ykpciftci/dropout-early-warning

How ykpciftci/dropout-early-warning works

This repository is a small, offline student-dropout prediction workflow: it loads the UCI CSV, creates binary dropout labels, trains enrollment- and semester-one models, then evaluates them. Training includes stratified splitting, preprocessing, cross-validation and model persistence; evaluation reports missed dropouts and classification metrics. The notebooks suggest separate exploration and model-comparison work, but their contents were not sampled, so no connections to runtime components are asserted. The graph reflects the shown Python calls and README dataset description; generated model artifacts are not present in the tree.

Main entry points: train.py Training workflow · evaluate.py Evaluation workflow · data.py Load and split data · config.py Paths and features

Components 12

Data preparation

Paths and features src/config.py
Load and split data src/data.py

Model training

Training workflow src/train.py
Preprocessing and classifier src/train.py
Cross-validation src/train.py
Saved model artifacts

Model evaluation

Evaluation workflow src/evaluate.py
Classification metrics src/evaluate.py

Notebook research

Data exploration notebooks/01_exploration.ipynb
Model comparison notebooks/02_model_comparison.ipynb

Other components

Workflow operator
UCI dataset

Connections 12

Workflow operator → Training workflow: runs training src/train.py
Workflow operator → Evaluation workflow: runs evaluation src/evaluate.py
UCI dataset → Load and split data: loads CSV src/data.py
Training workflow → Paths and features: uses settings src/train.py
Training workflow → Load and split data: loads and splits src/train.py
Training workflow → Preprocessing and classifier: builds and fits src/train.py
Training workflow → Cross-validation: cross-validates src/train.py
Training workflow → Saved model artifacts: saves model src/train.py
Evaluation workflow → Paths and features: uses settings src/evaluate.py
Evaluation workflow → Load and split data: loads and splits src/evaluate.py
Evaluation workflow → Saved model artifacts: loads model src/evaluate.py
Evaluation workflow → Classification metrics: prints metrics src/evaluate.py

Drawn by GitDiagram on November 13, 2026 from the repository's file tree, README and source files. Read as Markdown ·