dates_trades = pd.to_datetime(trades.index).date
# time vector of trades
t_k = np.array(list(map(lambda x: x.timestamp(),
pd.to_datetime(trades.index))))
p_last = np.array(trades.loc[:, 'price']) # last transaction values
delta_q = np.array(trades.loc[:, 'siz']) # flow of traded contracts' sizes
delta_sgn = np.array(trades.loc[:, 'aggress']) # trade sign flow
match = np.array(trades.loc[:, 'mtch']) # match events
# -
# ## [Step 1](https://www.arpm.co/lab/redirect.php?permalink=s_volume_cluster_signal-implementation-step01): Process the database
t, _, q_ask, p_ask, q_bid, p_bid, t_k, _, p_last, delta_q, _,\
_ = trade_quote_processing(t, dates_quotes, q_ask, p_ask, q_bid,
p_bid, t_k, dates_trades, p_last, delta_q,
delta_sgn, match)
# ## [Step 2](https://www.arpm.co/lab/redirect.php?permalink=s_volume_cluster_signal-implementation-step02): Compute the traded price, the bid/ask prices, the bid/ask sizes and the microprice
# +
tick_time = np.arange(len(p_last[k_0:k_1 + 1]))
i_ = len(tick_time)
# last transaction value within the time window as a function of tick time
p_last_k = p_last[k_0:k_1 + 1] # traded price
# indexes of bid/ask prices near to the traded prices
ti = np.zeros(i_, dtype=int)
for i in range(i_):
ti[i] = np.where(t <= t_k[k_0 + i])[0][-1]
time_trades = np.zeros(len(t_k0)) # time vector of trades
for i in range(len(time_trades)):
time_trades[i] = t_k0[i].timestamp()
p_last = np.array(trades.loc[:, 'price']) # last transaction values
delta_q = np.array(trades.loc[:, 'siz']) # flow of traded contracts' sizes
delta_sgn = np.array(trades.loc[:, 'aggress']) # trade sign flow
match = np.array(trades.loc[:, 'mtch']) # match events
# -
# ## [Step 1](https://www.arpm.co/lab/redirect.php?permalink=s_high_freq_stock_var-implementation-step01): Process the time series
# +
# process data
time_quotes, _, h_ask, p_ask, h_bid, p_bid, time_trades, _, p_last, delta_q,\
delta_sgn, _ = trade_quote_processing(time_quotes, dates_quotes, h_ask,
p_ask, h_bid, p_bid, time_trades,
dates_trades, p_last, delta_q,
delta_sgn, match)
time_quotes = time_quotes.flatten()
# index of the first trade within the time window
k_0 = np.where(time_trades >= time_quotes[i_0])[0][0]
# index of the last trade within the time window
k_1 = np.where(time_trades <= time_quotes[i_1])[0][-1]
# -
# ## [Step 2](https://www.arpm.co/lab/redirect.php?permalink=s_high_freq_stock_var-implementation-step02): Compute the market microstructure variables
# +
q = np.cumsum(delta_q) # cumulative volume series
sgn = np.cumsum(delta_sgn) # cumulative trade sign series