How gulkhan92/retaildemand-modeling works
RetailDemand-Modeling is a Rossmann retail-sales forecasting project. Its main user-to-result path is the CLI runner: load raw Kaggle tables, engineer aligned features, train and compare tabular models, then write test predictions and run summaries. The runner also produces separate statistical and aggregate time-series baselines. README-described notebook analyses are preserved as a workflow branch; their runtime wiring was not sampled, so no implementation links are asserted for them.
Main entry points: main.py Pipeline runner · ml_models.py Prediction generation · notebooks EDA and modeling notebooks · raw Rossmann raw data
Components 14
Data preparation
- Rossmann raw data
data/raw - Feature tables
src/data_preprocessing.py - Processed artifacts
data/processed
Baseline analyses
- Statistical baseline
src/statistical_models.py - SARIMAX baseline
src/timeseries_models.py
ML forecasting
- ML feature matrices
src/ml_models.py - Feature preprocessor
src/ml_models.py - Model training
src/ml_models.py - Prediction generation
src/ml_models.py - Kaggle submission
data/processed
Exploration workflow
- EDA and modeling notebooks
notebooks - Analysis report
reports/analysis_summary.pdf
Other components
- Analyst
- Pipeline runner
main.py
Connections 14
- Analyst → Pipeline runner: runs
README.md - Pipeline runner → Rossmann raw data: loads
- Pipeline runner → Feature tables: builds
main.py - Pipeline runner → Processed artifacts: writes tables
main.py - Pipeline runner → Statistical baseline: runs baseline
main.py - Pipeline runner → SARIMAX baseline: runs baseline
main.py - Pipeline runner → ML feature matrices: builds matrices
main.py - Pipeline runner → Feature preprocessor: builds
main.py - Pipeline runner → Model training: trains models
main.py - Pipeline runner → Prediction generation: generates predictions
main.py - Model training → Prediction generation: selects fitted model
main.py - Prediction generation → Kaggle submission: writes
- Pipeline runner → EDA and modeling notebooks: supports analysis
README.md - EDA and modeling notebooks → Analysis report: documents findings
README.md