pytorch搭建神经网络对气温预测

import numpy as np
import pandas as pd 
import matplotlib.pyplot as plt
import torch
import torch.optim as optim
import warnings
warnings.filterwarnings("ignore")
%matplotlib inline


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

#看看数据长什么样子
features.head()

# 处理时间数据：把所有时间列转化为datetime格式，方便可视化展示
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]

# 准备画图
# 指定默认风格
plt.style.use('fivethirtyeight')

# 设置布局
fig, ((ax1, ax2), (ax3, ax4)) = plt.subplots(nrows=2, ncols=2, figsize = (10,10))
fig.autofmt_xdate(rotation = 45)

# 标签值
ax1.plot(dates, features['actual'])
ax1.set_xlabel(''); ax1.set_ylabel('Temperature'); ax1.set_title('Max Temp')

# 昨天
ax2.plot(dates, features['temp_1'])
ax2.set_xlabel(''); ax2.set_ylabel('Temperature'); ax2.set_title('Previous Max Temp')

# 前天
ax3.plot(dates, features['temp_2'])
ax3.set_xlabel('Date'); ax3.set_ylabel('Temperature'); ax3.set_title('Two Days Prior Max Temp')

# 我的逗逼朋友
ax4.plot(dates, features['friend'])
ax4.set_xlabel('Date'); ax4.set_ylabel('Temperature'); ax4.set_title('Friend Estimate')

plt.tight_layout(pad=2)

# 独热编码 对周1到周天进行编码 把所有数据转化为数值的形式
features = pd.get_dummies(features)#把整个数据传进去pd.get_dummies会自动做判断那一列是字符串可以进行编码
features.head(5)

# 在训练模型之前指定好要训练的标签X Y
labels = np.array(features['actual'])#取y值

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

# 列名字单独保存一下，以备可视化展示
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)#有些列之间数据值差距比较大需要做数据标准化进行预处理，标准化后收敛的速度更快，损失值更小

torch构建网络模型

#首先对x y转化为tensor的格式
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) #隐层128个神经元，输入层经过隐层得到128个特征
biases = torch.randn(128, dtype = float, requires_grad = True) 
weights2 = torch.randn((128, 1), dtype = float, requires_grad = True) #因为是回归任务，所以最后要得到一个值代表w，所以要经过一个全连接层[128,1]
biases2 = torch.randn(1, dtype = float, requires_grad = True) 

learning_rate = 0.001 
losses = []

for i in range(1000):
    # 计算隐层
    hidden = x.mm(weights) + biases#[348,14] *[14,128]  x.mm()表示矩阵乘法
    # 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
    weights.data.add_(- learning_rate * weights.grad.data)  #负号代表梯度下降
    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_()

更简单的构建网络模型

前面是把所有输入数据一起计算，接下来用miniBatch小批量计算

input_size = input_features.shape[1]
hidden_size = 128
output_size = 1
batch_size = 16
#这里把网络架构提前构建出来
my_nn = torch.nn.Sequential(
    torch.nn.Linear(input_size, hidden_size),
    torch.nn.Sigmoid(),
    torch.nn.Linear(hidden_size, output_size),
)
cost = torch.nn.MSELoss(reduction='mean')
optimizer = torch.optim.Adam(my_nn.parameters(), lr = 0.001)#简单方法中代替了前面需要手写梯度下降和梯度更新 损失函数也直接调用MSE损失就好
#优化器用ADam可以动态调整学习率，加入衰减函数随着迭代进行使学习率慢慢减小

# 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)#前向传播预测
        loss = cost(prediction, yy)#计算损失
        optimizer.zero_grad()#梯度清零
        loss.backward(retain_graph=True)#反向传播
        optimizer.step()#梯度更新
        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))

预测训练结果

x = torch.tensor(input_features, dtype = torch.float)
predict = my_nn(x).data.numpy()#转化为numpy1格方便画图

# 转换日期格式
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)}) #predict.reshape(-1)表示一列，不能是矩阵格式

# 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');

实验数据集转化为.csv文件使用