{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "35e97960",
   "metadata": {},
   "source": [
    "# Preprocessing HIGGS dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b959547e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Note not every import is used here\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn.datasets import fetch_openml\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import accuracy_score, log_loss, ConfusionMatrixDisplay, confusion_matrix\n",
    "from sklearn.preprocessing import LabelEncoder\n",
    "\n",
    "import scipy as sp\n",
    "import matplotlib as mpl\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "# Apply the default theme\n",
    "sns.set_theme(rc={\"patch.force_edgecolor\": False})\n",
    "\n",
    "import os\n",
    "import wget\n",
    "from pathlib import Path\n",
    "import shutil\n",
    "import gzip\n",
    "\n",
    "import re\n",
    "\n",
    "pd.set_option('display.max_columns', None)\n",
    "\n",
    "import random\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0c493f24",
   "metadata": {},
   "outputs": [],
   "source": [
    "data = pd.read_csv(\"../HIGGS/HIGGS.csv\", header=None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2d6b18be",
   "metadata": {},
   "outputs": [],
   "source": [
    "COLUMNS_LIST = [\"target\", \"lepton pT\", \"lepton eta\", \"lepton phi\", \"missing energy magnitude\", \"missing energy phi\", \"jet 1 pt\", \"jet 1 eta\", \"jet 1 phi\", \"jet 1 b-tag\", \"jet 2 pt\", \"jet 2 eta\", \"jet 2 phi\", \"jet 2 b-tag\", \"jet 3 pt\", \"jet 3 eta\", \"jet 3 phi\", \"jet 3 b-tag\", \"jet 4 pt\", \"jet 4 eta\", \"jet 4 phi\", \"jet 4 b-tag\", \"m_jj\", \"m_jjj\", \"m_lv\", \"m_jlv\", \"m_bb\", \"m_wbb\", \"m_wwbb\"]\n",
    "data.columns = COLUMNS_LIST"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "40098294",
   "metadata": {},
   "outputs": [],
   "source": [
    "data[\"target\"] = data[\"target\"].astype(int)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "47dd6e40",
   "metadata": {},
   "outputs": [],
   "source": [
    "display(data)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "80659cf7",
   "metadata": {},
   "source": [
    "## Store resulting dataframe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "eb7cc222",
   "metadata": {},
   "outputs": [],
   "source": [
    "OUTPUT_PATH = \"../HIGGS/processed.pkl\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bc85154e",
   "metadata": {},
   "outputs": [],
   "source": [
    "data.to_pickle(OUTPUT_PATH)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ce29a453",
   "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": "3.10.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}