Python从入门到实战代码行行标注---较简单的构建网络模型

--------教程摘自b站【不愧是计算机博士唐宇迪128集课程一套搞定了我大学4年没学会的PyTorch】PyTorch从入门到实战全套课程（附带课程学习资料 )_哔哩哔哩_bilibili

input_size = input_features.shape[1] #总共样本的数量
hidden_size = 128  #隐层神经元的个数
output_size = 1      #输出结果是一个值
batch_size = 16      
my_nn = torch.nn.Sequential(
    torch.nn.Linear(input_size, hidden_size),  #第一层指定输入和隐层的神经元
    torch.nn.Sigmoid(),                #激活函数
    torch.nn.Linear(hidden_size, output_size), #再连一个全连接层
)
cost = torch.nn.MSELoss(reduction='mean') #损失函数 MSELoss包
optimizer = torch.optim.Adam(my_nn.parameters(), lr = 0.001) #优化器Adam 可以动态调节学习率
# 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)  #因为batch为16  所以每次start end 取的是16个数据
        yy = torch.tensor(labels[start:end], dtype = torch.float, requires_grad = True)
        prediction = my_nn(xx) #预测结果 即走一个前向传播
        loss = cost(prediction, yy)  #计算损失值
        optimizer.zero_grad() #优化时 迭代完 要梯度清零
        loss.backward(retain_graph=True)
        optimizer.step()# 参数更新
        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))
x = torch.tensor(input_features, dtype = torch.float)
predict = my_nn(x).data.numpy() #转换成array格式是为了换图
# 转换标准日期格式
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]

# 创建一个表格来存日期和其对应的标签数值
true_data = pd.Dataframe(data = {'date': dates, 'actual': labels})

# 同理，再创建一个来存日期和其对应的模型预测值
months = features[:, feature_list.index('month')]
days = features[:, feature_list.index('day')]
years = features[:, feature_list.index('year')]

test_dates = [str(int(year)) + '-' + str(int(month)) + '-' + str(int(day)) for year, month, day in zip(years, months, days)]

test_dates = [datetime.datetime.strptime(date, '%Y-%m-%d') for date in test_dates]

predictions_data = pd.Dataframe(data = {'date': test_dates, 'prediction': predict.reshape(-1)}) 
# 真实值
plt.plot(true_data['date'], true_data['actual'], 'b-', label = 'actual')

# 预测值
plt.plot(predictions_data['date'], predictions_data['prediction'], 'ro', label = 'prediction')
plt.xticks(rotation = '60'); 
plt.legend()

# 图名
plt.xlabel('Date'); plt.ylabel('Maximum Temperature (F)'); plt.title('Actual and Predicted Values');