PyTorch搭建CNN实现风速预测

目录

• 数据集
• 特征构造
• 一维卷积
• 数据处理
• 1.数据预处理
• 2.数据集构造
• CNN模型
• 1.模型搭建
• 2.模型训练
• 3.模型预测及表现

def load_data():
    global Max, Min
    df = pd.read_csv('Barcelona/Barcelona.csv')
    df.drop_duplicates(subset=[df.columns[0]], inplace=True)
    # weather_main
    listType = df['weather_main'].unique()
    df.fillna(method='ffill', inplace=True)
    dic = dict.fromkeys(listType)
    for i in range(len(listType)):
        dic[listType[i]] = i
    df['weather_main'] = df['weather_main'].map(dic)
    # weather_description
    listType = df['weather_description'].unique()
    dic = dict.fromkeys(listType)
    for i in range(len(listType)):
        dic[listType[i]] = i
    df['weather_description'] = df['weather_description'].map(dic)
    # weather_icon
    listType = df['weather_icon'].unique()
    dic = dict.fromkeys(listType)
    for i in range(len(listType)):
        dic[listType[i]] = i
    df['weather_icon'] = df['weather_icon'].map(dic)
    # print(df)
    columns = df.columns
    Max = np.max(df['wind_speed'])  # 归一化
    Min = np.min(df['wind_speed'])
    for i in range(2, 17):
        column = columns[i]
        if column == 'wind_speed':
            continue
        df[column] = df[column].astype('float64')
        if len(df[df[column] == 0]) == len(df):  # 全0
            continue
        mx = np.max(df[column])
        mn = np.min(df[column])
        df[column] = (df[column] - mn) / (mx - mn)
    # print(df.isna().sum())
    return df

def nn_seq():
    """
    :param flag:
    :param data: 待处理的数据
    :return: X和Y两个数据集,X=[当前时刻的year，month, hour, day, lowtemp, hightemp, 前一天当前时刻的负荷以及前23小时负荷]
                              Y=[当前时刻负荷]
    """
    print('处理数据:')
    data = load_data()
    speed = data['wind_speed']
    speed = speed.tolist()
    speed = torch.FloatTensor(speed).view(-1)
    data = data.values.tolist()
    seq = []
    for i in range(len(data) - 30):
        train_seq = []
        train_label = []
        for j in range(i, i + 24):
            train_seq.append(speed[j])
        # 添加温度、湿度、气压等信息
        for c in range(2, 7):
            train_seq.append(data[i + 24][c])
        for c in range(8, 17):
            train_seq.append(data[i + 24][c])
        train_label.append(speed[i + 24])
        train_seq = torch.FloatTensor(train_seq).view(-1)
        train_label = torch.FloatTensor(train_label).view(-1)
        seq.append((train_seq, train_label))
    # print(seq[:5])
    Dtr = seq[0:int(len(seq) * 0.5)]
    Den = seq[int(len(seq) * 0.50):int(len(seq) * 0.75)]
    Dte = seq[int(len(seq) * 0.75):len(seq)]
    return Dtr, Den, Dte

class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1d = nn.Conv1d(1, 64, kernel_size=2)
        self.relu = nn.ReLU(inplace=True)
        self.Linear1 = nn.Linear(64 * 37, 50)
        self.Linear2 = nn.Linear(50, 1) 
        def forward(self, x):
        x = self.conv1d(x)
        x = self.relu(x)
        x = x.view(-1)
        x = self.Linear1(x)
        x = self.relu(x)
        x = self.Linear2(x)
        return x

self.conv1d = nn.Conv1d(1, 64, kernel_size=2)

nn.Conv1d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True)

self.relu = nn.ReLU(inplace=True)

self.Linear1 = nn.Linear(64 * 37, 50)
self.Linear2 = nn.Linear(50, 1)

def CNN_train():
    Dtr, Den, Dte = nn_seq()
    print(Dte[0])
    epochs = 100
    model = CNN().to(device)
    loss_function = nn.MSELoss().to(device)
    optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
    # 训练
    print(len(Dtr))
    Dtr = Dtr[0:5000]
    for epoch in range(epochs):
        cnt = 0
        for seq, y_train in Dtr:
            cnt = cnt + 1
            seq, y_train = seq.to(device), y_train.to(device)
            # print(seq.size())
            # print(y_train.size())
            # 每次更新参数前都梯度归零和初始化
            optimizer.zero_grad()
            # 注意这里要对样本进行reshape，
            # 转换成conv1d的input size（batch size, channel, series length）
            y_pred = model(seq.reshape(1, 1, -1))
            loss = loss_function(y_pred, y_train)
            loss.backward()
            optimizer.step()
            if cnt % 500 == 0:
                print(f'epoch: {epoch:3} loss: {loss.item():10.8f}')
        print(f'epoch: {epoch:3} loss: {loss.item():10.10f}')
        state = {'model': model.state_dict(), 'optimizer': optimizer.state_dict()}
        torch.save(state, 'Barcelona' + CNN_PATH)

def CNN_predict(cnn, test_seq):
    pred = []
    for seq, labels in test_seq:
        seq = seq.to(device)
        with torch.no_grad():
            pred.append(cnn(seq.reshape(1, 1, -1)).item())
    pred = np.array([pred])
    return pred

def test():
    Dtr, Den, Dte = nn_seq()
    cnn = CNN().to(device)
    cnn.load_state_dict(torch.load('Barcelona' + CNN_PATH)['model'])
    cnn.eval()
    pred = CNN_predict(cnn, Dte)
    print(mean_absolute_error(te_y, pred2.T), np.sqrt(mean_squared_error(te_y, pred2.T)))