This dataset includes the resulting data of the research: Inferring vehicle spacing in urban traffic from trajectory data. It contains the processed outputs generated from raw vehicle trajectory data in the pNEUMA dataset. The objective of this research is to infer average two-dimensional vehicle spacing and analyse the interactions between vehicles through empirical experiments, particularly around intersections. The study employs a combination of data preprocessing, spatial transformation, intersection detection, and statistical inference (yielding interaction Fundamental Diagrams) to capture and summarise vehicle speed, spacing, and positional data. Data are collected from real-world traffic records, then transformed and sampled into various output formats (such as CSV and HDF5) that encapsulate both the inferred interaction metrics and the underlying trajectory information. The scripts that produced these data are open-sourced at https://github.com/Yiru-Jiao/DriverSpaceInference