PyTorch搭建神经网络进行气温预测——（一看就懂系列！！！）

PyTorch进行气温预测

需要CSV文件私聊

###########————————————————————导包————————————————————————————————##############
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")  #  将python中产生的warning信息忽略
%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
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
features = pd.get_dummies(features)
features.head(5)

# 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)

#数据预处理
from sklearn import preprocessing
input_features = preprocessing.StandardScaler().fit_transform(features)

##############——————————————————————————————搭建pytorch————————————————————##########
input_size = input_features.shape[1]
hidden_size = 128
output_size = 1
batch_size = 16
my_nn = torch.nn.Sequential(    # 类似keras
    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)

# 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))

x = torch.tensor(input_features, dtype = torch.float)
predict = my_nn(x).data.numpy()
# 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)}) 
# 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');