写一个lstm时间预测代码,进行归一化与反归一化
时间: 2023-10-13 16:21:13 浏览: 56
以下是一个简单的LSTM时间预测代码示例,包括归一化和反归一化:
首先,导入必要的库:
```python
import numpy as np
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
from keras.models import Sequential
from keras.layers import Dense, LSTM
import matplotlib.pyplot as plt
```
接下来,读取数据并进行归一化:
```python
# 读取数据
data = pd.read_csv('data.csv', usecols=[1])
# 归一化
scaler = MinMaxScaler(feature_range=(0, 1))
scaled_data = scaler.fit_transform(data)
```
然后,将数据划分为训练集和测试集,并创建LSTM模型:
```python
# 划分训练集和测试集
train_size = int(len(scaled_data) * 0.7)
test_size = len(scaled_data) - train_size
train_data = scaled_data[0:train_size, :]
test_data = scaled_data[train_size:len(scaled_data), :]
# 创建X_train和y_train
look_back = 3
def create_dataset(dataset, look_back=1):
X, Y = [], []
for i in range(len(dataset)-look_back-1):
a = dataset[i:(i+look_back), 0]
X.append(a)
Y.append(dataset[i + look_back, 0])
return np.array(X), np.array(Y)
X_train, y_train = create_dataset(train_data, look_back)
X_test, y_test = create_dataset(test_data, look_back)
# 转换为3D格式 [样本数, 时间步长, 特征数]
X_train = np.reshape(X_train, (X_train.shape[0], X_train.shape[1], 1))
X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], 1))
# 创建LSTM模型
model = Sequential()
model.add(LSTM(50, input_shape=(look_back, 1)))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
```
接下来,训练模型并进行预测:
```python
# 训练模型
model.fit(X_train, y_train, epochs=100, batch_size=1, verbose=2)
# 进行预测
train_predict = model.predict(X_train)
test_predict = model.predict(X_test)
# 反归一化
train_predict = scaler.inverse_transform(train_predict)
y_train = scaler.inverse_transform([y_train])
test_predict = scaler.inverse_transform(test_predict)
y_test = scaler.inverse_transform([y_test])
```
最后,绘制预测结果和实际结果的图形:
```python
# 绘制训练集预测结果
train_predict_plot = np.empty_like(scaled_data)
train_predict_plot[:, :] = np.nan
train_predict_plot[look_back:len(train_predict)+look_back, :] = train_predict
# 绘制测试集预测结果
test_predict_plot = np.empty_like(scaled_data)
test_predict_plot[:, :] = np.nan
test_predict_plot[len(train_predict)+(look_back*2)+1:len(scaled_data)-1, :] = test_predict
# 绘制原始数据、训练集预测结果和测试集预测结果的图形
plt.plot(scaler.inverse_transform(scaled_data))
plt.plot(train_predict_plot)
plt.plot(test_predict_plot)
plt.show()
```