{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.cluster import KMeans\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.model_selection import train_test_split\n",
    "import pickle"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "# Load dataset\n",
    "def load_data():\n",
    "    np.random.seed(42)\n",
    "    customers = pd.DataFrame({\n",
    "        'CustomerID': range(1, 101),\n",
    "        'Spending_Score': np.random.randint(1, 101, 100),\n",
    "        'Annual_Income': np.random.randint(15000, 120000, 100),\n",
    "        'Purchases': np.random.randint(1, 50, 100)\n",
    "    })\n",
    "    return customers\n",
    "\n",
    "customers = load_data()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "# Feature scaling\n",
    "scaler = StandardScaler()\n",
    "X = customers[['Spending_Score', 'Annual_Income', 'Purchases']]\n",
    "X_scaled = scaler.fit_transform(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "# KMeans clustering for customer segmentation\n",
    "kmeans = KMeans(n_clusters=3, random_state=42, n_init=10)\n",
    "customers['Segment'] = kmeans.fit_predict(X_scaled)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "# Train KNN classifier\n",
    "X_train, X_test, y_train, y_test = train_test_split(X_scaled, customers['Segment'], test_size=0.2, random_state=42)\n",
    "knn = KNeighborsClassifier(n_neighbors=5)\n",
    "knn.fit(X_train, y_train)\n",
    "accuracy = knn.score(X_test, y_test)\n",
    "print(f'KNN Model Accuracy: {accuracy:.2f}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "# Save models\n",
    "with open(\"scaler.pkl\", \"wb\") as f:\n",
    "    pickle.dump(scaler, f)\n",
    "with open(\"knn_model.pkl\", \"wb\") as f:\n",
    "    pickle.dump(knn, f)\n",
    "with open(\"kmeans_model.pkl\", \"wb\") as f:\n",
    "    pickle.dump(kmeans, f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "# Visualizing the clusters\n",
    "plt.figure(figsize=(8, 6))\n",
    "sns.scatterplot(x=customers['Annual_Income'], y=customers['Spending_Score'], hue=customers['Segment'], palette='viridis')\n",
    "plt.xlabel(\"Annual Income\")\n",
    "plt.ylabel(\"Spending Score\")\n",
    "plt.title(\"Customer Segmentation\")\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}