How rajeshdalvicode/composite-cement-strength-prediction-model works
This repository is a small concrete-strength data-preparation pipeline. Running main.py loads the concrete dataset, adds a water-to-cementitious-materials ratio, separates features and target, splits the data, scales features, and reports the resulting train/test shapes. The orchestration and both core modules are excerpted; the CSV is present in the tree. The separate feature-engineering module was not read, so its behavior and any connections are omitted.
Main entry points: main.py Pipeline entry · data_preprocessing.py Feature prep and split · data_ingestion.py Data ingestion · Concrete_Data - Concrete_Data.csv Concrete dataset
Components 6
Pipeline
- Pipeline entry
main.py - Data ingestion
src/data_ingestion.py - Feature prep and split
src/data_preprocessing.py
Concrete Data
- Concrete dataset
data/Concrete_Data - Concrete_Data.csv
Other components
- scikit-learn
- Console
Connections 6
- Pipeline entry → Data ingestion: calls
main.py - Data ingestion → Concrete dataset: reads
src/data_ingestion.py - Pipeline entry → Feature prep and split: passes data
main.py - Feature prep and split → scikit-learn: splits and scales
src/data_preprocessing.py - Feature prep and split → Pipeline entry: returns splits
main.py - Pipeline entry → Console: prints shapes
main.py