How sanchita-hasure21/compositecementstrength_predictionmodel1 works
This repository is a concrete compressive-strength prediction pipeline. Its principal workflow loads the concrete dataset, engineers and scales features, splits training and test data, fits several regression models, and reports R² scores. main.py orchestrates these stages and prints the returned scores. The graph reflects the sampled source; it does not imply additional prediction-serving or persistence capabilities.
Main entry points: main.py Pipeline entry point · model_build.py Regression training and evaluation · data_ingestion.py Data ingestion · data_preprocessing.py Feature preprocessing
Components 6
Prediction workflow
- Data ingestion
src/data_ingestion.py - Feature preprocessing
src/data_preprocessing.py - Pipeline entry point
main.py
Modeling and evaluation
- Regression training and evaluation
src/model_build.py
Input data
- Concrete dataset
data/Concrete_Data.csv
Other components
- Console output
Connections 7
- Data ingestion → Concrete dataset: reads
src/data_ingestion.py - Pipeline entry point → Data ingestion: calls
main.py - Pipeline entry point → Feature preprocessing: passes data
main.py - Pipeline entry point → Regression training and evaluation: passes splits
main.py - Regression training and evaluation → Pipeline entry point: returns scores
main.py - Regression training and evaluation → Console output: prints R²
src/model_build.py - Pipeline entry point → Console output: prints scores
main.py