1.项目说明
**选用Close和Low两个特征,使用窗口time_steps窗口的2个特征,然后预测Close这一个特征数据未来一天的数据
当batch_first=True,则LSTM的inputs=(batch_size,time_steps,input_size)
batch_size = len(data)-time_steps
time_steps = 滑动窗口,本项目中值为lookback
input_size = 2【因为选取了Close和Low两个特征】**
2.数据集
参考:https://blog.csdn.net/qq_38633279/article/details/134245512?spm=1001.2014.3001.5501中的数据集
3.数据预处理
3.1 读取数据
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.preprocessing import MinMaxScaler
import torch
import torch.nn as nn
import seaborn as sns
import math, time
from sklearn.metrics import mean_squared_error
filepath = './data/rlData.csv'
data = pd.read_csv(filepath)
data = data.sort_values('Date')
data.head()
data.shape
sns.set_style("darkgrid")
plt.figure(figsize = (15,9))
plt.plot(data[['Close']])
plt.xticks(range(0,data.shape[0],20), data['Date'].loc[::20], rotation=45)
plt.title("****** Stock Price",fontsize=18, fontweight='bold')
plt.xlabel('Date',fontsize=18)
plt.ylabel('Close Price (USD)',fontsize=18)
plt.show()
3.2 选取Close和Low两个特征
price = data[['Close', 'Low']]
3.3 数据归一化
scaler = MinMaxScaler(feature_range=(-1, 1))
price['Close'] = scaler.fit_transform(price['Close'].values.reshape(-1,1))
price['Low'] = scaler.fit_transform(price['Low'].values.reshape(-1,1))
3.4 数据集的制造[batch_size,time_steps,input_size]
本次选取2个维度特征作为输出,因此,input_size =2
x_train.shape = [batch_size,time_steps,input_size]
y_train.shape = [batch_size,1]
1. 输入选取的是Close和Low列作为多维度的输入,所以选择的是data数据中的第一列和第二列作为x_train【因此input_size=2】
2. 输出是选取的Close列作为预测,所以选取data数据的第一列作为y_train【即Close列作为y_train】。
#2.数据集的制作
def split_data(stock, lookback):
data_raw = stock.to_numpy()
data = []
for index in range(len(data_raw) - lookback):
data.append(data_raw[index: index + lookback])
data = np.array(data);
test_set_size = int(np.round(0.2 * data.shape[0]))
train_set_size = data.shape[0] - (test_set_size)
x_train = data[:train_set_size,:-1,:] #x_train.shape = (198, 4, 2)
y_train = data[:train_set_size,-1,0:1] #y_train.shape = (198, 1)
x_test = data[train_set_size:,:-1,:] #x_test.shape = (49, 4, 2)
y_test = data[train_set_size:,-1,0:1] #y_test.shape = (49, 1)
return [torch.Tensor(x_train), torch.Tensor(y_train), torch.Tensor(x_test),torch.Tensor(y_test)]
lookback = 5
x_train, y_train, x_test, y_test = split_data(price, lookback)
print('x_train.shape = ',x_train.shape)
print('y_train.shape = ',y_train.shape)
print('x_test.shape = ',x_test.shape)
print('y_test.shape = ',y_test.shape)
4.LSTM算法
这里的LSTM算法和单维单步预测中的LSTM预测算法一模一样。只不过我们在制作数据集的时候,对于LSTM模型中输入不一样了。
class LSTM(nn.Module):
def __init__(self, input_dim, hidden_dim, num_layers, output_dim):
super(LSTM, self).__init__()
self.hidden_dim = hidden_dim
self.num_layers = num_layers
self.lstm = nn.LSTM(input_dim, hidden_dim, num_layers, batch_first=True)
self.fc = nn.Linear(hidden_dim, output_dim)
def forward(self, x):
h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_dim).requires_grad_()
c0 = torch.zeros(self.num_layers, x.size(0), self.hidden_dim).requires_grad_()
out, (hn, cn) = self.lstm(x, (h0.detach(), c0.detach()))
out = self.fc(out[:, -1, :])
5.预训练
input_dim = 2
hidden_dim = 32
num_layers = 2
output_dim = 1
num_epochs = 100
model = LSTM(input_dim=input_dim, hidden_dim=hidden_dim, output_dim=output_dim, num_layers=num_layers)
criterion = torch.nn.MSELoss()
optimiser = torch.optim.Adam(model.parameters(), lr=0.01)
hist = np.zeros(num_epochs)
lstm = []
for t in range(num_epochs):
y_train_pred = model(x_train)
loss = criterion(y_train_pred, y_train)
hist[t] = loss.item()
# print("Epoch ", t, "MSE: ", loss.item())
optimiser.zero_grad()
loss.backward()
optimiser.step()
6.绘制预测值和真实值拟合图形,以及loss图形
predict = pd.DataFrame(scaler.inverse_transform(y_train_pred.detach().numpy()))
original = pd.DataFrame(scaler.inverse_transform(y_train.detach().numpy()))
sns.set_style("darkgrid")
fig = plt.figure()
fig.subplots_adjust(hspace=0.2, wspace=0.2)
plt.subplot(1, 2, 1)
ax = sns.lineplot(x = original.index, y = original[0], label="Data", color='royalblue')
ax = sns.lineplot(x = predict.index, y = predict[0], label="Training Prediction (LSTM)", color='tomato')
ax.set_title('Stock price', size = 14, fontweight='bold')
ax.set_xlabel("Days", size = 14)
ax.set_ylabel("Cost (USD)", size = 14)
ax.set_xticklabels('', size=10)
plt.subplot(1, 2, 2)
ax = sns.lineplot(data=hist, color='royalblue')
ax.set_xlabel("Epoch", size = 14)
ax.set_ylabel("Loss", size = 14)
ax.set_title("Training Loss", size = 14, fontweight='bold')
fig.set_figheight(6)
fig.set_figwidth(16)
# make predictions
y_test_pred = model(x_test)
# invert predictions
y_train_pred = scaler.inverse_transform(y_train_pred.detach().numpy())
y_train = scaler.inverse_transform(y_train.detach().numpy())
y_test_pred = scaler.inverse_transform(y_test_pred.detach().numpy())
y_test = scaler.inverse_transform(y_test.detach().numpy())
# calculate root mean squared error
trainScore = math.sqrt(mean_squared_error(y_train[:,0], y_train_pred[:,0]))
print('Train Score: %.2f RMSE' % (trainScore))
testScore = math.sqrt(mean_squared_error(y_test[:,0], y_test_pred[:,0]))
print('Test Score: %.2f RMSE' % (testScore))
lstm.append(trainScore)
lstm.append(testScore)
lstm.append(training_time)
完整代码
问题描述:
选用Close和Low两个特征,使用窗口time_steps窗口的2个特征,然后预测Close这一个特征数据未来一天的数据
当batch_first=True,则LSTM的inputs=(batch_size,time_steps,input_size)
batch_size = len(data)-time_steps
time_steps = 滑动窗口,本项目中值为lookback
input_size = 2【因为选取了Close和Low两个特征】
#%%
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.preprocessing import MinMaxScaler
import torch
import torch.nn as nn
import seaborn as sns
import math, time
from sklearn.metrics import mean_squared_error
filepath = './data/rlData.csv'
data = pd.read_csv(filepath)
data = data.sort_values('Date')
data.head()
data.shape
sns.set_style("darkgrid")
plt.figure(figsize = (15,9))
plt.plot(data[['Close']])
plt.xticks(range(0,data.shape[0],20), data['Date'].loc[::20], rotation=45)
plt.title("****** Stock Price",fontsize=18, fontweight='bold')
plt.xlabel('Date',fontsize=18)
plt.ylabel('Close Price (USD)',fontsize=18)
plt.show()
#1.选取特征工程2个
price = data[['Close', 'Low']]
scaler = MinMaxScaler(feature_range=(-1, 1))
price['Close'] = scaler.fit_transform(price['Close'].values.reshape(-1,1))
price['Low'] = scaler.fit_transform(price['Low'].values.reshape(-1,1))
#2.数据集的制作
def split_data(stock, lookback):
data_raw = stock.to_numpy()
data = []
for index in range(len(data_raw) - lookback):
data.append(data_raw[index: index + lookback])
data = np.array(data);
test_set_size = int(np.round(0.2 * data.shape[0]))
train_set_size = data.shape[0] - (test_set_size)
x_train = data[:train_set_size,:-1,:] #x_train.shape = (198, 4, 2)
y_train = data[:train_set_size,-1,0:1] #y_train.shape = (198, 1)
x_test = data[train_set_size:,:-1,:] #x_test.shape = (49, 4, 2)
y_test = data[train_set_size:,-1,0:1] #y_test.shape = (49, 1)
return [torch.Tensor(x_train), torch.Tensor(y_train), torch.Tensor(x_test),torch.Tensor(y_test)]
lookback = 5
x_train, y_train, x_test, y_test = split_data(price, lookback)
print('x_train.shape = ',x_train.shape)
print('y_train.shape = ',y_train.shape)
print('x_test.shape = ',x_test.shape)
print('y_test.shape = ',y_test.shape)
class LSTM(nn.Module):
def __init__(self, input_dim, hidden_dim, num_layers, output_dim):
super(LSTM, self).__init__()
self.hidden_dim = hidden_dim
self.num_layers = num_layers
self.lstm = nn.LSTM(input_dim, hidden_dim, num_layers, batch_first=True)
self.fc = nn.Linear(hidden_dim, output_dim)
def forward(self, x):
h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_dim).requires_grad_()
c0 = torch.zeros(self.num_layers, x.size(0), self.hidden_dim).requires_grad_()
out, (hn, cn) = self.lstm(x, (h0.detach(), c0.detach()))
out = self.fc(out[:, -1, :])
return out
input_dim = 2
hidden_dim = 32
num_layers = 2
output_dim = 1
num_epochs = 100
model = LSTM(input_dim=input_dim, hidden_dim=hidden_dim, output_dim=output_dim, num_layers=num_layers)
criterion = torch.nn.MSELoss()
optimiser = torch.optim.Adam(model.parameters(), lr=0.01)
hist = np.zeros(num_epochs)
lstm = []
for t in range(num_epochs):
y_train_pred = model(x_train)
loss = criterion(y_train_pred, y_train)
hist[t] = loss.item()
# print("Epoch ", t, "MSE: ", loss.item())
optimiser.zero_grad()
loss.backward()
optimiser.step()
predict = pd.DataFrame(scaler.inverse_transform(y_train_pred.detach().numpy()))
original = pd.DataFrame(scaler.inverse_transform(y_train.detach().numpy()))
sns.set_style("darkgrid")
fig = plt.figure()
fig.subplots_adjust(hspace=0.2, wspace=0.2)
plt.subplot(1, 2, 1)
ax = sns.lineplot(x = original.index, y = original[0], label="Data", color='royalblue')
ax = sns.lineplot(x = predict.index, y = predict[0], label="Training Prediction (LSTM)", color='tomato')
ax.set_title('Stock price', size = 14, fontweight='bold')
ax.set_xlabel("Days", size = 14)
ax.set_ylabel("Cost (USD)", size = 14)
ax.set_xticklabels('', size=10)
plt.subplot(1, 2, 2)
ax = sns.lineplot(data=hist, color='royalblue')
ax.set_xlabel("Epoch", size = 14)
ax.set_ylabel("Loss", size = 14)
ax.set_title("Training Loss", size = 14, fontweight='bold')
fig.set_figheight(6)
fig.set_figwidth(16)
# make predictions
y_test_pred = model(x_test)
# invert predictions
y_train_pred = scaler.inverse_transform(y_train_pred.detach().numpy())
y_train = scaler.inverse_transform(y_train.detach().numpy())
y_test_pred = scaler.inverse_transform(y_test_pred.detach().numpy())
y_test = scaler.inverse_transform(y_test.detach().numpy())
# calculate root mean squared error
trainScore = math.sqrt(mean_squared_error(y_train[:,0], y_train_pred[:,0]))
print('Train Score: %.2f RMSE' % (trainScore))
testScore = math.sqrt(mean_squared_error(y_test[:,0], y_test_pred[:,0]))
print('Test Score: %.2f RMSE' % (testScore))
lstm.append(trainScore)
lstm.append(testScore)
lstm.append(training_time)
参考:https://gitee.com/qiangchen_sh/stock-prediction/blob/master/%E4%BB%A3%E7%A0%81/LSTM%E4%BB%8E%E7%90%86%E8%AE%BA%E5%9F%BA%E7%A1%80%E5%88%B0%E4%BB%A3%E7%A0%81%E5%AE%9E%E6%88%98%204%20%E5%A4%9A%E7%BB%B4%E7%89%B9%E5%BE%81%E8%82%A1%E7%A5%A8%E4%BB%B7%E6%A0%BC%E9%A2%84%E6%B5%8B_Pytorch.ipynb