khundman/telemanom

How khundman/telemanom works

Telemanom processes spacecraft or other multivariate sensor streams: it shapes train/test channel data, trains or loads an LSTM, predicts telemetry, then thresholds prediction errors into anomalous sequences and writes per-run results. With labels, it also evaluates detections against labeled sequences. A notebook-oriented plotting component supports result review. The main orchestration calls are partly omitted from the excerpts, so uncertain runtime links are dashed; the plotting file directly shows its result and array reads.

Main entry points: detector.py Run orchestration · plotting.py Result plotting · modeling.py LSTM modeling · errors.py Error processing

Components 17

Inputs and Setup

CLI entry example.py
Run configuration telemanom/helpers.py
Channel shaping telemanom/channel.py
Train/test arrays
Anomaly labels labeled_anomalies.csv

Telemetry Prediction

LSTM modeling telemanom/modeling.py
Saved models
Telemetry predictions

Anomaly Detection

Run orchestration telemanom/detector.py
Error processing telemanom/errors.py
Dynamic thresholding telemanom/errors.py
Label evaluation telemanom/detector.py
Smoothed errors

Results and Review

Run result CSV telemanom/detector.py
Result plotting telemanom/plotting.py

Other components

Experiment operator
Notebook reviewer

Connections 21

Experiment operator → CLI entry: starts run example.py
CLI entry → Run orchestration: creates detector example.py
Run orchestration → Run configuration: loads settings telemanom/detector.py
Train/test arrays → Channel shaping: loads arrays telemanom/channel.py
Run orchestration → Channel shaping: processes channels telemanom/detector.py
Channel shaping → LSTM modeling: provides shaped data
Run orchestration → LSTM modeling: runs prediction telemanom/detector.py
LSTM modeling → Saved models: loads or saves telemanom/modeling.py
LSTM modeling → Telemetry predictions: writes predictions telemanom/modeling.py
Run orchestration → Error processing: processes prediction errors telemanom/detector.py
Error processing → Dynamic thresholding: finds thresholds telemanom/errors.py
Error processing → Smoothed errors: writes smoothed errors telemanom/errors.py
Anomaly labels → Run orchestration: supplies labels README.md
Run orchestration → Label evaluation: evaluates sequences telemanom/detector.py
Label evaluation → Run result CSV: adds evaluation telemanom/detector.py
Run orchestration → Run result CSV: writes run CSV telemanom/detector.py
Notebook reviewer → Result plotting: reviews results README.md
Result plotting → Run result CSV: reads results telemanom/plotting.py
Result plotting → Telemetry predictions: reads predictions telemanom/plotting.py
Result plotting → Smoothed errors: reads errors telemanom/plotting.py
Result plotting → Train/test arrays: reads channel arrays telemanom/plotting.py

Drawn by GitDiagram on November 12, 2026 from the repository's file tree, README and source files. Read as Markdown ·