waddi3/customer-churn-mlops

How waddi3/customer-churn-mlops works

This repository is a Telco customer-churn classification pipeline. The user starts it with run_pipeline.py; it loads the raw workbook, explores and preprocesses the data, engineers features, trains and selects a model, then evaluates it. The pipeline also saves versioned datasets and model artifacts and tracks training and evaluation in MLflow. The graph includes configuration and logging as internal support layers. README capabilities are retained; links for stages not shown in sampled code are omitted rather than inferred.

Main entry points: run_pipeline.py Pipeline Runner · train.py Model Training · logger.py Application Logging · data_loader.py Data Loading

Components 16

Pipeline Workflow

Pipeline Runner run_pipeline.py

Data Preparation

Raw Workbook data/v1/Telco_customer_churn.xlsx
Data Loading src/data_loader.py
Exploratory Analysis src/eda.py
Preprocessing src/preprocessing.py
Cleaned Dataset data/v2/cleaned_data.csv
Feature Engineering src/feature_engineering.py
Processed Dataset data/v3/processed_data.csv

Modeling And Evaluation

Model Training src/train.py
Saved Model Artifacts models
Model Evaluation src/evaluate.py

Tracking And Support

MLflow Setup src/mlflow_utils.py
MLflow Tracking
Path Configuration src/config.py
Application Logging src/logger.py

Other components

Pipeline User

Connections 24

Pipeline User → Pipeline Runner: starts README.md
Pipeline Runner → MLflow Setup: configures run_pipeline.py
Pipeline Runner → Data Loading: loads data run_pipeline.py
Data Loading → Raw Workbook: reads src/data_loader.py
Pipeline Runner → Exploratory Analysis: runs analysis run_pipeline.py
Pipeline Runner → Preprocessing: preprocesses run_pipeline.py
Preprocessing → Cleaned Dataset: writes src/preprocessing.py
Pipeline Runner → Feature Engineering: engineers features run_pipeline.py
Feature Engineering → Processed Dataset: writes src/feature_engineering.py
Pipeline Runner → Model Training: trains models run_pipeline.py
Model Training → Saved Model Artifacts: saves best model src/train.py
Model Training → MLflow Tracking: logs runs src/train.py
Pipeline Runner → Model Evaluation: evaluates model run_pipeline.py
Model Evaluation → MLflow Tracking: logs artifacts src/evaluate.py
MLflow Setup → MLflow Tracking: configures store src/mlflow_utils.py
Data Loading → Path Configuration: uses data path src/data_loader.py
Preprocessing → Path Configuration: uses output path src/preprocessing.py
Feature Engineering → Path Configuration: uses output paths src/feature_engineering.py
Model Training → Path Configuration: uses model path src/train.py
Data Loading → Application Logging: logs progress src/data_loader.py
Preprocessing → Application Logging: logs progress src/preprocessing.py
Feature Engineering → Application Logging: logs progress src/feature_engineering.py
Model Training → Application Logging: logs progress src/train.py
Model Evaluation → Application Logging: logs metrics src/evaluate.py

Drawn by GitDiagram on November 11, 2026 from the repository's file tree, README and source files. Read as Markdown ·