{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "19f0029a",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.datasets import make_classification\n",
    "\n",
    "# Not everything from this is used\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, StandardScaler\n",
    "\n",
    "import os\n",
    "import wget\n",
    "from pathlib import Path\n",
    "import shutil\n",
    "import gzip\n",
    "\n",
    "from matplotlib import 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 torch\n",
    "from pytorch_tabnet.tab_model import TabNetClassifier\n",
    "from xgboost import XGBClassifier, plot_importance\n",
    "from lightgbm import LGBMClassifier\n",
    "from catboost import CatBoostClassifier\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "\n",
    "pd.set_option('display.max_columns', None)\n",
    "\n",
    "import random\n",
    "import json"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e92a6259",
   "metadata": {},
   "outputs": [],
   "source": [
    "X, y = make_classification(\n",
    "    n_samples=100000,\n",
    "    n_features=10,\n",
    "    n_informative=5,\n",
    "    n_redundant=0,\n",
    "    n_repeated=0,\n",
    "    n_classes=2,\n",
    "    class_sep=1,\n",
    "    random_state=0\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "188ade18",
   "metadata": {},
   "outputs": [],
   "source": [
    "data = pd.DataFrame(X, columns = [\"f1\", \"f2\", \"f3\", \"f4\", \"f5\", \"f6\", \"f7\", \"f8\", \"f9\", \"f10\"])\n",
    "data[\"y\"] = y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3317628d",
   "metadata": {},
   "outputs": [],
   "source": [
    "print(data[\"y\"].value_counts())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7e64682e",
   "metadata": {},
   "outputs": [],
   "source": [
    "display(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b3ec059c",
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "plt.rcParams[\"figure.figsize\"] = (20, 6)\n",
    "plt.subplot(2, 5, 1)\n",
    "data[\"f1\"].hist(bins=100)\n",
    "plt.subplot(2, 5, 2)\n",
    "data[\"f2\"].hist(bins=100)\n",
    "plt.subplot(2, 5, 3)\n",
    "data[\"f3\"].hist(bins=100)\n",
    "plt.subplot(2, 5, 4)\n",
    "data[\"f4\"].hist(bins=100)\n",
    "plt.subplot(2, 5, 5)\n",
    "data[\"f5\"].hist(bins=100)\n",
    "plt.subplot(2, 5, 6)\n",
    "data[\"f6\"].hist(bins=100)\n",
    "plt.subplot(2, 5, 7)\n",
    "data[\"f7\"].hist(bins=100)\n",
    "plt.subplot(2, 5, 8)\n",
    "data[\"f8\"].hist(bins=100)\n",
    "plt.subplot(2, 5, 9)\n",
    "data[\"f9\"].hist(bins=100)\n",
    "plt.subplot(2, 5, 10)\n",
    "data[\"f10\"].hist(bins=100)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "83527c89",
   "metadata": {},
   "outputs": [],
   "source": [
    "data.to_pickle(\"../syn10.pkl\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b0e46afb",
   "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
}