pytorch迴歸模型

數據簡介

數據是常見的氣溫預測數據
先導入數據

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

• year,moth,day,week分別表示的具體的時間
• temp_2：前天的最高溫度值
• temp_1：昨天的最高溫度值
• average：在歷史中，每年這一天的平均最高溫度值
• actual：這就是我們的標籤值了，當天的真實最高溫度
• friend：這一列可能是湊熱鬧的，你的朋友猜測的可能值，咱們不管它就好了

我們需要把時間數據先進性簡單的處理

# 處理時間數據
import datetime

# 分別得到年，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)]

對星期進行獨熱編碼

# 獨熱編碼
features = pd.get_dummies(features)
features.head(5)

構建預測數據集，並標準化

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

# 在特徵中去掉標籤
features= features.drop('actual', axis = 1)

# 名字單獨保存一下，以備後患
feature_list = list(features.columns)

# 轉換成合適的格式
features = np.array(features)

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

構建預測網絡-基礎版

#先把數據轉化成tensor格式

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

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

# 權重參數初始化
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 = []

進行計算

for i in range(1000):
    # 計算隱層
    hidden = x.mm(weights) + biases
    # 加入激活函數
    hidden = torch.relu(hidden)
    # 預測結果
    predictions = hidden.mm(weights2) + biases2
    # 通計算損失
    loss = torch.mean((predictions - y) ** 2) 
    losses.append(loss.data.numpy())
    
    # 打印損失值
    if i % 100 == 0:
        print('loss:', loss)
    #返向傳播計算
    loss.backward()
    
    #更新參數,加上負的梯度
    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)
    
    # 每次迭代都得記得清空
    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=)

簡單版

利用pytorch下nn模塊

#參數設置
input_size = input_features.shape[1]
hidden_size = 128
output_size = 1
batch_size = 16
#整體模型架構
my_nn = torch.nn.Sequential(
    torch.nn.Linear(input_size, hidden_size),
    torch.nn.Sigmoid(),
    torch.nn.Linear(hidden_size, output_size),
)
#損失函數
cost = torch.nn.MSELoss(reduction='mean')
#參數
optimizer = torch.optim.Adam(my_nn.parameters(), lr = 0.001)

訓練

# 訓練網絡
losses = []
for i in range(1000):
    batch_loss = []
    # MINI-Batch方法來進行訓練
    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())
    
    # 打印損失
    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

數據預測

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