This dataset contains the database and statistical code used for a term paper in HIF-3082 Quantitative Methods in Linguistics, spring 2017. It includes two datasets (I and II). Dataset I is used for a synchronic analysis of the verb cluster putat’ ‘mix up, mess up, confuse, tangle’ in Russian. There are seven verbs in the analysis: the simplex imperfective putat’ and six of its perfectives. Dataset I involves 1400 examples from the Russian National Corpus (years 1950-2016) that are tagged with semantic category of the verbs’ patients. Based on these semantic categories, I run a Correspondence Analysis to explore the relationship between verb and type of patient. Dataset II involves 295 examples from the Russian National Corpus (years 1800-1849) of the same verbs. The examples are tagged with the same semantic categories of patients as the examples in Dataset I. I use Correspondence Analysis to see whether the behavior of the verbs have changed over 200 years, and with that, the relationships within the verb cluster.