PyMVPA eases pattern classification analyses of large datasets, with an accent on neuroimaging. It provides high-level abstraction of typical processing steps (e.g., data preparation, classification, feature selection, generalization testing), a number of implementations of some popular algorithms (e.g., kNN, Ridge Regressions, Sparse Multinomial Logistic Regression), and bindings to external machine learning libraries (libsvm, mdp, etc). While it is not limited to neuroimaging data (e.g. fMRI, or EEG) it is eminently suited for such datasets.