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')
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 |
---|
print('数据维度:', features.shape)
数据维度: (348, 9)
import datetime
years = features['year']
months = features['month']
days = features['day']
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)]
plt.style.use('fivethirtyeight')
fig, ((ax1, ax2), (ax3,ax4)) = plt.subplots(nrows=2,ncols=2,figsize= (10,10))
fig.autofmt_xdate(rotation = 45)
ax1.plot(dates, features['actual'])
ax1.set_xlabel('');ax1.set_ylabel('Temperature');ax1.set_title('Max Temp')
ax2.plot(dates, features['temp_1'])
ax2.set_xlabel('');ax2.set_ylabel('Temperature');ax2.set_title('Previous Max Temp')
ax3.plot(dates, features['temp_2'])
ax3.set_xlabel('Date'); ax3.set_ylabel('Temperature'); ax3.set_title('Two Days Prior Max Temp')
ax4.plot(dates, features['friend'])
ax4.set_xlabel('Date'); ax4.set_ylabel('Temperature'); ax4.set_title('Friend Estimate')
plt.tight_layout(pad=2)
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 |
---|
labels = np.array(features['actual'])
features = features.drop('actual', axis = 1)
features_list = list(features.columns)
features = np.array(features)
features.shape
(348, 14)
from sklearn import preprocessing
input_features = preprocessing.StandardScaler().fit_transform(features)
input_features[0]
array([ 0. , -1.5678393 , -1.65682171, -1.48452388, -1.49443549,
-1.3470703 , -1.98891668, 2.44131112, -0.40482045, -0.40961596,
-0.40482045, -0.40482045, -0.41913682, -0.40482045])
构建网络模型
x = torch.tensor(input_features,dtype = float)
y = torch.tensor(labels, dtype = float)
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):
hidden = x.mm(weights) + biases
hidden = torch.relu(hidden)
predictions = hidden.mm(weights2) + biases2
loss = torch.mean((predictions - y)** 2)
losses.append(loss.data.numpy)
if i%100 == 0:
print('loss:', loss)
loss.backward()
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)
weights.grad.data.zero_()
biases.grad.data.zero_()
weights2.grad.data.zero_()
biases2.grad.data.zero_()
loss: tensor(6368.9524, dtype=torch.float64, grad_fn=<MeanBackward0>)
loss: tensor(151.2947, dtype=torch.float64, grad_fn=<MeanBackward0>)
loss: tensor(145.1311, dtype=torch.float64, grad_fn=<MeanBackward0>)
loss: tensor(143.2606, dtype=torch.float64, grad_fn=<MeanBackward0>)
loss: tensor(142.2774, dtype=torch.float64, grad_fn=<MeanBackward0>)
loss: tensor(141.6266, dtype=torch.float64, grad_fn=<MeanBackward0>)
loss: tensor(141.1611, dtype=torch.float64, grad_fn=<MeanBackward0>)
loss: tensor(140.8115, dtype=torch.float64, grad_fn=<MeanBackward0>)
loss: tensor(140.5330, dtype=torch.float64, grad_fn=<MeanBackward0>)
loss: tensor(140.3194, dtype=torch.float64, grad_fn=<MeanBackward0>)
更简单的构建网络模型
input_size = input_features.shape[1]
hidden_size = 128
output_size = 1
batch_size = 16
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)
losses = []
for i in range(1000):
batch_loss = []
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())
if i % 100 ==0:
losses.append(np.mean(batch_loss))
print(i, np.mean(batch_loss))
0 3941.6274
100 37.70219
200 35.645916
300 35.286694
400 35.10114
500 34.958836
600 34.83496
700 34.715694
800 34.595165
900 34.469193
预测结果
x = torch.tensor(input_features, dtype = torch. float)
predict = my_nn(x).data.numpy()
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]
true_data = pd.DataFrame(data = {'date': dates, 'actual': labels})
months = features[:, features_list.index('month')]
days = features[:, features_list.index('day')]
years = features[:, features_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)})
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)]
plt.plot(true_data['date'], true_data['actual'], 'b-', label = 'actual')
plt.plot(predictions_data['date'], predictions_data['prediction'], 'ro', label = 'prediction')
plt.xticks(rotation = '60');
plt.legend()
plt.xlabel('Date'); plt.ylabel('Maximum Temperature (F)'); plt.title('Actual and Predicted Values');