# dimus0/telco-churn-dvc-mlflow architecture

> Architecture diagram of the GitHub repository dimus0/telco-churn-dvc-mlflow, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-05). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/dimus0/telco-churn-dvc-mlflow
- Repository: https://github.com/dimus0/telco-churn-dvc-mlflow

## Overview

This repository is a Telco customer-churn machine-learning workflow. Raw data is encoded, balanced, and split into prepared CSVs; users can train a configured random forest directly or run Optuna hyperparameter search, then record metrics and model artifacts with MLflow. The source excerpts establish these script-level data flows, but the README provides no additional capability descriptions. DVC files and configuration files are present, though their runtime wiring is not shown in the excerpts.

Main entry points: [`src/optimize.py`](https://github.com/dimus0/telco-churn-dvc-mlflow/blob/main/src/optimize.py) (Optimize parameters), [`src/train.py`](https://github.com/dimus0/telco-churn-dvc-mlflow/blob/main/src/train.py) (Train classifier), [`src/prepare.py`](https://github.com/dimus0/telco-churn-dvc-mlflow/blob/main/src/prepare.py) (Encode and split), [`data/prepared`](https://github.com/dimus0/telco-churn-dvc-mlflow/tree/main/data/prepared) (Prepared splits)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_prep["Data preparation"]
  node_raw["Raw churn data"]
  node_prepare["Encode and split<br/>[prepare.py]"]
  node_prepared["Prepared splits"]
end

subgraph group_model["Modeling"]
  node_train["Train classifier<br/>[train.py]"]
  node_modelcfg["Model settings<br/>[random_forest.yaml]"]
end

subgraph group_hpo["Hyperparameter search"]
  node_optimize["Optimize parameters<br/>[optimize.py]"]
  node_config["Workflow settings"]
end

subgraph group_tracking["Tracking and outputs"]
  node_mlflow["MLflow tracking"]
  node_modelout["Saved model"]
  node_metrics["Saved metrics"]
  node_runs[("Run artifacts")]
end

node_user(("Workflow user"))

node_raw -->|"reads"| node_prepare
node_prepare -->|"writes splits"| node_prepared
node_user -.->|"runs"| node_prepare
node_prepared -->|"loads splits"| node_train
node_modelcfg -.->|"sets defaults"| node_train
node_train -->|"logs run"| node_mlflow
node_train -->|"saves model"| node_modelout
node_train -->|"writes metrics"| node_metrics
node_mlflow -.->|"stores artifacts"| node_runs
node_user -.->|"runs"| node_train
node_config -->|"configures"| node_optimize
node_optimize -->|"loads data"| node_prepared
node_optimize -->|"logs trials"| node_mlflow
node_optimize -->|"saves model"| node_modelout
node_optimize -->|"writes metrics"| node_metrics
node_user -.->|"runs"| node_optimize

click node_raw "https://github.com/dimus0/telco-churn-dvc-mlflow/blob/main/data/raw/telco_dataset.csv.dvc"
click node_prepare "https://github.com/dimus0/telco-churn-dvc-mlflow/blob/main/src/prepare.py"
click node_prepared "https://github.com/dimus0/telco-churn-dvc-mlflow/tree/main/data/prepared"
click node_train "https://github.com/dimus0/telco-churn-dvc-mlflow/blob/main/src/train.py"
click node_modelcfg "https://github.com/dimus0/telco-churn-dvc-mlflow/blob/main/config/model/random_forest.yaml"
click node_optimize "https://github.com/dimus0/telco-churn-dvc-mlflow/blob/main/src/optimize.py"
click node_config "https://github.com/dimus0/telco-churn-dvc-mlflow/tree/main/config"
click node_runs "https://github.com/dimus0/telco-churn-dvc-mlflow/tree/main/mlartifacts"

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,node_prepare,node_prepared,node_user toneBlue
class node_train,node_modelcfg toneAmber
class node_optimize,node_config toneMint
class node_mlflow,node_modelout,node_metrics,node_runs toneRose
```

## Components

### Data preparation

- [Raw churn data](https://github.com/dimus0/telco-churn-dvc-mlflow/blob/main/data/raw/telco_dataset.csv.dvc): `data/raw/telco_dataset.csv.dvc`
- [Encode and split](https://github.com/dimus0/telco-churn-dvc-mlflow/blob/main/src/prepare.py): `src/prepare.py`
- [Prepared splits](https://github.com/dimus0/telco-churn-dvc-mlflow/tree/main/data/prepared): `data/prepared`

### Modeling

- [Train classifier](https://github.com/dimus0/telco-churn-dvc-mlflow/blob/main/src/train.py): `src/train.py`
- [Model settings](https://github.com/dimus0/telco-churn-dvc-mlflow/blob/main/config/model/random_forest.yaml): `config/model/random_forest.yaml`

### Hyperparameter search

- [Optimize parameters](https://github.com/dimus0/telco-churn-dvc-mlflow/blob/main/src/optimize.py): `src/optimize.py`
- [Workflow settings](https://github.com/dimus0/telco-churn-dvc-mlflow/tree/main/config): `config`

### Tracking and outputs

- **MLflow tracking**
- **Saved model**
- **Saved metrics**
- [Run artifacts](https://github.com/dimus0/telco-churn-dvc-mlflow/tree/main/mlartifacts): `mlartifacts`

### Other components

- **Workflow user**

## Connections

- Raw churn data → Encode and split: reads (evidence: `src/prepare.py`)
- Encode and split → Prepared splits: writes splits (evidence: `src/prepare.py`)
- Workflow user → Encode and split: runs
- Prepared splits → Train classifier: loads splits (evidence: `src/train.py`)
- Model settings → Train classifier: sets defaults
- Train classifier → MLflow tracking: logs run (evidence: `src/train.py`)
- Train classifier → Saved model: saves model (evidence: `src/train.py`)
- Train classifier → Saved metrics: writes metrics (evidence: `src/train.py`)
- MLflow tracking → Run artifacts: stores artifacts
- Workflow user → Train classifier: runs
- Workflow settings → Optimize parameters: configures (evidence: `src/optimize.py`)
- Optimize parameters → Prepared splits: loads data (evidence: `src/optimize.py`)
- Optimize parameters → MLflow tracking: logs trials (evidence: `src/optimize.py`)
- Optimize parameters → Saved model: saves model (evidence: `src/optimize.py`)
- Optimize parameters → Saved metrics: writes metrics (evidence: `src/optimize.py`)
- Workflow user → Optimize parameters: runs
