S&P 500 Intraday Data

Technical Information

Dates range from 2017-09-11 to 2018-02-16 and the time interval is 1 minute. This is a MultiIndex CSV file, to load in pandas use:

dataset = pd.read_csv('dataset.csv', index_col=0, header=[0, 1]).sort_index(axis=1)

Stocks that entered or exited the Index during the dataset time range are omitted.

Collection & Processing

These are the scripts used for collecting the data, and also utilities to clean & scale the dataset & convert it to a numpy array: https://github.com/nickdl/alpha