ABSTRACT
Data science is an exploratory and iterative process that often leads to complex and unstructured code. This code is usually poorly documented and, consequently, hard to understand by a third party. In this paper, we first collect empirical evidence for the non-linearity of data science code from real-world Jupyter notebooks, confirming the need for new approaches that aid in data science code interaction and comprehension. Second, we propose a visualisation method that elucidates implicit workflow information in data science code and assists data scientists in navigating the so-called garden of forking paths in non-linear code. The visualisation also provides information such as the rationale and the identification of the data science pipeline step based on cell annotations. We conducted a user experiment with data scientists to evaluate the proposed method, assessing the influence of (i) different workflow visualisations and (ii) cell annotations on code comprehension. Our results show that visualising the exploration helps the users obtain an overview of the notebook, significantly improving code comprehension. Furthermore, our qualitative analysis provides more insights into the difficulties faced during data science code comprehension.
ABSTRACT
Despite the ubiquity of data science, we are far from rigorously understanding how coding in data science is performed. Even though the scientific literature has hinted at the iterative and explorative nature of data science coding, we need further empirical evidence to understand this practice and its workflows in detail. Such understanding is critical to recognise the needs of data scientists and, for instance, inform tooling support. To obtain a deeper understanding of the iterative and explorative nature of data science coding, we analysed 470 Jupyter notebooks publicly available in GitHub repositories. We focused on the extent to which data scientists transition between different types of data science activities, or steps (such as data preprocessing and modelling), as well as the frequency and co-occurrence of such transitions. For our analysis, we developed a dataset with the help of five data science experts, who manually annotated the data science steps for each code cell within the aforementioned 470 notebooks. Using the first-order Markov chain model, we extracted the transitions and analysed the transition probabilities between the different steps. In addition to providing deeper insights into the implementation practices of data science coding, our results provide evidence that the steps in a data science workflow are indeed iterative and reveal specific patterns. We also evaluated the use of the annotated dataset to train machine-learning classifiers to predict the data science step(s) of a given code cell. We investigate the representativeness of the classification by comparing the workflow analysis applied to (a) the predicted data set and (b) the data set labelled by experts, finding an F1-score of about 71% for the 10-class data science step prediction problem.
