class SimDetect(Detect):
"""
- net_desc: description of the network
- norm_desc: description of the normal case
- ano_list: list of anomalies.
"""
def __init__(self, argv):
Detect.__init__(self, argv)
self.sim = Sim(argv)
self.output_flow_file = self.ROOT + \
'/Simulator/n%i_flow.txt'%(self.args.detect_node_id)
self.args.data = self.output_flow_file
self.export_abnormal_flow_file = self.ROOT + \
'/Simulator/abnormal_n%i_flow.txt'%(self.args.detect_node_id)
def init_parser(self, parser):
Detect.init_parser(self, parser)
parser.add_argument('--detect_node_id', default=0, type=int,
help = """ specify the node id you want to monitor,
default value is 0""")
parser.add_argument('--no_sim', default=False, action='store_true',
help = """turn on this switch to disable the fs simulaiton""")
def run(self):
if not self.args.no_sim:
self.sim.run()
Detect.run(self)
return self.detector
def main():
first_seen = []
random = []
sim_time = 100
# N, P, R
for i in range(sim_time):
sr = Sim(100, 1, 100, "r")
sf = Sim(100, 1, 100, "f")
sr_res = sr.run()
sf_res = sf.run()
# print("random: ", sr_res)
# print("first_seen: ", sf_res)
first_seen.append(sf_res)
random.append(sr_res)
print("round: ", i)
# print("first seen: ", sum(first_seen) / len(first_seen))
# print(first_seen)
# print("random: ", sum(random) / len(random))
# print(random)
print(first_seen)
print(random)
plt.scatter(range(sim_time), first_seen, color='red')
plt.hlines(sum(first_seen) / len(first_seen), 0, sim_time, colors='red')
plt.scatter(range(sim_time), random, color='blue')
plt.hlines(sum(random) / len(random), 0, sim_time, colors='blue')
plt.show()
class SimDetect(Detect):
"""
- net_desc: description of the network
- norm_desc: description of the normal case
- ano_list: list of anomalies.
"""
def __init__(self, argv):
Detect.__init__(self, argv)
self.sim = Sim(argv)
self.output_flow_file = self.ROOT + \
'/Simulator/n%i_flow.txt'%(self.args.detect_node_id)
self.args.data = self.output_flow_file
self.export_abnormal_flow_file = self.ROOT + \
'/Simulator/abnormal_n%i_flow.txt'%(self.args.detect_node_id)
def init_parser(self, parser):
Detect.init_parser(self, parser)
parser.add_argument('--detect_node_id',
default=0,
type=int,
help=""" specify the node id you want to monitor,
default value is 0""")
parser.add_argument(
'--no_sim',
default=False,
action='store_true',
help="""turn on this switch to disable the fs simulaiton""")
def run(self):
if not self.args.no_sim:
self.sim.run()
Detect.run(self)
return self.detector
def train_evaluate(search_params):
hyperparameters = {}
pick_kwargs = {}
for k in list(search_params.keys()):
if k in ['w_dfh', 'w_sharpe', 'w_100d', 'v_100d', 'v_dfh', 'v_rfl']:
pick_kwargs[k] = search_params[k]
else:
hyperparameters[k] = search_params[k]
hyperparameters['pick_kwargs'] = pick_kwargs
print('------------')
print(json.dumps(hyperparameters, indent=2, sort_keys=True))
sim = Sim(neptune=neptune,
period='2y',
timedelay=100,
window=100,
timestep=1,
budget=5000,
stockPicks=5,
avoidDowntrends=True,
sellAllOnCrash=False,
**hyperparameters)
stats = sim.run()
analysis = Analysis(neptune=neptune,
stats=stats,
positions=sim.portfolio.holdings,
prices=sim.downloader.prices)
#analysis.chart()
output, advanced_stats, obj_stats = analysis.positionStats()
for k in list(obj_stats.keys()):
neptune.log_metric(k, obj_stats[k])
print(output)
#neptune.log_artifact('data/output_1y.pkl')
sharpe = analysis.sharpe()
stats = sim.portfolio.summary()
if math.isnan(sharpe) or math.isinf(sharpe) or sharpe <= -2 or sharpe >= 5:
sharpe = -5
#neptune.log_metric('sharpe', sharpe)
#neptune.log_metric('start_value', 5000)
#neptune.log_metric('end_value', stats['total_value'])
report = {
'hyperparameters': hyperparameters,
'sharpe': sharpe,
'end_value': stats['total_value'],
'gains': (stats['total_value'] - 5000.0) / 5000.0
}
neptune.log_text('report', json.dumps(report, indent=2, sort_keys=True))
return sharpe
def Main():
if len(sys.argv) <= 1:
print("Argument required: create, watch, buy, sell, stats")
else:
if sys.argv[1] == 'create':
if len(sys.argv) < 3:
print("Invalid arguments. `python main.py create 5000`")
else:
watcher = Watcher(filename='data/portfolio',
hyperparameters=hyperparameters)
watcher.create(balance=float(sys.argv[2]))
elif sys.argv[1] == 'watch':
watcher = Watcher(filename='data/portfolio',
hyperparameters=hyperparameters)
watcher.start()
elif sys.argv[1] == 'buy':
# main.py buy 20 AMD 81.26
if len(sys.argv) < 5:
print("Invalid arguments. `python main.py buy 20 AMD 81.26`")
else:
executor = Executor(filename='data/portfolio',
hyperparameters=hyperparameters)
print(
executor.buy(symbol=sys.argv[3],
count=int(sys.argv[2]),
value=float(sys.argv[4])))
elif sys.argv[1] == 'sell':
# main.py sell 20 AMD 81.26
if len(sys.argv) < 5:
print("Invalid arguments. `python main.py sell 20 AMD 81.26`")
else:
executor = Executor(filename='data/portfolio',
hyperparameters=hyperparameters)
print(
executor.sell(symbol=sys.argv[3],
count=int(sys.argv[2]),
value=float(sys.argv[4])))
elif sys.argv[1] == 'stats':
watcher = Watcher(filename='data/portfolio',
hyperparameters=hyperparameters)
watcher.stats()
elif sys.argv[1] == 'sim':
from Sim import Sim
from Analysis import Analysis
sim = Sim(period='3y',
timedelay=100,
window=100,
timestep=1,
budget=5000,
stockPicks=5,
avoidDowntrends=True,
sellAllOnCrash=False,
**hyperparameters)
stats = sim.run()
analysis = Analysis(stats=stats,
positions=sim.portfolio.holdings,
prices=sim.downloader.prices)
analysis.chart('data/best_optimized_3y.png')
output, advanced_stats = analysis.positionStats()
print(output)
g = sim.portfolio.holdings.copy().groupby('label').sum()
g['profits_pct'] = (g['current_price'] - g['purchase_price']
) / g['purchase_price'] * 100
print(g)
elif sys.argv[1] == 'check':
watcher = Watcher(filename='data/portfolio',
hyperparameters=hyperparameters)
watcher.check(sys.argv[2])
else:
print("Unknown command")
pd.set_option('display.expand_frame_repr', False)
pd.set_option('max_colwidth', None)
from Sim import Sim
from Analysis import Analysis
sim = Sim(period='1y',
timedelay=100,
window=100,
timestep=1,
budget=10000,
stockPicks=5,
sl=-0.04,
tp=3.0,
ts=0.05,
ts_threshold=0.05,
avoidDowntrends=True,
sellAllOnCrash=False)
stats = sim.run()
analysis = Analysis(stats=stats,
positions=sim.portfolio.holdings,
prices=sim.downloader.prices)
analysis.chart('data/output_1y.png')
output, advanced_stats = analysis.positionStats()
print(output)
g = sim.portfolio.holdings.copy().groupby('label').sum()
g['profits_pct'] = (g['current_price'] -
g['purchase_price']) / g['purchase_price'] * 100
print(g)
