seed=np.random.randint(low=0, high=2**32)))
for j in range(agent_count, agent_count + num_noise)
])
agent_count += num_noise
agent_types.extend(['NoiseAgent'])
# 3) Value Agents
num_value = 100
agents.extend([
ValueAgent(id=j,
name="ValueAgent_{}".format(j),
type="ValueAgent",
symbol=symbol,
starting_cash=starting_cash,
sigma_n=r_bar / 10,
r_bar=r_bar,
kappa=1.67e-15,
lambda_a=7e-11,
log_orders=False,
log_to_file=False,
random_state=np.random.RandomState(
seed=np.random.randint(low=0, high=2**32)))
for j in range(agent_count, agent_count + num_value)
])
agent_count += num_value
agent_types.extend(['ValueAgent'])
# 4) Market Maker Agents
"""
window_size == Spread of market maker (in ticks) around the mid price
pov == Percentage of transacted volume seen in previous `mm_wake_up_freq` that
random_state=np.random.RandomState(
seed=np.random.randint(low=0, high=2**32, dtype='uint64')))
for j in range(agent_count, agent_count + num_noise)
])
agent_count += num_noise
agent_types.extend(['NoiseAgent'])
# 3) Value Agents
num_value = 100
agents.extend([
ValueAgent(id=j,
name="Value Agent {}".format(j),
type="ValueAgent",
symbol=symbol,
starting_cash=starting_cash,
sigma_n=sigma_n,
r_bar=r_bar,
kappa=kappa,
lambda_a=lambda_a,
random_state=np.random.RandomState(
seed=np.random.randint(low=0, high=2**32, dtype='uint64')))
for j in range(agent_count, agent_count + num_value)
])
agent_count += num_value
agent_types.extend(['ValueAgent'])
# 4) Market Maker Agent
num_mm_agents = 1
agents.extend([
MarketMakerAgent(
id=j,
['NoiseAgent' for j in range(agent_count, agent_count + num_noise)])
# 100 agents
num_value = num - num_noise
# ZI strategy split. Note that agent arrival rates are quite small, because our minimum
# time step is a nanosecond, and we want the agents to arrive more on the order of
# minutes.
agents.extend([
ValueAgent(
j,
"Value Agent {}".format(j),
"ValueAgent {}".format(j),
random_state=np.random.RandomState(
seed=np.random.randint(low=0, high=2**32, dtype='uint64')),
log_orders=log_orders,
symbol=symbol, # starting_cash=starting_cash,
sigma_n=sigma_n,
r_bar=s['r_bar'],
kappa=s['agent_kappa'],
sigma_s=s['fund_vol'],
lambda_a=1e-12) for j in range(agent_count, agent_count + num_value)
])
agent_types.extend(["ValueAgent {}".format(j) for j in range(num_value)])
agent_count += num_value
### Configure a simple message latency matrix for the agents. Each entry is the minimum
### nanosecond delay on communication [from][to] agent ID.
# Square numpy array with dimensions equal to total agent count. Most agents are handled
# at init, drawn from a uniform distribution from:
seed=np.random.randint(low=0, high=2**32, dtype="uint64")),
) for j in range(agent_count, agent_count + num_noise)
])
agent_count += num_noise
agent_types.extend(["NoiseAgent"])
# 3) Value Agents
num_value = 100
agents.extend([
ValueAgent(
id=j,
name="Value Agent {}".format(j),
type="ValueAgent",
symbol=symbol,
starting_cash=starting_cash,
sigma_n=sigma_n,
r_bar=r_bar,
kappa=kappa,
lambda_a=lambda_a,
log_orders=log_orders,
random_state=np.random.RandomState(
seed=np.random.randint(low=0, high=2**32, dtype="uint64")),
) for j in range(agent_count, agent_count + num_value)
])
agent_count += num_value
agent_types.extend(["ValueAgent"])
# 4) Market Maker Agents
"""
window_size == Spread of market maker (in ticks) around the mid price
pov == Percentage of transacted volume seen in previous `mm_wake_up_freq` that
the market maker places at each level
symbol=symbol,
starting_cash=starting_cash,
wakeup_time=mkt_open + np.random.rand() * (mkt_close - mkt_open))
for j in range(agent_count, agent_count + num_noise)
])
agent_count += num_noise
agent_types.extend(['NoiseAgent' for j in range(num_noise)])
# 3) Value Agents
agents.extend([
ValueAgent(
j,
"ValueAgent {}".format(j),
"ValueAgent {}".format(j),
random_state=np.random.RandomState(
seed=np.random.randint(low=0, high=2**32, dtype='uint64')),
r_bar=r_bar,
lambda_a=1e-13,
sigma_n=r_bar / 10,
kappa=kappa,
log_orders=log_orders,
symbol=symbol) for j in range(agent_count, agent_count + num_value)
])
agent_types.extend(["ValueAgent {}".format(j) for j in range(num_value)])
agent_count += num_value
#4) Market Maker Agent
num_mm_agents = 1
agents.extend([
MarketMakerAgent(
id=j,
name="MarketMakerAgent {}".format(j),
symbol = 'IBM'
s = symbols[symbol]
# ZI strategy split. Note that agent arrival rates are quite small, because our minimum
# time step is a nanosecond, and we want the agents to arrive more on the order of
# minutes.
for n, x in zip(zi, zi_strategy):
strat_name = agent_strats[agent_id]
while n > 0:
agents.append(ZeroIntelligenceAgent(agent_id, "ZI Agent {}".format(agent_id), strat_name, random_state = get_rand_obj(agent_seeds[agent_id]), log_orders=log_orders, symbol=symbol, starting_cash=starting_cash, sigma_n=zi_obs_noise, r_bar=s['r_bar'], kappa=s['agent_kappa'], sigma_s=s['fund_vol'], q_max=10, sigma_pv=5e6, R_min=x[0], R_max=x[1], eta=x[2], lambda_a=1e-12))
agent_id += 1
n -= 1
# Add value agents.
for i in range(num_val):
agents.extend([ ValueAgent(agent_id, "Value Agent {}".format(agent_id), "ValueAgent", symbol = symbol, random_state = get_rand_obj(agent_seeds[agent_id]), log_orders=log_orders, starting_cash=starting_cash, sigma_n=zi_obs_noise, r_bar=s['r_bar'], kappa=s['agent_kappa'], sigma_s=s['fund_vol'], lambda_a=1e-12) ])
agent_id += 1
# Add an OBI agent to try to beat this market.
for i in range(num_obi):
random_state = get_rand_obj(agent_seeds[agent_id])
agents.extend([ OrderBookImbalanceAgent(agent_id, "OBI Agent {}".format(agent_id), "OrderBookImbalanceAgent", symbol = symbol, starting_cash = starting_cash, levels = levels, entry_threshold = entry_threshold, trail_dist = trail_dist, freq = obi_freq, random_state = random_state) ])
agent_id += 1
# Add market maker agents.
for i in range(num_mm):
random_state = get_rand_obj(agent_seeds[agent_id])
agents.extend([ MarketMakerAgent(agent_id, "Market Maker Agent {}".format(agent_id), "MarketMakerAgent", symbol=symbol, starting_cash=starting_cash, min_size=500, max_size=1000, subscribe=True, log_orders=False, random_state = random_state) ])
agent_id += 1
def generateMidPrices(self, sigma_n): # Set random seed
if not self.seed:
self.seed = int(
pd.Timestamp.now().timestamp() * 1000000) % (2**32 - 1)
np.random.seed(self.seed)
# Note: sigma_s is no longer used by the agents or the fundamental (for sparse discrete simulation).
symbols = {
self.symbol: {
'r_bar':
self.r_bar,
'kappa':
self.kappa,
'agent_kappa':
1e-15,
'sigma_s':
0.,
'fund_vol':
self.sigma_s,
'megashock_lambda_a':
1e-15,
'megashock_mean':
0.,
'megashock_var':
1e-15,
"random_state":
np.random.RandomState(
seed=np.random.randint(low=0, high=2**32, dtype='uint64'))
}
}
util.silent_mode = True
LimitOrder.silent_mode = True
OrderBook.tqdm_used = False
kernel = CalculationKernel(
"Calculation Kernel",
random_state=np.random.RandomState(
seed=np.random.randint(low=0, high=2**32, dtype='uint64')))
### Configure the agents. When conducting "agent of change" experiments, the
### new agents should be added at the END only.
agent_count = 0
agents = []
agent_types = []
# Let's open the exchange at 9:30 AM.
mkt_open = self.midnight + pd.to_timedelta('09:30:00')
# And close it at 4:00 PM.
mkt_close = self.midnight + pd.to_timedelta('16:00:00')
# Configure an appropriate oracle for all traded stocks.
# All agents requiring the same type of Oracle will use the same oracle instance.
oracle = SparseMeanRevertingOracle(mkt_open, mkt_close, symbols)
# Create the exchange.
num_exchanges = 1
agents.extend([
ExchangeAgent(
j,
"Exchange Agent {}".format(j),
"ExchangeAgent",
mkt_open,
mkt_close, [s for s in symbols],
log_orders=False,
book_freq=self.freq,
pipeline_delay=0,
computation_delay=0,
stream_history=10,
random_state=np.random.RandomState(
seed=np.random.randint(low=0, high=2**32, dtype='uint64')))
for j in range(agent_count, agent_count + num_exchanges)
])
agent_types.extend(["ExchangeAgent" for j in range(num_exchanges)])
agent_count += num_exchanges
symbol = self.symbol
s = symbols[symbol]
# Some value agents.
agents.extend([
ValueAgent(
j,
"Value Agent {}".format(j),
"ValueAgent {}".format(j),
random_state=np.random.RandomState(
seed=np.random.randint(low=0, high=2**32, dtype='uint64')),
log_orders=False,
symbol=symbol,
starting_cash=self.starting_cash,
sigma_n=sigma_n,
r_bar=s['r_bar'],
kappa=s['agent_kappa'],
sigma_s=s['fund_vol'],
lambda_a=self.lambda_a)
for j in range(agent_count, agent_count + self.num_agents)
])
agent_types.extend(
["ValueAgent {}".format(j) for j in range(self.num_agents)])
agent_count += self.num_agents
# Config the latency model
latency = None
noise = None
latency_model = None
USE_NEW_MODEL = True
### BEGIN OLD LATENCY ATTRIBUTE CONFIGURATION ###
### Configure a simple message latency matrix for the agents. Each entry is the minimum
### nanosecond delay on communication [from][to] agent ID.
# Square numpy array with dimensions equal to total agent count. Most agents are handled
# at init, drawn from a uniform distribution from:
# Times Square (3.9 miles from NYSE, approx. 21 microseconds at the speed of light) to:
# Pike Place Starbucks in Seattle, WA (2402 miles, approx. 13 ms at the speed of light).
# Other agents can be explicitly set afterward (and the mirror half of the matrix is also).
if not USE_NEW_MODEL:
# This configures all agents to a starting latency as described above.
latency = np.random.uniform(low=21000,
high=13000000,
size=(len(agent_types),
len(agent_types)))
# Overriding the latency for certain agent pairs happens below, as does forcing mirroring
# of the matrix to be symmetric.
for i, t1 in zip(range(latency.shape[0]), agent_types):
for j, t2 in zip(range(latency.shape[1]), agent_types):
# Three cases for symmetric array. Set latency when j > i, copy it when i > j, same agent when i == j.
if j > i:
# Presently, strategy agents shouldn't be talking to each other, so we set them to extremely high latency.
if (t1 == "ZeroIntelligenceAgent"
and t2 == "ZeroIntelligenceAgent"):
latency[
i,
j] = 1000000000 * 60 * 60 * 24 # Twenty-four hours.
elif i > j:
# This "bottom" half of the matrix simply mirrors the top.
latency[i, j] = latency[j, i]
else:
# This is the same agent. How long does it take to reach localhost? In our data center, it actually
# takes about 20 microseconds.
latency[i, j] = 20000
# Configure a simple latency noise model for the agents.
# Index is ns extra delay, value is probability of this delay being applied.
noise = [0.25, 0.25, 0.20, 0.15, 0.10, 0.05]
### END OLD LATENCY ATTRIBUTE CONFIGURATION ###
### BEGIN NEW LATENCY MODEL CONFIGURATION ###
else:
# Get a new-style cubic LatencyModel from the networking literature.
pairwise = (len(agent_types), len(agent_types))
model_args = {
'connected':
True,
# All in NYC.
'min_latency':
np.random.uniform(low=21000, high=100000, size=pairwise),
'jitter':
0.3,
'jitter_clip':
0.05,
'jitter_unit':
5,
}
latency_model = LatencyModel(
latency_model='cubic',
random_state=np.random.RandomState(
seed=np.random.randint(low=0, high=2**31)),
kwargs=model_args)
# Start the kernel running.
with HiddenPrints():
midprices = kernel.runner(
agents=agents,
startTime=self.kernelStartTime,
stopTime=self.kernelStopTime,
agentLatencyModel=latency_model,
agentLatency=latency,
latencyNoise=noise,
defaultComputationDelay=self.defaultComputationDelay,
oracle=oracle,
log_dir=None,
return_value={self.symbol: "midprices"})
return midprices[self.symbol]
