def test_compare_order_metrics(self):
sim_root = self.config.sim_root + self.sim_st.date().isoformat(
) + "/" + self.sim_st.time().isoformat() + "/"
all_sims = DataLoader().load_sim_data(sim_root)
all_sim_limit_orders = list(
map(lambda sim: DataSplitter.get_limit_orders(sim[0].compute()),
all_sims))
all_sim_market_orders = list(
map(lambda sim: DataSplitter.get_market_orders(sim[0].compute()),
all_sims))
all_sim_trades = list(map(lambda sim: sim[1].compute(), all_sims))
all_sim_cancels = list(map(lambda sim: sim[2].compute(), all_sims))
feed_df = DataLoader().load_feed(
self.config.real_root, self.sim_st,
self.sim_st + timedelta(seconds=self.config.simulation_window),
self.config.product)
real_orders = DataSplitter.get_orders(feed_df)
real_limit_orders = DataSplitter.get_limit_orders(real_orders)
real_market_orders = DataSplitter.get_market_orders(real_orders)
real_trades = DataSplitter.get_trades(feed_df)
real_trades['size'] = pd.to_numeric(real_trades['remaining_size'])
real_cancels = DataSplitter.get_cancellations(feed_df)
real_cancels['size'] = pd.to_numeric(real_cancels['remaining_size'])
print("Order Buy/Sell limit metrics")
Evaluation.compare_order_metrics(real_limit_orders,
all_sim_limit_orders)
print("Order Buy/Sell market metrics")
Evaluation.compare_order_metrics(real_market_orders,
all_sim_market_orders)
print("Cancel metrics")
Evaluation.compare_order_metrics(real_cancels, all_sim_cancels)
print("Trade metrics")
Evaluation.compare_metrics(real_trades, all_sim_trades)
def load_split_data(real_root, start_time, end_time, product):
feed_df = DataLoader().load_feed(real_root, start_time, end_time,
product)
feed_df = DataSplitter.get_product(product, feed_df)
orders_df = DataSplitter.get_orders(feed_df)
trades_df = DataSplitter.get_trades(feed_df)
cancels_df = DataSplitter.get_cancellations(feed_df)
return orders_df, trades_df, cancels_df
def graph_order_cancel_relative_price_distribution(self, feed_df):
trades_df = DataSplitter.get_trades(feed_df)
cancels_df = DataSplitter.get_cancellations(feed_df)
self.graph_relative_price_distribution(trades_df, cancels_df)
def test_orders_per_minute_windowed(self):
product = "LTC-USD"
root = "/Users/jamesprince/project-data/data/consolidated-feed/"
st = datetime.datetime(2018, 5, 17, 0, 0, 0)
et = datetime.datetime(2018, 5, 17, 23, 59, 59)
feed_df = DataLoader.load_feed(root + product + "/", st, et, product)
orders = DataSplitter.get_orders(feed_df)
limit_orders = DataSplitter.get_limit_orders(orders)
market_orders = DataSplitter.get_market_orders(orders)
trades = DataSplitter.get_trades(feed_df)
cancels = DataSplitter.get_cancellations(feed_df)
print("Total limit orders: " + str(len(limit_orders)))
print("Total market orders: " + str(len(market_orders)))
print("Total trades: " + str(len(trades)))
print("Total cancels: " + str(len(cancels)))
# total_vol = trades['remaining_size'].sum()
# print("Total traded volume: " + str(total_vol))
window_minutes = 60
step_minutes = 5
times = []
num_limit_orders = []
num_market_orders = []
num_trades = []
num_cancels = []
traded_vols = []
for i in range(0, int((24 * 60) / step_minutes - 1)):
window_st = st + datetime.timedelta(seconds=i * step_minutes * 60)
window_et = window_st + datetime.timedelta(seconds=window_minutes *
60)
limit_orders_this_window = DataSplitter.get_between(
limit_orders, window_st, window_et)
market_orders_this_window = DataSplitter.get_between(
market_orders, window_st, window_et)
trades_this_window = DataSplitter.get_between(
trades, window_st, window_et)
cancels_this_window = DataSplitter.get_between(
cancels, window_st, window_et)
times.append(window_st)
num_limit_orders.append(len(limit_orders_this_window))
num_market_orders.append(len(market_orders_this_window))
num_trades.append(len(trades_this_window))
num_cancels.append(len(cancels_this_window))
# vol_this_window = trades_this_window['remaining_size'].sum()
# traded_vols.append(vol_this_window)
Statistics.plot_metric_daily_comparison(times, num_limit_orders,
num_cancels, "LTC-USD", st,
step_minutes, window_minutes,
"Limit Orders", "Cancels")
Statistics.plot_metric_daily(times, num_limit_orders, "LTC-USD", st,
step_minutes, window_minutes,
"Limit Orders")
Statistics.plot_metric_daily(times, num_market_orders, "LTC-USD", st,
step_minutes, window_minutes,
"Market Orders")
Statistics.plot_metric_daily(times, num_trades, "LTC-USD", st,
step_minutes, window_minutes, "Trades")
Statistics.plot_metric_daily(times, num_cancels, "LTC-USD", st,
step_minutes, window_minutes, "Cancels")
Statistics.plot_metric_daily(times, traded_vols, "LTC-USD", st,
step_minutes, window_minutes,
"Traded Volume")
def test_real_spread_plot(self):
plt.figure(figsize=(12, 8))
product = "LTC-USD"
root = "/Users/jamesprince/project-data/data/consolidated-feed/"
st = datetime.datetime(2018, 5, 17, 1, 0, 0)
et = datetime.datetime(2018, 5, 17, 1, 5, 0)
feed_df = DataLoader.load_feed(root + product + "/", st, et, product)
conf = configparser.ConfigParser()
conf.read("../config/backtest.ini")
config = BacktestConfig(conf)
ob_seq, ob_state = reconstruct_orderbook(config, st,
logging.getLogger("test"))
orderbook_evo = OrderBookEvolutor(ob_state, st, ob_seq)
res_df = orderbook_evo.evolve_orderbook(feed_df)
res_df['seconds'] = (
res_df['time'] -
res_df['time'].iloc[0]).apply(lambda x: x.total_seconds())
print(res_df)
limit_orders = DataSplitter.get_limit_orders_from_feed(feed_df)
limit_orders['seconds'] = (
limit_orders['time'] -
limit_orders['time'].iloc[0]).apply(lambda x: x.total_seconds())
buy_limit_orders = DataSplitter.get_side("buy", limit_orders)
sell_limit_orders = DataSplitter.get_side("sell", limit_orders)
cancels = DataSplitter.get_cancellations(feed_df)
# print(cancels)
cancels_merged = cancels.merge(limit_orders, on='order_id', how='left')
# print(cancels_merged)
cancels_merged['price'] = cancels_merged['price_x']
cancels_merged['side'] = cancels_merged['side_x']
cancels_merged['seconds'] = (cancels_merged['time_x'] -
cancels_merged['time_x'].iloc[0]
).apply(lambda x: x.total_seconds())
cancels_merged['lifetime'] = abs(cancels_merged['time_x'] -
cancels_merged['time_y']).dropna()
print(cancels_merged)
median_idx = int(len(cancels_merged['lifetime']) / 2)
print(cancels_merged['lifetime'].sort_values().iloc[median_idx])
buy_cancels = DataSplitter.get_side("buy", cancels_merged)
sell_cancels = DataSplitter.get_side("sell", cancels_merged)
plt.plot(buy_limit_orders['seconds'],
buy_limit_orders['price'],
'r+',
label="Buy limit orders")
plt.plot(sell_limit_orders['seconds'],
sell_limit_orders['price'],
'b+',
label="Sell limit orders")
# plt.plot(buy_cancels['seconds'], buy_cancels['price'], 'r+', label="Buy side cancels")
# plt.plot(sell_cancels['seconds'], sell_cancels['price'], 'b+', label="Sell side cancels")
plt.plot(res_df['seconds'], res_df['best_bid'], label='Best bid price')
plt.plot(res_df['seconds'], res_df['best_ask'], label='Best ask price')
start_price = res_df['midprice'].iloc[0]
plt.ylim(start_price - 5, start_price + 5)
plt.legend()
plt.show()