def initialize(context):
# Get continuous futures for Light Sweet Crude Oil...
context.crude_oil = continuous_future('CL', roll='calendar')
# ... and RBOB Gasoline
context.gasoline = continuous_future('RB', roll='calendar')
# If Zipline has trouble pulling the default benchmark, try setting the
# benchmark to something already in your bundle
set_benchmark(context.crude_oil)
# Ignore commissions and slippage for now
set_commission(us_futures=commission.PerTrade(cost=0))
set_slippage(us_futures=slippage.FixedSlippage(spread=0.0))
# Long and short moving average window lengths
context.long_ma = 65
context.short_ma = 5
# True if we currently hold a long position on the spread
context.currently_long_the_spread = False
# True if we currently hold a short position on the spread
context.currently_short_the_spread = False
# Rebalance pairs every day, 30 minutes after market open
schedule_function(func=rebalance_pairs,
date_rule=date_rules.every_day(),
time_rule=time_rules.market_open(minutes=30))
# Record Crude Oil and Gasoline Futures prices everyday
schedule_function(record_price, date_rules.every_day(),
time_rules.market_open())
def initialize(context):
# Turn off the slippage model
set_slippage(slippage.FixedSlippage(spread=0.0))
# Set the commission model
set_commission(commission.PerShare(cost=0.01, min_trade_cost=1.0))
context.day = -1 # using zero-based counter for days
context.set_benchmark(symbol('DIA'))
context.assets = []
print('Setup investable assets...')
for ticker in asset_tickers:
#print(ticker)
context.assets.append(symbol(ticker))
context.n_asset = len(context.assets)
context.n_portfolio = 40 # num mean-variance efficient portfolios to compute
context.today = None
context.tau = None
context.min_data_window = 756 # min of 3 yrs data for calculations
context.first_rebal_date = None
context.first_rebal_idx = None
context.weights = None
# Schedule dynamic allocation calcs to occur 1 day before month end - note that
# actual trading will occur on the close on the last trading day of the month
schedule_function(rebalance,
date_rule=date_rules.month_end(days_offset=1),
time_rule=time_rules.market_close())
# Record some stuff every day
schedule_function(record_vars,
date_rule=date_rules.every_day(),
time_rule=time_rules.market_close())
def initialize(self, context):
if self.verbose: print("Starting the robo advisor")
# Populate Portfolios
self.all_portfolios = initialize_portfolio(self.verbose)
# Set Commission model
self.initialize_commission(country=self.country, platform=self.trading_platform)
# Set Slippage model
set_slippage(slippage.FixedSlippage(spread=0.0)) # assume spread of 0
# Schedule Rebalancing check
rebalance_check_freq = date_rules.month_end()
if (self.rebalance_freq == 'daily'): rebalance_check_freq = date_rules.every_day()
elif (self.rebalance_freq == 'weekly'): rebalance_check_freq = date_rules.week_end()
if self.verbose: print('Rebalance checks will be done %s' % self.rebalance_freq)
schedule_function(
func=self.before_trading_starts,
date_rule=rebalance_check_freq,
time_rule=time_rules.market_open(hours=1))
# record daily weights at the end of each day
schedule_function(
func=record_current_weights,
date_rule=date_rules.every_day(),
time_rule=time_rules.market_close()
)
def initialize(context):
"""
Called once at the start of the algorithm.
"""
set_slippage(slippage.FixedSlippage(spread=0.00))
set_commission(commission.PerShare(cost=0, min_trade_cost=0))
schedule_function(rebalance, TRADE_FREQ,
date_rules.every_day(),
time_rules.market_open(hours=1, minutes=30),
)
schedule_function(record_vars, date_rules.every_day(),
time_rules.market_close())
ml_pipeline = make_ml_pipeline(universe,
n_forward_days=N_FORWARD_DAYS,
window_length=TRAINING_PERIOD)
# Create our dynamic stock selector.
attach_pipeline(ml_pipeline, 'ml_model')
context.past_predictions = {}
context.ic = 0
context.rmse = 0
context.mae = 0
context.returns_spread_bps = 0
def initialize(context):
context.fut = continuous_future('ES', roll='calendar')
# Ignore commissions and slippage for now
set_commission(us_futures=commission.PerTrade(cost=0))
set_slippage(us_futures=slippage.FixedSlippage(spread=0.0))
context.i = 0
context.invested = False
def initialize(context):
# This code runs once, when the sim starts up
log.debug('scheduling rebalance and recording')
set_slippage(slippage.FixedSlippage(spread=0.0))
set_commission(commission.PerShare(cost=0, min_trade_cost=0))
schedule_function(func=rebalance,
date_rule=date_rules.month_end(),
time_rule=time_rules.market_close(minutes=15))
schedule_function(func=record_daily,
date_rule=date_rules.every_day(),
time_rule=time_rules.market_close())
def initialize(self, context):
add_history(200, '1d', 'price')
set_slippage(slippage.FixedSlippage(spread=0.0))
set_commission(commission.PerShare(cost=0.01, min_trade_cost=1.0))
context.tick = 0
dp_data = self.data
df_data = pd.DataFrame(index=dp_data.axes[1])
df_data['close'] = dp_data[:, :, 'close']
df_data['open'] = dp_data[:, :, 'open']
df_data['high'] = dp_data[:, :, 'high']
df_data['low'] = dp_data[:, :, 'low']
df_data['volume'] = dp_data[:, :, 'volume']
self.atr = atr_per_close(df_data, atrLen = self.atr_len)
context.longstop = 0
def initialize(context):
"""
Called once at the start of the algorithm.
"""
context.n_longs = N_LONGS
context.n_shorts = N_SHORTS
context.min_positions = MIN_POSITIONS
context.universe = assets
set_slippage(slippage.FixedSlippage(spread=0.00))
set_commission(commission.PerShare(cost=0, min_trade_cost=0))
schedule_function(rebalance, date_rules.every_day(),
time_rules.market_open(hours=1, minutes=30))
schedule_function(record_vars, date_rules.every_day(),
time_rules.market_close())
pipeline = compute_signals()
attach_pipeline(pipeline, 'signals')
def initialize(context):
'''
Called once at the very beginning of a backtest (and live trading).
Use this method to set up any bookkeeping variables.
The context object is passed to all the other methods in your algorithm.
Parameters
context: An initialized and empty Python dictionary that has been
augmented so that properties can be accessed using dot
notation as well as the traditional bracket notation.
Returns None
'''
# Turn off the slippage model
set_slippage(slippage.FixedSlippage(spread=0.0))
# Set the commission model (Interactive Brokers Commission)
set_commission(commission.PerShare(cost=0.01, min_trade_cost=1.0))
context.tick = 0
def initialize(context):
context.record_rank = {}
context.save2mysql = 0
# 模型训练参数
context.horizon = 6
context.percent = 5
context.model_name = 'adaBoost'
context.rolling = 1 # 是否为滚动，0为不滚动
context.ishistory = 0 #是否用历史分类。0为不使用
context.train_period = 12 * 1
context.i = 0
set_slippage(slippage.FixedSlippage(spread=0.00))
set_commission(commission.PerDollar(cost=0.00325))
month = 21
week = 5
rf = 0.025
c = 252
if context.namespace["fund_type"] == 'stock':
benchmark = '000300.SH'
fund_type = 1
elif context.namespace["fund_type"] == 'hybrid':
benchmark = '000300.SH'
fund_type = 2
elif context.namespace["fund_type"] == 'bond':
benchmark = '037.CS'
fund_type = 3
# 选择基金池和benchmark
ben_sid = symbol(benchmark).sid
df_stock = df.query("update_time == update_time.max() and type_code=={"\
"type}".format(type = fund_type))
# 基金900 开头的不需要，专门去掉
df_stock = df_stock[df_stock["fund_code"] < '900000'].fund_code + ".OF"
sfilt = SpecificAssets(symbols(
benchmark, *tuple(df_stock))) # 使用到的数据，包括基金和对应benchmark指数
sample_filt = SpecificAssets(symbols(
*tuple(df_stock))) # 只包含基金，因为评级不应该包含benchmark，故在事后screen去掉benchmark
# 只包含基金，因为评级不应该包含benchmark，故在事后screen去掉benchmark
## 16个因子指标
down_sharpe = Down_sharpe(window_length=9 * month, rf=rf, c=c, mask=sfilt)
drawdown = Drawdown(window_length=9 * month, mask=sfilt)
dvar = Down_variation(window_length=9 * month, rf=rf, c=c, mask=sfilt)
mean_r = Average_return(window_length=9 * month, mask=sfilt)
lasting = Lasting(window_length=9 * month,
mask=sfilt,
time=6 * month,
percent=20)
emr = Emr(window_length=9 * month, mask=sfilt, time=6 * month)
rlt_var = Negative_variation(window_length=9 * month, c=c, mask=sfilt)
mcv_in = Mcv_in(window_length=9 * month,
rf=rf,
c=c,
mask=sfilt,
time=week,
index_sid=ben_sid)
rank_stable = Rank_stable(window_length=9 * month,
mask=sfilt,
time=6 * month)
select_time, select_stock = CL(window_length=9 * month,
rf=rf,
mask=sfilt,
time=week,
index_sid=ben_sid)
hit_rate = Hit_rate(window_length=10 * month,
mask=sfilt,
time=6 * month,
time_window=9 * month,
index_sid=ben_sid)
value_at_risk = Value_at_risk(window_length=9 * month,
mask=sfilt,
q_value=5,
time=6 * month)
beta_in = Beta_in(window_length=9 * month,
mask=sfilt,
rf=rf,
time=week,
index_sid=ben_sid)
bias_in = Bias_in(window_length=9 * month, mask=sfilt, time=126)
ir = Information_ratio(window_length=9 * month,
mask=sfilt,
time=1,
index_sid=ben_sid)
# 预测因变量Y
_ry = Lag_Return(window_length=context.horizon * month, mask=sfilt)
_sp = Lag_Sharpe(window_length=context.horizon * month, mask=sfilt)
pipe = Pipeline(columns={
"dhsp": down_sharpe,
"drwd": drawdown,
"dvar": dvar,
"mean_r": mean_r,
"lasting": lasting,
"emr": emr,
"rlt_var": rlt_var,
"mcv_in": mcv_in,
"rank_stable": rank_stable,
"select_time": select_time,
"select_stock": select_stock,
"hit_rate": hit_rate,
"value_at_risk": value_at_risk,
"beta_in": beta_in,
"bias_in": bias_in,
"ir": ir,
"_ry": _sp
},
screen=sample_filt)
attach_pipeline(pipe, 'my_pipeline')
set_max_leverage(1.1)
schedule_function(rebalance,
date_rule=date_rules.month_start(),
time_rule=time_rules.market_open())
# 初始化记录变量
context.rank_score = pd.Series()
context.f = pd.Panel()
context.f_dict = {}
context.reb_flag = False
context.B = {}
def initialize(context):
context.i = 0
context.sym = symbol('LKTB')
context.hold = False
set_commission(commission.PerShare(cost=0.000008))
set_slippage(slippage.FixedSlippage(spread=0))
def initialize(self, context):
add_history(60, '1d', 'price')
set_slippage(slippage.FixedSlippage(spread=0.0))
set_commission(commission.PerShare(cost=0.01, min_trade_cost=1.0))
context.tick = 0
