#加载飞桨和相关类库
import paddle
from paddle.nn import Linear
import paddle.nn.functional as F
import os
import numpy as np
import matplotlib.pyplot as plt

def load_data():
    # 读入训练数据
    datafile = "./dataset/housing.data"
    data = np.fromfile(datafile, sep=' ')
    #print(data)

    feature_names = [ 'CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE','DIS',
                     'RAD', 'TAX', 'PTRATIO', 'B', 'LSTAT', 'MEDV' ]
    feature_num = len(feature_names)
    data = data.reshape([data.shape[0] // feature_num, feature_num])
    print(data.shape[0])
    x = data[0]
    print(x.shape)
    print(x)

    # 划分数据集
    ratio = 0.8
    offset = int(data.shape[0] * ratio)
    training_data = data[:offset]
    training_data.shape

    # 计算train数据集的最大值，最小值，平均值
    maximums, minimums, avgs = training_data.max(axis=0), training_data.min(axis=0), \
                               training_data.sum(axis=0) / training_data.shape[0]
    #print(maximums, minimums, avgs)

    # 记录数据的归一化参数，在预测时对数据做归一化
    global max_values
    global min_values
    global avg_values
    max_values = maximums
    min_values = minimums
    avg_values = avgs

    # 对数据进行归一化处理
    for i in range(feature_num):
        #print(maximums[i], minimums[i], avgs[i])
        data[:, i] = (data[:, i] - minimums[i]) / (maximums[i] - minimums[i]) # 使得每个特征的取值缩放到0~1之间。

    training_data = data[:offset]
    test_data = data[offset:]
    return training_data, test_data



class Regressor(paddle.nn.Layer):

    # self代表类的实例自身
    def __init__(self):
        # 初始化父类中的一些参数
        super(Regressor, self).__init__()

        # 定义一层全连接层，输入维度是13，输出维度是1
        self.fc = paddle.nn.Linear(in_features=13, out_features=1)
    # 网络的前向计算
    def forward(self, inputs):
        x = self.fc(inputs)
        return x

# 声明定义好的线性回归模型
model = Regressor()
# 开启模型训练模式
model.train()
# 加载数据
training_data, test_data = load_data()
# 定义优化算法，使用随机梯度下降SGD
# 学习率设置为0.01
opt = paddle.optimizer.SGD(learning_rate=0.01, parameters=model.parameters())

EPOCH_NUM = 10  # 设置外层循环次数
BATCH_SIZE = 10  # 设置batch大小

# 定义外层循环
for epoch_id in range(EPOCH_NUM):
    # 在每轮迭代开始之前，将训练数据的顺序随机的打乱
    np.random.shuffle(training_data)
    # 将训练数据进行拆分，每个batch包含10条数据
    mini_batches = [training_data[k:k + BATCH_SIZE] for k in range(0, len(training_data), BATCH_SIZE)]
    # 定义内层循环
    for iter_id, mini_batch in enumerate(mini_batches):
        x = np.array(mini_batch[:, :-1])  # 获得当前批次训练数据
        y = np.array(mini_batch[:, -1:])  # 获得当前批次训练标签（真实房价）
        # 将numpy数据转为飞桨动态图tensor形式
        house_features = paddle.to_tensor(x)
        prices = paddle.to_tensor(y)
        print(house_features.shape)

        # 前向计算
        predicts = model(house_features)

        # 计算损失
        loss = F.square_error_cost(predicts, label=prices)
        avg_loss = paddle.mean(loss)
        if iter_id % 20 == 0:
            print("epoch: {}, iter: {}, loss is: {}".format(epoch_id, iter_id, avg_loss.numpy()))

        # 反向传播
        avg_loss.backward()
        # 最小化loss,更新参数
        opt.step()
        # 清除梯度
        opt.clear_grad()