神经网络气温预测

#引用所需要的库

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

import torch

import torch.optim as optim#优化器

#过滤警告

import warnings

warnings.filterwarnings("ignore")

%matplotlib inline

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

features.head()

year 	month 	day 	week 	temp_2 	temp_1 	average 	actual 	friend

0 2016 1 1 Fri 45 45 45.6 45 29

1 2016 1 2 Sat 44 45 45.7 44 61

2 2016 1 3 Sun 45 44 45.8 41 56

3 2016 1 4 Mon 44 41 45.9 40 53

4 2016 1 5 Tues 41 40 46.0 44 41

#把列转为时间处理数据

import datetime

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]

features.shape

(348, 9)

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)

#小展示，看看数据集长什么样

#独热编码

features=pd.get_dummies(features)

features.head(5)

year 	month 	day 	temp_2 	temp_1 	average 	actual 	friend 	week_Fri 	week_Mon 	week_Sat 	week_Sun 	week_Thurs 	week_Tues 	week_Wed

0 2016 1 1 45 45 45.6 45 29 1 0 0 0 0 0 0

1 2016 1 2 44 45 45.7 44 61 0 0 1 0 0 0 0

2 2016 1 3 45 44 45.8 41 56 0 0 0 1 0 0 0

3 2016 1 4 44 41 45.9 40 53 0 1 0 0 0 0 0

4 2016 1 5 41 40 46.0 44 41 0 0 0 0 0 1 0

features.shape

(348, 15)

#标签(Y)

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

#在特征集中剔除标签，剩下x

features=features.drop('actual',axis=1)

#单独保存名字，以备后患

feature_list=list(features.columns)

#转成数组格式->后续还需要转换成tensor张量

features=np.array(features)

features.shape

(348, 14)

#因为数据有大有小，归一化(数值浮动范围小)

from sklearn import preprocessing

input_features=preprocessing.StandardScaler().fit_transform(features)

#构建网络模型(复杂版)

#转为tensor

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 = []

for i in range(1000):

#计算隐藏层

hidden = x.mm(weights)+biases

#给激活函数

hidden = torch.relu(hidden)

#预测

predictions = hidden.mm(weights2)+biases2

#计算损失

loss = torch.mean((predictions - y) ** 2)

losses.append(loss.data.numpy())

if i % 100 == 0 :
    print('loss：',loss)
# 反向传播计算  
loss.backward()

#更新参数
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)
#记得清空权重参数，因为每次迭代会累计
weights.grad.data.zero_()
biases.grad.data.zero_()
weights2.grad.data.zero_()
biases2.grad.data.zero_()

loss： tensor(8652.8872, dtype=torch.float64, grad_fn=)

loss： tensor(155.4351, dtype=torch.float64, grad_fn=)

loss： tensor(147.5643, dtype=torch.float64, grad_fn=)

loss： tensor(144.6621, dtype=torch.float64, grad_fn=)

loss： tensor(143.1741, dtype=torch.float64, grad_fn=)

loss： tensor(142.2740, dtype=torch.float64, grad_fn=)

loss： tensor(141.6748, dtype=torch.float64, grad_fn=)

loss： tensor(141.2530, dtype=torch.float64, grad_fn=)

loss： tensor(140.9336, dtype=torch.float64, grad_fn=)

loss： tensor(140.6799, dtype=torch.float64, grad_fn=)

简化实现

指定规模

input_size = input_features.shape[1]

hidden_size = 128

output_size = 1

batch_size = 16

搭建网络

my_nn = torch.nn.Sequential(

torch.nn.Linear(input_size,hidden_size),

torch.nn.Sigmoid(),

torch.nn.Linear(hidden_size,output_size),

)

定义损失函数

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 = []

小批量随机梯度下降进行训练

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
# 打印损失值
if i % 100 == 0:
    losses.append(np.mean(batch_loss))
    print(i,np.mean(batch_loss))

0 4015.5623

100 38.040577

200 35.64831

300 35.261333

400 35.099106

500 34.968235

600 34.84836

700 34.728233

800 34.605637

900 34.48074

#评估模型

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，在创建一个来存日期和其对应的模型预测值

mouths = 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')

plt.show()

ValueError: rotation must be 'vertical', 'horizontal' or a number, not 60