Pandas - the Python Data Analysis Library - is a powerful and widely used framework for data analytics. In this work we present our approach to push down the computational part of Pandas scripts into the DBMS by using a transpiler. In addition to basic data processing operations, our approach also supports access to external data stored in files instead of the DBMS. Moreover, user-defined Python functions are transformed automatically to SQL UDFs executed in the DBMS. The latter allows the integration of complex computational tasks including machine learning. We show the usage of this feature to implement a so-called model join, i.e. applying pre-trained ML models to data in SQL tables.