How mihirj2002/cementstrength_machine_learning-_with_pipeline works
This repository implements a small concrete-strength regression workflow: load concrete data, prepare train/test inputs, fit a random-forest regressor, and report its R² score. main.py orchestrates the stages and prints the result. The loader reads from a remote GitHub CSV; although a CSV also exists in data/, the sampled loader does not use it. The graph follows the sampled calls; no additional README-described product capabilities are evident.
Main entry points: main.py Pipeline entry · data_ingestion.py Data loader · data_preprocessing.py Preprocessing · model_building.py Model building
Components 7
Workflow orchestration
- Pipeline entry
main.py - Printed R² score
main.py
Data preparation
- Data loader
src/data_ingestion.py - Preprocessing
src/data_preprocessing.py
Modeling and evaluation
- Model building
src/model_building.py
Other components
- User
- Remote CSV
Connections 9
- User → Pipeline entry: runs
- Pipeline entry → Data loader: calls
- Data loader → Remote CSV: reads
- Data loader → Pipeline entry: returns data
- Pipeline entry → Preprocessing: passes data
- Preprocessing → Pipeline entry: returns splits
- Pipeline entry → Model building: passes splits
- Model building → Pipeline entry: returns R²
- Pipeline entry → Printed R² score: prints