Goal: Predict multivariate time-series with exogenous variables
Assuming a pandas DataFrame with T rows and M+N columns, where each row t represents one time stamp, M columns represent the corresponding RNN output at time t, and N columns represent the corresponding RNN input at time t.
Ideally, the user can hand the dataframe, or two data frames, say, X (TxN) for the input and y (TxM) for the output, to the theanets API and the API takes care of reformatting it into the required 3 dimensional format required to train RNNs.
Goal: Predict multivariate time-series with exogenous variables
Assuming a pandas DataFrame with T rows and M+N columns, where each row t represents one time stamp, M columns represent the corresponding RNN output at time t, and N columns represent the corresponding RNN input at time t.
Ideally, the user can hand the dataframe, or two data frames, say, X (TxN) for the input and y (TxM) for the output, to the theanets API and the API takes care of reformatting it into the required 3 dimensional format required to train RNNs.