koutammoulaye/geoport-intelligence

How koutammoulaye/geoport-intelligence works

GeoPort Intelligence combines geopolitical, port, trade, and macroeconomic data to assess maritime risk and predict container throughput. Its main user workflow is to explore live indicators and submit risk or TEU scenarios through the dashboard or REST API, then inspect predictions and model comparisons. Internally, the documented pipeline prepares features for classification and regression; model training and evaluation produce artifacts and comparison results. The README also describes SHAP interpretability and live market/GDELT indicators. Some subsystem links are documented rather than visible in sampled runtime code.

Main entry points: data_pipeline.py Feature pipeline · app.py Interactive dashboard · processed Processed datasets · models_saved Model artifacts

Components 23

Data ingestion

GDELT ingestion src/fetch_gdelt.py
Feature pipeline src/data_pipeline.py
Live indicators src/realtime_apis.py

Modeling and evaluation

Risk classifier src/models/classification.py
TEU regression src/models/regression.py
Keras models src/models/deep_learning.py
Model comparison src/evaluation.py

Prediction services

REST prediction API api/main.py
Request schemas api/schemas.py

User experience

Interactive dashboard dashboard/app.py
SHAP explanations dashboard/app.py

Persisted artifacts

Model artifacts models_saved
Processed datasets data/processed
Evaluation results data/processed

Other components

Analyst
GDELT events
UCDP conflicts
Port index
UNCTAD traffic
World Bank GDP
AIS positions
Market data
Live GDELT

Connections 30

GDELT events → GDELT ingestion: provides events README.md
GDELT ingestion → Processed datasets: writes events src/fetch_gdelt.py
GDELT events → Feature pipeline: provides features README.md
UCDP conflicts → Feature pipeline: provides conflicts README.md
Port index → Feature pipeline: provides port data README.md
UNCTAD traffic → Feature pipeline: provides traffic README.md
World Bank GDP → Feature pipeline: provides GDP README.md
AIS positions → Feature pipeline: provides positions README.md
Feature pipeline → Processed datasets: builds datasets README.md
Processed datasets → Risk classifier: loads training data src/models/classification.py
Risk classifier → Model artifacts: saves model README.md
Processed datasets → TEU regression: prepares regression README.md
TEU regression → Model artifacts: saves model README.md
Processed datasets → Keras models: trains MLPs README.md
Keras models → Model artifacts: saves models src/models/deep_learning.py
Risk classifier → Model comparison: reports metrics README.md
TEU regression → Model comparison: reports metrics README.md
Keras models → Model comparison: contributes results src/evaluation.py
Model comparison → Evaluation results: exports results src/evaluation.py
Analyst → Interactive dashboard: explores README.md
Analyst → REST prediction API: submits requests README.md
Interactive dashboard → Live indicators: fetches indicators dashboard/app.py
Market data → Live indicators: supplies prices src/realtime_apis.py
Live GDELT → Live indicators: supplies articles src/realtime_apis.py
REST prediction API → Request schemas: validates input api/main.py
REST prediction API → Model artifacts: loads models README.md
REST prediction API → Evaluation results: reads results api/main.py
Interactive dashboard → Model artifacts: uses predictors README.md
Interactive dashboard → Evaluation results: shows comparisons README.md
Interactive dashboard → SHAP explanations: renders explanations README.md

More Jupyter Notebook diagrams: claudiashu/sonnet · dermatologist/fhiry · fpv-iplab/easg · microsoft/unified-data-foundation-with-fabric-solution-accelerator · osemosys/osemosys_global

Drawn by GitDiagram on October 1, 2026 from the repository's file tree, README and source files. Read as Markdown ·