{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Decison Tree"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Import Data from Database"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# connect to the database\n",
    "conn = sqlite3.connect('../features.db')\n",
    "c = conn.cursor()\n",
    "# get training, validation and test data\n",
    "train = pd.read_sql_query(\"SELECT * FROM train\", conn)\n",
    "valid = pd.read_sql_query(\"SELECT * FROM validation\", conn)\n",
    "test = pd.read_sql_query(\"SELECT * FROM test\", conn)\n",
    "# close the connection\n",
    "conn.close()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Format Data for Machine Learning"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# get the target and features\n",
    "train_y = train['y']\n",
    "train_y = train_y.map({'GSVT': 0, 'AFIB': 1, 'SR': 2, 'SB': 3})\n",
    "train_x = train.drop(columns=['y'])\n",
    "\n",
    "valid_y = valid['y']\n",
    "valid_y = valid_y.map({'GSVT': 0, 'AFIB': 1, 'SR': 2, 'SB': 3})\n",
    "valid_x = valid.drop(columns=['y'])\n",
    "\n",
    "test_y = test['y']\n",
    "test_y = test_y.map({'GSVT': 0, 'AFIB': 1, 'SR': 2, 'SB': 3})\n",
    "test_x = test.drop(columns=['y'])\n",
    "\n",
    "# drop id column\n",
    "train_x = train_x.drop(columns=['id'])\n",
    "valid_x = valid_x.drop(columns=['id'])\n",
    "test_x = test_x.drop(columns=['id'])\n",
    "\n",
    "print('train_x shape:', train_x.shape)\n",
    "print('test_x shape:', test_x.shape)\n",
    "print('valid_x shape:', valid_x.shape)\n",
    "# print column names\n",
    "print('features:', train_x.columns.to_list())\n",
    "feature_names = train_x.columns.to_list()\n",
    "\n",
    "# Create an imputer object with a mean filling strategy\n",
    "imputer = SimpleImputer(strategy='mean')\n",
    "\n",
    "train_x = imputer.fit_transform(train_x)\n",
    "valid_x = imputer.transform(valid_x)\n",
    "test_x = imputer.transform(test_x)\n",
    "\n",
    "# Scale Data between 0 and 1\n",
    "scaler = MinMaxScaler()\n",
    "# Fit the scaler to your data and then transform it\n",
    "train_x = scaler.fit_transform(train_x)\n",
    "valid_x = scaler.transform(valid_x)\n",
    "test_x = scaler.transform(test_x)\n",
    "\n",
    "\n",
    "\n",
    "# use xgboost\n",
    "dtrain = xgb.DMatrix(train_x, label=train_y)\n",
    "dvalid = xgb.DMatrix(valid_x, label=valid_y)\n",
    "dtest = xgb.DMatrix(test_x, label=test_y)\n",
    "\n",
    "num_classes= len(set(valid_y.to_list()))\n",
    "print('number of classes:', num_classes)"
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}