Recognition of Magnetic Reconnection structures in 2D dataset, via Unsupervised machine learning techniques (in particular using KMeans and DBscan). The codes and their instructions referring to a journal article titled "Detecting Reconnection Events in Kinetic Vlasov Hybrid Simulations Using Clustering Techniques". This project has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 776262 (AIDA, www.aida-space.eu). MODULES OVERVIEW This package contains: check_utils.py -> utilities to check libraries version, variables type, presence in metdata; ingester.py -> containd the class DataIngestion, useful to manage data and metadata organically; calc_utils.py -> contains functions useful to perform computations (norms, scalar product, cross product, derivatives, curl, ...); plot_utils.py -> contains funtion that plots some of the intermediate results; km_utils_2d.py -> suit of function used to perfrom KMeans clusterization, including the crossvalidation phase; dbscan_utils_2d.py -> DBscan algorithm applied to one selected cluster, among those found using KMeans algorithm; ar_utils_2d.py -> compute with, thickness and aspect ratio of the regions found by the DBscan; metadata_example.cfg -> an example of metadata/configuration file; test_script.py -> a script with perform a test of these modules. WARNING: usually on small dataset no physically meningful results are obtained; test_data.h5 -> a small datased useful to test the scripts functionality.