In the era of big data, how to quickly extract effective information from the massive, complex and diverse electromagnetic big data based on artificial intelligence technology represented by machine learning is a research hotspot. However, machine learning algorithms for electromagnetic data are diverse and variable, and it is difficult for the people without relevant professional and programming knowledge to get started. To solve the complex programming problem of Electromagnetic(EM) big data mining, a graphical programming platform for EM big data is proposed. Various algorithms of machine learning are designed into independent components so that users can build machine learning models and workflows to analyze data without writing code. The EM data is analyzed by visual diagrams to help users better understand the data. The platform can bulid workflows quickly and it is easy for users to get started.