pytorch/浙江行业电量/行业电量_输出为3_27步长.py

import torch
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from torch import nn
import os
from torch.utils.data import TensorDataset, DataLoader
import datetime

torch.manual_seed(42)
os.environ[
    "KMP_DUPLICATE_LIB_OK"] = "TRUE"  # 解决OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized.
pd.set_option('display.width', None)


class LSTM(nn.Module):
    def __init__(self, input_size, hidden_size, output_size, num_layers=3):
        super().__init__()
        self.lstm = nn.LSTM(input_size, hidden_size, num_layers)
        self.fc1 = nn.Linear(hidden_size, 64)
        self.fc2 = nn.Linear(64, 128)
        self.fc3 = nn.Linear(128, output_size)
        self.ReLu = nn.ReLU()
        self.dropout = nn.Dropout()

    def forward(self, x):
        output, _ = self.lstm(x)
        s, b, h = output.shape
        output = output.reshape(-1, h)
        output = self.ReLu(self.fc1(output))
        output = self.ReLu(self.fc2(output))
        output = self.fc3(output)
        return output


def normal(df):
    drop_col = [x for x in df.columns if len(df[df[x]==0])/len(df) >= 0.5]
    df.drop(columns=drop_col,inplace=True)
    for col in df.columns:
        try:
            high = df[col].describe()['75%'] + 1.5 * (df[col].describe()['75%'] - df[col].describe()['25%'])
            low = df[col].describe()['25%'] - 1.5 * (df[col].describe()['75%'] - df[col].describe()['25%'])
            df[col] = df[col].map(lambda x: np.nan if (x >= high) | (x <= low) else x)
            df[col] = df[col].fillna(method='ffill')
            df[col] = df[col].fillna(method='bfill')
        except:
            pass
    return df

def create_data(df_industry, industry):
    dataset_x = []
    dataset_y = []
    # 按月份分组
    grouped = df_industry.groupby(df_industry['stat_date'].dt.to_period('M'))

    # 遍历每个月的数据
    for name, group in grouped:
        if len(group) == 31:
            dataset_x.append(list(group[industry].values[1:28]))
            dataset_y.append(list(group[industry].values[-3:]))
        if len(group) == 30:
            dataset_x.append(list(group[industry].values[:27]))
            dataset_y.append(list(group[industry].values[-3:]))
        if len(group) == 28:
            fst = group[industry].values[0]

            dataset_x.append([fst, fst, fst] + list(group[industry].values[1:25]))
            dataset_y.append(list(group[industry].values[-3:]))
        else:
            fst = group[industry].values[0]
            if len([fst, fst] + list(group[industry].values[1:26])) != 27:
                break
            dataset_x.append([fst, fst] + list(group[industry].values[1:26]))
            dataset_y.append(list(group[industry].values[-3:]))

    return np.array(dataset_x), np.array(dataset_y)


# 创建数据集
file_dir = './浙江各地市行业电量数据'
city1 = os.listdir(file_dir)[0]
df_city = pd.read_excel(os.path.join(file_dir, city1))
df_city = normal(df_city)
df_city = df_city.drop(columns='地市')
df_city[df_city.columns[1:]] /= 10000
df_city['stat_date'] = df_city['stat_date'].map(lambda x: str(x).strip()[:10])
df_city.stat_date = pd.to_datetime(df_city.stat_date)



industry = '全社会用电总计'
df_industry = df_city[['stat_date', industry]]
dataset_x, dataset_y = create_data(df_industry, industry)


for industry in df_city.columns[2:]:
    df_level = df_city[['stat_date', industry]]
    x, y = create_data(df_level, industry)
    dataset_x = np.concatenate([dataset_x, x])
    dataset_y = np.concatenate([dataset_y, y])

for excel in os.listdir(file_dir)[1:]:
    df_city = pd.read_excel(os.path.join(file_dir, excel)).drop(columns='地市')
    df_city = normal(df_city)
    df_city[df_city.columns[1:]] /= 10000
    df_city['stat_date'] = df_city['stat_date'].map(lambda x: str(x).strip()[:10])
    df_city.stat_date = pd.to_datetime(df_city.stat_date)
    for industry in df_city.columns[1:]:
        df_level = df_city[['stat_date', industry]]
        x, y = create_data(df_level, industry)
        dataset_x = np.concatenate([dataset_x, x])
        dataset_y = np.concatenate([dataset_y, y])


print(dataset_x.shape, dataset_y.shape)

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)

print(max_value, min_value)


# 划分训练集和测试集
train_size = int(len(dataset_x) * 0.8)
train_x = dataset_x[:train_size]
train_y = dataset_y[:train_size]
eval_x = dataset_x[train_size:]
eval_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, 27)
train_y = train_y.reshape(-1, 1, 3)
eval_x = eval_x.reshape(-1, 1, 27)
eval_y = eval_y.reshape(-1, 1, 3)

# # 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)
eval_x = torch.from_numpy(eval_x).to(device).type(torch.float32)
eval_y = torch.from_numpy(eval_y).to(device).type(torch.float32)

train_ds = TensorDataset(train_x, train_y)
train_dl = DataLoader(train_ds, batch_size=32, shuffle=True, drop_last=True)
eval_ds = TensorDataset(eval_x, eval_y)
eval_dl = DataLoader(eval_ds, batch_size=64, drop_last=True)

model = LSTM(27, 16, output_size=3, num_layers=3).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)
min_loss = 1
for i in range(10):
    model.train()
    for j, (x, y) in enumerate(train_dl):
        x, y = x.to(device), y.to(device)
        out = model(x)
        loss = loss_function(out, y)
        loss.backward()
        optimizer.step()
        optimizer.zero_grad()
        train_loss.append(loss.item())
        # if (i+1) % 100 == 0:
        #     print(f'epoch {i+1}/1500 loss:{round(loss.item(),5)}')
        if (j + 1) % 10 == 0:
            print(f'epoch {i + 1}/200 step {j + 1}/{len(train_dl)} loss:{loss}')
    test_running_loss = 0
    model.eval()
    with torch.no_grad():
        for x, y in eval_dl:
            pred = model(eval_x)
            loss = loss_function(pred, y)
            test_running_loss += loss.item()
    test_loss = test_running_loss / len(eval_dl)
    if test_loss < min_loss:
        min_loss = test_loss
        best_model_weight = model.state_dict()
    print(f'epoch {i + 1} test_loss:{test_loss}')

total_params = sum(p.numel() for p in model.parameters() if p.requires_grad)
print(f"Total parameters in the LSTM model: {total_params}")
# 保存模型
torch.save(best_model_weight, 'dy3.pth')

# 读取模型
model = LSTM(27, 16, output_size=3, num_layers=3).to(device)
model.load_state_dict(torch.load('dy3.pth'))
# for test

dataset_x = dataset_x.reshape(-1, 1, 27)  # (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).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 * 3, train_size * 3), (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()