How princetaddy/princetaddy-taddiasprince-imrd-thesis works
This repository is a seven-notebook IMRD thesis workflow, rather than a packaged application. Its named stages cover preprocessing and imputation, index construction, clustering, PLS-SEM, spatiotemporal analysis, and machine-learning model selection and feature importance. The tree and README establish these capabilities and their numbered order, but provide no notebook contents or documented data handoffs. Accordingly, the graph shows the workflow stages without asserting calls or transfers between them.
Components 8
Data preparation
- Preprocessing
01_Pre-processing_feature_eng_and_imputation.ipynb
Index construction
- Normalization and CAI
02_Normalization, Reverse, Entropy Weights and CAI aggregation.ipynb
Statistical analysis
- Hybrid clustering
03_Target Transformation-hybrid clustering.ipynb - PLS-SEM
04_PLS-SEM.ipynb - Spatiotemporal analysis
05_Spatio-Temporal Analysis.ipynb
Machine learning
- Model selection
06_lazypredict_model_selection.ipynb - Feature importance
07_Machine Learning_Feature Importance Workflow_Combined.ipynb
Other components
- Researcher