le = LabelEncoder() le.fit(data['Activity']) data['Activity'] = le.transform(data['Activity']) X = data.drop('Activity', axis=1) y = data['Activity'] # split the dataset into train and test X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=40) # Baseline model classifier = SVC() clf = classifier.fit(X_train, y_train) y_pred = clf.predict(X_test) precision, accuracy, f_score, _ = error_metric(y_test, y_pred, average='weighted') print(precision) print(accuracy) print(f_score) model1_score = accuracy_score(y_test, y_pred) print(model1_score) # -------------- # importing libraries from sklearn.feature_selection import SelectFromModel from sklearn.svm import LinearSVC # Feature selection using Linear SVC lsvc = LinearSVC(C=0.01, penalty="l1", dual=False,
# split the dataset into train and test X = data.drop(['Activity'], 1) y = data['Activity'] X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=40) # Baseline model classifier = SVC() clf = classifier.fit(X_train, y_train) y_pred = clf.predict(X_test) precision = error_metric(y_test, y_pred, average='weighted')[0] recall = error_metric(y_test, y_pred, average='weighted')[1] f_score = error_metric(y_test, y_pred, average='weighted')[2] model1_score = accuracy_score(y_test, y_pred) print("Accuracy SVC : ", model1_score) print("Precision SVC : ", precision) print("Recall SVC : ", recall) print("F1 Score SVC : ", f_score) # -------------- # importing libraries from sklearn.svm import LinearSVC from sklearn.feature_selection import SelectFromModel from sklearn.metrics import f1_score
# Encoding the target variable le = LabelEncoder() data['Activity'] = le.fit_transform(data['Activity']) # split the dataset into train and test X = data.drop('Activity',1) y = data['Activity'] X_train, X_test, y_train , y_test = train_test_split(X,y,test_size = 0.3, random_state = 40) # Baseline model classifier = SVC() clf = classifier.fit(X_train, y_train) y_pred = clf.predict(X_test) precision, recall, f_score, support = error_metric(y_test, y_pred, average = 'weighted') model1_score = classifier.score(X_test, y_test) print('precision',precision) print('\n') print('recall',recall) print('\n') print('f1_score',f_score) print('\n') print('score',model1_score) print('\n')
param_grid={ 'kernel': ['linear', 'rbf'], 'C': [100, 20, 1, 0.1] }, scoring='accuracy') selector.fit(new_train_features, y_train) print(selector.best_params_) print(selector.cv_results_) # Usage of grid search to select the best hyperparmeters means = selector.cv_results_['mean_test_score'] stds = selector.cv_results_['std_test_score'] parameters = selector.cv_results_['params'] print(means) print(stds) print(parameters) classifier_3 = SVC(kernel='rbf', C=100) # Model building after Hyperparameter tuning clf_3 = classifier_3.fit(new_train_features, y_train) y_pred_final = clf_3.predict(new_test_features) model3_score = accuracy_score(y_test, y_pred_final) precision, recall, f_score, _ = error_metric(y_test, y_pred, average='weighted') print(precision) print(recall) print(f_score)