Causation is of major importance in medicine and the health sciences. To establish causation in a watertight fashion, I hold, one would need to have a way to measure token causation, i.e., to do “causometry”. I summarize what can be called causal principles in causal data science, i.e., data observation, quasi-determinism, statistical independence, Bayesian interpretation of probability, manipulation, and randomization based on counterfactualism. I review three causal methods, including causal inference based on randomization, graph-based causal discovery, and coherentist heuristics. The chapter ends with the suggestion that a token “causometer” cannot exist but that it is possible to establish the presence of type causation and to quantify the causal vigor of the cause using epidemiological measures.