaces.
As the main focus of the training R is introduced and discussed. In academic as well as in industry, R has become the most widely used tool in data-science. Machine learning tasks are strongly associated with the field of data science and R provides a rich set of ready-to-use algorithms. In the training the machine learning process is introduced theoretically and applied in two scenarios build upon a sample data set directly in R. The scenarios solve a classification- and a regression problem.
The training is addressed to researchers and scientists who want to use R for analytics and acquire wider knowledge in machine learning techniques. The training is an introductory course and no prior knowledge is required for participation.
- A brief overview about data science
- Concept and philosophy of R, CRAN-Mirror, R-Studio, help sources
- Data types in R and their characteristics
- Data management in R (attribute assigning, aggregations, transformations,conditional transformations, selecting / filtering)
- Basis descriptive statistics in R
- Introduction to the machine learning process
- Building machine learning models (classification und regression) in R
- Make predictions and evaluate machine learning forecasts
Please note: each participant is required to bring a laptop, with following software (latest versions!) installed:
- R in current version
- R-Studio in current version
- Java (JRE) (otherwise some packages might not work)