Hands-On Machine Learning for Algorithmic Trading

Tick bars

A plot of the raw tick price and volume data for AAPL looks as follows:

stock, date = 'AAPL', '20180329'title = '{} | {}'.format(stock, pd.to_datetime(date).date()with pd.HDFStore(itch_store) as store:    s = store['S'].set_index('event_code') # system events    s.timestamp = s.timestamp.add(pd.to_datetime(date)).dt.time    market_open = s.loc['Q', 'timestamp']     market_close = s.loc['M', 'timestamp']with pd.HDFStore(stock_store) as store:    trades = store['{}/trades'.format(stock)].reset_index()trades = trades[trades.cross == 0] # excluding data from open/close crossingstrades.price = trades.price.mul(1e-4)trades.price = trades.price.mul(1e-4) # format pricetrades = trades[trades.cross == 0]    # exclude crossing tradestrades = trades.between_time(market_open, ...