785 lines
26 KiB
Plaintext
785 lines
26 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 163,
|
|
"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>1.274429</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>1.261477</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>1.234322</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>3</th>\n",
|
|
" <td>40</td>\n",
|
|
" <td>0.0</td>\n",
|
|
" <td>0.0</td>\n",
|
|
" <td>1.220283</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>4</th>\n",
|
|
" <td>45</td>\n",
|
|
" <td>0.0</td>\n",
|
|
" <td>0.0</td>\n",
|
|
" <td>1.205995</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"text/plain": [
|
|
" T Al2O3 TiO2 Density\n",
|
|
"0 20 0.0 0.0 1.274429\n",
|
|
"1 25 0.0 0.0 1.261477\n",
|
|
"2 35 0.0 0.0 1.234322\n",
|
|
"3 40 0.0 0.0 1.220283\n",
|
|
"4 45 0.0 0.0 1.205995"
|
|
]
|
|
},
|
|
"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>1.248056</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>1.176984</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>1.382694</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>3</th>\n",
|
|
" <td>30</td>\n",
|
|
" <td>0.05</td>\n",
|
|
" <td>0.0</td>\n",
|
|
" <td>1.366141</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>4</th>\n",
|
|
" <td>35</td>\n",
|
|
" <td>0.05</td>\n",
|
|
" <td>0.0</td>\n",
|
|
" <td>1.349487</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"text/plain": [
|
|
" T Al2O3 TiO2 Density\n",
|
|
"0 30 0.00 0.0 1.248056\n",
|
|
"1 55 0.00 0.0 1.176984\n",
|
|
"2 25 0.05 0.0 1.382694\n",
|
|
"3 30 0.05 0.0 1.366141\n",
|
|
"4 35 0.05 0.0 1.349487"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
}
|
|
],
|
|
"source": [
|
|
"import pandas as pd\n",
|
|
"\n",
|
|
"train = pd.read_csv(\"data/density_train.csv\", sep=\";\", decimal=\",\")\n",
|
|
"test = pd.read_csv(\"data/density_test.csv\", sep=\";\", decimal=\",\")\n",
|
|
"\n",
|
|
"train[\"Density\"] = pow(train[\"Density\"], 4)\n",
|
|
"test[\"Density\"] = pow(test[\"Density\"], 4)\n",
|
|
"\n",
|
|
"display(train.head())\n",
|
|
"display(test.head())"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 164,
|
|
"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>Al2O3</th>\n",
|
|
" <th>TiO2</th>\n",
|
|
" <th>Density</th>\n",
|
|
" </tr>\n",
|
|
" </thead>\n",
|
|
" <tbody>\n",
|
|
" <tr>\n",
|
|
" <th>0</th>\n",
|
|
" <td>0.0</td>\n",
|
|
" <td>0.0</td>\n",
|
|
" <td>1.274429</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>1</th>\n",
|
|
" <td>0.0</td>\n",
|
|
" <td>0.0</td>\n",
|
|
" <td>1.261477</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2</th>\n",
|
|
" <td>0.0</td>\n",
|
|
" <td>0.0</td>\n",
|
|
" <td>1.234322</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>3</th>\n",
|
|
" <td>0.0</td>\n",
|
|
" <td>0.0</td>\n",
|
|
" <td>1.220283</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>4</th>\n",
|
|
" <td>0.0</td>\n",
|
|
" <td>0.0</td>\n",
|
|
" <td>1.205995</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"text/plain": [
|
|
" Al2O3 TiO2 Density\n",
|
|
"0 0.0 0.0 1.274429\n",
|
|
"1 0.0 0.0 1.261477\n",
|
|
"2 0.0 0.0 1.234322\n",
|
|
"3 0.0 0.0 1.220283\n",
|
|
"4 0.0 0.0 1.205995"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"0 20\n",
|
|
"1 25\n",
|
|
"2 35\n",
|
|
"3 40\n",
|
|
"4 45\n",
|
|
"Name: T, dtype: int64"
|
|
]
|
|
},
|
|
"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>Al2O3</th>\n",
|
|
" <th>TiO2</th>\n",
|
|
" <th>Density</th>\n",
|
|
" </tr>\n",
|
|
" </thead>\n",
|
|
" <tbody>\n",
|
|
" <tr>\n",
|
|
" <th>0</th>\n",
|
|
" <td>0.00</td>\n",
|
|
" <td>0.0</td>\n",
|
|
" <td>1.248056</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>1</th>\n",
|
|
" <td>0.00</td>\n",
|
|
" <td>0.0</td>\n",
|
|
" <td>1.176984</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2</th>\n",
|
|
" <td>0.05</td>\n",
|
|
" <td>0.0</td>\n",
|
|
" <td>1.382694</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>3</th>\n",
|
|
" <td>0.05</td>\n",
|
|
" <td>0.0</td>\n",
|
|
" <td>1.366141</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>4</th>\n",
|
|
" <td>0.05</td>\n",
|
|
" <td>0.0</td>\n",
|
|
" <td>1.349487</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"text/plain": [
|
|
" Al2O3 TiO2 Density\n",
|
|
"0 0.00 0.0 1.248056\n",
|
|
"1 0.00 0.0 1.176984\n",
|
|
"2 0.05 0.0 1.382694\n",
|
|
"3 0.05 0.0 1.366141\n",
|
|
"4 0.05 0.0 1.349487"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"0 30\n",
|
|
"1 55\n",
|
|
"2 25\n",
|
|
"3 30\n",
|
|
"4 35\n",
|
|
"Name: T, dtype: int64"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
}
|
|
],
|
|
"source": [
|
|
"y_train = train[\"T\"]\n",
|
|
"X_train = train.drop([\"T\"], axis=1)\n",
|
|
"\n",
|
|
"display(X_train.head())\n",
|
|
"display(y_train.head())\n",
|
|
"\n",
|
|
"y_test = test[\"T\"]\n",
|
|
"X_test = test.drop([\"T\"], axis=1)\n",
|
|
"\n",
|
|
"display(X_test.head())\n",
|
|
"display(y_test.head())"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 165,
|
|
"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(random_state=random_state, max_depth=6, criterion=\"absolute_error\")\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": 166,
|
|
"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",
|
|
" X_train.values, y_train.values.ravel()\n",
|
|
" )\n",
|
|
" y_train_pred = fitted_model.predict(X_train.values)\n",
|
|
" y_test_pred = fitted_model.predict(X_test.values)\n",
|
|
" models[model_name][\"fitted\"] = fitted_model\n",
|
|
" models[model_name][\"MSE_train\"] = metrics.mean_squared_error(y_train, y_train_pred)\n",
|
|
" models[model_name][\"MSE_test\"] = metrics.mean_squared_error(y_test, y_test_pred)\n",
|
|
" models[model_name][\"MAE_train\"] = metrics.mean_absolute_error(y_train, y_train_pred)\n",
|
|
" models[model_name][\"MAE_test\"] = metrics.mean_absolute_error(y_test, y_test_pred)\n",
|
|
" models[model_name][\"R2_train\"] = metrics.r2_score(y_train, y_train_pred)\n",
|
|
" models[model_name][\"R2_test\"] = metrics.r2_score(y_test, y_test_pred)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 167,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<style type=\"text/css\">\n",
|
|
"#T_0b007_row0_col0, #T_0b007_row0_col1 {\n",
|
|
" background-color: #26818e;\n",
|
|
" color: #f1f1f1;\n",
|
|
"}\n",
|
|
"#T_0b007_row0_col3, #T_0b007_row6_col5 {\n",
|
|
" background-color: #4e02a2;\n",
|
|
" color: #f1f1f1;\n",
|
|
"}\n",
|
|
"#T_0b007_row0_col5, #T_0b007_row6_col3 {\n",
|
|
" background-color: #da5a6a;\n",
|
|
" color: #f1f1f1;\n",
|
|
"}\n",
|
|
"#T_0b007_row1_col0 {\n",
|
|
" background-color: #23888e;\n",
|
|
" color: #f1f1f1;\n",
|
|
"}\n",
|
|
"#T_0b007_row1_col1, #T_0b007_row4_col0 {\n",
|
|
" background-color: #228b8d;\n",
|
|
" color: #f1f1f1;\n",
|
|
"}\n",
|
|
"#T_0b007_row1_col3 {\n",
|
|
" background-color: #7e03a8;\n",
|
|
" color: #f1f1f1;\n",
|
|
"}\n",
|
|
"#T_0b007_row1_col5 {\n",
|
|
" background-color: #d04d73;\n",
|
|
" color: #f1f1f1;\n",
|
|
"}\n",
|
|
"#T_0b007_row2_col0 {\n",
|
|
" background-color: #21908d;\n",
|
|
" color: #f1f1f1;\n",
|
|
"}\n",
|
|
"#T_0b007_row2_col1 {\n",
|
|
" background-color: #1f988b;\n",
|
|
" color: #f1f1f1;\n",
|
|
"}\n",
|
|
"#T_0b007_row2_col3 {\n",
|
|
" background-color: #920fa3;\n",
|
|
" color: #f1f1f1;\n",
|
|
"}\n",
|
|
"#T_0b007_row2_col5 {\n",
|
|
" background-color: #c33d80;\n",
|
|
" color: #f1f1f1;\n",
|
|
"}\n",
|
|
"#T_0b007_row3_col0 {\n",
|
|
" background-color: #25858e;\n",
|
|
" color: #f1f1f1;\n",
|
|
"}\n",
|
|
"#T_0b007_row3_col1 {\n",
|
|
" background-color: #1f9f88;\n",
|
|
" color: #f1f1f1;\n",
|
|
"}\n",
|
|
"#T_0b007_row3_col3 {\n",
|
|
" background-color: #a21d9a;\n",
|
|
" color: #f1f1f1;\n",
|
|
"}\n",
|
|
"#T_0b007_row3_col5 {\n",
|
|
" background-color: #bc3587;\n",
|
|
" color: #f1f1f1;\n",
|
|
"}\n",
|
|
"#T_0b007_row4_col1 {\n",
|
|
" background-color: #20a386;\n",
|
|
" color: #f1f1f1;\n",
|
|
"}\n",
|
|
"#T_0b007_row4_col3 {\n",
|
|
" background-color: #ad2793;\n",
|
|
" color: #f1f1f1;\n",
|
|
"}\n",
|
|
"#T_0b007_row4_col5 {\n",
|
|
" background-color: #b6308b;\n",
|
|
" color: #f1f1f1;\n",
|
|
"}\n",
|
|
"#T_0b007_row5_col0 {\n",
|
|
" background-color: #6ece58;\n",
|
|
" color: #000000;\n",
|
|
"}\n",
|
|
"#T_0b007_row5_col1 {\n",
|
|
" background-color: #81d34d;\n",
|
|
" color: #000000;\n",
|
|
"}\n",
|
|
"#T_0b007_row5_col3 {\n",
|
|
" background-color: #ce4b75;\n",
|
|
" color: #f1f1f1;\n",
|
|
"}\n",
|
|
"#T_0b007_row5_col5 {\n",
|
|
" background-color: #6600a7;\n",
|
|
" color: #f1f1f1;\n",
|
|
"}\n",
|
|
"#T_0b007_row6_col0, #T_0b007_row6_col1 {\n",
|
|
" background-color: #a8db34;\n",
|
|
" color: #000000;\n",
|
|
"}\n",
|
|
"</style>\n",
|
|
"<table id=\"T_0b007\">\n",
|
|
" <thead>\n",
|
|
" <tr>\n",
|
|
" <th class=\"blank level0\" > </th>\n",
|
|
" <th id=\"T_0b007_level0_col0\" class=\"col_heading level0 col0\" >MSE_train</th>\n",
|
|
" <th id=\"T_0b007_level0_col1\" class=\"col_heading level0 col1\" >MSE_test</th>\n",
|
|
" <th id=\"T_0b007_level0_col2\" class=\"col_heading level0 col2\" >MAE_train</th>\n",
|
|
" <th id=\"T_0b007_level0_col3\" class=\"col_heading level0 col3\" >MAE_test</th>\n",
|
|
" <th id=\"T_0b007_level0_col4\" class=\"col_heading level0 col4\" >R2_train</th>\n",
|
|
" <th id=\"T_0b007_level0_col5\" class=\"col_heading level0 col5\" >R2_test</th>\n",
|
|
" </tr>\n",
|
|
" </thead>\n",
|
|
" <tbody>\n",
|
|
" <tr>\n",
|
|
" <th id=\"T_0b007_level0_row0\" class=\"row_heading level0 row0\" >linear_poly</th>\n",
|
|
" <td id=\"T_0b007_row0_col0\" class=\"data row0 col0\" >0.465283</td>\n",
|
|
" <td id=\"T_0b007_row0_col1\" class=\"data row0 col1\" >0.209921</td>\n",
|
|
" <td id=\"T_0b007_row0_col2\" class=\"data row0 col2\" >0.513527</td>\n",
|
|
" <td id=\"T_0b007_row0_col3\" class=\"data row0 col3\" >0.374980</td>\n",
|
|
" <td id=\"T_0b007_row0_col4\" class=\"data row0 col4\" >0.998248</td>\n",
|
|
" <td id=\"T_0b007_row0_col5\" class=\"data row0 col5\" >0.999016</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th id=\"T_0b007_level0_row1\" class=\"row_heading level0 row1\" >linear_interact</th>\n",
|
|
" <td id=\"T_0b007_row1_col0\" class=\"data row1 col0\" >16.021929</td>\n",
|
|
" <td id=\"T_0b007_row1_col1\" class=\"data row1 col1\" >16.881061</td>\n",
|
|
" <td id=\"T_0b007_row1_col2\" class=\"data row1 col2\" >3.268616</td>\n",
|
|
" <td id=\"T_0b007_row1_col3\" class=\"data row1 col3\" >3.266739</td>\n",
|
|
" <td id=\"T_0b007_row1_col4\" class=\"data row1 col4\" >0.939657</td>\n",
|
|
" <td id=\"T_0b007_row1_col5\" class=\"data row1 col5\" >0.920866</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th id=\"T_0b007_level0_row2\" class=\"row_heading level0 row2\" >linear</th>\n",
|
|
" <td id=\"T_0b007_row2_col0\" class=\"data row2 col0\" >30.840398</td>\n",
|
|
" <td id=\"T_0b007_row2_col1\" class=\"data row2 col1\" >36.882107</td>\n",
|
|
" <td id=\"T_0b007_row2_col2\" class=\"data row2 col2\" >4.679503</td>\n",
|
|
" <td id=\"T_0b007_row2_col3\" class=\"data row2 col3\" >4.594400</td>\n",
|
|
" <td id=\"T_0b007_row2_col4\" class=\"data row2 col4\" >0.883846</td>\n",
|
|
" <td id=\"T_0b007_row2_col5\" class=\"data row2 col5\" >0.827106</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th id=\"T_0b007_level0_row3\" class=\"row_heading level0 row3\" >decision_tree</th>\n",
|
|
" <td id=\"T_0b007_row3_col0\" class=\"data row3 col0\" >10.526316</td>\n",
|
|
" <td id=\"T_0b007_row3_col1\" class=\"data row3 col1\" >47.426471</td>\n",
|
|
" <td id=\"T_0b007_row3_col2\" class=\"data row3 col2\" >1.842105</td>\n",
|
|
" <td id=\"T_0b007_row3_col3\" class=\"data row3 col3\" >5.735294</td>\n",
|
|
" <td id=\"T_0b007_row3_col4\" class=\"data row3 col4\" >0.960355</td>\n",
|
|
" <td id=\"T_0b007_row3_col5\" class=\"data row3 col5\" >0.777676</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th id=\"T_0b007_level0_row4\" class=\"row_heading level0 row4\" >random_forest</th>\n",
|
|
" <td id=\"T_0b007_row4_col0\" class=\"data row4 col0\" >20.214645</td>\n",
|
|
" <td id=\"T_0b007_row4_col1\" class=\"data row4 col1\" >54.501240</td>\n",
|
|
" <td id=\"T_0b007_row4_col2\" class=\"data row4 col2\" >3.570892</td>\n",
|
|
" <td id=\"T_0b007_row4_col3\" class=\"data row4 col3\" >6.598133</td>\n",
|
|
" <td id=\"T_0b007_row4_col4\" class=\"data row4 col4\" >0.923866</td>\n",
|
|
" <td id=\"T_0b007_row4_col5\" class=\"data row4 col5\" >0.744512</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th id=\"T_0b007_level0_row5\" class=\"row_heading level0 row5\" >knn</th>\n",
|
|
" <td id=\"T_0b007_row5_col0\" class=\"data row5 col0\" >161.291622</td>\n",
|
|
" <td id=\"T_0b007_row5_col1\" class=\"data row5 col1\" >140.006002</td>\n",
|
|
" <td id=\"T_0b007_row5_col2\" class=\"data row5 col2\" >10.206767</td>\n",
|
|
" <td id=\"T_0b007_row5_col3\" class=\"data row5 col3\" >9.537815</td>\n",
|
|
" <td id=\"T_0b007_row5_col4\" class=\"data row5 col4\" >0.392527</td>\n",
|
|
" <td id=\"T_0b007_row5_col5\" class=\"data row5 col5\" >0.343686</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th id=\"T_0b007_level0_row6\" class=\"row_heading level0 row6\" >ridge</th>\n",
|
|
" <td id=\"T_0b007_row6_col0\" class=\"data row6 col0\" >204.018844</td>\n",
|
|
" <td id=\"T_0b007_row6_col1\" class=\"data row6 col1\" >162.078696</td>\n",
|
|
" <td id=\"T_0b007_row6_col2\" class=\"data row6 col2\" >12.353188</td>\n",
|
|
" <td id=\"T_0b007_row6_col3\" class=\"data row6 col3\" >10.798642</td>\n",
|
|
" <td id=\"T_0b007_row6_col4\" class=\"data row6 col4\" >0.231604</td>\n",
|
|
" <td id=\"T_0b007_row6_col5\" class=\"data row6 col5\" >0.240215</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n"
|
|
],
|
|
"text/plain": [
|
|
"<pandas.io.formats.style.Styler at 0x169d246e0>"
|
|
]
|
|
},
|
|
"execution_count": 167,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"reg_metrics = pd.DataFrame.from_dict(models, \"index\")[\n",
|
|
" [\"MSE_train\", \"MSE_test\", \"MAE_train\", \"MAE_test\", \"R2_train\", \"R2_test\"]\n",
|
|
"]\n",
|
|
"reg_metrics.sort_values(by=\"MAE_test\").style.background_gradient(\n",
|
|
" cmap=\"viridis\", low=1, high=0.3, subset=[\"MSE_train\", \"MSE_test\"]\n",
|
|
").background_gradient(cmap=\"plasma\", low=0.3, high=1, subset=[\"MAE_test\", \"R2_test\"])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 168,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"|--- Density <= 1.18\n",
|
|
"| |--- Density <= 1.14\n",
|
|
"| | |--- value: [70.00]\n",
|
|
"| |--- Density > 1.14\n",
|
|
"| | |--- Density <= 1.15\n",
|
|
"| | | |--- value: [65.00]\n",
|
|
"| | |--- Density > 1.15\n",
|
|
"| | | |--- value: [60.00]\n",
|
|
"|--- Density > 1.18\n",
|
|
"| |--- Density <= 1.31\n",
|
|
"| | |--- TiO2 <= 0.03\n",
|
|
"| | | |--- Al2O3 <= 0.03\n",
|
|
"| | | | |--- Density <= 1.23\n",
|
|
"| | | | | |--- Density <= 1.20\n",
|
|
"| | | | | | |--- value: [50.00]\n",
|
|
"| | | | | |--- Density > 1.20\n",
|
|
"| | | | | | |--- value: [42.50]\n",
|
|
"| | | | |--- Density > 1.23\n",
|
|
"| | | | | |--- Density <= 1.25\n",
|
|
"| | | | | | |--- value: [35.00]\n",
|
|
"| | | | | |--- Density > 1.25\n",
|
|
"| | | | | | |--- value: [22.50]\n",
|
|
"| | | |--- Al2O3 > 0.03\n",
|
|
"| | | | |--- Density <= 1.26\n",
|
|
"| | | | | |--- Density <= 1.24\n",
|
|
"| | | | | | |--- value: [70.00]\n",
|
|
"| | | | | |--- Density > 1.24\n",
|
|
"| | | | | | |--- value: [65.00]\n",
|
|
"| | | | |--- Density > 1.26\n",
|
|
"| | | | | |--- Density <= 1.29\n",
|
|
"| | | | | | |--- value: [55.00]\n",
|
|
"| | | | | |--- Density > 1.29\n",
|
|
"| | | | | | |--- value: [50.00]\n",
|
|
"| | |--- TiO2 > 0.03\n",
|
|
"| | | |--- Density <= 1.25\n",
|
|
"| | | | |--- value: [70.00]\n",
|
|
"| | | |--- Density > 1.25\n",
|
|
"| | | | |--- Density <= 1.27\n",
|
|
"| | | | | |--- value: [65.00]\n",
|
|
"| | | | |--- Density > 1.27\n",
|
|
"| | | | | |--- value: [60.00]\n",
|
|
"| |--- Density > 1.31\n",
|
|
"| | |--- Density <= 1.57\n",
|
|
"| | | |--- Density <= 1.37\n",
|
|
"| | | | |--- Density <= 1.33\n",
|
|
"| | | | | |--- value: [45.00]\n",
|
|
"| | | | |--- Density > 1.33\n",
|
|
"| | | | | |--- Density <= 1.36\n",
|
|
"| | | | | | |--- value: [40.00]\n",
|
|
"| | | | | |--- Density > 1.36\n",
|
|
"| | | | | | |--- value: [35.00]\n",
|
|
"| | | |--- Density > 1.37\n",
|
|
"| | | | |--- Density <= 1.39\n",
|
|
"| | | | | |--- value: [30.00]\n",
|
|
"| | | | |--- Density > 1.39\n",
|
|
"| | | | | |--- Al2O3 <= 0.03\n",
|
|
"| | | | | | |--- value: [22.50]\n",
|
|
"| | | | | |--- Al2O3 > 0.03\n",
|
|
"| | | | | | |--- value: [20.00]\n",
|
|
"| | |--- Density > 1.57\n",
|
|
"| | | |--- Density <= 1.93\n",
|
|
"| | | | |--- Density <= 1.74\n",
|
|
"| | | | | |--- value: [70.00]\n",
|
|
"| | | | |--- Density > 1.74\n",
|
|
"| | | | | |--- Al2O3 <= 0.15\n",
|
|
"| | | | | | |--- value: [65.00]\n",
|
|
"| | | | | |--- Al2O3 > 0.15\n",
|
|
"| | | | | | |--- value: [50.00]\n",
|
|
"| | | |--- Density > 1.93\n",
|
|
"| | | | |--- Al2O3 <= 0.15\n",
|
|
"| | | | | |--- Density <= 2.09\n",
|
|
"| | | | | | |--- value: [50.00]\n",
|
|
"| | | | | |--- Density > 2.09\n",
|
|
"| | | | | | |--- value: [30.00]\n",
|
|
"| | | | |--- Al2O3 > 0.15\n",
|
|
"| | | | | |--- Density <= 1.95\n",
|
|
"| | | | | | |--- value: [30.00]\n",
|
|
"| | | | | |--- Density > 1.95\n",
|
|
"| | | | | | |--- value: [22.50]\n",
|
|
"\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"model = models[\"decision_tree\"][\"fitted\"]\n",
|
|
"rules = tree.export_text(\n",
|
|
" model, feature_names=X_train.columns.values.tolist()\n",
|
|
")\n",
|
|
"print(rules)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 169,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import pickle\n",
|
|
"\n",
|
|
"pickle.dump(model, open(\"data/temp_density_tree.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": "3.12.9"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|