How tudelft-cda-lab/encode works
ENCODE learns feature-value cluster assignments from NetFlow data. The main workflow accepts a CSV or DataFrame, orders records by the chosen connection/host/time level, computes contextual frequencies for neighboring values, builds a context matrix, and selects the best of repeated K-Means runs by silhouette score. It writes the matrix and resulting encoding to CSV and returns the encoding mapping. The graph separates data preparation, context construction, and clustering/output. Edges reflect the sampled source and README; unsampled behavior is not inferred.
Main entry points: encode.py Encode API · matrix_operations.py Context matrix · frequency_utils.py Neighbor counts · utils.py CSV input
Components 14
Data preparation
- Encode API
encode/encode.py - CSV input
encode/utils.py - Sort and prepare
encode/encode.py - Data utilities
encode/utils.py
Context modeling
- Neighbor counts
encode/frequency_utils.py - Frequency bins
encode/frequency_utils.py - Context matrix
encode/matrix_operations.py - Matrix CSV
Encoding
- K-Means selection
encode/encode.py - Feature mapping
encode/encode.py - Encoding CSV
- Encoding result
Other components
- ENCODE user
- NetFlow data
Connections 15
- ENCODE user → Encode API: invokes
README.md - NetFlow data → Encode API: supplies data
README.md - Encode API → CSV input: reads CSV
encode/encode.py - Encode API → Sort and prepare: prepares data
encode/encode.py - Sort and prepare → Data utilities: sorts and indexes
encode/encode.py - Sort and prepare → Neighbor counts: computes neighbors
encode/encode.py - Neighbor counts → Frequency bins: bins counts
encode/encode.py - Encode API → Context matrix: builds matrix
encode/encode.py - Context matrix → Matrix CSV: writes matrix
- Encode API → Context matrix: loads precomputed
encode/encode.py - Encode API → K-Means selection: clusters rows
encode/encode.py - K-Means selection → Feature mapping: assigns clusters
encode/encode.py - Encode API → Feature mapping: maps values
encode/encode.py - Encode API → Encoding CSV: writes mapping
encode/encode.py - Encode API → Encoding result: returns mapping
encode/encode.py