# -*- coding: UTF-8 -*-
# 利用鸢尾花数据集，实现前向传播、反向传播，可视化loss曲线

import tensorflow as tf
from sklearn import datasets
from matplotlib import pyplot as plt
import numpy as np

x_data = datasets.load_iris().data
y_data = datasets.load_iris().target

# 随机打乱数据（因为原始数据是顺序的，顺序不打乱会影响准确率）
np.random.seed(116)  # 使用相同的seed，保证输入特征和标签一一对应
np.random.shuffle(x_data)
np.random.seed(116)
np.random.shuffle(y_data)
tf.random.set_seed(116)


x_train = x_data[:-30]
y_train = y_data[:-30]
x_test = x_data[-30:]
y_test = y_data[-30:]

x_train = tf.cast(x_train, tf.float32)
x_test = tf.cast(x_test, tf.float32)


train_db = tf.data.Dataset.from_tensor_slices((x_train, y_train)).batch(32)
test_db = tf.data.Dataset.from_tensor_slices((x_test, y_test)).batch(32)

w1 = tf.Variable(tf.random.truncated_normal([4, 3], stddev=0.1, seed=1))
b1 = tf.Variable(tf.random.truncated_normal([3], stddev=0.1, seed=1))

lr = 0.1  # 学习率为0.1
train_loss_results = []
test_acc = []
epoch = 500
loss_all = 0

# 训练部分
for epoch in range(epoch):
    for step, (x_train, y_train) in enumerate(train_db):
        with tf.GradientTape() as tape:  # with结构记录梯度信息
            y = tf.matmul(x_train, w1) + b1
            y = tf.nn.softmax(y)
            y_ = tf.one_hot(y_train, depth=3)
            loss = tf.reduce_mean(tf.square(y_ - y))
            loss_all += loss.numpy()
        # 计算loss对各个参数的梯度
        grads = tape.gradient(loss, [w1, b1])

        # 实现梯度更新 w1 = w1 - lr * w1_grad    b = b - lr * b_grad
        w1.assign_sub(lr * grads[0])  # 参数w1自更新
        b1.assign_sub(lr * grads[1])  # 参数b自更新

    # 每个epoch，打印loss信息
    print("Epoch {}, loss: {}".format(epoch, loss_all/4))
    train_loss_results.append(loss_all / 4)  # 将4个step的loss求平均记录在此变量中
    loss_all = 0  # loss_all归零，为记录下一个epoch的loss做准备

    # 测试部分
    total_correct, total_number = 0, 0
    for x_test, y_test in test_db:
        # 使用更新后的参数进行预测
        y = tf.matmul(x_test, w1) + b1
        y = tf.nn.softmax(y)
        pred = tf.argmax(y, axis=1)  # 返回y中最大值的索引，即预测的分类
        # 将pred转换为y_test的数据类型
        pred = tf.cast(pred, dtype=y_test.dtype)
        # 若分类正确，则correct=1，否则为0，将bool型的结果转换为int型
        correct = tf.cast(tf.equal(pred, y_test), dtype=tf.int32)
        # 将每个batch的correct数加起来
        correct = tf.reduce_sum(correct)
        # 将所有batch中的correct数加起来
        total_correct += int(correct)
        # total_number为测试的总样本数，也就是x_test的行数，shape[0]返回变量的行数
        total_number += x_test.shape[0]
    # 总的准确率等于total_correct/total_number
    acc = total_correct / total_number
    test_acc.append(acc)
    print("Test_acc:", acc)
    print("--------------------------")

# 绘制 loss 曲线
plt.title(‘Loss Function Curve‘)
plt.xlabel(‘Epoch‘)
plt.ylabel(‘Loss‘)
plt.plot(train_loss_results, label="$Loss$")
plt.legend()
plt.show()

# 绘制 Accuracy 曲线
plt.title(‘Acc Curve‘)
plt.xlabel(‘Epoch‘)
plt.ylabel(‘Acc‘)
plt.plot(test_acc, label="$Accuracy$")
plt.legend()
plt.show()