How july514/predictive-maintenance-nasa-cmapss works
This is a NASA CMAPSS FD003 research project with two analysis tracks: R prepares engine data and runs survival analyses, while Python trains and compares RUL regressors. The user-facing results are survival analyses and a Shiny dashboard on the R side, and model predictions and evaluation reports on the Python side. README statements and sampled Python modules support the main data and results links; the R analysis and dashboard internals are represented at directory level because their source was not sampled.
Main entry points: results.py Result persistence · processed Processed CSVs · notebooks RUL model notebooks · loader.py ML data loader
Components 15
Data preparation
- R preprocessing
statistik/analysis/02_preprocessing.qmd - Processed CSVs
data/processed
Survival analysis
- Exploratory analysis
statistik/analysis/01_eda.qmd - Survival models
statistik/analysis
Shiny dashboard
- Shiny app
statistik/shiny-app/app.R - Dashboard data loader
statistik/shiny-app/R/data_loader.R
RUL machine learning
- RUL model notebooks
ml/notebooks - ML configuration
ml/src/config.py - ML data loader
ml/src/data/loader.py
Evaluation results
- Evaluation metrics
ml/src/evaluation/metrics.py - Result persistence
ml/src/evaluation/results.py - Model metrics
ml/reports/model_results.json - Test predictions
ml/reports/predictions_test.csv
Other components
- Researcher
- NASA CMAPSS FD003
Connections 15
- Researcher → Shiny app: uses dashboard
README.md - NASA CMAPSS FD003 → R preprocessing: supplies raw data
README.md - R preprocessing → Processed CSVs: exports data
README.md - Researcher → Exploratory analysis: reviews analysis
README.md - Researcher → Survival models: reviews models
README.md - Shiny app → Dashboard data loader: loads data via
README.md - Dashboard data loader → Processed CSVs: reads CSVs
README.md - Researcher → RUL model notebooks: runs models
README.md - RUL model notebooks → Processed CSVs: reads CSVs
README.md - ML data loader → Processed CSVs: loads CSVs
ml/src/data/loader.py - ML data loader → ML configuration: uses paths and features
ml/src/data/loader.py - RUL model notebooks → Result persistence: writes model results
ml/src/evaluation/results.py - Result persistence → ML configuration: uses output paths
ml/src/evaluation/results.py - Result persistence → Model metrics: writes metrics
ml/src/evaluation/results.py - Result persistence → Test predictions: writes predictions
ml/src/evaluation/results.py