CONST_TRAINTING_SEQUENCE_LENGTH = 12CONST_TESTING_CASES = 5def dataNormalization(data):    return [(datum - data[0]) / data[0] for datum in data]def dataDeNormalization(data, base):    return [(datum + 1) * base for datum in data]def getDeepLearningData(ticker):    # 步骤1. 加载数据    data = pandas.read_csv('/Users/yindeyong/Desktop/Django_Projects/pythonstock/data/Intraday/' + ticker + '.csv')[        'close'].tolist()    # 步骤2. 构建训练数据    dataTraining = []    for i in range(len(data) - CONST_TESTING_CASES * CONST_TRAINTING_SEQUENCE_LENGTH):        dataSegment = data[i:i + CONST_TRAINTING_SEQUENCE_LENGTH + 1]        dataTraining.append(dataNormalization(dataSegment))    dataTraining = numpy.array(dataTraining)    numpy.random.shuffle(dataTraining)    X_Training = dataTraining[:, :-1]    Y_Training = dataTraining[:, -1]    # 步骤3. 构建测试数据    X_Testing = []    Y_Testing_Base = []    for i in range(CONST_TESTING_CASES, 0, -1):        dataSegment = data[-(i + 1) * CONST_TRAINTING_SEQUENCE_LENGTH:-i * CONST_TRAINTING_SEQUENCE_LENGTH]        Y_Testing_Base.append(dataSegment[0])        X_Testing.append(dataNormalization(dataSegment))    Y_Testing = data[-CONST_TESTING_CASES * CONST_TRAINTING_SEQUENCE_LENGTH:]    X_Testing = numpy.array(X_Testing)    Y_Testing = numpy.array(Y_Testing)    # 步骤4. 为深度学习重塑数据    X_Training = numpy.reshape(X_Training, (X_Training.shape[0], X_Training.shape[1], 1))    X_Testing = numpy.reshape(X_Testing, (X_Testing.shape[0], X_Testing.shape[1], 1))    return X_Training, Y_Training, X_Testing, Y_Testing, Y_Testing_Basedef predictLSTM(ticker):    # 步骤1. 加载数据    X_Training, Y_Training, X_Testing, Y_Testing, Y_Testing_Base = getDeepLearningData(ticker)    # 步骤2. 构建模型    model = Sequential()    model.add(LSTM(        input_shape=1,        output_dim=50,        return_sequences=True))    model.add(Dropout(0.2))    model.add(LSTM(        200,        return_sequences=False))    model.add(Dropout(0.2))    model.add(Dense(output_dim=1))    model.add(Activation('linear'))    model.compile(lose='mse', optimizer='rmsprop')    # 步骤3. 训练模型    model.fit(X_Training, Y_Training,              batch_size=512,              nb_epoch=5,              validation_split=0.05)predictLSTM(ticker='MRIN')

我遇到了一个错误：

文件 “/Users/yindeyong/Desktop/Django_Projects/envs/stockenv/lib/python3.6/site-packages/keras/engine/base_layer.py”, 行147，在init batch_size,) + tuple(kwargs[‘input_shape’])TypeError: ‘int’对象不可迭代

我尝试将input_shape=1改为input_shape=(1,)，然后得到了另一个错误：

ValueError: 输入0与层lstm_1不兼容：期望ndim=3，发现ndim=2

回答：

LSTM是一种处理序列数据的递归网络

序列必须有长度和特征，您的输入形状必须包含这两个：input_shape=(length, features)。

您的数据也必须相应地进行形状调整，使用(sequences, length, features)。

对于可变长度，您可以使用input_shape=(None,features)。