lstmPM2.5预测运行代码

LSTM（长短期记忆网络）常用于时间序列数据分析，例如PM2.5（细颗粒物）浓度预测。这类模型通常包含以下几个步骤的运行代码：

1. **导入库**:

import numpy as np
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import LSTM, Dense, Dropout

2. **数据预处理**:

data = pd.read_csv('pm2_5_data.csv') # 假设从CSV文件加载数据
scaler = MinMaxScaler(feature_range=(0, 1))
scaled_data = scaler.fit_transform(data['PM2.5'].values.reshape(-1, 1))

3. **分割训练集和测试集**:

train_size = int(len(scaled_data) * 0.8)
test_size = len(scaled_data) - train_size
train, test = scaled_data[0:train_size], scaled_data[train_size:len(scaled_data)]

4. **创建序列数据** (对于LSTM输入窗口大小为`look_back`):

look_back = 5  # 例如，考虑前5天的数据
X_train, y_train = [], []
for i in range(train_size - look_back - 1):
    X_train.append(train[i:(i + look_back), 0])
    y_train.append(train[i + look_back, 0])
X_train, y_train = np.array(X_train), np.array(y_train)

X_test, y_test = [], []
for i in range(test_size - look_back - 1):
    X_test.append(test[i:(i + look_back), 0])
    y_test.append(test[i + look_back, 0])
X_test, y_test = np.array(X_test), np.array(y_test)

5. **定义并编译模型**:

model = Sequential()
model.add(LSTM(units=50, return_sequences=True, input_shape=(look_back, 1)))
model.add(Dropout(0.2))
model.add(LSTM(units=50, return_sequences=False))
model.add(Dropout(0.2))
model.add(Dense(units=1))

model.compile(optimizer='adam', loss='mean_squared_error')

6. **训练模型**:

model.fit(X_train, y_train, epochs=50, batch_size=32)

7. **评估和预测**:

predictions = model.predict(X_test)
predicted_pm25 = scaler.inverse_transform(predictions)