Dataset

Upload CSV or Excel (.xlsx) file

Try with a sample dataset

Pick one to explore instantly — no upload needed

Outlier Detection

Exemplar distance scoring

AP Parameters

Message-Passing

Auto-discovers cluster count via exemplars

Damping Factor0.50

Higher = more stable convergence (0.5–1.0). Try 0.9 if not converging.

Preference (Cluster Count Control)

Median similarity → moderate cluster count

No K required! Affinity Propagation discovers the number of clusters automatically based on the data and preference setting.

Advanced

Preprocessing

Drop Constant Columns

Missing Value Imputation

Feature Scaling

L2 Normalize (unit vectors)

Visualization

2D Projection Method

Parameter Guide

Click to expand

Performance Metrics

Clusters

—

Auto-Discovered

Exemplars

—

Cluster Representatives

Silhouette

—

Weak separation

Damping

—

Convergence control

Duration

—

Compute Time

About Affinity Propagation

Unlike K-Means, Affinity Propagation automatically discovers the number of clusters. It identifies exemplars – actual data points that serve as cluster centers – through a message-passing algorithm. Points "vote" for their preferred exemplars via "responsibility" and "availability" messages.

Interactive Visualization

Cluster Visualization

Interactive scatter plot with cluster centroids

Run training to render the scatter plot

Advanced Analysis

Deep Dive Analysis

Advanced metrics and interpretation tools

Recent Jobs

Job History

Recent jobs — auto-pruned to keep 10 per type

No jobs recorded yet. Run a clustering, classification, or pipeline job to see results here.

Loading…