Adding all files to the project

.github/workflows/CI_CD.yml

@@ -0,0 +1,45 @@
+name: Python Installation Check
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Set up Python
+        uses: actions/setup-python@v6
+        with:
+          python-version: '3.13.5'
+          cache: 'pip'
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+
+
+  deploy: 
+    needs: build 
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          fetch-depth: 0
+          lfs: true
+
+      - name: Push to Hub
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: git push --force https://KLEB38:$HF_TOKEN@huggingface.co/KLEB38/OC_P5 main
+
+      - name: Check large files
+        uses: ActionsDesk/lfs-warning@v2.0
+        with:
+          filesizelimit: 10485760 # 10MB

.gitignore

@@ -0,0 +1,18 @@
+# Python bytecode (fichiers générés automatiquement)
+__pycache__/
+*.py[cod]
+
+# Environnements virtuels (trop lourds pour Git)
+venv/
+env/
+.env
+
+# Configuration VS Code
+.vscode/
+
+# Jupyter Notebook checkpoints
+.ipynb_checkpoints/
+
+# Fichiers système
+.DS_Store
+Thumbs.db

README.md

@@ -0,0 +1,57 @@
+# HR Attrition Prediction API - Futurisys
+
+This project provides a professional-grade REST API designed to predict employee attrition for **Futurisys**. 
+It uses a Machine Learning pipeline to analyze employee data and provide actionable insights for HR departments.
+
+## Project Overview
+The objective is to identify employees at risk of leaving the company by analyzing HR features.
+
+**Key Features:**
+- **Machine Learning Pipeline:** A robust model (Gradient Boosting/Random Forest) integrated with automated preprocessing.
+- **FastAPI Framework:** High-performance API with built-in validation and asynchronous support.
+
+---
+
+## Project Structure
+
+```text
+.
+├── app/
+│   ├── main.py              # Core API logic and Pydantic schemas
+│   └── pipeline_rh.joblib    # Serialized Scikit-Learn pipeline (Model + Scalers)
+├── notebooks/               # Research, EDA, and model training notebooks
+├── .gitignore               # Ensures clean version control by ignoring temp files
+├── requirements.txt         # List of Python dependencies
+└── README.md                # Project documentation
+
+```
+## Installation & Setup
+
+1. Prerequisites
+
+  Python 3.8+
+  Git
+
+3. Clone the Repository
+
+  git clone <your-repository-url>
+  cd <your-project-folder>
+
+3. Install dependencies
+
+  pip install -r requirements.txt
+
+## Usage
+
+### Running the API
+
+## API Endpoints
+
+GET / 
+
+POST /predict
+
+## Author
+Kevin L. - Data Science & Machine Learning Student
+
+  

app/main.py

@@ -0,0 +1,24 @@
+from fastapi import FastAPI
+import joblib
+
+app = FastAPI() # On crée l'outil (le guichet)
+
+# Au démarrage, on charge ton pipeline
+model = joblib.load('app/pipeline_rh.joblib')
+
+@app.get("/") # La page d'accueil de ton API
+def read_root():
+    return {"message": "Bienvenue sur l'API RH de Futurisys"}
+
+@app.post("/predict")
+def predict(data: dict):
+    # 1. On transforme le dictionnaire reçu en DataFrame pandas
+    df = pd.DataFrame([data])
+    
+    # 2. On utilise le pipeline pour faire la prédiction
+    prediction = model.predict(df)
+    
+    # 3. On renvoie le résultat au format JSON
+    return {
+        "statut_employe": int(prediction[0])
+    }

app/pipeline_rh.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2f9f36f06fd2578a274d7661a710f7c0693dad3ecc83e2c2f80b5ad674852f9
+size 197529

notebooks/Lebayle_Kevin_1_EDA_16012026.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb8b396c439597c3b2784b7e16a907d2c3f31f50238ec74c96a89c4895f5243a
+size 15777318

notebooks/Lebayle_Kevin_2_FE et Modelisation_16012026.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0804493151cd1c12848cc08fcba20dc6a0c57dc8f93fae24f17414d494ff357
+size 4669452

notebooks/Lebayle_Kevin_3_pyproject_16012026.toml

@@ -0,0 +1,20 @@
+[project]
+name = "p4 Kevin Lebayle"
+version = "1.0"
+description = "Attrition in ESN"
+requires-python = ">=3.13"
+
+dependencies = [
+    "pandas>=2.3.3",
+    "numpy>=2.3.5",
+    "matplotlib>=3.10.8",
+    "seaborn>=0.13.2",
+    "scikit-learn>=1.8.0",
+    "shap>=0.50.0",
+    "ipykernel>=6.31.0",
+    "skopt>=0.10.2",
+       ,
+]
+
+
+

requirements.txt

@@ -0,0 +1,6 @@
+fastapi
+uvicorn
+joblib
+scikit-learn
+pandas
+psycopg2-binary