愉快的学习就从翻译开始吧_Multi-step Time Series Forecasting_10_Multi-Step LSTM Network_Make LSTM Forecasts

Make LSTM Forecasts/让LSTM预测

The next step is to use the fit LSTM network to make forecasts.

下一步是用拟合的LSTM网络来做预测

A single forecast can be made with the fit LSTM network by calling model.predict(). Again, the data must be formatted into a 3D array with the format [samples, timesteps, features].

通过调用model.predict()，拟合的LSTM网络可以做单个预测，再次，数据必须被格式化为【samples，timesteps，features】的3D数组。

We can wrap this up into a function called forecast_lstm().

我们可以把这打包到一个名为forecast_lstm()的函数。

1 2 3 4 5 6 7 8

# make one forecast with an LSTM, def forecast_lstm ( model , X , n_batch ) : # reshape input pattern to [samples, timesteps, features] X = X . reshape ( 1 , 1 , len ( X ) ) # make forecast forecast = model . predict ( X , batch_size = n_batch ) # convert to array return [ x for x in forecast [ 0 , : ] ]

We can call this function from the make_forecasts() function and update it to accept the model as an argument. The updated version is listed below.

我们可以从make_forecasts()中调用这个函数，并将其更新为接受模型作为参数，下面列出了更新版本

1 2 3 4 5 6 7 8 9 10

# evaluate the persistence model def make_forecasts ( model , n_batch , train , test , n_lag , n_seq ) : forecasts = list ( ) for i in range ( len ( test ) ) : X , y = test [ i , 0 : n_lag ] , test [ i , n_lag : ] # make forecast forecast = forecast_lstm ( model , X , n_batch ) # store the forecast forecasts . append ( forecast ) return forecasts

This updated version of the make_forecasts() function can be called as follows:

make_forecasts（）函数的更新版本可以调用如下：

1 2	# make forecasts forecasts = make_forecasts ( model , 1 , train , test , 1 , 3 )