# mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel architecture

> Architecture diagram of the GitHub repository mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-20). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel
- Repository: https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel

## Overview

This is a telecom customer-churn ML template organized around data ingestion and preprocessing, with documented training, evaluation, prediction, CLI, and web-serving capabilities. The sampled runtime code verifies ingestion and preprocessing; README claims describe the broader workflow, but the listed model-stage files are empty and the documented API source is absent from the tree, so those relationships are shown only where documented.

Main entry points: [`main.py`](https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/blob/main/main.py) (Pipeline CLI), [`src/model_evaluation.py`](https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/blob/main/src/model_evaluation.py) (Model evaluation), [`src`](https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/tree/main/src) (REST API), [`data/processed`](https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/tree/main/data/processed) (Train and test data)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_data["Data preparation"]
  node_raw_data[("Raw churn data")]
  node_ingestion["Data ingestion<br/>[data_ingestion.py]"]
  node_interim_data[("Ingested data")]
  node_preprocessing["Data preprocessing"]
  node_processed_data[("Train and test data")]
end

subgraph group_model["Model workflow"]
  node_training["Model training<br/>[model_building.py]"]
  node_model_registry[("Versioned models")]
  node_evaluation["Model evaluation"]
  node_reports[("Evaluation reports")]
  node_prediction["Model prediction"]
end

subgraph group_interfaces["User interfaces"]
  node_cli["Pipeline CLI<br/>[main.py]"]
  node_api["REST API"]
  node_web_console["Web console<br/>[index.html]"]
end

subgraph group_settings["Configuration"]
  node_configuration["Pipeline configuration<br/>[config.yaml]"]
end

node_cli_user(("CLI user"))
node_browser(("Browser"))

node_cli_user -->|"runs stages"| node_cli
node_cli -->|"calls"| node_ingestion
node_ingestion -->|"reads CSV"| node_raw_data
node_ingestion -.->|"writes data"| node_interim_data
node_cli -->|"calls"| node_preprocessing
node_preprocessing -.->|"reads data"| node_interim_data
node_preprocessing -.->|"writes splits"| node_processed_data
node_cli -.->|"runs stage"| node_training
node_training -.->|"reads splits"| node_processed_data
node_training -.->|"saves model"| node_model_registry
node_cli -.->|"runs stage"| node_evaluation
node_evaluation -.->|"reads splits"| node_processed_data
node_evaluation -.->|"loads model"| node_model_registry
node_evaluation -.->|"writes metrics"| node_reports
node_cli -.->|"runs stage"| node_prediction
node_prediction -.->|"loads model"| node_model_registry
node_cli_user -.->|"sends requests"| node_api
node_browser -.->|"uses"| node_web_console
node_web_console -.->|"sends HTTP"| node_api
node_api -.->|"loads cached model"| node_model_registry
node_api -.->|"reads features"| node_processed_data
node_cli -.->|"uses settings"| node_configuration

click node_raw_data "https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/tree/main/data/raw"
click node_ingestion "https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/blob/main/src/data_ingestion.py"
click node_interim_data "https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/tree/main/data/interim"
click node_preprocessing "https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/blob/main/src/data_preprocessing.py"
click node_processed_data "https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/tree/main/data/processed"
click node_training "https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/blob/main/src/model_building.py"
click node_model_registry "https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/tree/main/models"
click node_evaluation "https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/blob/main/src/model_evaluation.py"
click node_reports "https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/tree/main/reports"
click node_prediction "https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/blob/main/src/model_prediction.py"
click node_cli "https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/blob/main/main.py"
click node_api "https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/tree/main/src"
click node_web_console "https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/blob/main/frontend/index.html"
click node_configuration "https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/blob/main/config.yaml"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_raw_data,node_ingestion,node_interim_data,node_preprocessing,node_processed_data,node_cli_user,node_browser toneBlue
class node_training,node_model_registry,node_evaluation,node_reports,node_prediction toneAmber
class node_cli,node_api,node_web_console toneMint
class node_configuration toneRose
```

## Components

### Data preparation

- [Raw churn data](https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/tree/main/data/raw): `data/raw`
- [Data ingestion](https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/blob/main/src/data_ingestion.py): `src/data_ingestion.py`
- [Ingested data](https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/tree/main/data/interim): `data/interim`
- [Data preprocessing](https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/blob/main/src/data_preprocessing.py): `src/data_preprocessing.py`
- [Train and test data](https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/tree/main/data/processed): `data/processed`

### Model workflow

- [Model training](https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/blob/main/src/model_building.py): `src/model_building.py`
- [Versioned models](https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/tree/main/models): `models`
- [Model evaluation](https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/blob/main/src/model_evaluation.py): `src/model_evaluation.py`
- [Evaluation reports](https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/tree/main/reports): `reports`
- [Model prediction](https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/blob/main/src/model_prediction.py): `src/model_prediction.py`

### User interfaces

- [Pipeline CLI](https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/blob/main/main.py): `main.py`
- [REST API](https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/tree/main/src): `src`
- [Web console](https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/blob/main/frontend/index.html): `frontend/index.html`

### Configuration

- [Pipeline configuration](https://github.com/mrinalgaurkhede/mlops_telecom_customerchurnpredictionmodel/blob/main/config.yaml): `config.yaml`

### Other components

- **CLI user**
- **Browser**

## Connections

- CLI user → Pipeline CLI: runs stages (evidence: `README.md`)
- Pipeline CLI → Data ingestion: calls (evidence: `main.py`)
- Data ingestion → Raw churn data: reads CSV (evidence: `src/data_ingestion.py`)
- Data ingestion → Ingested data: writes data (evidence: `README.md`)
- Pipeline CLI → Data preprocessing: calls (evidence: `main.py`)
- Data preprocessing → Ingested data: reads data (evidence: `README.md`)
- Data preprocessing → Train and test data: writes splits (evidence: `README.md`)
- Pipeline CLI → Model training: runs stage (evidence: `README.md`)
- Model training → Train and test data: reads splits (evidence: `README.md`)
- Model training → Versioned models: saves model (evidence: `README.md`)
- Pipeline CLI → Model evaluation: runs stage (evidence: `README.md`)
- Model evaluation → Train and test data: reads splits (evidence: `README.md`)
- Model evaluation → Versioned models: loads model (evidence: `README.md`)
- Model evaluation → Evaluation reports: writes metrics (evidence: `README.md`)
- Pipeline CLI → Model prediction: runs stage (evidence: `README.md`)
- Model prediction → Versioned models: loads model (evidence: `README.md`)
- CLI user → REST API: sends requests (evidence: `README.md`)
- Browser → Web console: uses (evidence: `README.md`)
- Web console → REST API: sends HTTP (evidence: `README.md`)
- REST API → Versioned models: loads cached model (evidence: `README.md`)
- REST API → Train and test data: reads features (evidence: `README.md`)
- Pipeline CLI → Pipeline configuration: uses settings (evidence: `README.md`)
