共享单车需求LSTM预测代码
时间: 2023-06-24 21:08:37 浏览: 52
以下是一个使用LSTM(长短时记忆网络)预测共享单车需求的Python代码示例:
```python
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.preprocessing import MinMaxScaler
from keras.models import Sequential
from keras.layers import Dense, LSTM
# 读取数据
data = pd.read_csv('bike-sharing.csv', index_col='datetime', parse_dates=['datetime'])
data.drop('casual', axis=1, inplace=True)
data.drop('registered', axis=1, inplace=True)
# 数据归一化
scaler = MinMaxScaler(feature_range=(0, 1))
scaled_data = scaler.fit_transform(data)
# 划分训练集和测试集
train_size = int(len(scaled_data) * 0.8)
test_size = len(scaled_data) - train_size
train_data, test_data = scaled_data[0:train_size,:], scaled_data[train_size:len(scaled_data),:]
# 创建时序数据
def create_dataset(dataset, look_back=1):
dataX, dataY = [], []
for i in range(len(dataset) - look_back -1):
a = dataset[i:(i+look_back), 0]
dataX.append(a)
dataY.append(dataset[i + look_back, 0])
return np.array(dataX), np.array(dataY)
look_back = 12
trainX, trainY = create_dataset(train_data, look_back)
testX, testY = create_dataset(test_data, look_back)
# 转换成LSTM的输入格式 [样本数, 时间步, 特征数]
trainX = np.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))
testX = np.reshape(testX, (testX.shape[0], 1, testX.shape[1]))
# 构建LSTM模型
model = Sequential()
model.add(LSTM(50, input_shape=(1, look_back)))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
# 训练模型
model.fit(trainX, trainY, epochs=50, batch_size=72, verbose=2)
# 预测数据
train_predict = model.predict(trainX)
test_predict = model.predict(testX)
# 反归一化
train_predict = scaler.inverse_transform(train_predict)
trainY = scaler.inverse_transform([trainY])
test_predict = scaler.inverse_transform(test_predict)
testY = scaler.inverse_transform([testY])
# 计算RMSE误差
train_score = np.sqrt(mean_squared_error(trainY[0], train_predict[:,0]))
test_score = np.sqrt(mean_squared_error(testY[0], test_predict[:,0]))
print('Train Score: %.2f RMSE' % (train_score))
print('Test Score: %.2f RMSE' % (test_score))
# 可视化结果
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
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
plt.plot(scaler.inverse_transform(scaled_data))
plt.plot(train_predict_plot)
plt.plot(test_predict_plot)
plt.show()
```
在这个示例中,我们使用了一个LSTM模型来预测未来几个小时的共享单车需求。我们首先读取数据,将数据归一化,然后将数据集划分为训练集和测试集。接下来,我们创建时序数据并将其转换为LSTM的输入格式。然后,我们使用Keras创建一个LSTM模型,将其拟合到训练数据中,并使用该模型预测测试数据。最后,我们计算预测结果的RMSE误差,并将结果可视化。