Back to GalleryDBSCAN
DBSCAN (Density-Based Spatial Clustering of Applications with Noise) groups points based on spatial density. It identifies 'core points' in high-density regions, recursively expands clusters along density paths, and marks points in low-density regions as noise/outliers.
Key Parameters & Visual Influence:
• Epsilon (ε): The maximum radius of a point's neighborhood. If Epsilon is too small, most points become outliers. If too large, separate clusters merge into one.
• Min Points: The minimum number of neighbors required within the Epsilon radius to form a dense core region.
Dataset Studio
CSV format: Headers in first row, last column = label/target. All values must be numeric.
Example: x1, x2, label