# hiba-ben-ali/churn_prediction_telco architecture

> Architecture diagram of the GitHub repository hiba-ben-ali/churn_prediction_telco, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-22). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/hiba-ben-ali/churn_prediction_telco
- Repository: https://github.com/hiba-ben-ali/churn_prediction_telco

## Overview

Ce dépôt est un notebook d’analyse et de prédiction du churn télécom, alimenté par un jeu de données CSV. Le parcours documenté va du nettoyage à l’analyse exploratoire, puis à la préparation, la modélisation et l’évaluation, avec optimisation du seuil pour privilégier le recall. Les étapes de traitement sont décrites dans le README, mais aucun extrait du notebook n’est fourni ; les liens représentent donc uniquement cette démarche documentée, pas des appels de code vérifiés.

Main entry points: [`churn_prediction_telco.ipynb`](https://github.com/hiba-ben-ali/churn_prediction_telco/blob/main/churn_prediction_telco.ipynb) (Préparation), [`WA_Fn-UseC_-Telco-Customer-Churn.csv`](https://github.com/hiba-ben-ali/churn_prediction_telco/blob/main/WA_Fn-UseC_-Telco-Customer-Churn.csv) (Données clients)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_data["Données"]
  node_customer_data["Données clients"]
end

subgraph group_analysis["Analyse"]
  node_cleaning["Nettoyage"]
  node_exploration["Analyse exploratoire"]
  node_preparation["Préparation"]
end

subgraph group_modeling["Modélisation"]
  node_logistic["Régression logistique"]
  node_forest["Random Forest"]
  node_evaluation["Évaluation"]
  node_threshold["Optimisation du seuil"]
end

node_analyst(("Analyste"))

node_analyst -->|"lance"| node_cleaning
node_customer_data -->|"alimente"| node_cleaning
node_cleaning -->|"précède"| node_exploration
node_exploration -->|"précède"| node_preparation
node_preparation -->|"prépare"| node_logistic
node_preparation -->|"prépare"| node_forest
node_logistic -->|"évalué par"| node_evaluation
node_forest -->|"évalué par"| node_evaluation
node_evaluation -->|"guide"| node_threshold

click node_customer_data "https://github.com/hiba-ben-ali/churn_prediction_telco/blob/main/WA_Fn-UseC_-Telco-Customer-Churn.csv"
click node_cleaning "https://github.com/hiba-ben-ali/churn_prediction_telco/blob/main/churn_prediction_telco.ipynb"
click node_exploration "https://github.com/hiba-ben-ali/churn_prediction_telco/blob/main/churn_prediction_telco.ipynb"
click node_preparation "https://github.com/hiba-ben-ali/churn_prediction_telco/blob/main/churn_prediction_telco.ipynb"
click node_logistic "https://github.com/hiba-ben-ali/churn_prediction_telco/blob/main/churn_prediction_telco.ipynb"
click node_forest "https://github.com/hiba-ben-ali/churn_prediction_telco/blob/main/churn_prediction_telco.ipynb"
click node_evaluation "https://github.com/hiba-ben-ali/churn_prediction_telco/blob/main/churn_prediction_telco.ipynb"
click node_threshold "https://github.com/hiba-ben-ali/churn_prediction_telco/blob/main/churn_prediction_telco.ipynb"

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_customer_data toneBlue
class node_cleaning,node_exploration,node_preparation toneAmber
class node_logistic,node_forest,node_evaluation,node_threshold toneMint
class node_analyst toneIndigo
```

## Components

### Données

- [Données clients](https://github.com/hiba-ben-ali/churn_prediction_telco/blob/main/WA_Fn-UseC_-Telco-Customer-Churn.csv): `WA_Fn-UseC_-Telco-Customer-Churn.csv`

### Analyse

- [Nettoyage](https://github.com/hiba-ben-ali/churn_prediction_telco/blob/main/churn_prediction_telco.ipynb): `churn_prediction_telco.ipynb`
- [Analyse exploratoire](https://github.com/hiba-ben-ali/churn_prediction_telco/blob/main/churn_prediction_telco.ipynb): `churn_prediction_telco.ipynb`
- [Préparation](https://github.com/hiba-ben-ali/churn_prediction_telco/blob/main/churn_prediction_telco.ipynb): `churn_prediction_telco.ipynb`

### Modélisation

- [Régression logistique](https://github.com/hiba-ben-ali/churn_prediction_telco/blob/main/churn_prediction_telco.ipynb): `churn_prediction_telco.ipynb`
- [Random Forest](https://github.com/hiba-ben-ali/churn_prediction_telco/blob/main/churn_prediction_telco.ipynb): `churn_prediction_telco.ipynb`
- [Évaluation](https://github.com/hiba-ben-ali/churn_prediction_telco/blob/main/churn_prediction_telco.ipynb): `churn_prediction_telco.ipynb`
- [Optimisation du seuil](https://github.com/hiba-ben-ali/churn_prediction_telco/blob/main/churn_prediction_telco.ipynb): `churn_prediction_telco.ipynb`

### Other components

- **Analyste**

## Connections

- Analyste → Nettoyage: lance (evidence: `README.md`)
- Données clients → Nettoyage: alimente (evidence: `README.md`)
- Nettoyage → Analyse exploratoire: précède (evidence: `README.md`)
- Analyse exploratoire → Préparation: précède (evidence: `README.md`)
- Préparation → Régression logistique: prépare (evidence: `README.md`)
- Préparation → Random Forest: prépare (evidence: `README.md`)
- Régression logistique → Évaluation: évalué par (evidence: `README.md`)
- Random Forest → Évaluation: évalué par (evidence: `README.md`)
- Évaluation → Optimisation du seuil: guide (evidence: `README.md`)
