{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b0e43fdc-4787-4b95-ae75-6f73750c0e78",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Defaulting to user installation because normal site-packages is not writeable\n",
      "Requirement already satisfied: scikit-learn in /home/hayden/.local/lib/python3.10/site-packages (1.4.2)\n",
      "Requirement already satisfied: scipy>=1.6.0 in /home/hayden/.local/lib/python3.10/site-packages (from scikit-learn) (1.13.0)\n",
      "Requirement already satisfied: joblib>=1.2.0 in /home/hayden/.local/lib/python3.10/site-packages (from scikit-learn) (1.4.0)\n",
      "Requirement already satisfied: threadpoolctl>=2.0.0 in /home/hayden/.local/lib/python3.10/site-packages (from scikit-learn) (3.4.0)\n",
      "Requirement already satisfied: numpy>=1.19.5 in /home/hayden/.local/lib/python3.10/site-packages (from scikit-learn) (1.26.4)\n",
      "Note: you may need to restart the kernel to use updated packages.\n",
      "1.4.2\n"
     ]
    }
   ],
   "source": [
    "%pip install scikit-learn\n",
    "import sklearn\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "af4e3bc3-6fcc-46d8-b7cc-d2fed9a05fc1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "sklearn version: 1.4.2\n"
     ]
    }
   ],
   "source": [
    "print(f\"sklearn version: {sklearn.__version__}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "ee4d871c-441c-4ee9-8af0-415047644335",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.datasets import load_iris\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.metrics import accuracy_score\n",
    "\n",
    "# Load the Iris dataset\n",
    "iris = load_iris()\n",
    "X, y = iris.data, iris.target\n",
    "\n",
    "# Split the data into training and test sets\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)\n",
    "\n",
    "# Initialize the classifier\n",
    "classifier = RandomForestClassifier(n_estimators=100, random_state=42)\n",
    "\n",
    "# Train the classifier\n",
    "classifier.fit(X_train, y_train)\n",
    "\n",
    "# Make predictions on the test set\n",
    "predictions = classifier.predict(X_test)\n",
    "\n",
    "# Calculate the accuracy\n",
    "accuracy = accuracy_score(y_test, predictions)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "84cd4fc6-4e68-4c79-bfeb-777bce8e62e5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['model.joblib']"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from joblib import dump\n",
    "dump(classifier, 'model.joblib')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "022af2af-01fd-4de5-a056-0f41337c0c1a",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}