How darshanghole7-maker/mlops_customer_prediction_model works
This repository is a customer-churn ML project, but the checked-in implementation is much smaller than the README’s production-template description. The visible workflow loads a CSV and preprocesses it into train/test data; training, evaluation, and prediction modules are empty in the supplied excerpts. The README also documents a model registry, REST API, web console, and Docker services, but the API source it names is absent from the tree. Those documented capabilities are shown where their paths are supported; edges reflect only the visible calls or README workflow.
Main entry points: docker-compose.yml Stage services · data_ingestion.py CSV ingestion · processed Train/test data · data_preprocessing.py Data preprocessing
Components 16
Data workflow
- Pipeline entry
main.py - CSV ingestion
src/data_ingestion.py - Raw churn CSV
data/raw/churn - churn.csv - Data preprocessing
src/data_preprocessing.py - Train/test data
data/processed
Model lifecycle
- Model training
src/model_building.py - Model registry
- Model evaluation
src/model_evaluation.py - Evaluation reports
reports - Prediction
src/model_prediction.py
Serving
- REST API
- Web console
frontend/index.html - Stage services
docker/docker-compose.yml
Other components
- Operator
- Browser
- API client
Connections 21
- Operator → Pipeline entry: runs
main.py - Pipeline entry → CSV ingestion: calls
main.py - CSV ingestion → Raw churn CSV: reads
- Pipeline entry → Data preprocessing: calls
main.py - CSV ingestion → Data preprocessing: passes data
main.py - Data preprocessing → Train/test data: produces
README.md - Train/test data → Model training: feeds
README.md - Model training → Model registry: saves model
README.md - Train/test data → Model evaluation: feeds
README.md - Model registry → Model evaluation: loads model
README.md - Model evaluation → Evaluation reports: writes metrics
README.md - Model registry → Prediction: loads model
README.md - Browser → Web console: opens
README.md - Web console → REST API: HTTP
README.md - API client → REST API: REST
README.md - REST API → Model registry: loads model
README.md - REST API → Train/test data: reads features
README.md - Stage services → CSV ingestion: runs stage
README.md - Stage services → Data preprocessing: runs stage
README.md - Stage services → Model training: runs stage
README.md - Stage services → Model evaluation: runs stage
README.md