Deep Learning Quick Reference

Creating a lagged training set

For each training example, we want to train the network to predict a value x_t , given a sequence of lags . The ideal number of lags is a hyperparameter, so some experimentation is in order.

Structuring the input in this way is a requirement of the BPTT algorithm, as we have previously talked about. We will use the following code to train the dataset:

def lag_dataframe(data, lags=1):    df = pd.DataFrame(data)    columns = [df.shift(i) for i in range(lags, 0, -1)]    columns.append(df)    df = pd.concat(columns, axis=1)    df.fillna(0, inplace=True)    cols = df.columns.tolist()    for i, col in enumerate(cols):        if i == 0: cols[i] ...