数据简介

数据是常见的气温预测数据
先导入数据

features = pd.read_csv('temps.csv')
features.head()

• year,moth,day,week分别表示的具体的时间
• temp_2：前天的最高温度值
• temp_1：昨天的最高温度值
• average：在历史中，每年这一天的平均最高温度值
• actual：这就是我们的标签值了，当天的真实最高温度
• friend：这一列可能是凑热闹的，你的朋友猜测的可能值，咱们不管它就好了

我们需要把时间数据先进性简单的处理

# 处理时间数据
import datetime

# 分别得到年，月，日
years = features['year']
months = features['month']
days = features['day']

# datetime格式
dates = [str(int(year)) + '-' + str(int(month)) + '-' + str(int(day)) for year, month, day in zip(years, months, days)]
dates = [datetime.datetime.strptime(date, '%Y-%m-%d') for date in dates]

dates[:5]

[datetime.datetime(2016, 1, 1, 0, 0),
datetime.datetime(2016, 1, 2, 0, 0),
datetime.datetime(2016, 1, 3, 0, 0),
datetime.datetime(2016, 1, 4, 0, 0),
datetime.datetime(2016, 1, 5, 0, 0)]

对星期进行独热编码

# 独热编码
features = pd.get_dummies(features)
features.head(5)

构建预测数据集，并标准化

# 标签
labels = np.array(features['actual'])

# 在特征中去掉标签
features= features.drop('actual', axis = 1)

# 名字单独保存一下，以备后患
feature_list = list(features.columns)

# 转换成合适的格式
features = np.array(features)

from sklearn import preprocessing
input_features = preprocessing.StandardScaler().fit_transform(features)

构建预测网络-基础版

#先把数据转化成tensor格式

x = torch.tensor(input_features, dtype = float)

y = torch.tensor(labels, dtype = float)

# 权重参数初始化
weights = torch.randn((14, 128), dtype = float, requires_grad = True) 
biases = torch.randn(128, dtype = float, requires_grad = True) 
weights2 = torch.randn((128, 1), dtype = float, requires_grad = True) 
biases2 = torch.randn(1, dtype = float, requires_grad = True) 

learning_rate = 0.001 
losses = []

进行计算

for i in range(1000):
    # 计算隐层
    hidden = x.mm(weights) + biases
    # 加入激活函数
    hidden = torch.relu(hidden)
    # 预测结果
    predictions = hidden.mm(weights2) + biases2
    # 通计算损失
    loss = torch.mean((predictions - y) ** 2) 
    losses.append(loss.data.numpy())
    
    # 打印损失值
    if i % 100 == 0:
        print('loss:', loss)
    #返向传播计算
    loss.backward()
    
    #更新参数,加上负的梯度
    weights.data.add_(- learning_rate * weights.grad.data)  
    biases.data.add_(- learning_rate * biases.grad.data)
    weights2.data.add_(- learning_rate * weights2.grad.data)
    biases2.data.add_(- learning_rate * biases2.grad.data)
    
    # 每次迭代都得记得清空
    weights.grad.data.zero_()
    biases.grad.data.zero_()
    weights2.grad.data.zero_()
    biases2.grad.data.zero_()

loss: tensor(4505.6704, dtype=torch.float64, grad_fn=)
loss: tensor(151.8154, dtype=torch.float64, grad_fn=)
loss: tensor(146.2549, dtype=torch.float64, grad_fn=)
loss: tensor(144.3417, dtype=torch.float64, grad_fn=)
loss: tensor(143.3004, dtype=torch.float64, grad_fn=)
loss: tensor(142.5979, dtype=torch.float64, grad_fn=)
loss: tensor(142.0784, dtype=torch.float64, grad_fn=)
loss: tensor(141.6847, dtype=torch.float64, grad_fn=)
loss: tensor(141.3721, dtype=torch.float64, grad_fn=)
loss: tensor(141.1166, dtype=torch.float64, grad_fn=)

简单版

利用pytorch下nn模块

#参数设置
input_size = input_features.shape[1]
hidden_size = 128
output_size = 1
batch_size = 16
#整体模型架构
my_nn = torch.nn.Sequential(
    torch.nn.Linear(input_size, hidden_size),
    torch.nn.Sigmoid(),
    torch.nn.Linear(hidden_size, output_size),
)
#损失函数
cost = torch.nn.MSELoss(reduction='mean')
#参数
optimizer = torch.optim.Adam(my_nn.parameters(), lr = 0.001)

训练

# 训练网络
losses = []
for i in range(1000):
    batch_loss = []
    # MINI-Batch方法来进行训练
    for start in range(0, len(input_features), batch_size):
        end = start + batch_size if start + batch_size < len(input_features) else len(input_features)
        xx = torch.tensor(input_features[start:end], dtype = torch.float, requires_grad = True)
        yy = torch.tensor(labels[start:end], dtype = torch.float, requires_grad = True)
        prediction = my_nn(xx)
        loss = cost(prediction, yy)
        optimizer.zero_grad()
        loss.backward(retain_graph=True)
        optimizer.step()
        batch_loss.append(loss.data.numpy())
    
    # 打印损失
    if i % 100==0:
        losses.append(np.mean(batch_loss))
        print(i, np.mean(batch_loss))

0 3950.7627
100 37.9201
200 35.654438
300 35.278366
400 35.116814
500 34.986076
600 34.868954
700 34.75414
800 34.637356
900 34.516705

数据预测

x = torch.tensor(input_features, dtype = torch.float)
predict = my_nn(x).data.numpy()