breast-cancer-detection/Projet_Naive_Bayes.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "8797cb42",
   "metadata": {},
   "source": [
    "# Étape 1 — Chargement et exploration initiale"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "391c54d2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(116, 10)\n",
      "   Age        BMI  Glucose  Insulin      HOMA   Leptin  Adiponectin  Resistin  \\\n",
      "0   48  23.500000       70    2.707  0.467409   8.8071     9.702400   7.99585   \n",
      "1   83  20.690495       92    3.115  0.706897   8.8438     5.429285   4.06405   \n",
      "2   82  23.124670       91    4.498  1.009651  17.9393    22.432040   9.27715   \n",
      "3   68  21.367521       77    3.226  0.612725   9.8827     7.169560  12.76600   \n",
      "4   86  21.111111       92    3.549  0.805386   6.6994     4.819240  10.57635   \n",
      "\n",
      "     MCP.1  Classification  \n",
      "0  417.114               1  \n",
      "1  468.786               1  \n",
      "2  554.697               1  \n",
      "3  928.220               1  \n",
      "4  773.920               1  \n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 116 entries, 0 to 115\n",
      "Data columns (total 10 columns):\n",
      " #   Column          Non-Null Count  Dtype  \n",
      "---  ------          --------------  -----  \n",
      " 0   Age             116 non-null    int64  \n",
      " 1   BMI             116 non-null    float64\n",
      " 2   Glucose         116 non-null    int64  \n",
      " 3   Insulin         116 non-null    float64\n",
      " 4   HOMA            116 non-null    float64\n",
      " 5   Leptin          116 non-null    float64\n",
      " 6   Adiponectin     116 non-null    float64\n",
      " 7   Resistin        116 non-null    float64\n",
      " 8   MCP.1           116 non-null    float64\n",
      " 9   Classification  116 non-null    int64  \n",
      "dtypes: float64(7), int64(3)\n",
      "memory usage: 9.2 KB\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x800 with 12 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Import des bibliothèques\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "# Chargement des données\n",
    "data = pd.read_csv('dataR2.csv')\n",
    "\n",
    "# Aperçu des données\n",
    "print(data.shape)\n",
    "print(data.head())\n",
    "data.info()\n",
    "\n",
    "# Liste des variables explicatives\n",
    "features = data.columns[:-1]\n",
    "target = 'Classification'\n",
    "\n",
    "# Histogrammes des variables\n",
    "data.hist(bins=50, figsize=(12, 8))\n",
    "plt.suptitle(\"Histogrammes des variables\", fontsize=16)\n",
    "plt.tight_layout()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a862efa5",
   "metadata": {},
   "source": [
    "## Definition of X and y\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "c4cb9164",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = data.drop(columns='Classification')\n",
    "y = data['Classification']\n",
    "Y_binarized = (y == 2).astype(int)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "446a3793",
   "metadata": {},
   "source": [
    "## NAIVE BAYES"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1af36855",
   "metadata": {},
   "source": [
    "### Why do we use a Gaussian NB"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "d0cd967c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "We cannot reject H0: The column Age follows a normal distribution as p= 0.008932850613695056 > 0.05\n",
      "We cannot reject H0: The column BMI follows a normal distribution as p= 0.00765341311315994 > 0.05\n",
      "We cannot reject H0: The column Glucose follows a normal distribution as p= 1.2014716303695527e-12 > 0.05\n",
      "We cannot reject H0: The column Insulin follows a normal distribution as p= 1.5076048136113956e-14 > 0.05\n",
      "We cannot reject H0: The column HOMA follows a normal distribution as p= 4.300187278780875e-17 > 0.05\n",
      "We cannot reject H0: The column Leptin follows a normal distribution as p= 1.1868019935827926e-08 > 0.05\n",
      "We cannot reject H0: The column Adiponectin follows a normal distribution as p= 2.764933584842159e-10 > 0.05\n",
      "We cannot reject H0: The column Resistin follows a normal distribution as p= 6.705226955771421e-13 > 0.05\n",
      "We cannot reject H0: The column MCP.1 follows a normal distribution as p= 5.076835730086118e-08 > 0.05\n"
     ]
    }
   ],
   "source": [
    "from scipy.stats import shapiro\n",
    "\n",
    "for col in X.columns:\n",
    "    stat, p = shapiro(X[col])\n",
    "    if p>0.05:\n",
    "        print(f\"We cannot reject H0: The column {col} follows a normal distribution as p= {p} > 0.05\")\n",
    "    else:\n",
    "        print(f\"We cannot reject H0: The column {col} follows a normal distribution as p= {p} > 0.05\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "74cef382",
   "metadata": {},
   "source": [
    "So we use a Gaussian Naive Bayes method."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "a2e1af5c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Naive Bayes Classification Accuracy: 0.7586\n"
     ]
    }
   ],
   "source": [
    "from sklearn.naive_bayes import GaussianNB\n",
    "from sklearn.metrics import accuracy_score\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "# Binarize the dataset: Convert classification values to {0, 1}\n",
    "Y_binarized = (y == 2).astype(int)\n",
    "\n",
    "# Split into training and test sets\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, Y_binarized, test_size=0.25, random_state=42)\n",
    "\n",
    "# Initialize and train a Naive Bayes classifier\n",
    "nb_classifier = GaussianNB()\n",
    "nb_classifier.fit(X_train, y_train)\n",
    "\n",
    "# Make predictions on the test set\n",
    "y_pred = nb_classifier.predict(X_test)\n",
    "\n",
    "# Compute accuracy\n",
    "accuracy = accuracy_score(y_test, y_pred)\n",
    "print(f\"Naive Bayes Classification Accuracy: {accuracy:.4f}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "96408f32",
   "metadata": {},
   "source": [
    "## Évaluation du modèle et Cross-validation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "d0267905",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy : 0.759\n",
      "F1-score : 0.696\n",
      "\n",
      "Classification Report :\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.70      0.93      0.80        15\n",
      "           1       0.89      0.57      0.70        14\n",
      "\n",
      "    accuracy                           0.76        29\n",
      "   macro avg       0.79      0.75      0.75        29\n",
      "weighted avg       0.79      0.76      0.75        29\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import f1_score, classification_report\n",
    "\n",
    "# Accuracy\n",
    "accuracy = accuracy_score(y_test, y_pred)\n",
    "print(f\"Accuracy : {accuracy:.3f}\")\n",
    "\n",
    "# F1-score (binaire par défaut)\n",
    "f1 = f1_score(y_test, y_pred)\n",
    "print(f\"F1-score : {f1:.3f}\")\n",
    "\n",
    "# Rapport complet\n",
    "print(\"\\nClassification Report :\")\n",
    "print(classification_report(y_test, y_pred))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "7afddd86",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Validation croisée (5 folds)\n",
      "F1-score moyen     : 0.496 ± 0.228\n",
      "Accuracy moyen     : 0.589 ± 0.153\n"
     ]
    }
   ],
   "source": [
    "from sklearn.model_selection import cross_val_score\n",
    "\n",
    "# Initialisation du modèle\n",
    "model = GaussianNB()\n",
    "\n",
    "# Validation croisée avec scoring F1\n",
    "f1_scores = cross_val_score(model, X_train, y_train, cv=5, scoring='f1')\n",
    "acc_scores = cross_val_score(model, X_train, y_train, cv=5, scoring='accuracy')\n",
    "\n",
    "# Résumé\n",
    "print(\"Validation croisée (5 folds)\")\n",
    "print(f\"F1-score moyen     : {f1_scores.mean():.3f} ± {f1_scores.std():.3f}\")\n",
    "print(f\"Accuracy moyen     : {acc_scores.mean():.3f} ± {acc_scores.std():.3f}\")\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5e3cf2bb",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ff150ac7",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "3d724867",
   "metadata": {},
   "source": []
  }
 ],
 "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": "3.9.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}