Hands-On Machine Learning for Algorithmic Trading

Loading the data

For comparison, we illustrate the application of RNNs to modeling and forecasting several time series using the same dataset we used for the VAR example, monthly data on consumer sentiment, and industrial production from the Federal Reserve's FRED service, as follows:

df = web.DataReader(['UMCSENT', 'IPGMFN'], 'fred', '1980', '2017-                     12').dropna()df.columns = ['sentiment', 'ip']df.info()DatetimeIndex: 456 entries, 1980-01-01 to 2017-12-01Data columns (total 2 columns):     sentiment 456 non-null float64     ip 456 non-null float64