Medical text mining is an exciting area and is becoming more attractive to natural language processing (NLP) researchers. We work on text mining and machine learning with Electronic Health Records (EHR) data. In our project, we have various research topics including abbreviation disambiguation, patient representation, medical coding classification, and clinical notes text segmentation. We are also interested in developing a python library that directly works on clinical notes. The library will provide the interface for text classification, named entity extraction and so on. At Yale, we also collaborate with the Center for Outcomes Research and Evaluation (CORE) from Yale School of Medicine to work on additional interesting research.