{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>T</th>\n",
       "      <th>Al2O3</th>\n",
       "      <th>TiO2</th>\n",
       "      <th>Density</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>20</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.06250</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>25</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.05979</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>35</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.05404</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    T  Al2O3  TiO2  Density\n",
       "0  20    0.0   0.0  1.06250\n",
       "1  25    0.0   0.0  1.05979\n",
       "2  35    0.0   0.0  1.05404"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>T</th>\n",
       "      <th>Al2O3</th>\n",
       "      <th>TiO2</th>\n",
       "      <th>Density</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>30</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.05696</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>55</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.04158</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>25</td>\n",
       "      <td>0.05</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.08438</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    T  Al2O3  TiO2  Density\n",
       "0  30   0.00   0.0  1.05696\n",
       "1  55   0.00   0.0  1.04158\n",
       "2  25   0.05   0.0  1.08438"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "density_train = pd.read_csv(\"data/density_train.csv\", sep=\";\", decimal=\",\")\n",
    "density_test = pd.read_csv(\"data/density_test.csv\", sep=\";\", decimal=\",\")\n",
    "\n",
    "display(density_train.head(3))\n",
    "display(density_test.head(3))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>T</th>\n",
       "      <th>Al2O3</th>\n",
       "      <th>TiO2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>20</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>25</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>35</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    T  Al2O3  TiO2\n",
       "0  20    0.0   0.0\n",
       "1  25    0.0   0.0\n",
       "2  35    0.0   0.0"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "0    1.06250\n",
       "1    1.05979\n",
       "2    1.05404\n",
       "Name: Density, dtype: float64"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>T</th>\n",
       "      <th>Al2O3</th>\n",
       "      <th>TiO2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>30</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>55</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>25</td>\n",
       "      <td>0.05</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    T  Al2O3  TiO2\n",
       "0  30   0.00   0.0\n",
       "1  55   0.00   0.0\n",
       "2  25   0.05   0.0"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "0    1.05696\n",
       "1    1.04158\n",
       "2    1.08438\n",
       "Name: Density, dtype: float64"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "density_y_train = density_train[\"Density\"]\n",
    "density_train = density_train.drop([\"Density\"], axis=1)\n",
    "\n",
    "display(density_train.head(3))\n",
    "display(density_y_train.head(3))\n",
    "\n",
    "density_y_test = density_test[\"Density\"]\n",
    "density_test = density_test.drop([\"Density\"], axis=1)\n",
    "\n",
    "display(density_test.head(3))\n",
    "display(density_y_test.head(3))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.pipeline import make_pipeline\n",
    "from sklearn.preprocessing import PolynomialFeatures\n",
    "from sklearn import linear_model, tree, neighbors, ensemble\n",
    "\n",
    "random_state = 9\n",
    "\n",
    "models = {\n",
    "    \"linear\": {\"model\": linear_model.LinearRegression(n_jobs=-1)},\n",
    "    \"linear_poly\": {\n",
    "        \"model\": make_pipeline(\n",
    "            PolynomialFeatures(degree=2),\n",
    "            linear_model.LinearRegression(fit_intercept=False, n_jobs=-1),\n",
    "        )\n",
    "    },\n",
    "    \"linear_interact\": {\n",
    "        \"model\": make_pipeline(\n",
    "            PolynomialFeatures(interaction_only=True),\n",
    "            linear_model.LinearRegression(fit_intercept=False, n_jobs=-1),\n",
    "        )\n",
    "    },\n",
    "    \"ridge\": {\"model\": linear_model.RidgeCV()},\n",
    "    \"decision_tree\": {\n",
    "        \"model\": tree.DecisionTreeRegressor(max_depth=7, random_state=random_state)\n",
    "    },\n",
    "    \"knn\": {\"model\": neighbors.KNeighborsRegressor(n_neighbors=7, n_jobs=-1)},\n",
    "    \"random_forest\": {\n",
    "        \"model\": ensemble.RandomForestRegressor(\n",
    "            max_depth=7, random_state=random_state, n_jobs=-1\n",
    "        )\n",
    "    },\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: linear\n",
      "Model: linear_poly\n",
      "Model: linear_interact\n",
      "Model: ridge\n",
      "Model: decision_tree\n",
      "Model: knn\n",
      "Model: random_forest\n"
     ]
    }
   ],
   "source": [
    "import math\n",
    "from sklearn import metrics\n",
    "\n",
    "for model_name in models.keys():\n",
    "    print(f\"Model: {model_name}\")\n",
    "    fitted_model = models[model_name][\"model\"].fit(\n",
    "        density_train.values, density_y_train.values.ravel()\n",
    "    )\n",
    "    y_train_pred = fitted_model.predict(density_train.values)\n",
    "    y_test_pred = fitted_model.predict(density_test.values)\n",
    "    models[model_name][\"fitted\"] = fitted_model\n",
    "    models[model_name][\"train_preds\"] = y_train_pred\n",
    "    models[model_name][\"preds\"] = y_test_pred\n",
    "    models[model_name][\"RMSE_train\"] = math.sqrt(\n",
    "        metrics.mean_squared_error(density_y_train, y_train_pred)\n",
    "    )\n",
    "    models[model_name][\"RMSE_test\"] = math.sqrt(\n",
    "        metrics.mean_squared_error(density_y_test, y_test_pred)\n",
    "    )\n",
    "    models[model_name][\"RMAE_test\"] = math.sqrt(\n",
    "        metrics.mean_absolute_error(density_y_test, y_test_pred)\n",
    "    )\n",
    "    models[model_name][\"R2_test\"] = metrics.r2_score(density_y_test, y_test_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style type=\"text/css\">\n",
       "#T_472ca_row0_col0, #T_472ca_row0_col1, #T_472ca_row4_col0 {\n",
       "  background-color: #26818e;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_472ca_row0_col2, #T_472ca_row6_col3 {\n",
       "  background-color: #4e02a2;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_472ca_row0_col3, #T_472ca_row1_col3, #T_472ca_row2_col3, #T_472ca_row6_col2 {\n",
       "  background-color: #da5a6a;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_472ca_row1_col0, #T_472ca_row1_col1 {\n",
       "  background-color: #26828e;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_472ca_row1_col2 {\n",
       "  background-color: #5c01a6;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_472ca_row2_col0 {\n",
       "  background-color: #25848e;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_472ca_row2_col1 {\n",
       "  background-color: #24868e;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_472ca_row2_col2 {\n",
       "  background-color: #6a00a8;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_472ca_row3_col0 {\n",
       "  background-color: #25858e;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_472ca_row3_col1 {\n",
       "  background-color: #238a8d;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_472ca_row3_col2 {\n",
       "  background-color: #7a02a8;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_472ca_row3_col3, #T_472ca_row4_col3 {\n",
       "  background-color: #d9586a;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_472ca_row4_col1 {\n",
       "  background-color: #228c8d;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_472ca_row4_col2 {\n",
       "  background-color: #8104a7;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_472ca_row5_col0, #T_472ca_row5_col1 {\n",
       "  background-color: #1e9c89;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_472ca_row5_col2 {\n",
       "  background-color: #a01a9c;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_472ca_row5_col3 {\n",
       "  background-color: #d35171;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_472ca_row6_col0, #T_472ca_row6_col1 {\n",
       "  background-color: #a8db34;\n",
       "  color: #000000;\n",
       "}\n",
       "</style>\n",
       "<table id=\"T_472ca\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th class=\"blank level0\" >&nbsp;</th>\n",
       "      <th id=\"T_472ca_level0_col0\" class=\"col_heading level0 col0\" >RMSE_train</th>\n",
       "      <th id=\"T_472ca_level0_col1\" class=\"col_heading level0 col1\" >RMSE_test</th>\n",
       "      <th id=\"T_472ca_level0_col2\" class=\"col_heading level0 col2\" >RMAE_test</th>\n",
       "      <th id=\"T_472ca_level0_col3\" class=\"col_heading level0 col3\" >R2_test</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th id=\"T_472ca_level0_row0\" class=\"row_heading level0 row0\" >linear_poly</th>\n",
       "      <td id=\"T_472ca_row0_col0\" class=\"data row0 col0\" >0.000319</td>\n",
       "      <td id=\"T_472ca_row0_col1\" class=\"data row0 col1\" >0.000362</td>\n",
       "      <td id=\"T_472ca_row0_col2\" class=\"data row0 col2\" >0.016643</td>\n",
       "      <td id=\"T_472ca_row0_col3\" class=\"data row0 col3\" >0.999965</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_472ca_level0_row1\" class=\"row_heading level0 row1\" >linear_interact</th>\n",
       "      <td id=\"T_472ca_row1_col0\" class=\"data row1 col0\" >0.001131</td>\n",
       "      <td id=\"T_472ca_row1_col1\" class=\"data row1 col1\" >0.001491</td>\n",
       "      <td id=\"T_472ca_row1_col2\" class=\"data row1 col2\" >0.033198</td>\n",
       "      <td id=\"T_472ca_row1_col3\" class=\"data row1 col3\" >0.999413</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_472ca_level0_row2\" class=\"row_heading level0 row2\" >linear</th>\n",
       "      <td id=\"T_472ca_row2_col0\" class=\"data row2 col0\" >0.002464</td>\n",
       "      <td id=\"T_472ca_row2_col1\" class=\"data row2 col1\" >0.003261</td>\n",
       "      <td id=\"T_472ca_row2_col2\" class=\"data row2 col2\" >0.049891</td>\n",
       "      <td id=\"T_472ca_row2_col3\" class=\"data row2 col3\" >0.997191</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_472ca_level0_row3\" class=\"row_heading level0 row3\" >random_forest</th>\n",
       "      <td id=\"T_472ca_row3_col0\" class=\"data row3 col0\" >0.002716</td>\n",
       "      <td id=\"T_472ca_row3_col1\" class=\"data row3 col1\" >0.005575</td>\n",
       "      <td id=\"T_472ca_row3_col2\" class=\"data row3 col2\" >0.067298</td>\n",
       "      <td id=\"T_472ca_row3_col3\" class=\"data row3 col3\" >0.991788</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_472ca_level0_row4\" class=\"row_heading level0 row4\" >decision_tree</th>\n",
       "      <td id=\"T_472ca_row4_col0\" class=\"data row4 col0\" >0.000346</td>\n",
       "      <td id=\"T_472ca_row4_col1\" class=\"data row4 col1\" >0.006433</td>\n",
       "      <td id=\"T_472ca_row4_col2\" class=\"data row4 col2\" >0.076138</td>\n",
       "      <td id=\"T_472ca_row4_col3\" class=\"data row4 col3\" >0.989067</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_472ca_level0_row5\" class=\"row_heading level0 row5\" >ridge</th>\n",
       "      <td id=\"T_472ca_row5_col0\" class=\"data row5 col0\" >0.013989</td>\n",
       "      <td id=\"T_472ca_row5_col1\" class=\"data row5 col1\" >0.015356</td>\n",
       "      <td id=\"T_472ca_row5_col2\" class=\"data row5 col2\" >0.116380</td>\n",
       "      <td id=\"T_472ca_row5_col3\" class=\"data row5 col3\" >0.937703</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_472ca_level0_row6\" class=\"row_heading level0 row6\" >knn</th>\n",
       "      <td id=\"T_472ca_row6_col0\" class=\"data row6 col0\" >0.053108</td>\n",
       "      <td id=\"T_472ca_row6_col1\" class=\"data row6 col1\" >0.056776</td>\n",
       "      <td id=\"T_472ca_row6_col2\" class=\"data row6 col2\" >0.217611</td>\n",
       "      <td id=\"T_472ca_row6_col3\" class=\"data row6 col3\" >0.148414</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n"
      ],
      "text/plain": [
       "<pandas.io.formats.style.Styler at 0x21f02523b00>"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reg_metrics = pd.DataFrame.from_dict(models, \"index\")[\n",
    "    [\"RMSE_train\", \"RMSE_test\", \"RMAE_test\", \"R2_test\"]\n",
    "]\n",
    "reg_metrics.sort_values(by=\"RMSE_test\").style.background_gradient(\n",
    "    cmap=\"viridis\", low=1, high=0.3, subset=[\"RMSE_train\", \"RMSE_test\"]\n",
    ").background_gradient(cmap=\"plasma\", low=0.3, high=1, subset=[\"RMAE_test\", \"R2_test\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\user\\Projects\\python\\fuzzy\\.venv\\Lib\\site-packages\\numpy\\ma\\core.py:2881: RuntimeWarning: invalid value encountered in cast\n",
      "  _data = np.array(data, dtype=dtype, copy=copy,\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'criterion': 'absolute_error', 'max_depth': 7}"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import numpy as np\n",
    "from sklearn import model_selection\n",
    "\n",
    "parameters = {\n",
    "    \"criterion\": [\"squared_error\", \"absolute_error\", \"friedman_mse\", \"poisson\"],\n",
    "    \"max_depth\": np.arange(1, 21).tolist()[0::2],\n",
    "    # \"min_samples_split\": np.arange(2, 11).tolist()[0::2],\n",
    "}\n",
    "\n",
    "grid = model_selection.GridSearchCV(\n",
    "    tree.DecisionTreeRegressor(random_state=random_state), parameters, n_jobs=-1\n",
    ")\n",
    "\n",
    "grid.fit(density_train, density_y_train)\n",
    "grid.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'RMSE_test': 0.006433043831746894,\n",
       " 'RMAE_test': 0.07613841884048704,\n",
       " 'R2_test': 0.989067217447684}"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "{'RMSE_test': 0.005040505635233745,\n",
       " 'RMAE_test': 0.06943469212568175,\n",
       " 'R2_test': 0.9932880934907101}"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "model = grid.best_estimator_\n",
    "y_pred = model.predict(density_test)\n",
    "old_metrics = {\n",
    "    \"RMSE_test\": models[\"decision_tree\"][\"RMSE_test\"],\n",
    "    \"RMAE_test\": models[\"decision_tree\"][\"RMAE_test\"],\n",
    "    \"R2_test\": models[\"decision_tree\"][\"R2_test\"],\n",
    "}\n",
    "new_metrics = {}\n",
    "new_metrics[\"RMSE_test\"] = math.sqrt(metrics.mean_squared_error(density_y_test, y_pred))\n",
    "new_metrics[\"RMAE_test\"] = math.sqrt(metrics.mean_absolute_error(density_y_test, y_pred))\n",
    "new_metrics[\"R2_test\"] = metrics.r2_score(density_y_test, y_pred)\n",
    "\n",
    "display(old_metrics)\n",
    "display(new_metrics)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "|--- Al2O3 <= 0.18\n",
      "|   |--- TiO2 <= 0.18\n",
      "|   |   |--- T <= 32.50\n",
      "|   |   |   |--- TiO2 <= 0.03\n",
      "|   |   |   |   |--- Al2O3 <= 0.03\n",
      "|   |   |   |   |   |--- T <= 22.50\n",
      "|   |   |   |   |   |   |--- value: [1.06]\n",
      "|   |   |   |   |   |--- T >  22.50\n",
      "|   |   |   |   |   |   |--- value: [1.06]\n",
      "|   |   |   |   |--- Al2O3 >  0.03\n",
      "|   |   |   |   |   |--- value: [1.09]\n",
      "|   |   |   |--- TiO2 >  0.03\n",
      "|   |   |   |   |--- T <= 27.50\n",
      "|   |   |   |   |   |--- T <= 22.50\n",
      "|   |   |   |   |   |   |--- value: [1.09]\n",
      "|   |   |   |   |   |--- T >  22.50\n",
      "|   |   |   |   |   |   |--- value: [1.09]\n",
      "|   |   |   |   |--- T >  27.50\n",
      "|   |   |   |   |   |--- value: [1.08]\n",
      "|   |   |--- T >  32.50\n",
      "|   |   |   |--- TiO2 <= 0.03\n",
      "|   |   |   |   |--- Al2O3 <= 0.03\n",
      "|   |   |   |   |   |--- T <= 55.00\n",
      "|   |   |   |   |   |   |--- T <= 47.50\n",
      "|   |   |   |   |   |   |   |--- value: [1.05]\n",
      "|   |   |   |   |   |   |--- T >  47.50\n",
      "|   |   |   |   |   |   |   |--- value: [1.04]\n",
      "|   |   |   |   |   |--- T >  55.00\n",
      "|   |   |   |   |   |   |--- T <= 62.50\n",
      "|   |   |   |   |   |   |   |--- value: [1.04]\n",
      "|   |   |   |   |   |   |--- T >  62.50\n",
      "|   |   |   |   |   |   |   |--- value: [1.03]\n",
      "|   |   |   |   |--- Al2O3 >  0.03\n",
      "|   |   |   |   |   |--- T <= 60.00\n",
      "|   |   |   |   |   |   |--- T <= 52.50\n",
      "|   |   |   |   |   |   |   |--- value: [1.07]\n",
      "|   |   |   |   |   |   |--- T >  52.50\n",
      "|   |   |   |   |   |   |   |--- value: [1.06]\n",
      "|   |   |   |   |   |--- T >  60.00\n",
      "|   |   |   |   |   |   |--- T <= 67.50\n",
      "|   |   |   |   |   |   |   |--- value: [1.06]\n",
      "|   |   |   |   |   |   |--- T >  67.50\n",
      "|   |   |   |   |   |   |   |--- value: [1.05]\n",
      "|   |   |   |--- TiO2 >  0.03\n",
      "|   |   |   |   |--- T <= 50.00\n",
      "|   |   |   |   |   |--- T <= 37.50\n",
      "|   |   |   |   |   |   |--- value: [1.08]\n",
      "|   |   |   |   |   |--- T >  37.50\n",
      "|   |   |   |   |   |   |--- value: [1.08]\n",
      "|   |   |   |   |--- T >  50.00\n",
      "|   |   |   |   |   |--- T <= 67.50\n",
      "|   |   |   |   |   |   |--- T <= 62.50\n",
      "|   |   |   |   |   |   |   |--- value: [1.06]\n",
      "|   |   |   |   |   |   |--- T >  62.50\n",
      "|   |   |   |   |   |   |   |--- value: [1.06]\n",
      "|   |   |   |   |   |--- T >  67.50\n",
      "|   |   |   |   |   |   |--- value: [1.06]\n",
      "|   |--- TiO2 >  0.18\n",
      "|   |   |--- T <= 40.00\n",
      "|   |   |   |--- T <= 30.00\n",
      "|   |   |   |   |--- value: [1.22]\n",
      "|   |   |   |--- T >  30.00\n",
      "|   |   |   |   |--- value: [1.21]\n",
      "|   |   |--- T >  40.00\n",
      "|   |   |   |--- T <= 60.00\n",
      "|   |   |   |   |--- T <= 52.50\n",
      "|   |   |   |   |   |--- T <= 47.50\n",
      "|   |   |   |   |   |   |--- value: [1.20]\n",
      "|   |   |   |   |   |--- T >  47.50\n",
      "|   |   |   |   |   |   |--- value: [1.19]\n",
      "|   |   |   |   |--- T >  52.50\n",
      "|   |   |   |   |   |--- value: [1.19]\n",
      "|   |   |   |--- T >  60.00\n",
      "|   |   |   |   |--- value: [1.18]\n",
      "|--- Al2O3 >  0.18\n",
      "|   |--- T <= 35.00\n",
      "|   |   |--- T <= 22.50\n",
      "|   |   |   |--- value: [1.19]\n",
      "|   |   |--- T >  22.50\n",
      "|   |   |   |--- T <= 27.50\n",
      "|   |   |   |   |--- value: [1.18]\n",
      "|   |   |   |--- T >  27.50\n",
      "|   |   |   |   |--- value: [1.18]\n",
      "|   |--- T >  35.00\n",
      "|   |   |--- T <= 52.50\n",
      "|   |   |   |--- T <= 42.50\n",
      "|   |   |   |   |--- value: [1.17]\n",
      "|   |   |   |--- T >  42.50\n",
      "|   |   |   |   |--- T <= 47.50\n",
      "|   |   |   |   |   |--- value: [1.17]\n",
      "|   |   |   |   |--- T >  47.50\n",
      "|   |   |   |   |   |--- value: [1.16]\n",
      "|   |   |--- T >  52.50\n",
      "|   |   |   |--- T <= 65.00\n",
      "|   |   |   |   |--- T <= 57.50\n",
      "|   |   |   |   |   |--- value: [1.16]\n",
      "|   |   |   |   |--- T >  57.50\n",
      "|   |   |   |   |   |--- value: [1.15]\n",
      "|   |   |   |--- T >  65.00\n",
      "|   |   |   |   |--- value: [1.14]\n",
      "\n"
     ]
    }
   ],
   "source": [
    "rules = tree.export_text(\n",
    "    model,\n",
    "    feature_names=density_train.columns.values.tolist()\n",
    ")\n",
    "print(rules)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "\n",
    "pickle.dump(model, open(\"data/dtree.model.sav\", \"wb\"))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "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": "3.12.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}