使用具有张量流作为后端的LSTM和Keras来预测数据点的下一个值

Question

我有65个样本的数据。例如：2697,2825,2136,2824,3473,2513,2538,3051,2737.9805,3133.849,2350.8695,6000,3121.225

我在训练和测试（训练和测试）中划分了数据，对其进行了缩放并对其进行了监督。我必须预测第66个样本值是什么。

2697,2825,2136,2824,3473,2513,2538,3051,2737.9805,3133.849,2350.8695,6000,3121.225，？，？，？

我尝试了各种方法。其中之一是：

enter code here

lstm_model = fit_lstm(train_scaled, 1, 100, 4)

train_reshaped = train_scaled[:, 0].reshape(len(train_scaled), 1, 1)

lstm_model.predict(train_reshaped, batch_size=1)

predictions = list()
expected = list()
for i in range(len(test_scaled)):
     X, y = test_scaled[i, 0:-1], test_scaled[i, -1]
     yhat = forecast_lstm(lstm_model, 1, X)
     # invert scaling
     yhat = invert_scale(scaler, X, yhat)

    yhat = pred(raw_values, yhat, len(test_scaled)-i+1)

    # store forecast
    predictions.append(yhat)

    expected_1 = raw_values[len(train) + i]

    expected.append(expected_1)

print('Predicted=%f, Expected=%f' % (yhat, expected_1))

任何领导都会有所帮助。

先谢谢。