import numpy as np
import pandas as pd
import torch
from torch import nn
from multiprocessing import Pool
import matplotlib.pyplot as plt
import os
os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
DAYS_FOR_TRAIN = 10
torch.manual_seed(42)
class LSTM_Regression(nn.Module):

    def __init__(self, input_size, hidden_size, output_size=1, num_layers=2):
        super().__init__()

        self.lstm = nn.LSTM(input_size, hidden_size, num_layers)
        self.fc = nn.Linear(hidden_size, output_size)

    def forward(self, _x):
        x, _ = self.lstm(_x)  # _x is input, size (seq_len, batch, input_size)
        s, b, h = x.shape  # x is output, size (seq_len, batch, hidden_size)
        x = x.view(s * b, h)
        x = self.fc(x)
        x = x.view(s, b, -1)  # 把形状改回来
        return x


def create_dataset(data, days_for_train=5) -> (np.array, np.array):
    dataset_x, dataset_y = [], []
    for i in range(len(data) - days_for_train-5):
        dataset_x.append(data[i:(i + days_for_train)])
        dataset_y.append(data[i + days_for_train:i + days_for_train+5])
        # print(dataset_x,dataset_y)
    return (np.array(dataset_x), np.array(dataset_y))

def normal(nd):
    high = nd.describe()['75%'] + 1.5*(nd.describe()['75%']-nd.describe()['25%'])
    low = nd.describe()['25%'] - 1.5*(nd.describe()['75%']-nd.describe()['25%'])
    return nd[(nd<high)&(nd>low)]

def data_preprocessing(data):
    data.columns = data.columns.map(lambda x: x.strip())
    data.index = pd.to_datetime(data.index)
    data.sort_index(inplace=True)
    data = data.loc['2021-01':'2023-08']
    data.drop(columns=[i for i in data.columns if (data[i] == 0).sum() / len(data) >= 0.5], inplace=True)  # 去除0值列

    data = data.astype(float)
    for col in data.columns:
        data[col] = normal(data[col])

    return data

# 拼接数据集
file_dir = r'C:\Users\user\Desktop\浙江各地市分电压日电量数据'
excel = os.listdir(file_dir)[0]
data = pd.read_excel(os.path.join(file_dir, excel), sheet_name=0, index_col='stat_date')
data.drop(columns='地市',inplace=True)
data = data_preprocessing(data)

df = data[data.columns[0]]
df.dropna(inplace = True)
dataset_x, dataset_y = create_dataset(df, DAYS_FOR_TRAIN)

for level in data.columns[1:]:
    df = data[level]
    df.dropna(inplace=True)
    x, y = create_dataset(df, DAYS_FOR_TRAIN)
    dataset_x = np.concatenate((dataset_x, x))
    dataset_y = np.concatenate((dataset_y, y))


for excel in os.listdir(file_dir)[1:]:

    data = pd.read_excel(os.path.join(file_dir,excel), sheet_name=0,index_col='stat_date')
    data.drop(columns='地市', inplace=True)
    data = data_preprocessing(data)

    for level in data.columns:
        df = data[level]
        df.dropna(inplace=True)
        x,y = create_dataset(df,DAYS_FOR_TRAIN)
        dataset_x = np.concatenate((dataset_x,x))
        dataset_y = np.concatenate((dataset_y,y))



# 训练
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

# 标准化到0~1
max_value = np.max(dataset_x)
min_value = np.min(dataset_x)
dataset_x = (dataset_x - min_value) / (max_value - min_value)
dataset_y = (dataset_y - min_value) / (max_value - min_value)

# 划分训练集和测试集
train_size = int(len(dataset_x)*0.7)
train_x = dataset_x[:train_size]
train_y = dataset_y[:train_size]

# 将数据改变形状，RNN 读入的数据维度是 (seq_size, batch_size, feature_size)
train_x = train_x.reshape(-1, 1, DAYS_FOR_TRAIN)
train_y = train_y.reshape(-1, 1, 5)

# 转为pytorch的tensor对象
train_x = torch.from_numpy(train_x).to(device).type(torch.float32)
train_y = torch.from_numpy(train_y).to(device).type(torch.float32)

model = LSTM_Regression(DAYS_FOR_TRAIN, 32, output_size=5, num_layers=2).to(device)  # 导入模型并设置模型的参数输入输出层、隐藏层等


train_loss = []
loss_function = nn.MSELoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.005, betas=(0.9, 0.999), eps=1e-08, weight_decay=0)
for i in range(1500):
    out = model(train_x)
    loss = loss_function(out, train_y)
    loss.backward()
    optimizer.step()
    optimizer.zero_grad()
    train_loss.append(loss.item())

# 保存模型
torch.save(model.state_dict(),'dy5.pth')

# for test
model = model.eval()  # 转换成测试模式
# model.load_state_dict(torch.load(os.path.join(model_save_dir,model_file)))  # 读取参数
dataset_x = dataset_x.reshape(-1, 1, DAYS_FOR_TRAIN)  # (seq_size, batch_size, feature_size)
dataset_x = torch.from_numpy(dataset_x).to(device).type(torch.float32)

pred_test = model(dataset_x)  # 全量训练集
# 模型输出 (seq_size, batch_size, output_size)
pred_test = pred_test.view(-1)
pred_test = np.concatenate((np.zeros(DAYS_FOR_TRAIN), pred_test.cpu().detach().numpy()))

plt.plot(pred_test.reshape(-1), 'r', label='prediction')
plt.plot(dataset_y.reshape(-1), 'b', label='real')
plt.plot((train_size*5, train_size*5), (0, 1), 'g--')  # 分割线 左边是训练数据 右边是测试数据的输出
plt.legend(loc='best')
plt.show()


# 创建测试集
# result_list = []
# 以x为基础实际数据，滚动预测未来3天
# x = torch.from_numpy(df[-14:-4]).to(device)
# pred = model(x.reshape(-1,1,DAYS_FOR_TRAIN)).view(-1).detach().numpy()


# 反归一化
# pred = pred * (max_value - min_value) + min_value
# df = df * (max_value - min_value) + min_value

# print(pred)
# # 打印指标
# print(abs(pred - df[-3:]).mean() / df[-3:].mean())
# result_eight = pd.DataFrame({'pred': np.round(pred,1),'real': df[-3:]})
# target = (result_eight['pred'].sum() - result_eight['real'].sum()) / df[-31:].sum()
# result_eight['loss_rate'] = round(target, 5)
# result_eight['level'] = level
# list_app.append(result_eight)
# print(target)
# print(result_eight)
# final_df = pd.concat(list_app,ignore_index=True)
# final_df.to_csv('市行业电量.csv',encoding='gbk')
# print(final_df)