In recent years, the importance of data science applications to analyse phenomena in different areas of knowledge has increased, so it has become essential to verify the correctness of this type of programs. One of the ways in which a data science application can be verified is through the analysis of the use of the data it reads and manipulates, so in this talk we propose an static analysis method to detect the use (or non-use) of columns in tabular data, extending previous work (Urban et al, 2018) to deal with dataframe variables manipulated by data science notebooks. Finally, we will present real examples of Jupyter notebooks where our analysis captures mistakes related to column data usage.
