import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import torch
from sklearn import preprocessing
from torch.utils.data import DataLoader,TensorDataset



data = pd.read_excel(r'C:\python-project\pytorch3\入模数据\杭州数据.xlsx',index_col='dtdate')
print(data.columns)


x = np.array(data.drop(columns=['售电量','city_name']).loc['2021-1':'2023-6'])
y = np.array(data['售电量'].loc['2021-1':'2023-6'])

# 数据标准化操作：(x-均值μ) / 标准差σ ，使数据关于原点对称，提升训练效率
input_features = preprocessing.StandardScaler().fit_transform(np.array(x))  # fit：求出均值和标准差 transform：求解

# y归一化
min = np.min(y)
max = np.max(y)
y = (y - min)/(max - min)

x_eval = torch.from_numpy(data.drop(columns=['售电量','city_name']).loc['2023-7'].values).type(torch.float32)
y_eval = torch.from_numpy(data['售电量'].loc['2023-7'].values).type(torch.float32)

ds = TensorDataset(torch.from_numpy(x),torch.from_numpy(y))
dl = DataLoader(ds,batch_size=12,shuffle=True,drop_last=True)


# 设定神经网络的输入参数、隐藏层神经元、输出参数的个数
input_size = input_features.shape[1]  # 设定输入特征个数

hidden_size = 64
output_size =1

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")  # 选择使用GPU训练

my_nn = torch.nn.Sequential(
    torch.nn.Linear(input_size, hidden_size).to(device),  # 输入层 → 第一层
    torch.nn.ReLU().to(device),
    torch.nn.Linear(hidden_size, hidden_size).to(device),  # 第一层 → 第二层
    torch.nn.ReLU().to(device),
    torch.nn.Linear(hidden_size, hidden_size).to(device),  # 第二层 → 第三层
    torch.nn.ReLU().to(device),
    torch.nn.Linear(hidden_size, output_size)
).to(device)
cost = torch.nn.MSELoss().to(device)
optimizer = torch.optim.Adam(my_nn.parameters(), lr=0.0001)

# 训练网络
losses = []
for i in range(1000):
    batch_loss = []
    # 采用MINI-Batch的方法进行训练
    for X,y in dl:
        X,y = X.to(device).type(torch.float32),y.to(device).type(torch.float32)

        prediction = my_nn(X)
        loss = cost(y, prediction)
        optimizer.zero_grad()
        loss.backward(retain_graph=True)
        optimizer.step()
        batch_loss.append(loss.data.cpu().numpy())

    if i % 10 == 0:
        losses.append(np.mean(batch_loss))
        print(i, np.mean(batch_loss))

# 保存模型
# torch.save(my_nn, 'BP.pt')

# 绘制图像
# dev_x = [i * 10 for i in range(20)]
# plt.xlabel('step count')
# plt.ylabel('loss')
# plt.xlim((0, 200))
# plt.ylim((0, 1000))
# plt.plot(dev_x, losses)
# plt.show()