diff --git a/data/temp_density_tree.model.sav b/data/temp_density_tree.model.sav new file mode 100644 index 0000000..69c059a Binary files /dev/null and b/data/temp_density_tree.model.sav differ diff --git a/data/temp_viscosity_tree.model.sav b/data/temp_viscosity_tree.model.sav new file mode 100644 index 0000000..8f85a5d Binary files /dev/null and b/data/temp_viscosity_tree.model.sav differ diff --git a/temp_density_regression.ipynb b/temp_density_regression.ipynb new file mode 100644 index 0000000..03ee448 --- /dev/null +++ b/temp_density_regression.ipynb @@ -0,0 +1,773 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
TAl2O3TiO2Density
0200.00.01.06250
1250.00.01.05979
2350.00.01.05404
3400.00.01.05103
4450.00.01.04794
\n", + "
" + ], + "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\n", + "3 40 0.0 0.0 1.05103\n", + "4 45 0.0 0.0 1.04794" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
TAl2O3TiO2Density
0300.000.01.05696
1550.000.01.04158
2250.050.01.08438
3300.050.01.08112
4350.050.01.07781
\n", + "
" + ], + "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\n", + "3 30 0.05 0.0 1.08112\n", + "4 35 0.05 0.0 1.07781" + ] + }, + "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", + "display(train.head())\n", + "display(test.head())" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Al2O3TiO2Density
00.00.01.06250
10.00.01.05979
20.00.01.05404
30.00.01.05103
40.00.01.04794
\n", + "
" + ], + "text/plain": [ + " Al2O3 TiO2 Density\n", + "0 0.0 0.0 1.06250\n", + "1 0.0 0.0 1.05979\n", + "2 0.0 0.0 1.05404\n", + "3 0.0 0.0 1.05103\n", + "4 0.0 0.0 1.04794" + ] + }, + "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": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Al2O3TiO2Density
00.000.01.05696
10.000.01.04158
20.050.01.08438
30.050.01.08112
40.050.01.07781
\n", + "
" + ], + "text/plain": [ + " Al2O3 TiO2 Density\n", + "0 0.00 0.0 1.05696\n", + "1 0.00 0.0 1.04158\n", + "2 0.05 0.0 1.08438\n", + "3 0.05 0.0 1.08112\n", + "4 0.05 0.0 1.07781" + ] + }, + "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": 29, + "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": 30, + "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": 31, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
 MSE_trainMSE_testMAE_trainMAE_testR2_trainR2_test
linear_poly0.3027680.2032930.4194670.3926870.9988600.999047
linear_interact9.69332310.8754422.5449442.7184240.9634920.949019
linear10.46850314.8203152.6574762.9302290.9605720.930526
decision_tree10.52631647.4264711.8421055.7352940.9603550.777676
random_forest20.24387654.5012403.5929536.5981330.9237550.744512
knn174.100430191.17647110.80827111.6806720.3442850.103812
ridge243.364664199.60147713.47272412.3967990.0834150.064317
\n" + ], + "text/plain": [ + "" + ] + }, + "execution_count": 31, + "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": 32, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "|--- Density <= 1.04\n", + "| |--- Density <= 1.03\n", + "| | |--- value: [70.00]\n", + "| |--- Density > 1.03\n", + "| | |--- Density <= 1.04\n", + "| | | |--- value: [65.00]\n", + "| | |--- Density > 1.04\n", + "| | | |--- value: [60.00]\n", + "|--- Density > 1.04\n", + "| |--- Density <= 1.07\n", + "| | |--- TiO2 <= 0.03\n", + "| | | |--- Al2O3 <= 0.03\n", + "| | | | |--- Density <= 1.05\n", + "| | | | | |--- Density <= 1.05\n", + "| | | | | | |--- value: [50.00]\n", + "| | | | | |--- Density > 1.05\n", + "| | | | | | |--- value: [42.50]\n", + "| | | | |--- Density > 1.05\n", + "| | | | | |--- Density <= 1.06\n", + "| | | | | | |--- value: [35.00]\n", + "| | | | | |--- Density > 1.06\n", + "| | | | | | |--- value: [22.50]\n", + "| | | |--- Al2O3 > 0.03\n", + "| | | | |--- Density <= 1.06\n", + "| | | | | |--- Density <= 1.05\n", + "| | | | | | |--- value: [70.00]\n", + "| | | | | |--- Density > 1.05\n", + "| | | | | | |--- value: [65.00]\n", + "| | | | |--- Density > 1.06\n", + "| | | | | |--- Density <= 1.07\n", + "| | | | | | |--- value: [55.00]\n", + "| | | | | |--- Density > 1.07\n", + "| | | | | | |--- value: [50.00]\n", + "| | |--- TiO2 > 0.03\n", + "| | | |--- Density <= 1.06\n", + "| | | | |--- value: [70.00]\n", + "| | | |--- Density > 1.06\n", + "| | | | |--- Density <= 1.06\n", + "| | | | | |--- value: [65.00]\n", + "| | | | |--- Density > 1.06\n", + "| | | | | |--- value: [60.00]\n", + "| |--- Density > 1.07\n", + "| | |--- Density <= 1.12\n", + "| | | |--- Density <= 1.08\n", + "| | | | |--- Density <= 1.07\n", + "| | | | | |--- value: [45.00]\n", + "| | | | |--- Density > 1.07\n", + "| | | | | |--- Density <= 1.08\n", + "| | | | | | |--- value: [40.00]\n", + "| | | | | |--- Density > 1.08\n", + "| | | | | | |--- value: [35.00]\n", + "| | | |--- Density > 1.08\n", + "| | | | |--- Density <= 1.09\n", + "| | | | | |--- value: [30.00]\n", + "| | | | |--- Density > 1.09\n", + "| | | | | |--- Al2O3 <= 0.03\n", + "| | | | | | |--- value: [22.50]\n", + "| | | | | |--- Al2O3 > 0.03\n", + "| | | | | | |--- value: [20.00]\n", + "| | |--- Density > 1.12\n", + "| | | |--- Density <= 1.18\n", + "| | | | |--- Density <= 1.15\n", + "| | | | | |--- value: [70.00]\n", + "| | | | |--- Density > 1.15\n", + "| | | | | |--- Al2O3 <= 0.15\n", + "| | | | | | |--- value: [65.00]\n", + "| | | | | |--- Al2O3 > 0.15\n", + "| | | | | | |--- value: [50.00]\n", + "| | | |--- Density > 1.18\n", + "| | | | |--- Al2O3 <= 0.15\n", + "| | | | | |--- Density <= 1.20\n", + "| | | | | | |--- value: [50.00]\n", + "| | | | | |--- Density > 1.20\n", + "| | | | | | |--- value: [30.00]\n", + "| | | | |--- Al2O3 > 0.15\n", + "| | | | | |--- Density <= 1.18\n", + "| | | | | | |--- value: [30.00]\n", + "| | | | | |--- Density > 1.18\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": 33, + "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 +} diff --git a/temp_density_tree.ipynb b/temp_density_tree.ipynb new file mode 100644 index 0000000..750f8f7 --- /dev/null +++ b/temp_density_tree.ipynb @@ -0,0 +1,1417 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 88, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "|--- Density <= 1.04\n", + "| |--- Density <= 1.03\n", + "| | |--- value: [70.00]\n", + "| |--- Density > 1.03\n", + "| | |--- Density <= 1.04\n", + "| | | |--- value: [65.00]\n", + "| | |--- Density > 1.04\n", + "| | | |--- value: [60.00]\n", + "|--- Density > 1.04\n", + "| |--- Density <= 1.07\n", + "| | |--- TiO2 <= 0.03\n", + "| | | |--- Al2O3 <= 0.03\n", + "| | | | |--- Density <= 1.05\n", + "| | | | | |--- Density <= 1.05\n", + "| | | | | | |--- value: [50.00]\n", + "| | | | | |--- Density > 1.05\n", + "| | | | | | |--- value: [42.50]\n", + "| | | | |--- Density > 1.05\n", + "| | | | | |--- Density <= 1.06\n", + "| | | | | | |--- value: [35.00]\n", + "| | | | | |--- Density > 1.06\n", + "| | | | | | |--- value: [22.50]\n", + "| | | |--- Al2O3 > 0.03\n", + "| | | | |--- Density <= 1.06\n", + "| | | | | |--- Density <= 1.05\n", + "| | | | | | |--- value: [70.00]\n", + "| | | | | |--- Density > 1.05\n", + "| | | | | | |--- value: [65.00]\n", + "| | | | |--- Density > 1.06\n", + "| | | | | |--- Density <= 1.07\n", + "| | | | | | |--- value: [55.00]\n", + "| | | | | |--- Density > 1.07\n", + "| | | | | | |--- value: [50.00]\n", + "| | |--- TiO2 > 0.03\n", + "| | | |--- Density <= 1.06\n", + "| | | | |--- value: [70.00]\n", + "| | | |--- Density > 1.06\n", + "| | | | |--- Density <= 1.06\n", + "| | | | | |--- value: [65.00]\n", + "| | | | |--- Density > 1.06\n", + "| | | | | |--- value: [60.00]\n", + "| |--- Density > 1.07\n", + "| | |--- Density <= 1.12\n", + "| | | |--- Density <= 1.08\n", + "| | | | |--- Density <= 1.07\n", + "| | | | | |--- value: [45.00]\n", + "| | | | |--- Density > 1.07\n", + "| | | | | |--- Density <= 1.08\n", + "| | | | | | |--- value: [40.00]\n", + "| | | | | |--- Density > 1.08\n", + "| | | | | | |--- value: [35.00]\n", + "| | | |--- Density > 1.08\n", + "| | | | |--- Density <= 1.09\n", + "| | | | | |--- value: [30.00]\n", + "| | | | |--- Density > 1.09\n", + "| | | | | |--- Al2O3 <= 0.03\n", + "| | | | | | |--- value: [22.50]\n", + "| | | | | |--- Al2O3 > 0.03\n", + "| | | | | | |--- value: [20.00]\n", + "| | |--- Density > 1.12\n", + "| | | |--- Density <= 1.18\n", + "| | | | |--- Density <= 1.15\n", + "| | | | | |--- value: [70.00]\n", + "| | | | |--- Density > 1.15\n", + "| | | | | |--- Al2O3 <= 0.15\n", + "| | | | | | |--- value: [65.00]\n", + "| | | | | |--- Al2O3 > 0.15\n", + "| | | | | | |--- value: [50.00]\n", + "| | | |--- Density > 1.18\n", + "| | | | |--- Al2O3 <= 0.15\n", + "| | | | | |--- Density <= 1.20\n", + "| | | | | | |--- value: [50.00]\n", + "| | | | | |--- Density > 1.20\n", + "| | | | | | |--- value: [30.00]\n", + "| | | | |--- Al2O3 > 0.15\n", + "| | | | | |--- Density <= 1.18\n", + "| | | | | | |--- value: [30.00]\n", + "| | | | | |--- Density > 1.18\n", + "| | | | | | |--- value: [22.50]\n", + "\n" + ] + } + ], + "source": [ + "import pickle\n", + "import pandas as pd\n", + "from sklearn import tree\n", + "\n", + "model = pickle.load(open(\"data/temp_density_tree.model.sav\", \"rb\"))\n", + "features = (\n", + " pd.read_csv(\"data/density_train.csv\", sep=\";\", decimal=\",\")\n", + " .drop([\"T\"], axis=1)\n", + " .columns.values.tolist()\n", + ")\n", + "\n", + "rules = tree.export_text(model, feature_names=features)\n", + "print(rules)" + ] + }, + { + "cell_type": "code", + "execution_count": 89, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "27" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [ + "[if (Density > 1.042) and (Density > 1.069) and (Density <= 1.118) and (Density > 1.083) and (Density > 1.086) and (Al2O3 > 0.025) -> 20.0,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 <= 0.025) and (Al2O3 <= 0.025) and (Density > 1.053) and (Density > 1.057) -> 22.5,\n", + " if (Density <= 1.042) and (Density > 1.033) and (Density > 1.037) -> 60.0,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 <= 0.025) and (Al2O3 <= 0.025) and (Density <= 1.053) and (Density <= 1.046) -> 50.0,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 <= 0.025) and (Al2O3 <= 0.025) and (Density <= 1.053) and (Density > 1.046) -> 42.5,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 <= 0.025) and (Al2O3 <= 0.025) and (Density > 1.053) and (Density <= 1.057) -> 35.0,\n", + " if (Density <= 1.042) and (Density > 1.033) and (Density <= 1.037) -> 65.0,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 <= 0.025) and (Al2O3 > 0.025) and (Density <= 1.061) and (Density <= 1.055) -> 70.0,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 <= 0.025) and (Al2O3 > 0.025) and (Density <= 1.061) and (Density > 1.055) -> 65.0,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 <= 0.025) and (Al2O3 > 0.025) and (Density > 1.061) and (Density <= 1.066) -> 55.0,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 <= 0.025) and (Al2O3 > 0.025) and (Density > 1.061) and (Density > 1.066) -> 50.0,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 > 0.025) and (Density <= 1.058) -> 70.0,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 > 0.025) and (Density > 1.058) and (Density <= 1.062) -> 65.0,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 > 0.025) and (Density > 1.058) and (Density > 1.062) -> 60.0,\n", + " if (Density > 1.042) and (Density > 1.069) and (Density <= 1.118) and (Density <= 1.083) and (Density <= 1.074) -> 45.0,\n", + " if (Density > 1.042) and (Density > 1.069) and (Density <= 1.118) and (Density <= 1.083) and (Density > 1.074) and (Density <= 1.079) -> 40.0,\n", + " if (Density > 1.042) and (Density > 1.069) and (Density <= 1.118) and (Density <= 1.083) and (Density > 1.074) and (Density > 1.079) -> 35.0,\n", + " if (Density > 1.042) and (Density > 1.069) and (Density <= 1.118) and (Density > 1.083) and (Density <= 1.086) -> 30.0,\n", + " if (Density > 1.042) and (Density > 1.069) and (Density <= 1.118) and (Density > 1.083) and (Density > 1.086) and (Al2O3 <= 0.025) -> 22.5,\n", + " if (Density <= 1.042) and (Density <= 1.033) -> 70.0,\n", + " if (Density > 1.042) and (Density > 1.069) and (Density > 1.118) and (Density <= 1.179) and (Density <= 1.148) -> 70.0,\n", + " if (Density > 1.042) and (Density > 1.069) and (Density > 1.118) and (Density <= 1.179) and (Density > 1.148) and (Al2O3 <= 0.15) -> 65.0,\n", + " if (Density > 1.042) and (Density > 1.069) and (Density > 1.118) and (Density <= 1.179) and (Density > 1.148) and (Al2O3 > 0.15) -> 50.0,\n", + " if (Density > 1.042) and (Density > 1.069) and (Density > 1.118) and (Density > 1.179) and (Al2O3 <= 0.15) and (Density <= 1.203) -> 50.0,\n", + " if (Density > 1.042) and (Density > 1.069) and (Density > 1.118) and (Density > 1.179) and (Al2O3 <= 0.15) and (Density > 1.203) -> 30.0,\n", + " if (Density > 1.042) and (Density > 1.069) and (Density > 1.118) and (Density > 1.179) and (Al2O3 > 0.15) and (Density <= 1.182) -> 30.0,\n", + " if (Density > 1.042) and (Density > 1.069) and (Density > 1.118) and (Density > 1.179) and (Al2O3 > 0.15) and (Density > 1.182) -> 22.5]" + ] + }, + "execution_count": 89, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from src.rules import get_rules\n", + "\n", + "\n", + "rules = get_rules(model, features)\n", + "display(len(rules))\n", + "rules" + ] + }, + { + "cell_type": "code", + "execution_count": 90, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "27" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [ + "[if (Density > 1.042) and (Density <= 1.118) and (Al2O3 > 0.025) -> 20.0,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 <= 0.025) and (Al2O3 <= 0.025) -> 22.5,\n", + " if (Density <= 1.042) and (Density > 1.033) -> 60.0,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 <= 0.025) and (Al2O3 <= 0.025) -> 50.0,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 <= 0.025) and (Al2O3 <= 0.025) -> 42.5,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 <= 0.025) and (Al2O3 <= 0.025) -> 35.0,\n", + " if (Density <= 1.042) and (Density > 1.033) -> 65.0,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 <= 0.025) and (Al2O3 > 0.025) -> 70.0,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 <= 0.025) and (Al2O3 > 0.025) -> 65.0,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 <= 0.025) and (Al2O3 > 0.025) -> 55.0,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 <= 0.025) and (Al2O3 > 0.025) -> 50.0,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 > 0.025) -> 70.0,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 > 0.025) -> 65.0,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 > 0.025) -> 60.0,\n", + " if (Density > 1.042) and (Density <= 1.118) -> 45.0,\n", + " if (Density > 1.042) and (Density <= 1.118) -> 40.0,\n", + " if (Density > 1.042) and (Density <= 1.118) -> 35.0,\n", + " if (Density > 1.042) and (Density <= 1.118) -> 30.0,\n", + " if (Density > 1.042) and (Density <= 1.118) and (Al2O3 <= 0.025) -> 22.5,\n", + " if (Density <= 1.042) -> 70.0,\n", + " if (Density > 1.042) and (Density <= 1.179) -> 70.0,\n", + " if (Density > 1.042) and (Density <= 1.179) and (Al2O3 <= 0.15) -> 65.0,\n", + " if (Density > 1.042) and (Density <= 1.179) and (Al2O3 > 0.15) -> 50.0,\n", + " if (Density > 1.042) and (Density <= 1.203) and (Al2O3 <= 0.15) -> 50.0,\n", + " if (Density > 1.042) and (Al2O3 <= 0.15) -> 30.0,\n", + " if (Density > 1.042) and (Density <= 1.182) and (Al2O3 > 0.15) -> 30.0,\n", + " if (Density > 1.042) and (Al2O3 > 0.15) -> 22.5]" + ] + }, + "execution_count": 90, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from src.rules import normalise_rules\n", + "\n", + "\n", + "rules = normalise_rules(rules)\n", + "display(len(rules))\n", + "rules" + ] + }, + { + "cell_type": "code", + "execution_count": 91, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "15" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [ + "[if (Density > 1.042) and (Density <= 1.118) and (Al2O3 > 0.025) -> 20.0,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 <= 0.025) and (Al2O3 <= 0.025) -> 37.5,\n", + " if (Density <= 1.042) and (Density > 1.033) -> 62.5,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 <= 0.025) and (Al2O3 > 0.025) -> 60.0,\n", + " if (Density > 1.042) and (Density <= 1.069) and (TiO2 > 0.025) -> 65.0,\n", + " if (Density > 1.042) and (Density <= 1.118) -> 37.5,\n", + " if (Density > 1.042) and (Density <= 1.118) and (Al2O3 <= 0.025) -> 22.5,\n", + " if (Density <= 1.042) -> 70.0,\n", + " if (Density > 1.042) and (Density <= 1.179) -> 70.0,\n", + " if (Density > 1.042) and (Density <= 1.179) and (Al2O3 <= 0.15) -> 65.0,\n", + " if (Density > 1.042) and (Density <= 1.179) and (Al2O3 > 0.15) -> 50.0,\n", + " if (Density > 1.042) and (Density <= 1.203) and (Al2O3 <= 0.15) -> 50.0,\n", + " if (Density > 1.042) and (Al2O3 <= 0.15) -> 30.0,\n", + " if (Density > 1.042) and (Density <= 1.182) and (Al2O3 > 0.15) -> 30.0,\n", + " if (Density > 1.042) and (Al2O3 > 0.15) -> 22.5]" + ] + }, + "execution_count": 91, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from src.rules import delete_same_rules\n", + "\n", + "\n", + "rules = delete_same_rules(rules)\n", + "display(len(rules))\n", + "rules" + ] + }, + { + "cell_type": "code", + "execution_count": 92, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
TAl2O3TiO2Density
0200.00.01.06250
1250.00.01.05979
2350.00.01.05404
\n", + "
" + ], + "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": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
TAl2O3TiO2Density
0300.000.01.05696
1550.000.01.04158
2250.050.01.08438
\n", + "
" + ], + "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": [ + "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": 93, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "15" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [ + "[if (Density = 1.08) and (Al2O3 = 0.3) -> 20.0,\n", + " if (Density = 1.055) and (TiO2 = 0.0) and (Al2O3 = 0.0) -> 37.5,\n", + " if (Density = 1.037) -> 62.5,\n", + " if (Density = 1.055) and (TiO2 = 0.0) and (Al2O3 = 0.3) -> 60.0,\n", + " if (Density = 1.055) and (TiO2 = 0.3) -> 65.0,\n", + " if (Density = 1.08) -> 37.5,\n", + " if (Density = 1.08) and (Al2O3 = 0.0) -> 22.5,\n", + " if (Density = 1.032) -> 70.0,\n", + " if (Density = 1.11) -> 70.0,\n", + " if (Density = 1.11) and (Al2O3 = 0.0) -> 65.0,\n", + " if (Density = 1.11) and (Al2O3 = 0.3) -> 50.0,\n", + " if (Density = 1.122) and (Al2O3 = 0.0) -> 50.0,\n", + " if (Density = 1.219) and (Al2O3 = 0.0) -> 30.0,\n", + " if (Density = 1.112) and (Al2O3 = 0.3) -> 30.0,\n", + " if (Density = 1.219) and (Al2O3 = 0.3) -> 22.5]" + ] + }, + "execution_count": 93, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from src.rules import simplify_rules\n", + "\n", + "rules = simplify_rules(density_train, rules)\n", + "display(len(rules))\n", + "rules" + ] + }, + { + "cell_type": "code", + "execution_count": 107, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/Users/user/Projects/python/fuzzy-rules-generator/.venv/lib/python3.12/site-packages/skfuzzy/control/fuzzyvariable.py:125: UserWarning: FigureCanvasAgg is non-interactive, and thus cannot be shown\n", + " fig.show()\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "import numpy as np\n", + "from skfuzzy import control as ctrl\n", + "import skfuzzy as fuzz\n", + "\n", + "al = ctrl.Antecedent(np.arange(0, 0.3, 0.005), \"al\")\n", + "ti = ctrl.Antecedent(np.arange(0, 0.3, 0.005), \"ti\")\n", + "density = ctrl.Antecedent(np.arange(1.03, 1.22, 0.00001), \"density\")\n", + "temp = ctrl.Consequent(density_train[\"T\"].sort_values().unique(), \"temp\")\n", + "# temp = ctrl.Consequent(np.arange(20, 70, 5), \"temp\")\n", + "\n", + "al.automf(3, variable_type=\"quant\")\n", + "al.view()\n", + "ti.automf(3, variable_type=\"quant\")\n", + "ti.view()\n", + "density.automf(3, variable_type=\"quant\")\n", + "density.view()\n", + "temp.automf(3, variable_type=\"quant\")\n", + "temp.view()" + ] + }, + { + "cell_type": "code", + "execution_count": 108, + "metadata": {}, + "outputs": [], + "source": [ + "# from skfuzzy.control.fuzzyvariable import FuzzyVariable\n", + "# from skfuzzy.control.rule import Rule as FuzzyRule\n", + "# from skfuzzy.control.term import Term\n", + "# from typing import List, Tuple\n", + "\n", + "# from functools import reduce\n", + "# from operator import and_\n", + "\n", + "# from src.rules import RuleAtom\n", + "\n", + "# def gfa(\n", + "# fuzzy_variable: FuzzyVariable, value: float\n", + "# ) -> Tuple[Term, float]:\n", + "# values = {}\n", + "# for term in fuzzy_variable.terms:\n", + "# mval = np.interp(value, fuzzy_variable.universe, fuzzy_variable[term].mf)\n", + "# values[term] = mval\n", + "# best_value = sorted(values.items(), key=lambda x: x[1], reverse=True)[0]\n", + "# return (fuzzy_variable[best_value[0]], best_value[1])\n", + "\n", + "\n", + "# def dsfr(\n", + "# rules: List[Tuple[List[RuleAtom], Term, float]]\n", + "# ) -> List[Tuple[List[RuleAtom], Term, float]]:\n", + "# same_rules: List[int] = []\n", + "# for rule1_index, rule1 in enumerate(rules):\n", + "# for rule2_index, rule2 in enumerate(rules):\n", + "# if rule1_index >= rule2_index:\n", + "# continue\n", + "# # Remove the same rules\n", + "# if str(rule1[0]) == str(rule2[0]) and str(rule1[1]) == str(rule2[1]):\n", + "# same_rules.append(rule1_index)\n", + "# break\n", + "# # If antecedents is equals, but consequents is not equals then\n", + "# # Remove rule with the higher antecedent weight\n", + "# if str(rule1[0]) == str(rule2[0]) and str(rule1[2]) <= str(rule2[2]):\n", + "# same_rules.append(rule2_index)\n", + "# break\n", + "# if str(rule1[0]) == str(rule2[0]) and str(rule1[2]) > str(rule2[2]):\n", + "# same_rules.append(rule1_index)\n", + "# break\n", + "# return [rule for index, rule in enumerate(rules) if index not in same_rules]\n", + "\n", + "# display(rules)\n", + "\n", + "# fuzzy_variables = {\"Al2O3\": al, \"TiO2\": ti, \"Density\": density, \"consequent\": temp}\n", + "# fuzzy_rules: List[Tuple[List[RuleAtom], Term, float]] = []\n", + "# for rule in rules:\n", + "# tmp_rule = []\n", + "# for atom in rule.get_antecedent():\n", + "# if fuzzy_variables.get(atom.get_varaible(), None) is None:\n", + "# continue\n", + "# variable = gfa(fuzzy_variables[atom.get_varaible()], atom.get_value())\n", + "# tmp_rule.append(variable)\n", + "# # if tmp_rule.get(variable[0].parent, None) is None:\n", + "# # tmp_rule[variable[0].parent] = variable\n", + "# # else:\n", + "# # if tmp_rule[variable[0].parent][1] > variable[1]:\n", + "# # tmp_rule[variable[0].parent] = variable\n", + "# consequent = gfa(\n", + "# fuzzy_variables[\"consequent\"], rule.get_consequent()\n", + "# )[0]\n", + "# fuzzy_rules.append(\n", + "# (\n", + "# # FuzzyRule(reduce(and_, [atom[0] for atom in antecedent]), consequent),\n", + "# [atom[0] for atom in tmp_rule],\n", + "# consequent,\n", + "# sum([atom[1] for atom in tmp_rule]),\n", + "# )\n", + "# )\n", + "# fuzzy_rules = dsfr(fuzzy_rules)\n", + "# frules = [FuzzyRule(reduce(and_, item[0]), item[1]) for item in fuzzy_rules]\n", + "# display(len(frules))\n", + "# display(frules)\n", + "\n", + "# # fuzzy_cntrl = ctrl.ControlSystem(frules)\n", + "\n", + "# # sim = ctrl.ControlSystemSimulation(fuzzy_cntrl, lenient=False)" + ] + }, + { + "cell_type": "code", + "execution_count": 109, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "9" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [ + "[IF density[average] AND al[high] THEN temp[low]\n", + " \tAND aggregation function : fmin\n", + " \tOR aggregation function : fmax,\n", + " IF (density[low] AND ti[low]) AND al[low] THEN temp[average]\n", + " \tAND aggregation function : fmin\n", + " \tOR aggregation function : fmax,\n", + " IF (density[low] AND ti[low]) AND al[high] THEN temp[high]\n", + " \tAND aggregation function : fmin\n", + " \tOR aggregation function : fmax,\n", + " IF density[low] AND ti[high] THEN temp[high]\n", + " \tAND aggregation function : fmin\n", + " \tOR aggregation function : fmax,\n", + " IF density[average] THEN temp[average]\n", + " \tAND aggregation function : fmin\n", + " \tOR aggregation function : fmax,\n", + " IF density[average] AND al[low] THEN temp[low]\n", + " \tAND aggregation function : fmin\n", + " \tOR aggregation function : fmax,\n", + " IF density[low] THEN temp[high]\n", + " \tAND aggregation function : fmin\n", + " \tOR aggregation function : fmax,\n", + " IF density[high] AND al[low] THEN temp[low]\n", + " \tAND aggregation function : fmin\n", + " \tOR aggregation function : fmax,\n", + " IF density[high] AND al[high] THEN temp[low]\n", + " \tAND aggregation function : fmin\n", + " \tOR aggregation function : fmax]" + ] + }, + "execution_count": 109, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from src.rules import get_fuzzy_rules\n", + "\n", + "fuzzy_variables = {\"Al2O3\": al, \"TiO2\": ti, \"Density\": density, \"consequent\": temp}\n", + "fuzzy_rules = get_fuzzy_rules(rules, fuzzy_variables)\n", + "\n", + "fuzzy_cntrl = ctrl.ControlSystem(fuzzy_rules)\n", + "\n", + "sim = ctrl.ControlSystemSimulation(fuzzy_cntrl, lenient=False)\n", + "\n", + "display(len(fuzzy_rules))\n", + "fuzzy_rules" + ] + }, + { + "cell_type": "code", + "execution_count": 110, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "=============\n", + " Antecedents \n", + "=============\n", + "Antecedent: density = 1.0569013636039\n", + " - low : 0.716812846952748\n", + " - average : 0.283187153047252\n", + " - high : 0.0\n", + "Antecedent: al = 0.0\n", + " - low : 1.0\n", + " - average : 0.0\n", + " - high : 0.0\n", + "Antecedent: ti = 0.0\n", + " - low : 1.0\n", + " - average : 0.0\n", + " - high : 0.0\n", + "\n", + "=======\n", + " Rules \n", + "=======\n", + "RULE #0:\n", + " IF density[average] AND al[high] THEN temp[low]\n", + "\tAND aggregation function : fmin\n", + "\tOR aggregation function : fmax\n", + "\n", + " Aggregation (IF-clause):\n", + " - density[average] : 0.283187153047252\n", + " - al[high] : 0.0\n", + " density[average] AND al[high] = 0.0\n", + " Activation (THEN-clause):\n", + " temp[low] : 0.0\n", + "\n", + "RULE #1:\n", + " IF (density[low] AND ti[low]) AND al[low] THEN temp[average]\n", + "\tAND aggregation function : fmin\n", + "\tOR aggregation function : fmax\n", + "\n", + " Aggregation (IF-clause):\n", + " - density[low] : 0.716812846952748\n", + " - ti[low] : 1.0\n", + " - al[low] : 1.0\n", + " (density[low] AND ti[low]) AND al[low] = 0.716812846952748\n", + " Activation (THEN-clause):\n", + " temp[average] : 0.716812846952748\n", + "\n", + "RULE #2:\n", + " IF (density[low] AND ti[low]) AND al[high] THEN temp[high]\n", + "\tAND aggregation function : fmin\n", + "\tOR aggregation function : fmax\n", + "\n", + " Aggregation (IF-clause):\n", + " - density[low] : 0.716812846952748\n", + " - ti[low] : 1.0\n", + " - al[high] : 0.0\n", + " (density[low] AND ti[low]) AND al[high] = 0.0\n", + " Activation (THEN-clause):\n", + " temp[high] : 0.0\n", + "\n", + "RULE #3:\n", + " IF density[low] AND ti[high] THEN temp[high]\n", + "\tAND aggregation function : fmin\n", + "\tOR aggregation function : fmax\n", + "\n", + " Aggregation (IF-clause):\n", + " - density[low] : 0.716812846952748\n", + " - ti[high] : 0.0\n", + " density[low] AND ti[high] = 0.0\n", + " Activation (THEN-clause):\n", + " temp[high] : 0.0\n", + "\n", + "RULE #4:\n", + " IF density[average] THEN temp[average]\n", + "\tAND aggregation function : fmin\n", + "\tOR aggregation function : fmax\n", + "\n", + " Aggregation (IF-clause):\n", + " - density[average] : 0.283187153047252\n", + " density[average] = 0.283187153047252\n", + " Activation (THEN-clause):\n", + " temp[average] : 0.283187153047252\n", + "\n", + "RULE #5:\n", + " IF density[average] AND al[low] THEN temp[low]\n", + "\tAND aggregation function : fmin\n", + "\tOR aggregation function : fmax\n", + "\n", + " Aggregation (IF-clause):\n", + " - density[average] : 0.283187153047252\n", + " - al[low] : 1.0\n", + " density[average] AND al[low] = 0.283187153047252\n", + " Activation (THEN-clause):\n", + " temp[low] : 0.283187153047252\n", + "\n", + "RULE #6:\n", + " IF density[low] THEN temp[high]\n", + "\tAND aggregation function : fmin\n", + "\tOR aggregation function : fmax\n", + "\n", + " Aggregation (IF-clause):\n", + " - density[low] : 0.716812846952748\n", + " density[low] = 0.716812846952748\n", + " Activation (THEN-clause):\n", + " temp[high] : 0.716812846952748\n", + "\n", + "RULE #7:\n", + " IF density[high] AND al[low] THEN temp[low]\n", + "\tAND aggregation function : fmin\n", + "\tOR aggregation function : fmax\n", + "\n", + " Aggregation (IF-clause):\n", + " - density[high] : 0.0\n", + " - al[low] : 1.0\n", + " density[high] AND al[low] = 0.0\n", + " Activation (THEN-clause):\n", + " temp[low] : 0.0\n", + "\n", + "RULE #8:\n", + " IF density[high] AND al[high] THEN temp[low]\n", + "\tAND aggregation function : fmin\n", + "\tOR aggregation function : fmax\n", + "\n", + " Aggregation (IF-clause):\n", + " - density[high] : 0.0\n", + " - al[high] : 0.0\n", + " density[high] AND al[high] = 0.0\n", + " Activation (THEN-clause):\n", + " temp[low] : 0.0\n", + "\n", + "\n", + "==============================\n", + " Intermediaries and Conquests \n", + "==============================\n", + "Consequent: temp = 47.897027582440735\n", + " low:\n", + " Accumulate using accumulation_max : 0.283187153047252\n", + " average:\n", + " Accumulate using accumulation_max : 0.716812846952748\n", + " high:\n", + " Accumulate using accumulation_max : 0.716812846952748\n", + "\n" + ] + }, + { + "data": { + "text/plain": [ + "np.float64(47.897027582440735)" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# sim.input[\"al\"] = 0.0\n", + "# sim.input[\"ti\"] = 0.0\n", + "# sim.input[\"density\"] = 1.05979\n", + "sim.input[\"al\"] = 0.0\n", + "sim.input[\"ti\"] = 0.0\n", + "sim.input[\"density\"] = 1.0569013636039\n", + "sim.compute()\n", + "sim.print_state()\n", + "display(sim.output[\"temp\"])\n", + "temp.view(sim=sim)" + ] + }, + { + "cell_type": "code", + "execution_count": 111, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
TAl2O3TiO2DensityRealInferredRMSE
0200.000.01.062502047.32794527.327945
1250.000.01.059792547.61147022.611470
2350.000.01.054043548.16503113.165031
3400.000.01.051034048.4329718.432971
4450.000.01.047944548.6518483.651848
5500.000.01.044775048.7796121.220388
6600.000.01.038266049.00736410.992636
7650.000.01.034846549.10921915.890781
8700.000.01.031827049.18916720.810833
9200.050.01.087552043.23573023.235730
10450.050.01.071054546.1596811.159681
11500.050.01.067605046.7455013.254499
12550.050.01.064095547.1536997.846301
13650.050.01.056916547.98349817.016502
14700.050.01.052917048.42865121.571349
\n", + "
" + ], + "text/plain": [ + " T Al2O3 TiO2 Density Real Inferred RMSE\n", + "0 20 0.00 0.0 1.06250 20 47.327945 27.327945\n", + "1 25 0.00 0.0 1.05979 25 47.611470 22.611470\n", + "2 35 0.00 0.0 1.05404 35 48.165031 13.165031\n", + "3 40 0.00 0.0 1.05103 40 48.432971 8.432971\n", + "4 45 0.00 0.0 1.04794 45 48.651848 3.651848\n", + "5 50 0.00 0.0 1.04477 50 48.779612 1.220388\n", + "6 60 0.00 0.0 1.03826 60 49.007364 10.992636\n", + "7 65 0.00 0.0 1.03484 65 49.109219 15.890781\n", + "8 70 0.00 0.0 1.03182 70 49.189167 20.810833\n", + "9 20 0.05 0.0 1.08755 20 43.235730 23.235730\n", + "10 45 0.05 0.0 1.07105 45 46.159681 1.159681\n", + "11 50 0.05 0.0 1.06760 50 46.745501 3.254499\n", + "12 55 0.05 0.0 1.06409 55 47.153699 7.846301\n", + "13 65 0.05 0.0 1.05691 65 47.983498 17.016502\n", + "14 70 0.05 0.0 1.05291 70 48.428651 21.571349" + ] + }, + "execution_count": 111, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from sklearn import metrics\n", + "import math\n", + "\n", + "\n", + "def fuzzy_pred(row):\n", + " sim.input[\"al\"] = row[\"Al2O3\"]\n", + " sim.input[\"ti\"] = row[\"TiO2\"]\n", + " sim.input[\"density\"] = row[\"Density\"]\n", + " sim.compute()\n", + " return sim.output[\"temp\"]\n", + "\n", + "\n", + "def rmse(row):\n", + " return math.sqrt(metrics.mean_squared_error([row[\"Real\"]], [row[\"Inferred\"]]))\n", + "\n", + "\n", + "result_train = density_train.copy()\n", + "result_train[\"Real\"] = result_train[\"T\"]\n", + "result_train[\"Inferred\"] = result_train.apply(fuzzy_pred, axis=1)\n", + "result_train[\"RMSE\"] = result_train.apply(rmse, axis=1)\n", + "result_test = result_test.round({\"RMSE\": 3})\n", + "result_train.head(15)" + ] + }, + { + "cell_type": "code", + "execution_count": 112, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
TAl2O3TiO2DensityRealInferredRMSE
0300.000.001.056963047.89138817.891
1550.000.001.041585548.8968686.103
2250.050.001.084382543.76338518.763
3300.050.001.081123044.34349714.343
4350.050.001.077813544.9427689.943
5400.050.001.074464045.5514335.551
6600.050.001.060536047.56126512.439
7350.300.001.174593541.7250736.725
8650.300.001.148126541.02711023.973
9450.000.051.074244545.5909850.591
10500.000.051.070755046.2127533.787
11550.000.051.067215546.7925898.207
12200.000.301.224172028.3333338.333
13300.000.301.213103032.0522132.052
14400.000.301.202654035.8878974.112
15600.000.301.182656040.49472919.505
16700.000.301.172617042.00721727.993
\n", + "
" + ], + "text/plain": [ + " T Al2O3 TiO2 Density Real Inferred RMSE\n", + "0 30 0.00 0.00 1.05696 30 47.891388 17.891\n", + "1 55 0.00 0.00 1.04158 55 48.896868 6.103\n", + "2 25 0.05 0.00 1.08438 25 43.763385 18.763\n", + "3 30 0.05 0.00 1.08112 30 44.343497 14.343\n", + "4 35 0.05 0.00 1.07781 35 44.942768 9.943\n", + "5 40 0.05 0.00 1.07446 40 45.551433 5.551\n", + "6 60 0.05 0.00 1.06053 60 47.561265 12.439\n", + "7 35 0.30 0.00 1.17459 35 41.725073 6.725\n", + "8 65 0.30 0.00 1.14812 65 41.027110 23.973\n", + "9 45 0.00 0.05 1.07424 45 45.590985 0.591\n", + "10 50 0.00 0.05 1.07075 50 46.212753 3.787\n", + "11 55 0.00 0.05 1.06721 55 46.792589 8.207\n", + "12 20 0.00 0.30 1.22417 20 28.333333 8.333\n", + "13 30 0.00 0.30 1.21310 30 32.052213 2.052\n", + "14 40 0.00 0.30 1.20265 40 35.887897 4.112\n", + "15 60 0.00 0.30 1.18265 60 40.494729 19.505\n", + "16 70 0.00 0.30 1.17261 70 42.007217 27.993" + ] + }, + "execution_count": 112, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "result_test = density_test.copy()\n", + "result_test[\"Real\"] = result_test[\"T\"]\n", + "result_test[\"Inferred\"] = result_test.apply(fuzzy_pred, axis=1)\n", + "result_test[\"RMSE\"] = result_test.apply(rmse, axis=1)\n", + "# result_test[\"RMSE\"] = result_test[\"RMSE\"].apply(lambda x: \"{:,.4f}\".format(x))\n", + "result_test = result_test.round({\"RMSE\": 3})\n", + "result_test" + ] + }, + { + "cell_type": "code", + "execution_count": 113, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'RMSE_train': 15.400435161512734,\n", + " 'RMSE_test': 13.625552728224925,\n", + " 'RMAE_test': 3.345881099161754,\n", + " 'R2_test': 0.12969191263186874}" + ] + }, + "execution_count": 113, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "rmetrics = {}\n", + "rmetrics[\"RMSE_train\"] = math.sqrt(\n", + " metrics.mean_squared_error(result_train[\"Real\"], result_train[\"Inferred\"])\n", + ")\n", + "rmetrics[\"RMSE_test\"] = math.sqrt(\n", + " metrics.mean_squared_error(result_test[\"Real\"], result_test[\"Inferred\"])\n", + ")\n", + "rmetrics[\"RMAE_test\"] = math.sqrt(\n", + " metrics.mean_absolute_error(result_test[\"Real\"], result_test[\"Inferred\"])\n", + ")\n", + "rmetrics[\"R2_test\"] = metrics.r2_score(result_test[\"Real\"], result_test[\"Inferred\"])\n", + "\n", + "rmetrics" + ] + } + ], + "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 +} diff --git a/temp_viscosity_regression.ipynb b/temp_viscosity_regression.ipynb new file mode 100644 index 0000000..1695b81 --- /dev/null +++ b/temp_viscosity_regression.ipynb @@ -0,0 +1,763 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
TAl2O3TiO2Viscosity
0200.00.03.707
1250.00.03.180
2350.00.02.361
3450.00.01.832
4500.00.01.629
\n", + "
" + ], + "text/plain": [ + " T Al2O3 TiO2 Viscosity\n", + "0 20 0.0 0.0 3.707\n", + "1 25 0.0 0.0 3.180\n", + "2 35 0.0 0.0 2.361\n", + "3 45 0.0 0.0 1.832\n", + "4 50 0.0 0.0 1.629" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
TAl2O3TiO2Viscosity
0300.000.02.716
1400.000.02.073
2600.000.01.329
3650.000.01.211
4250.050.04.120
\n", + "
" + ], + "text/plain": [ + " T Al2O3 TiO2 Viscosity\n", + "0 30 0.00 0.0 2.716\n", + "1 40 0.00 0.0 2.073\n", + "2 60 0.00 0.0 1.329\n", + "3 65 0.00 0.0 1.211\n", + "4 25 0.05 0.0 4.120" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "import pandas as pd\n", + "\n", + "train = pd.read_csv(\"data/viscosity_train.csv\", sep=\";\", decimal=\",\")\n", + "test = pd.read_csv(\"data/viscosity_test.csv\", sep=\";\", decimal=\",\")\n", + "\n", + "display(train.head())\n", + "display(test.head())" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Al2O3TiO2Viscosity
00.00.03.707
10.00.03.180
20.00.02.361
30.00.01.832
40.00.01.629
\n", + "
" + ], + "text/plain": [ + " Al2O3 TiO2 Viscosity\n", + "0 0.0 0.0 3.707\n", + "1 0.0 0.0 3.180\n", + "2 0.0 0.0 2.361\n", + "3 0.0 0.0 1.832\n", + "4 0.0 0.0 1.629" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [ + "0 20\n", + "1 25\n", + "2 35\n", + "3 45\n", + "4 50\n", + "Name: T, dtype: int64" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Al2O3TiO2Viscosity
00.000.02.716
10.000.02.073
20.000.01.329
30.000.01.211
40.050.04.120
\n", + "
" + ], + "text/plain": [ + " Al2O3 TiO2 Viscosity\n", + "0 0.00 0.0 2.716\n", + "1 0.00 0.0 2.073\n", + "2 0.00 0.0 1.329\n", + "3 0.00 0.0 1.211\n", + "4 0.05 0.0 4.120" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [ + "0 30\n", + "1 40\n", + "2 60\n", + "3 65\n", + "4 25\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": 10, + "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": 11, + "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": 12, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
 MSE_trainMSE_testMAE_trainMAE_testR2_trainR2_test
linear_poly4.8277684.8772961.5226431.7430580.9808640.974964
linear_interact21.78634823.4595723.8309964.3811150.9136440.879577
linear27.76651035.4303134.0880065.1067820.8899400.818129
ridge31.82747636.2306064.3830085.2264800.8738430.814021
random_forest8.52528545.4446512.5429355.7495100.9662080.766723
decision_tree3.28947445.5882350.9210536.1764710.9869610.765986
knn61.85553264.1656666.5225566.8067230.7548190.670624
\n" + ], + "text/plain": [ + "" + ] + }, + "execution_count": 12, + "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": 13, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "|--- Viscosity <= 2.86\n", + "| |--- Viscosity <= 1.38\n", + "| | |--- value: [70.00]\n", + "| |--- Viscosity > 1.38\n", + "| | |--- Viscosity <= 1.78\n", + "| | | |--- Viscosity <= 1.72\n", + "| | | | |--- TiO2 <= 0.03\n", + "| | | | | |--- Al2O3 <= 0.03\n", + "| | | | | | |--- value: [52.50]\n", + "| | | | | |--- Al2O3 > 0.03\n", + "| | | | | | |--- value: [57.50]\n", + "| | | | |--- TiO2 > 0.03\n", + "| | | | | |--- value: [60.00]\n", + "| | | |--- Viscosity > 1.72\n", + "| | | | |--- value: [70.00]\n", + "| | |--- Viscosity > 1.78\n", + "| | | |--- TiO2 <= 0.18\n", + "| | | | |--- Al2O3 <= 0.18\n", + "| | | | | |--- Viscosity <= 2.24\n", + "| | | | | | |--- value: [50.00]\n", + "| | | | | |--- Viscosity > 2.24\n", + "| | | | | | |--- value: [40.00]\n", + "| | | | |--- Al2O3 > 0.18\n", + "| | | | | |--- Viscosity <= 2.29\n", + "| | | | | | |--- value: [60.00]\n", + "| | | | | |--- Viscosity > 2.29\n", + "| | | | | | |--- value: [55.00]\n", + "| | | |--- TiO2 > 0.18\n", + "| | | | |--- Viscosity <= 2.22\n", + "| | | | | |--- value: [70.00]\n", + "| | | | |--- Viscosity > 2.22\n", + "| | | | | |--- Viscosity <= 2.69\n", + "| | | | | | |--- value: [60.00]\n", + "| | | | | |--- Viscosity > 2.69\n", + "| | | | | | |--- value: [55.00]\n", + "|--- Viscosity > 2.86\n", + "| |--- Viscosity <= 3.64\n", + "| | |--- TiO2 <= 0.18\n", + "| | | |--- Viscosity <= 3.15\n", + "| | | | |--- value: [35.00]\n", + "| | | |--- Viscosity > 3.15\n", + "| | | | |--- Viscosity <= 3.47\n", + "| | | | | |--- Al2O3 <= 0.03\n", + "| | | | | | |--- value: [25.00]\n", + "| | | | | |--- Al2O3 > 0.03\n", + "| | | | | | |--- value: [30.00]\n", + "| | | | |--- Viscosity > 3.47\n", + "| | | | | |--- value: [40.00]\n", + "| | |--- TiO2 > 0.18\n", + "| | | |--- value: [45.00]\n", + "| |--- Viscosity > 3.64\n", + "| | |--- Viscosity <= 6.27\n", + "| | | |--- TiO2 <= 0.18\n", + "| | | | |--- Al2O3 <= 0.18\n", + "| | | | | |--- TiO2 <= 0.03\n", + "| | | | | | |--- value: [20.00]\n", + "| | | | | |--- TiO2 > 0.03\n", + "| | | | | | |--- value: [22.50]\n", + "| | | | |--- Al2O3 > 0.18\n", + "| | | | | |--- Viscosity <= 4.42\n", + "| | | | | | |--- value: [35.00]\n", + "| | | | | |--- Viscosity > 4.42\n", + "| | | | | | |--- value: [27.50]\n", + "| | | |--- TiO2 > 0.18\n", + "| | | | |--- Viscosity <= 4.65\n", + "| | | | | |--- value: [35.00]\n", + "| | | | |--- Viscosity > 4.65\n", + "| | | | | |--- Viscosity <= 5.40\n", + "| | | | | | |--- value: [30.00]\n", + "| | | | | |--- Viscosity > 5.40\n", + "| | | | | | |--- value: [25.00]\n", + "| | |--- Viscosity > 6.27\n", + "| | | |--- value: [20.00]\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": 14, + "metadata": {}, + "outputs": [], + "source": [ + "import pickle\n", + "\n", + "pickle.dump(model, open(\"data/temp_viscosity_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 +} diff --git a/temp_viscosity_tree.ipynb b/temp_viscosity_tree.ipynb new file mode 100644 index 0000000..c04f9e9 --- /dev/null +++ b/temp_viscosity_tree.ipynb @@ -0,0 +1,1357 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "|--- Viscosity <= 2.86\n", + "| |--- Viscosity <= 1.38\n", + "| | |--- value: [70.00]\n", + "| |--- Viscosity > 1.38\n", + "| | |--- Viscosity <= 1.78\n", + "| | | |--- Viscosity <= 1.72\n", + "| | | | |--- TiO2 <= 0.03\n", + "| | | | | |--- Al2O3 <= 0.03\n", + "| | | | | | |--- value: [52.50]\n", + "| | | | | |--- Al2O3 > 0.03\n", + "| | | | | | |--- value: [57.50]\n", + "| | | | |--- TiO2 > 0.03\n", + "| | | | | |--- value: [60.00]\n", + "| | | |--- Viscosity > 1.72\n", + "| | | | |--- value: [70.00]\n", + "| | |--- Viscosity > 1.78\n", + "| | | |--- TiO2 <= 0.18\n", + "| | | | |--- Al2O3 <= 0.18\n", + "| | | | | |--- Viscosity <= 2.24\n", + "| | | | | | |--- value: [50.00]\n", + "| | | | | |--- Viscosity > 2.24\n", + "| | | | | | |--- value: [40.00]\n", + "| | | | |--- Al2O3 > 0.18\n", + "| | | | | |--- Viscosity <= 2.29\n", + "| | | | | | |--- value: [60.00]\n", + "| | | | | |--- Viscosity > 2.29\n", + "| | | | | | |--- value: [55.00]\n", + "| | | |--- TiO2 > 0.18\n", + "| | | | |--- Viscosity <= 2.22\n", + "| | | | | |--- value: [70.00]\n", + "| | | | |--- Viscosity > 2.22\n", + "| | | | | |--- Viscosity <= 2.69\n", + "| | | | | | |--- value: [60.00]\n", + "| | | | | |--- Viscosity > 2.69\n", + "| | | | | | |--- value: [55.00]\n", + "|--- Viscosity > 2.86\n", + "| |--- Viscosity <= 3.64\n", + "| | |--- TiO2 <= 0.18\n", + "| | | |--- Viscosity <= 3.15\n", + "| | | | |--- value: [35.00]\n", + "| | | |--- Viscosity > 3.15\n", + "| | | | |--- Viscosity <= 3.47\n", + "| | | | | |--- Al2O3 <= 0.03\n", + "| | | | | | |--- value: [25.00]\n", + "| | | | | |--- Al2O3 > 0.03\n", + "| | | | | | |--- value: [30.00]\n", + "| | | | |--- Viscosity > 3.47\n", + "| | | | | |--- value: [40.00]\n", + "| | |--- TiO2 > 0.18\n", + "| | | |--- value: [45.00]\n", + "| |--- Viscosity > 3.64\n", + "| | |--- Viscosity <= 6.27\n", + "| | | |--- TiO2 <= 0.18\n", + "| | | | |--- Al2O3 <= 0.18\n", + "| | | | | |--- TiO2 <= 0.03\n", + "| | | | | | |--- value: [20.00]\n", + "| | | | | |--- TiO2 > 0.03\n", + "| | | | | | |--- value: [22.50]\n", + "| | | | |--- Al2O3 > 0.18\n", + "| | | | | |--- Viscosity <= 4.42\n", + "| | | | | | |--- value: [35.00]\n", + "| | | | | |--- Viscosity > 4.42\n", + "| | | | | | |--- value: [27.50]\n", + "| | | |--- TiO2 > 0.18\n", + "| | | | |--- Viscosity <= 4.65\n", + "| | | | | |--- value: [35.00]\n", + "| | | | |--- Viscosity > 4.65\n", + "| | | | | |--- Viscosity <= 5.40\n", + "| | | | | | |--- value: [30.00]\n", + "| | | | | |--- Viscosity > 5.40\n", + "| | | | | | |--- value: [25.00]\n", + "| | |--- Viscosity > 6.27\n", + "| | | |--- value: [20.00]\n", + "\n" + ] + } + ], + "source": [ + "import pickle\n", + "import pandas as pd\n", + "from sklearn import tree\n", + "\n", + "model = pickle.load(open(\"data/temp_viscosity_tree.model.sav\", \"rb\"))\n", + "features = (\n", + " pd.read_csv(\"data/viscosity_train.csv\", sep=\";\", decimal=\",\")\n", + " .drop([\"T\"], axis=1)\n", + " .columns.values.tolist()\n", + ")\n", + "\n", + "rules = tree.export_text(model, feature_names=features)\n", + "print(rules)" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "25" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [ + "[if (Viscosity > 2.856) and (Viscosity > 3.636) and (Viscosity <= 6.267) and (TiO2 <= 0.175) and (Al2O3 <= 0.175) and (TiO2 <= 0.025) -> 20.0,\n", + " if (Viscosity > 2.856) and (Viscosity > 3.636) and (Viscosity > 6.267) -> 20.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (Viscosity <= 1.78) and (Viscosity <= 1.719) and (TiO2 <= 0.025) and (Al2O3 > 0.025) -> 57.5,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (Viscosity <= 1.78) and (Viscosity <= 1.719) and (TiO2 > 0.025) -> 60.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (Viscosity <= 1.78) and (Viscosity > 1.719) -> 70.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (Viscosity > 1.78) and (TiO2 <= 0.175) and (Al2O3 <= 0.175) and (Viscosity <= 2.235) -> 50.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (Viscosity > 1.78) and (TiO2 <= 0.175) and (Al2O3 <= 0.175) and (Viscosity > 2.235) -> 40.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (Viscosity > 1.78) and (TiO2 <= 0.175) and (Al2O3 > 0.175) and (Viscosity <= 2.293) -> 60.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (Viscosity > 1.78) and (TiO2 <= 0.175) and (Al2O3 > 0.175) and (Viscosity > 2.293) -> 55.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (Viscosity > 1.78) and (TiO2 > 0.175) and (Viscosity <= 2.224) -> 70.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (Viscosity > 1.78) and (TiO2 > 0.175) and (Viscosity > 2.224) and (Viscosity <= 2.688) -> 60.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (Viscosity > 1.78) and (TiO2 > 0.175) and (Viscosity > 2.224) and (Viscosity > 2.688) -> 55.0,\n", + " if (Viscosity > 2.856) and (Viscosity <= 3.636) and (TiO2 <= 0.175) and (Viscosity <= 3.151) -> 35.0,\n", + " if (Viscosity > 2.856) and (Viscosity <= 3.636) and (TiO2 <= 0.175) and (Viscosity > 3.151) and (Viscosity <= 3.473) and (Al2O3 <= 0.025) -> 25.0,\n", + " if (Viscosity > 2.856) and (Viscosity <= 3.636) and (TiO2 <= 0.175) and (Viscosity > 3.151) and (Viscosity <= 3.473) and (Al2O3 > 0.025) -> 30.0,\n", + " if (Viscosity > 2.856) and (Viscosity <= 3.636) and (TiO2 <= 0.175) and (Viscosity > 3.151) and (Viscosity > 3.473) -> 40.0,\n", + " if (Viscosity > 2.856) and (Viscosity <= 3.636) and (TiO2 > 0.175) -> 45.0,\n", + " if (Viscosity <= 2.856) and (Viscosity <= 1.377) -> 70.0,\n", + " if (Viscosity > 2.856) and (Viscosity > 3.636) and (Viscosity <= 6.267) and (TiO2 <= 0.175) and (Al2O3 <= 0.175) and (TiO2 > 0.025) -> 22.5,\n", + " if (Viscosity > 2.856) and (Viscosity > 3.636) and (Viscosity <= 6.267) and (TiO2 <= 0.175) and (Al2O3 > 0.175) and (Viscosity <= 4.424) -> 35.0,\n", + " if (Viscosity > 2.856) and (Viscosity > 3.636) and (Viscosity <= 6.267) and (TiO2 <= 0.175) and (Al2O3 > 0.175) and (Viscosity > 4.424) -> 27.5,\n", + " if (Viscosity > 2.856) and (Viscosity > 3.636) and (Viscosity <= 6.267) and (TiO2 > 0.175) and (Viscosity <= 4.649) -> 35.0,\n", + " if (Viscosity > 2.856) and (Viscosity > 3.636) and (Viscosity <= 6.267) and (TiO2 > 0.175) and (Viscosity > 4.649) and (Viscosity <= 5.404) -> 30.0,\n", + " if (Viscosity > 2.856) and (Viscosity > 3.636) and (Viscosity <= 6.267) and (TiO2 > 0.175) and (Viscosity > 4.649) and (Viscosity > 5.404) -> 25.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (Viscosity <= 1.78) and (Viscosity <= 1.719) and (TiO2 <= 0.025) and (Al2O3 <= 0.025) -> 52.5]" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from src.rules import get_rules\n", + "\n", + "\n", + "rules = get_rules(model, features)\n", + "display(len(rules))\n", + "rules" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "25" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [ + "[if (Viscosity > 2.856) and (Viscosity <= 6.267) and (TiO2 <= 0.175) and (Al2O3 <= 0.175) -> 20.0,\n", + " if (Viscosity > 2.856) -> 20.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (TiO2 <= 0.025) and (Al2O3 > 0.025) -> 57.5,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (TiO2 > 0.025) -> 60.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) -> 70.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (TiO2 <= 0.175) and (Al2O3 <= 0.175) -> 50.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (TiO2 <= 0.175) and (Al2O3 <= 0.175) -> 40.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (TiO2 <= 0.175) and (Al2O3 > 0.175) -> 60.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (TiO2 <= 0.175) and (Al2O3 > 0.175) -> 55.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (TiO2 > 0.175) -> 70.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (TiO2 > 0.175) -> 60.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (TiO2 > 0.175) -> 55.0,\n", + " if (Viscosity > 2.856) and (Viscosity <= 3.636) and (TiO2 <= 0.175) -> 35.0,\n", + " if (Viscosity > 2.856) and (Viscosity <= 3.636) and (TiO2 <= 0.175) and (Al2O3 <= 0.025) -> 25.0,\n", + " if (Viscosity > 2.856) and (Viscosity <= 3.636) and (TiO2 <= 0.175) and (Al2O3 > 0.025) -> 30.0,\n", + " if (Viscosity > 2.856) and (Viscosity <= 3.636) and (TiO2 <= 0.175) -> 40.0,\n", + " if (Viscosity > 2.856) and (Viscosity <= 3.636) and (TiO2 > 0.175) -> 45.0,\n", + " if (Viscosity <= 2.856) -> 70.0,\n", + " if (Viscosity > 2.856) and (Viscosity <= 6.267) and (TiO2 <= 0.175) and (TiO2 > 0.025) and (Al2O3 <= 0.175) -> 22.5,\n", + " if (Viscosity > 2.856) and (Viscosity <= 6.267) and (TiO2 <= 0.175) and (Al2O3 > 0.175) -> 35.0,\n", + " if (Viscosity > 2.856) and (Viscosity <= 6.267) and (TiO2 <= 0.175) and (Al2O3 > 0.175) -> 27.5,\n", + " if (Viscosity > 2.856) and (Viscosity <= 6.267) and (TiO2 > 0.175) -> 35.0,\n", + " if (Viscosity > 2.856) and (Viscosity <= 6.267) and (TiO2 > 0.175) -> 30.0,\n", + " if (Viscosity > 2.856) and (Viscosity <= 6.267) and (TiO2 > 0.175) -> 25.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (TiO2 <= 0.025) and (Al2O3 <= 0.025) -> 52.5]" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from src.rules import normalise_rules\n", + "\n", + "\n", + "rules = normalise_rules(rules)\n", + "display(len(rules))\n", + "rules" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "17" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [ + "[if (Viscosity > 2.856) and (Viscosity <= 6.267) and (TiO2 <= 0.175) and (Al2O3 <= 0.175) -> 20.0,\n", + " if (Viscosity > 2.856) -> 20.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (TiO2 <= 0.025) and (Al2O3 > 0.025) -> 57.5,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (TiO2 > 0.025) -> 60.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) -> 70.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (TiO2 <= 0.175) and (Al2O3 <= 0.175) -> 45.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (TiO2 <= 0.175) and (Al2O3 > 0.175) -> 57.5,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (TiO2 > 0.175) -> 61.667,\n", + " if (Viscosity > 2.856) and (Viscosity <= 3.636) and (TiO2 <= 0.175) and (Al2O3 <= 0.025) -> 25.0,\n", + " if (Viscosity > 2.856) and (Viscosity <= 3.636) and (TiO2 <= 0.175) and (Al2O3 > 0.025) -> 30.0,\n", + " if (Viscosity > 2.856) and (Viscosity <= 3.636) and (TiO2 <= 0.175) -> 37.5,\n", + " if (Viscosity > 2.856) and (Viscosity <= 3.636) and (TiO2 > 0.175) -> 45.0,\n", + " if (Viscosity <= 2.856) -> 70.0,\n", + " if (Viscosity > 2.856) and (Viscosity <= 6.267) and (TiO2 <= 0.175) and (TiO2 > 0.025) and (Al2O3 <= 0.175) -> 22.5,\n", + " if (Viscosity > 2.856) and (Viscosity <= 6.267) and (TiO2 <= 0.175) and (Al2O3 > 0.175) -> 31.25,\n", + " if (Viscosity > 2.856) and (Viscosity <= 6.267) and (TiO2 > 0.175) -> 30.0,\n", + " if (Viscosity <= 2.856) and (Viscosity > 1.377) and (TiO2 <= 0.025) and (Al2O3 <= 0.025) -> 52.5]" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from src.rules import delete_same_rules\n", + "\n", + "\n", + "rules = delete_same_rules(rules)\n", + "display(len(rules))\n", + "rules" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
TAl2O3TiO2Viscosity
0200.00.03.707
1250.00.03.180
2350.00.02.361
\n", + "
" + ], + "text/plain": [ + " T Al2O3 TiO2 Viscosity\n", + "0 20 0.0 0.0 3.707\n", + "1 25 0.0 0.0 3.180\n", + "2 35 0.0 0.0 2.361" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
TAl2O3TiO2Viscosity
0300.00.02.716
1400.00.02.073
2600.00.01.329
\n", + "
" + ], + "text/plain": [ + " T Al2O3 TiO2 Viscosity\n", + "0 30 0.0 0.0 2.716\n", + "1 40 0.0 0.0 2.073\n", + "2 60 0.0 0.0 1.329" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "train = pd.read_csv(\"data/viscosity_train.csv\", sep=\";\", decimal=\",\")\n", + "test = pd.read_csv(\"data/viscosity_test.csv\", sep=\";\", decimal=\",\")\n", + "\n", + "display(train.head(3))\n", + "display(test.head(3))" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "17" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [ + "[if (Viscosity = 4.562) and (TiO2 = 0.0) and (Al2O3 = 0.0) -> 20.0,\n", + " if (Viscosity = 7.132) -> 20.0,\n", + " if (Viscosity = 2.117) and (TiO2 = 0.0) and (Al2O3 = 0.3) -> 57.5,\n", + " if (Viscosity = 2.117) and (TiO2 = 0.3) -> 60.0,\n", + " if (Viscosity = 2.117) -> 70.0,\n", + " if (Viscosity = 2.117) and (TiO2 = 0.0) and (Al2O3 = 0.0) -> 45.0,\n", + " if (Viscosity = 2.117) and (TiO2 = 0.0) and (Al2O3 = 0.3) -> 57.5,\n", + " if (Viscosity = 2.117) and (TiO2 = 0.3) -> 61.667,\n", + " if (Viscosity = 3.246) and (TiO2 = 0.0) and (Al2O3 = 0.0) -> 25.0,\n", + " if (Viscosity = 3.246) and (TiO2 = 0.0) and (Al2O3 = 0.3) -> 30.0,\n", + " if (Viscosity = 3.246) and (TiO2 = 0.0) -> 37.5,\n", + " if (Viscosity = 3.246) and (TiO2 = 0.3) -> 45.0,\n", + " if (Viscosity = 1.194) -> 70.0,\n", + " if (Viscosity = 4.562) and (TiO2 = 0.1) and (Al2O3 = 0.0) -> 22.5,\n", + " if (Viscosity = 4.562) and (TiO2 = 0.0) and (Al2O3 = 0.3) -> 31.25,\n", + " if (Viscosity = 4.562) and (TiO2 = 0.3) -> 30.0,\n", + " if (Viscosity = 2.117) and (TiO2 = 0.0) and (Al2O3 = 0.0) -> 52.5]" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from src.rules import simplify_rules\n", + "\n", + "rules = simplify_rules(train, rules)\n", + "display(len(rules))\n", + "rules" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/Users/user/Projects/python/fuzzy-rules-generator/.venv/lib/python3.12/site-packages/skfuzzy/control/fuzzyvariable.py:125: UserWarning: FigureCanvasAgg is non-interactive, and thus cannot be shown\n", + " fig.show()\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "import numpy as np\n", + "from skfuzzy import control as ctrl\n", + "import skfuzzy as fuzz\n", + "\n", + "al = ctrl.Antecedent(np.arange(0, 0.3, 0.005), \"al\")\n", + "ti = ctrl.Antecedent(np.arange(0, 0.3, 0.005), \"ti\")\n", + "viscosity = ctrl.Antecedent(np.arange(1.18, 3.71, 0.00001), \"viscosity\")\n", + "temp = ctrl.Consequent(train[\"T\"].sort_values().unique(), \"temp\")\n", + "\n", + "al.automf(3, variable_type=\"quant\")\n", + "al.view()\n", + "ti.automf(3, variable_type=\"quant\")\n", + "ti.view()\n", + "viscosity.automf(3, variable_type=\"quant\")\n", + "viscosity.view()\n", + "temp.automf(5, variable_type=\"quant\")\n", + "temp.view()" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "11" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [ + "[IF viscosity[high] THEN temp[lower]\n", + " \tAND aggregation function : fmin\n", + " \tOR aggregation function : fmax,\n", + " IF viscosity[average] THEN temp[higher]\n", + " \tAND aggregation function : fmin\n", + " \tOR aggregation function : fmax,\n", + " IF (viscosity[average] AND ti[low]) AND al[low] THEN temp[average]\n", + " \tAND aggregation function : fmin\n", + " \tOR aggregation function : fmax,\n", + " IF (viscosity[average] AND ti[low]) AND al[high] THEN temp[high]\n", + " \tAND aggregation function : fmin\n", + " \tOR aggregation function : fmax,\n", + " IF viscosity[average] AND ti[high] THEN temp[high]\n", + " \tAND aggregation function : fmin\n", + " \tOR aggregation function : fmax,\n", + " IF (viscosity[high] AND ti[low]) AND al[low] THEN temp[lower]\n", + " \tAND aggregation function : fmin\n", + " \tOR aggregation function : fmax,\n", + " IF viscosity[high] AND ti[low] THEN temp[low]\n", + " \tAND aggregation function : fmin\n", + " \tOR aggregation function : fmax,\n", + " IF viscosity[high] AND ti[high] THEN temp[average]\n", + " \tAND aggregation function : fmin\n", + " \tOR aggregation function : fmax,\n", + " IF viscosity[low] THEN temp[higher]\n", + " \tAND aggregation function : fmin\n", + " \tOR aggregation function : fmax,\n", + " IF (viscosity[high] AND ti[average]) AND al[low] THEN temp[lower]\n", + " \tAND aggregation function : fmin\n", + " \tOR aggregation function : fmax,\n", + " IF (viscosity[high] AND ti[low]) AND al[high] THEN temp[low]\n", + " \tAND aggregation function : fmin\n", + " \tOR aggregation function : fmax]" + ] + }, + "execution_count": 28, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from src.rules import get_fuzzy_rules\n", + "\n", + "fuzzy_variables = {\"Al2O3\": al, \"TiO2\": ti, \"Viscosity\": viscosity, \"consequent\": temp}\n", + "fuzzy_rules = get_fuzzy_rules(rules, fuzzy_variables)\n", + "\n", + "fuzzy_cntrl = ctrl.ControlSystem(fuzzy_rules)\n", + "\n", + "sim = ctrl.ControlSystemSimulation(fuzzy_cntrl, lenient=False)\n", + "\n", + "display(len(fuzzy_rules))\n", + "fuzzy_rules" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "=============\n", + " Antecedents \n", + "=============\n", + "Antecedent: viscosity = 2.716\n", + " - low : 0.0\n", + " - average : 0.7857659516520321\n", + " - high : 0.2142340483479678\n", + "Antecedent: ti = 0.0\n", + " - low : 1.0\n", + " - average : 0.0\n", + " - high : 0.0\n", + "Antecedent: al = 0.0\n", + " - low : 1.0\n", + " - average : 0.0\n", + " - high : 0.0\n", + "\n", + "=======\n", + " Rules \n", + "=======\n", + "RULE #0:\n", + " IF viscosity[high] THEN temp[lower]\n", + "\tAND aggregation function : fmin\n", + "\tOR aggregation function : fmax\n", + "\n", + " Aggregation (IF-clause):\n", + " - viscosity[high] : 0.2142340483479678\n", + " viscosity[high] = 0.2142340483479678\n", + " Activation (THEN-clause):\n", + " temp[lower] : 0.2142340483479678\n", + "\n", + "RULE #1:\n", + " IF viscosity[average] THEN temp[higher]\n", + "\tAND aggregation function : fmin\n", + "\tOR aggregation function : fmax\n", + "\n", + " Aggregation (IF-clause):\n", + " - viscosity[average] : 0.7857659516520321\n", + " viscosity[average] = 0.7857659516520321\n", + " Activation (THEN-clause):\n", + " temp[higher] : 0.7857659516520321\n", + "\n", + "RULE #2:\n", + " IF (viscosity[average] AND ti[low]) AND al[low] THEN temp[average]\n", + "\tAND aggregation function : fmin\n", + "\tOR aggregation function : fmax\n", + "\n", + " Aggregation (IF-clause):\n", + " - viscosity[average] : 0.7857659516520321\n", + " - ti[low] : 1.0\n", + " - al[low] : 1.0\n", + " (viscosity[average] AND ti[low]) AND al[low] = 0.7857659516520321\n", + " Activation (THEN-clause):\n", + " temp[average] : 0.7857659516520321\n", + "\n", + "RULE #3:\n", + " IF (viscosity[average] AND ti[low]) AND al[high] THEN temp[high]\n", + "\tAND aggregation function : fmin\n", + "\tOR aggregation function : fmax\n", + "\n", + " Aggregation (IF-clause):\n", + " - viscosity[average] : 0.7857659516520321\n", + " - ti[low] : 1.0\n", + " - al[high] : 0.0\n", + " (viscosity[average] AND ti[low]) AND al[high] = 0.0\n", + " Activation (THEN-clause):\n", + " temp[high] : 0.0\n", + "\n", + "RULE #4:\n", + " IF viscosity[average] AND ti[high] THEN temp[high]\n", + "\tAND aggregation function : fmin\n", + "\tOR aggregation function : fmax\n", + "\n", + " Aggregation (IF-clause):\n", + " - viscosity[average] : 0.7857659516520321\n", + " - ti[high] : 0.0\n", + " viscosity[average] AND ti[high] = 0.0\n", + " Activation (THEN-clause):\n", + " temp[high] : 0.0\n", + "\n", + "RULE #5:\n", + " IF (viscosity[high] AND ti[low]) AND al[low] THEN temp[lower]\n", + "\tAND aggregation function : fmin\n", + "\tOR aggregation function : fmax\n", + "\n", + " Aggregation (IF-clause):\n", + " - viscosity[high] : 0.2142340483479678\n", + " - ti[low] : 1.0\n", + " - al[low] : 1.0\n", + " (viscosity[high] AND ti[low]) AND al[low] = 0.2142340483479678\n", + " Activation (THEN-clause):\n", + " temp[lower] : 0.2142340483479678\n", + "\n", + "RULE #6:\n", + " IF viscosity[high] AND ti[low] THEN temp[low]\n", + "\tAND aggregation function : fmin\n", + "\tOR aggregation function : fmax\n", + "\n", + " Aggregation (IF-clause):\n", + " - viscosity[high] : 0.2142340483479678\n", + " - ti[low] : 1.0\n", + " viscosity[high] AND ti[low] = 0.2142340483479678\n", + " Activation (THEN-clause):\n", + " temp[low] : 0.2142340483479678\n", + "\n", + "RULE #7:\n", + " IF viscosity[high] AND ti[high] THEN temp[average]\n", + "\tAND aggregation function : fmin\n", + "\tOR aggregation function : fmax\n", + "\n", + " Aggregation (IF-clause):\n", + " - viscosity[high] : 0.2142340483479678\n", + " - ti[high] : 0.0\n", + " viscosity[high] AND ti[high] = 0.0\n", + " Activation (THEN-clause):\n", + " temp[average] : 0.0\n", + "\n", + "RULE #8:\n", + " IF viscosity[low] THEN temp[higher]\n", + "\tAND aggregation function : fmin\n", + "\tOR aggregation function : fmax\n", + "\n", + " Aggregation (IF-clause):\n", + " - viscosity[low] : 0.0\n", + " viscosity[low] = 0.0\n", + " Activation (THEN-clause):\n", + " temp[higher] : 0.0\n", + "\n", + "RULE #9:\n", + " IF (viscosity[high] AND ti[average]) AND al[low] THEN temp[lower]\n", + "\tAND aggregation function : fmin\n", + "\tOR aggregation function : fmax\n", + "\n", + " Aggregation (IF-clause):\n", + " - viscosity[high] : 0.2142340483479678\n", + " - ti[average] : 0.0\n", + " - al[low] : 1.0\n", + " (viscosity[high] AND ti[average]) AND al[low] = 0.0\n", + " Activation (THEN-clause):\n", + " temp[lower] : 0.0\n", + "\n", + "RULE #10:\n", + " IF (viscosity[high] AND ti[low]) AND al[high] THEN temp[low]\n", + "\tAND aggregation function : fmin\n", + "\tOR aggregation function : fmax\n", + "\n", + " Aggregation (IF-clause):\n", + " - viscosity[high] : 0.2142340483479678\n", + " - ti[low] : 1.0\n", + " - al[high] : 0.0\n", + " (viscosity[high] AND ti[low]) AND al[high] = 0.0\n", + " Activation (THEN-clause):\n", + " temp[low] : 0.0\n", + "\n", + "\n", + "==============================\n", + " Intermediaries and Conquests \n", + "==============================\n", + "Consequent: temp = 48.54014115741227\n", + " lower:\n", + " Accumulate using accumulation_max : 0.2142340483479678\n", + " low:\n", + " Accumulate using accumulation_max : 0.2142340483479678\n", + " average:\n", + " Accumulate using accumulation_max : 0.7857659516520321\n", + " high:\n", + " Accumulate using accumulation_max : 0.0\n", + " higher:\n", + " Accumulate using accumulation_max : 0.7857659516520321\n", + "\n" + ] + }, + { + "data": { + "text/plain": [ + "np.float64(48.54014115741227)" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "sim.input[\"al\"] = 0.0\n", + "sim.input[\"ti\"] = 0.0\n", + "sim.input[\"viscosity\"] = 2.716\n", + "sim.compute()\n", + "sim.print_state()\n", + "display(sim.output[\"temp\"])\n", + "temp.view(sim=sim)" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
TAl2O3TiO2ViscosityRealInferredRMSE
0200.000.03.7072030.37718110.377181
1250.000.03.1802541.91906916.919069
2350.000.02.3613551.83163216.831632
3450.000.01.8324551.5976786.597678
4500.000.01.6295053.4975093.497509
5550.000.01.4655555.7613430.761343
6700.000.01.1947064.5496595.450341
7200.050.04.6602030.26881710.268817
8300.050.03.3803038.6452748.645274
9350.050.02.8743546.35960711.359607
10400.050.02.4894051.77694511.776945
11500.050.01.8975051.6407591.640759
12550.050.01.7095552.6125822.387418
13600.050.01.4706055.6791324.320868
14200.300.06.6702030.26881710.268817
\n", + "
" + ], + "text/plain": [ + " T Al2O3 TiO2 Viscosity Real Inferred RMSE\n", + "0 20 0.00 0.0 3.707 20 30.377181 10.377181\n", + "1 25 0.00 0.0 3.180 25 41.919069 16.919069\n", + "2 35 0.00 0.0 2.361 35 51.831632 16.831632\n", + "3 45 0.00 0.0 1.832 45 51.597678 6.597678\n", + "4 50 0.00 0.0 1.629 50 53.497509 3.497509\n", + "5 55 0.00 0.0 1.465 55 55.761343 0.761343\n", + "6 70 0.00 0.0 1.194 70 64.549659 5.450341\n", + "7 20 0.05 0.0 4.660 20 30.268817 10.268817\n", + "8 30 0.05 0.0 3.380 30 38.645274 8.645274\n", + "9 35 0.05 0.0 2.874 35 46.359607 11.359607\n", + "10 40 0.05 0.0 2.489 40 51.776945 11.776945\n", + "11 50 0.05 0.0 1.897 50 51.640759 1.640759\n", + "12 55 0.05 0.0 1.709 55 52.612582 2.387418\n", + "13 60 0.05 0.0 1.470 60 55.679132 4.320868\n", + "14 20 0.30 0.0 6.670 20 30.268817 10.268817" + ] + }, + "execution_count": 30, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from sklearn import metrics\n", + "import math\n", + "\n", + "\n", + "def fuzzy_pred(row):\n", + " sim.input[\"al\"] = row[\"Al2O3\"]\n", + " sim.input[\"ti\"] = row[\"TiO2\"]\n", + " sim.input[\"viscosity\"] = row[\"Viscosity\"]\n", + " sim.compute()\n", + " return sim.output[\"temp\"]\n", + "\n", + "\n", + "def rmse(row):\n", + " return math.sqrt(metrics.mean_squared_error([row[\"Real\"]], [row[\"Inferred\"]]))\n", + "\n", + "\n", + "result_train = train.copy()\n", + "result_train[\"Real\"] = result_train[\"T\"]\n", + "result_train[\"Inferred\"] = result_train.apply(fuzzy_pred, axis=1)\n", + "result_train[\"RMSE\"] = result_train.apply(rmse, axis=1)\n", + "result_test = test.round({\"RMSE\": 3})\n", + "result_train.head(15)" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
TAl2O3TiO2ViscosityRealInferredRMSE
0300.000.002.7163048.54014118.540
1400.000.002.0734051.73899811.739
2600.000.001.3296058.6962171.304
3650.000.001.2116563.5091231.491
4250.050.004.1202530.2688175.269
5450.050.002.2174552.1895747.190
6650.050.001.3156559.1216715.878
7700.050.001.1057065.5128214.487
8450.300.003.1114544.2902530.710
9500.300.002.7355052.5198642.520
10650.300.001.9366559.2582485.742
11300.000.053.5873034.2851104.285
12550.000.051.9535551.6749683.325
13650.000.051.4436556.1365108.863
14400.000.303.9904038.1623931.838
15500.000.303.1895044.9083425.092
16650.000.302.2876559.9714265.029
\n", + "
" + ], + "text/plain": [ + " T Al2O3 TiO2 Viscosity Real Inferred RMSE\n", + "0 30 0.00 0.00 2.716 30 48.540141 18.540\n", + "1 40 0.00 0.00 2.073 40 51.738998 11.739\n", + "2 60 0.00 0.00 1.329 60 58.696217 1.304\n", + "3 65 0.00 0.00 1.211 65 63.509123 1.491\n", + "4 25 0.05 0.00 4.120 25 30.268817 5.269\n", + "5 45 0.05 0.00 2.217 45 52.189574 7.190\n", + "6 65 0.05 0.00 1.315 65 59.121671 5.878\n", + "7 70 0.05 0.00 1.105 70 65.512821 4.487\n", + "8 45 0.30 0.00 3.111 45 44.290253 0.710\n", + "9 50 0.30 0.00 2.735 50 52.519864 2.520\n", + "10 65 0.30 0.00 1.936 65 59.258248 5.742\n", + "11 30 0.00 0.05 3.587 30 34.285110 4.285\n", + "12 55 0.00 0.05 1.953 55 51.674968 3.325\n", + "13 65 0.00 0.05 1.443 65 56.136510 8.863\n", + "14 40 0.00 0.30 3.990 40 38.162393 1.838\n", + "15 50 0.00 0.30 3.189 50 44.908342 5.092\n", + "16 65 0.00 0.30 2.287 65 59.971426 5.029" + ] + }, + "execution_count": 31, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "result_test = test.copy()\n", + "result_test[\"Real\"] = result_test[\"T\"]\n", + "result_test[\"Inferred\"] = result_test.apply(fuzzy_pred, axis=1)\n", + "result_test[\"RMSE\"] = result_test.apply(rmse, axis=1)\n", + "# result_test[\"RMSE\"] = result_test[\"RMSE\"].apply(lambda x: \"{:,.4f}\".format(x))\n", + "result_test = result_test.round({\"RMSE\": 3})\n", + "result_test" + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'RMSE_train': 8.5839725721675,\n", + " 'RMSE_test': 6.953595788353505,\n", + " 'RMAE_test': 2.34270500726715,\n", + " 'R2_test': 0.7517962543858544}" + ] + }, + "execution_count": 32, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "rmetrics = {}\n", + "rmetrics[\"RMSE_train\"] = math.sqrt(\n", + " metrics.mean_squared_error(result_train[\"Real\"], result_train[\"Inferred\"])\n", + ")\n", + "rmetrics[\"RMSE_test\"] = math.sqrt(\n", + " metrics.mean_squared_error(result_test[\"Real\"], result_test[\"Inferred\"])\n", + ")\n", + "rmetrics[\"RMAE_test\"] = math.sqrt(\n", + " metrics.mean_absolute_error(result_test[\"Real\"], result_test[\"Inferred\"])\n", + ")\n", + "rmetrics[\"R2_test\"] = metrics.r2_score(result_test[\"Real\"], result_test[\"Inferred\"])\n", + "\n", + "rmetrics" + ] + } + ], + "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 +}