mk = markers[int(trainy[i, 0])]
plt.scatter(Xtsne[i, 0], Xtsne[i, 1], Xtsne[i, 2], c=color, marker=mk)
plt.show()
#%% 创建模型对象
n_feature = trainX.shape[1]
model = LogisticRegression(n_feature, lr)
#%% 梯度检验
# 任务1：实现 LogisticRegression 中的 get_grad 方法
print(model.check_grad(validX, validy))
#%% 训练
for i in range(n_iter):
model.update(trainX, trainy)
model.evaluate(validX, validy)
utils.plot_loss(model, n_iter)
utils.plot_F1(model, n_iter)
#%% 评估模型
# 任务2： 实现 utils 中的 confusion_matrix 函数
# 试着从 F1 score 的角度或验证误差的角度选择最佳模型
#idx = np.argmax(model.validF1)
idx = np.argmin(model.validloss)
model.W = model.snapshot[idx]
y_hat = model.predict(testX)
threshold = 0.5
TP, FP, FN, TN = utils.confusion_matrix(threshold, y_hat, testy)
if __name__ == "__main__":
#################################### LOGISTIC REGRESSION #####################################
print("\n\nLOGISTIC:\n")
data = pd.read_csv('data/data_banknote_authentication.txt', header=None)
X_train, X_test, X_val, Y_train, Y_test, Y_val = preprocess_for_gradient_descent(
data, 'rowwise', 'standardization', (0.7, 0.15, 0.15))
# print(X_train.shape, X_val.shape, X_test.shape, Y_train.shape, Y_val.shape, Y_test.shape)
model = LogisticRegression(learning_rate=0.005,
initialisation='gaussian',
regularisation='None',
lambda_reg=0.01)
model.fit(X_train, Y_train, 5000, 'BGD')
output_val = model.predict(X_val)
output_test = model.predict(X_test)
val_accuracy, val_f_score = model.evaluate(output_val, Y_val)
test_accuracy, test_f_score = model.evaluate(output_test, Y_test)
print("Train accuracy: ", model.train_accuracy)
print("Val accuracy: ", val_accuracy)
print("Test accuracy: ", test_accuracy)
print("\nVal F1-Score: ", val_f_score)
print("Test F1-Score: ", test_f_score)
# print(model._weights)
# print("\n\n", model.costs)
plot_loss(model.costs, 'logistic_5000_epochs')
