def __init__(self,
code,
start,
end,
capital_base=100000,
consume_portfolio=None):
super(ZiplineRunThread, self).__init__()
self.code = code
self.start_date = Date(tz='utc', as_timestamp=True).parser(start)
self.end_date = Date(tz='utc', as_timestamp=True).parser(end)
self.capital_base = capital_base
self.consume_portfolio = consume_portfolio
'--bundle',
default='quantopian-quandl',
metavar='BUNDLE-NAME',
show_default=True,
help='The data bundle to use for the simulation.',
)
@click.option('--bundle-timestamp',
type=Timestamp(),
default=pd.Timestamp.utcnow(),
show_default=False,
help='The date to lookup data on or before.\n'
'[default: <current-time>]')
@click.option(
'-s',
'--start',
type=Date(tz='utc', as_timestamp=True),
help='The start date of the simulation.',
)
@click.option(
'-e',
'--end',
type=Date(tz='utc', as_timestamp=True),
help='The end date of the simulation.',
)
@click.option(
'-o',
'--output',
default='-',
metavar='FILENAME',
show_default=True,
help="The location to write the perf data. If this is '-' the perf will"
bundle_data.equity_minute_bar_reader.first_trading_day
data = DataPortal(
trading_environment.asset_finder,
trading_calendar,
first_trading_day=first_trading_day,
equity_minute_reader=bundle_data.equity_minute_bar_reader,
equity_daily_reader=bundle_data.equity_daily_bar_reader,
adjustment_reader=bundle_data.adjustment_reader,
)
################################## sim_params
capital_base = DEFAULT_CAPITAL_BASE
start = '2017-1-1'
end = '2017-11-30'
sim_params = create_simulation_parameters(
capital_base=capital_base,
start=Date(tz='utc', as_timestamp=True).parser(start),
end=Date(tz='utc', as_timestamp=True).parser(end),
data_frequency='daily',
trading_calendar=trading_calendar,
)
#######################################################################
def rebalance(context, data):
#print ("rebalance:",get_datetime())
#print context.pipeline_data
pipeline_data = context.pipeline_data
keys = list(context.posset)
for asset in keys:
if data.can_trade(asset):
#print("flattern:",asset)
# coding=utf-8
from zipline.api import order, record, symbol
def initialize(context):
pass
def handle_data(context, data):
order(symbol('000001'), 10)
record(AAPL=data.current(symbol('000001'), 'price'))
if __name__ == '__main__':
from cn_zipline.utils.run_algo import run_algorithm
from zipline.utils.cli import Date
from cn_stock_holidays.zipline.default_calendar import shsz_calendar
start = Date(tz='utc', as_timestamp=True).parser('2017-01-01')
end = Date(tz='utc', as_timestamp=True).parser('2017-10-20')
run_algorithm(start,
end,
initialize,
10e6,
handle_data=handle_data,
bundle='tdx',
trading_calendar=shsz_calendar,
output='out.pickle')
order(symbol('002450'), 300, limit_price=buy_price)
buy_status = True
if __name__ == '__main__':
from zipline.utils.cli import Date
from zipline.utils.run_algo import run_algorithm
from zipline.gens.brokers.tdx_shipane_broker import TdxShipaneBroker
from zipline.gens.shipane_client import ShipaneClient
import pandas as pd
import os
import datetime
if platform.architecture()[0] == '32bit':
client_uri = 'config.json'
else:
client_uri = "tcp://127.0.0.1:4242"
shipane_client = ShipaneClient(client_key="1")
broker = TdxShipaneBroker(client_uri, shipane_client)
if not os.path.exists('tmp'):
os.mkdir('tmp')
realtime_bar_target = 'tmp/real-bar-{}'.format(str(pd.to_datetime('today').date()))
state_filename = 'tmp/live-state'
start = Date(tz='utc', as_timestamp=True).parser('2017-10-01')
end = Date(tz='utc', as_timestamp=True).parser(datetime.datetime.now().strftime("%Y-%m-%d"))
run_algorithm(start, end, initialize, 10e6, handle_data=handle_data, bundle='tdx',
trading_calendar='SHSZ', data_frequency="minute", output='out.pickle',
broker=broker, state_filename=state_filename, realtime_bar_target=realtime_bar_target)
"--benchmark-sid",
default=None,
type=int,
help="The sid of the instrument to be used as a benchmark "
"(should exist in the ingested bundle)",
)
@click.option(
"--no-benchmark",
is_flag=True,
default=False,
help="If passed, use a benchmark of zero returns.",
)
@click.option(
"-s",
"--start",
type=Date(tz="utc", as_timestamp=True),
help="The start date of the simulation.",
)
@click.option(
"-e",
"--end",
type=Date(tz="utc", as_timestamp=True),
help="The end date of the simulation.",
)
@click.option(
"-o",
"--output",
default="-",
metavar="FILENAME",
show_default=True,
help="The location to write the perf data. If this is '-' the perf will"
pipe = Pipeline(columns=pipe_columns,
screen=private_universe,
)
i = 0
for c in ONEHOTCLASS:
pipe.add(c,sector_indict_keys[i])
i +=1
return pipe
pd.set_option('display.width', 8000)
research = Research()
#print(research.get_engine()._finder)
my_pipe = make_pipeline(research.get_engine()._finder)
result = research.run_pipeline(my_pipe,
Date(tz='utc', as_timestamp=True).parser(start),
Date(tz='utc', as_timestamp=True).parser(end))
result = result.reset_index().drop(['level_0','level_1'],axis = 1).replace([np.inf,-np.inf],np.nan).fillna(0)
print "############################################"
X = result.drop('returns', 1)
Y = result['returns']
print ("total data size :",len(result))
#test_size=2000
Train_X = X.values
Train_Y = Y.values
# Test_X = X[-test_size:].values
# Test_Y = Y[-test_size:].values