rnn循环神经网络jupyter notebook

### 关于RNN的Jupyter Notebook教程

#### 创建简单的RNN模型用于时间序列预测

为了创建一个基于RNN的时间序列预测模型，可以采用如下方法构建并训练该模型。此过程不仅展示了如何定义网络架构，还涵盖了数据预处理、模型编译与评估等方面的内容。

import numpy as np
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import SimpleRNN, Dense
from sklearn.preprocessing import MinMaxScaler
import matplotlib.pyplot as plt

# 数据准备阶段
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)

# 加载并缩放数据集
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(np.random.rand(100).reshape(-1, 1))

train_size = int(len(dataset) * 0.67)
test_size = len(dataset) - train_size
train, test = dataset[0:train_size,:], dataset[train_size:len(dataset),:]

look_back = 1
trainX, trainY = create_dataset(train, look_back)
testX, testY = create_dataset(test, look_back)

# 将输入重塑成[samples, time steps, features] 的形式
trainX = np.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))
testX = np.reshape(testX, (testX.shape[0], 1, testX.shape[1]))

# 构建简单RNN模型
model = Sequential()
model.add(SimpleRNN(units=32, input_shape=(1, look_back)))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
history = model.fit(trainX, trainY, epochs=100, batch_size=1, verbose=2)

# 预测并对结果反向转换
trainPredict = model.predict(trainX)
testPredict = model.predict(testX)

trainPredict = scaler.inverse_transform(trainPredict)
testPredict = scaler.inverse_transform(testPredict)

plt.plot(scaler.inverse_transform(dataset))
plt.plot([None for _ in range(train_size)] + [x[0] for x in testPredict.tolist()])
plt.show()

上述代码片段提供了一个基础框架来理解怎样利用Keras库中的`SimpleRNN`层建立基本的循环神经网络，并应用于时间序列分析的任务上[^1]。