In this lab, I focused on analyzing crime data and its correlation with population density. The first task involved importing the crime data into QGIS, defining the appropriate coordinate system, and reprojecting it to the Estonian National CRS. I explored the precision of the data, identifying privacy-based aggregation and examining crime incidents across different times (month, day, hour) and monetary damage. I then performed data conversions, such as extracting temporal features and reclassifying monetary damage into numerical categories. I visualized crime patterns and monetary damage using histograms in QGIS and Python. For the second task, I performed point density analysis by applying K-means clustering to group crime points into 300 clusters, representing areas of high crime density. I generated centroids for each cluster, visualized them using proportional symbols, and checked the population_admin_units dataset for topology issues, which I corrected. I then created thematic maps that combined clustered crime data with population density and used kernel density estimation (heatmaps) to visualize crime density. I also explored different aggregation methods to visualize crimes by administrative units using proportional symbols. Finally, in the third task, I performed a spatial join to associate crime incidents with administrative units and conducted a simple correlation analysis to explore the relationship between population density and crime. I created a scatter plot with a logarithmic scale to better interpret the correlation and added a trendline to assess the linear relationship between the two variables, interpreting how the relationship varied across different administrative units.