validation_alphas = linspace(0.015, 0.01, 20) for realization in range(1): train, test = split_random(iris_base, train_percentage=0.8) train, train_val = split_random(train, train_percentage=0.8) x_train = train.drop(['Species'], axis=1) y_train = train['Species'] x_train_val = train_val.drop(['Species'], axis=1) y_train_val = train_val['Species'] x_test = test.drop(['Species'], axis=1) y_test = test['Species'] classifier_perceptron = sigmoid_perceptron_network( epochs=10000, learning_rate=0.01) classifier_perceptron.fit(x_train.to_numpy(), y_train.to_numpy(), x_train_val.to_numpy(), y_train_val.to_numpy(), alphas=validation_alphas) y_out_perceptron = classifier_perceptron.predict(x_test.to_numpy()) metrics_calculator = metric( list(y_test), y_out_perceptron, types=['ACCURACY', 'AUC', 'precision', 'recall', 'f1_score']) metric_results = metrics_calculator.calculate(average='macro')
for realization in range(20): train, test = split_random(base, train_percentage=.8) train, train_val = split_random(train, train_percentage=.8) x_train = train[:, :2] y_train = train[:, 2:] x_train_val = train_val[:, :2] y_train_val = train_val[:, 2:] x_test = test[:, :2] y_test = test[:, 2:] validation_alphas = linspace(0.015, 0.1, 20) simple_net = sigmoid_perceptron_network(epochs=10000, number_of_neurons=3, learning_rate=0.1) simple_net.fit(x_train, y_train, x_train_val, y_train_val, alphas=validation_alphas) y_out_simple_net = simple_net.predict(x_test) y_out = out_of_c_to_label(y_out_simple_net) y_test = out_of_c_to_label(y_test) metrics_calculator = metric( y_test, y_out, types=['ACCURACY', 'precision', 'recall', 'f1_score'])
train, test = split_random(base, train_percentage=.8) train, train_val = split_random(train, train_percentage=.8) x_train = train[:, :2] y_train = train[:, 2:] x_train_val = train_val[:, :2] y_train_val = train_val[:, 2:] x_test = test[:, :2] y_test = test[:, 2:] validation_alphas = linspace(0.015, 0.1, 20) sigmoid_net = sigmoid_perceptron_network( epochs=1000, number_of_neurons=1, learning_rate=0.1, activation_function='sigmoid logistic') sigmoid_net.fit(x_train, y_train, x_train_val, y_train_val, alphas=validation_alphas, validation=False) y_out = sigmoid_net.predict(x_test) metrics_calculator = metric( y_test, y_out, types=['ACCURACY', 'precision', 'recall', 'f1_score'])