Model-Management-and-Reproducible-Workflows/lab.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import tensorflow as tf\n",
    "from tensorflow import keras\n",
    "from sklearn.datasets import make_classification\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "import random\n",
    "import joblib"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Creating Reproducible Datasets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": "# 1. Set random seeds for reproducibility\n# Définir les graines aléatoires pour la reproductibilité\nrandom.seed(42)           # Pour le module random\nnp.random.seed(42)        # Pour NumPy\ntf.random.set_seed(42)    # Pour TensorFlow\n\nprint(\"✓ Graines aléatoires définies avec succès !\")"
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": "# 2. Generate synthetic data\n# Générer des données synthétiques pour la classification\nX, y = make_classification(\n    n_samples=1000,        # 1000 exemples\n    n_features=20,         # 20 caractéristiques\n    n_informative=15,      # 15 caractéristiques utiles\n    n_redundant=5,         # 5 caractéristiques redondantes\n    n_classes=2,           # 2 classes (classification binaire)\n    random_state=42        # Graine aléatoire pour reproductibilité\n)\n\nprint(f\"✓ Données générées : {X.shape[0]} exemples, {X.shape[1]} caractéristiques\")"
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Training Reproducible Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": "# 3. Split and scale the data\n# Diviser les données en ensembles d'entraînement (80%) et de test (20%)\nX_train, X_test, y_train, y_test = train_test_split(\n    X, y, \n    test_size=0.2,         # 20% pour le test\n    random_state=42        # Important pour la reproductibilité !\n)\n\n# Normaliser les données (StandardScaler centre les données autour de 0)\nscaler = StandardScaler()\nX_train = scaler.fit_transform(X_train)  # Apprendre et transformer les données d'entraînement\nX_test = scaler.transform(X_test)        # Transformer les données de test\n\nprint(f\"✓ Données divisées :\")\nprint(f\"  - Entraînement : {X_train.shape[0]} exemples\")\nprint(f\"  - Test : {X_test.shape[0]} exemples\")"
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": "# Sauvegarder les données d'entraînement et de test pour la reproductibilité\njoblib.dump((X_train, y_train), 'train_data.pkl')\njoblib.dump((X_test, y_test), 'test_data.pkl')\n\nprint(\"✓ Données sauvegardées :\")\nprint(\"  - train_data.pkl\")\nprint(\"  - test_data.pkl\")"
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Model Initalization and Training"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 4. Build a neural network\n",
    "model = keras.Sequential([\n",
    "    keras.layers.Dense(32, activation='relu', input_shape=(X_train.shape[1],)),\n",
    "    keras.layers.Dense(16, activation='relu'),\n",
    "    keras.layers.Dense(1, activation='sigmoid')\n",
    "])\n",
    "\n",
    "model.compile(\n",
    "    optimizer='adam',\n",
    "    loss='binary_crossentropy',\n",
    "    metrics=['accuracy']\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 5. Train the model\n",
    "model.fit(X_train, y_train, epochs=20, batch_size=32, validation_split=0.1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 6. Evaluate the model\n",
    "loss, accuracy = model.evaluate(X_test, y_test)\n",
    "print(f\"Test accuracy: {accuracy:.2f}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Saving Models"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": "# 7. Save the model and scaler\n# Sauvegarder le modèle entraîné\nmodel.save('my_model.keras')\n\nprint(\"✓ Modèle sauvegardé : my_model.keras\")"
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Reproducing Models"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": "#8. Reloading model later\n# Recharger le modèle et les données sauvegardées\nfrom tensorflow.keras.models import load_model\n\nmodelReloaded = load_model('my_model.keras')\nX_train_reloaded, y_train_reloaded = joblib.load('train_data.pkl')\nX_test_reloaded, y_test_reloaded = joblib.load('test_data.pkl')\n\nprint(\"✓ Modèle et données rechargés avec succès !\")"
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": "# Vérifier que le modèle rechargé donne les mêmes résultats\nloss_reloaded, accuracy_reloaded = modelReloaded.evaluate(X_test_reloaded, y_test_reloaded)\nprint(f\"\\n🎯 Précision du modèle rechargé : {accuracy_reloaded:.2f}\")\nprint(\"\\n💡 Si la précision est identique à celle obtenue plus haut,\")\nprint(\"   votre workflow est reproductible ! ✓\")"
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}