import matplotlib.pyplot as plt
import tensorflow as tf
import numpy as np
import keras
from data_load import data_format

# 加载数据集
X_train, X_test, Y_train, Y_test = data_format('data/archive/PowerQualityDistributionDataset1.csv')

# 设置随机种子以确保重现性
np.random.seed(7)
np.random.shuffle(X_test)
np.random.seed(7)
np.random.shuffle(Y_test)
tf.random.set_seed(7)

# 加载训练好的模型
model = keras.models.load_model('model_nomal')

# 使用测试集评估模型的初始准确率
loss, accuracy = model.evaluate(X_test, Y_test)
print("Test original accuracy:", accuracy)

# 定义损失函数
loss_fn = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)

# 将测试数据转换为TensorFlow张量
X_test_tensor = tf.convert_to_tensor(X_test, dtype=tf.float64)
Y_test_tensor = tf.convert_to_tensor(Y_test, dtype=tf.int32)

# 用于存储不同gamma值下的准确率
accuracy_per_gamma = {}

# 遍历不同的gamma值
for gamma in [0.05, 0.1, 0.2, 0.4]:
    # 使用GradientTape计算梯度
    with tf.GradientTape() as tape:
        tape.watch(X_test_tensor)
        predictions = model(X_test_tensor)
        loss = loss_fn(Y_test_tensor, predictions)

    # 计算关于输入的梯度
    gradients = tape.gradient(loss, X_test_tensor)

    # 平坦化梯度以便进行处理
    flattened_gradients = tf.reshape(gradients, [-1])

    # 选择最大的γ * |X|个梯度
    num_gradients_to_select = int(gamma * tf.size(flattened_gradients, out_type=tf.dtypes.float32))
    top_gradients_indices = tf.argsort(flattened_gradients, direction='DESCENDING')[:num_gradients_to_select]

    # 创建新的梯度张量，初始值为原始梯度
    updated_gradients = tf.identity(flattened_gradients)

    # 创建布尔掩码，用于选择特定梯度
    mask = tf.ones_like(updated_gradients, dtype=bool)
    mask = tf.tensor_scatter_nd_update(mask, tf.expand_dims(top_gradients_indices, 1), tf.zeros_like(top_gradients_indices, dtype=bool))

    # 应用掩码更新梯度
    updated_gradients = tf.where(mask, tf.zeros_like(updated_gradients), updated_gradients)

    # 将梯度恢复到原始形状
    updated_gradients = tf.reshape(updated_gradients, tf.shape(gradients))

    # 用于存储不同学习率下的准确率
    accuracy_list = []

    # 遍历不同的学习率
    for learning_rate in [0.1, 0.2, 0.3, 0.4, 0.5]:
        # 应用学习率到梯度
        scaled_gradients = (learning_rate * 700) * updated_gradients
        # 更新X_test_tensor
        X_train_updated = tf.add(X_test_tensor, scaled_gradients)
        X_train_updated = X_train_updated.numpy()

        # 评估更新后的模型
        loss, accuracy = model.evaluate(X_train_updated, Y_test)
        print(f"Accuracy gamma: {gamma},learning:{learning_rate}", accuracy)

        # 记录准确率
        accuracy_list.append(accuracy)

    # 存储每个gamma值下的准确率
    accuracy_per_gamma[gamma] = accuracy_list

# 定义学习率和gamma值
learning_rates = [0.1, 0.2, 0.3, 0.4, 0.5]
gammas = [0.05, 0.1, 0.2, 0.4]

# 创建并绘制结果图
plt.figure(figsize=(10, 6))
for gamma in gammas:
    plt.plot(learning_rates, accuracy_per_gamma[gamma], marker='o', label=f'Gamma={gamma}')

plt.title('Accuracy vs Learning Rate for Different Gammas')
plt.xlabel('Learning Rate')
plt.ylabel('Accuracy')
plt.legend()
plt.show()