How akshatugale/mlopps_telecomm_customer_churnpredictionmodel works
This repository currently contains a small churn-data ingestion and preprocessing script, rather than the complete MLOps template described in the README. The visible runtime starts in main.py, reads data through data_ingestion, and passes it to data_preprocessing. The README documents later training, evaluation, prediction, API, and console capabilities, but the model modules are empty and src/api.py is absent from the tree; those capabilities therefore cannot be shown as implemented runtime components. Edges reflect the sampled calls or explicit README statements.
Main entry points: data_preprocessing.py Data preprocessing · main.py Pipeline entry · model_building.py Model training · data_ingestion.py Data ingestion
Components 8
Data workflow
- Pipeline entry
main.py - Churn CSV
data/raw/churn - churn.csv - Data ingestion
src/data_ingestion.py - Data preprocessing
src/data_preprocessing.py
Model lifecycle
- Model training
src/model_building.py - Model evaluation
src/model_evaluation.py - Model prediction
src/model_prediction.py
Other components
- CLI user
Connections 8
- CLI user → Pipeline entry: runs CLI
README.md - Pipeline entry → Data ingestion: calls
main.py - Pipeline entry → Data preprocessing: calls
main.py - Data ingestion → Data preprocessing: passes data
main.py - Data preprocessing → Model training: precedes training
README.md - Data preprocessing → Model evaluation: feeds evaluation
README.md - Model training → Model evaluation: evaluated by
README.md - Model training → Model prediction: supports prediction
README.md