{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [] }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" } }, "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "id": "si0nQQNnT_3V" }, "outputs": [], "source": [ "#SVR\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "import pandas as pd\n", "from sklearn.preprocessing import scale\n", "from sklearn.model_selection import train_test_split\n", "from io import StringIO\n", "from sklearn.preprocessing import StandardScaler\n", "from sklearn.svm import SVR\n", "from sklearn.metrics import r2_score,mean_squared_error\n", "dataset = pd.read_csv('/content/drive/MyDrive/SHM dataset/finaldataset.csv', dtype='unicode') dataset.shape\n", "X=dataset.iloc[:,0:5].values\n", "print(X)\n", "\n", "y=dataset.iloc[:,5].values\n", "print(y)\n", "X_train,X_test,Y_train,Y_test=train_test_split(X,y,test_size=0.25,random_state=20000)\n", "print(X_train)\n", "X_train.shape\n", "\n", "print(X_test)\n", "X_test.shape\n", "supportvector=SVR()\n", "supportvector.fit(X_train,Y_train)\n", "SVR(C=1.0, cache_size=200, coef0=0.0, degree=3, epsilon=0.1, gamma='scale', kernel='rbf', max_iter=-1, shrinking=True, tol=0.001, verbose=False)\n", "\n", "Y_pred=supportvector.predict(X_test)\n", "print(Y_pred[5039])\n", "mse=mean_squared_error(Y_test, Y_pred)\n", "print(mse)\n", "rmse=np.sqrt(mse)\n", "print(rmse)\n", "print(rmse/150948)\n" ] }, { "cell_type": "code", "source": [ "#Gradient Boost\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "import pandas as pd\n", "from sklearn.preprocessing import scale\n", "from sklearn.model_selection import train_test_split\n", "from io import StringIO\n", "from sklearn.preprocessing import MinMaxScaler\n", "import sklearn\n", "# test regression dataset\n", "from sklearn.datasets import make_regression#1\n", "from sklearn.ensemble import GradientBoostingRegressor #2\n", "from sklearn.metrics import r2_score,mean_squared_error\n", "\n", "dataset = pd.read_csv('/content/drive/MyDrive/SHM final dataset/finaldataset.csv', dtype='unicode')\n", "dataset.head(n=3)\n", "#dataset.shape\n", "scaler=MinMaxScaler()\n", "scaler.fit(dataset.iloc[:,5:6])\n", "dataset[\"Ground truth\"]=scaler.transform(dataset.iloc[:,5:6])\n", "dataset\n", "X=dataset.iloc[:,0:5].values\n", "y=dataset.iloc[:,5].values\n", "X_train,X_test,Y_train,Y_test=train_test_split(X,y,test_size=0.25,random_state=20000)\n", "model=GradientBoostingRegressor(n_estimators = 100, learning_rate =\n", "0.8, max_depth = 1, random_state = 0,loss='ls')\n", "model.fit(X_train,Y_train)\n", "GradientBoostingRegressor(alpha=0.9, ccp_alpha=0.0, criterion='friedman_mse', init=None, learning_rate=0.8, loss='ls', max_depth=1, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=1, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_iter_no_change=None, presort='deprecated', random_state=0, subsample=1.0, tol=0.0001, validation_fraction=0.1, verbose=0, warm_start=False)\n", "Y_pred=model.predict(X_test)\n", "model.score(X,y)\n", "mse=mean_squared_error(Y_test, Y_pred)\n", "print(mse)\n", "rmse=np.sqrt(mse)\n", "rmse\n" ], "metadata": { "id": "OmtX3s2_Uc_z" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "#Extra tree\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "import pandas as pd\n", "from sklearn.preprocessing import scale\n", "from sklearn.model_selection import train_test_split\n", "from io import StringIO\n", "from sklearn.preprocessing import MinMaxScaler\n", "import sklearn\n", "from sklearn.datasets import make_regression#1\n", "from sklearn.ensemble import ExtraTreesRegressor#2\n", "from sklearn.metrics import r2_score,mean_squared_error\n", "dataset = pd.read_csv('/content/drive/MyDrive/SHM final dataset/finaldataset.csv', dtype='unicode')\n", "dataset.head(n=3)\n", "dataset.shape\n", "scaler=MinMaxScaler()\n", "scaler.fit(dataset.iloc[:,5:6])\n", "dataset[\"Ground truth\"]=scaler.transform(dataset.iloc[:,5:6])\n", "dataset\n", "X=dataset.iloc[:,0:5].values\n", "y=dataset.iloc[:,5].values\n", "X_train,X_test,Y_train,Y_test=train_test_split(X,y,test_size=0.25,random_state=20000)\n", "model=ExtraTreesRegressor(n_estimators = 500, max_leaf_nodes =\n", "10, random_state = 0)\n", "model.fit(X_train,Y_train)\n", "ExtraTreesRegressor(bootstrap=False, ccp_alpha=0.0, criterion='mse', max_depth=None, max_features='auto', max_leaf_nodes=10, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=1, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=500, n_jobs=None, oob_score=False, random_state=0, verbose=0, warm_start=False)\n", "Y_pred=model.predict(X_test)\n", "model.score(X,y)\n", "mse=mean_squared_error(Y_test, Y_pred)\n", "print(mse)\n", "rmse=np.sqrt(mse)\n", "rmse\n" ], "metadata": { "id": "Ks2psTFqUp0O" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "#ADA boost\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "import pandas as pd\n", "from sklearn.preprocessing import scale\n", "from sklearn.model_selection import train_test_split\n", "from io import StringIO\n", "from sklearn.preprocessing import MinMaxScaler\n", "import sklearn\n", "# test regression dataset\n", "from sklearn.datasets import make_regression#1\n", "from sklearn.ensemble import AdaBoostRegressor#2\n", "from sklearn.metrics import r2_score,mean_squared_error\n", "dataset = pd.read_csv('/content/drive/MyDrive/SHM final dataset/finaldataset.csv', dtype='unicode')\n", "dataset.head(n=3)\n", "dataset.shape\n", "scaler=MinMaxScaler()\n", "scaler.fit(dataset.iloc[:,5:6])\n", "dataset[\"Ground truth\"]=scaler.transform(dataset.iloc[:,5:6])\n", "dataset\n", "X=dataset.iloc[:,0:5].values\n", "y=dataset.iloc[:,5].values\n", "X_train,X_test,Y_train,Y_test=train_test_split(X,y,test_size=0.25,random_state=20000)\n", "model=AdaBoostRegressor(n_estimators = 200, learning_rate =\n", "1.0, random_state = 80,loss='linear')\n", "model.fit(X_train,Y_train)\n", "AdaBoostRegressor(base_estimator=None, learning_rate=1.0, loss='linear', n_estimators=200, random_state=80)\n", "Y_pred=model.predict(X_test)\n", "model.score(X,y)\n", "mse=mean_squared_error(Y_test, Y_pred)\n", "print(mse)\n", "rmse=np.sqrt(mse)\n", "rmse\n" ], "metadata": { "id": "NuaHMHlUUwnE" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "#Decision Tree\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "import pandas as pd\n", "from sklearn.preprocessing import scale\n", "from sklearn.model_selection import train_test_split\n", "from io import StringIO\n", "from sklearn.preprocessing import MinMaxScaler\n", "import sklearn\n", "# test regression dataset\n", "from sklearn.datasets import make_regression#1\n", "from sklearn.tree import DecisionTreeRegressor#2\n", "from sklearn.metrics import r2_score,mean_squared_error\n", "dataset = pd.read_csv('/content/drive/MyDrive/SHM final dataset/finaldataset.csv', dtype='unicode')\n", "dataset.head(n=3)\n", "dataset.shape\n", "scaler=MinMaxScaler()\n", "scaler.fit(dataset.iloc[:,5:6])\n", "dataset[\"Ground truth\"]=scaler.transform(dataset.iloc[:,5:6])\n", "dataset\n", "X=dataset.iloc[:,0:5].values\n", "y=dataset.iloc[:,5].values\n", "X_train,X_test,Y_train,Y_test=train_test_split(X,y,test_size=0.25,random_state=20000)\n", "model=DecisionTreeRegressor(random_state = 50)\n", "model.fit(X_train,Y_train)\n", "DecisionTreeRegressor(ccp_alpha=0.0, criterion='mse', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=1, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=50, splitter='best')\n", "Y_pred=model.predict(X_test)\n", "model.score(X,y)\n", "mse=mean_squared_error(Y_test, Y_pred)\n", "print(mse)\n", "rmse=np.sqrt(mse)\n", "rmse\n" ], "metadata": { "id": "tVi2ln2iU2-D" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "#Ensemble\n", "import sklearn\n", "import pandas as pd\n", "from sklearn.preprocessing import MinMaxScaler\n", "from sklearn.model_selection import train_test_split\n", "# test regression dataset\n", "from sklearn.datasets import make_regression#1\n", "from sklearn.ensemble import AdaBoostRegressor#2\n", "from sklearn.metrics import r2_score,mean_squared_error\n", "\n", "from sklearn.datasets import make_regression\n", "\n", "from sklearn.ensemble import SVMRegressor\n", "from sklearn.ensemble import GradientBoostingRegressor\n", "from sklearn.ensemble import ExtraTreesRegressor\n", "from sklearn.ensemble import AdaBoostRegressor\n", "from sklearn.tree import DecisionTreeRegressor\n", "from sklearn.linear_model import LinearRegression\n", "from sklearn.ensemble import StackingRegressor\n", "\n", "dataset = pd.read_csv('/content/drive/MyDrive/SHM final dataset/finaldataset.csv', dtype='unicode')\n", "dataset.head(n=3)\n", "dataset.shape\n", "\n", "scaler=MinMaxScaler()\n", "scaler.fit(dataset.iloc[:,5:6])\n", "dataset[\"Ground truth\"]=scaler.transform(dataset.iloc[:,5:6])\n", "dataset\n", "\n", "X=dataset.iloc[:,0:5].values\n", "y=dataset.iloc[:,5].values\n", "X_train,X_test,Y_train,Y_test=train_test_split(X,y,test_size=0.25,random_state=20000)\n", "def get_stacking():\n", "level0 = list()\n", " level0.append(('svr', SVMRegressor()))\n", " level0.append(('gbr', GradientBoostingRegressor()))\n", " level0.append(('etr', ExtraTreesRegressor()))\n", " level0.append(('abr', AdaBoostRegressor()))\n", " level0.append(('cart', DecisionTreeRegressor()))\n", " level1 = LinearRegression()\n", " model = StackingRegressor(estimators=level0, final_estimator=level1, cv=5)\n", " return model\n", "models = get_stacking()\n", "models.fit(X, y)\n", "models.score(X,y)\n", "Y_pred=models.predict(X_test)\n", "mse=mean_squared_error(Y_test, Y_pred)\n", "print(mse)\n", "rmse=np.sqrt(mse)\n", "rmse\n" ], "metadata": { "id": "2X_tT-ZaU9Z3" }, "execution_count": null, "outputs": [] } ] }