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):
"""
Called once at the start of the algorithm.
"""
feature_num = 11
context.orders_submitted = False
large_num = 9999999
least_num = 0
context.n_components = feature_num
context.security = symbol(SYMBOL) # Trade SPY
set_benchmark(symbol(SYMBOL)) # Set benchmarks
context.model = DecisionTreeClassifier(criterion='entropy',
max_depth=feature_num,
random_state=0)
context.lookback = 350 # Look back 62 days
context.history_range = 350 # Only consider the past 400 days' history
context.threshold = 4.05
context.longprices = large_num
context.shortprices = least_num
set_long_only()
# Generate a new model every week
schedule_function(create_model, date_rules.week_end(),
time_rules.market_close(minutes=10))
"""
# Generate a new model every week
schedule_function(create_model1, date_rules.week_end(), time_rules.market_close(minutes=10))
"""
# Trade at the start of every day
schedule_function(rebalance, date_rules.every_day(),
time_rules.market_open(minutes=1))
def initialize(context):
"""
Called once at the start of the algorithm.
"""
feature_num = 11
context.orders_submitted = False
large_num = 9999999
least_num = 0
context.n_components = 6
context.security = symbol(SYMBOL) # Trade SPY
set_benchmark(symbol(SYMBOL)) # Set benchmarks
context.model2 = SVC(kernel='rbf', tol=1e-3, random_state=0, gamma=0.2, C=10.0, verbose=True) # 8.05 for SVM model
context.model3 = KNeighborsClassifier(n_neighbors=feature_num, p=3, metric='minkowski') # 7.05 for model
context.model = DecisionTreeClassifier(criterion='entropy', max_depth=feature_num, random_state=0)
context.model4 = RandomForestClassifier(criterion='entropy', n_estimators=feature_num, random_state=1,
n_jobs=2) # 5.2 for randomforest
context.model1 = LogisticRegression(random_state=0, solver='lbfgs', multi_class='multinomial')
context.modellist = {'SVM':context.model2,'KNeighbors':context.model3,'DecisionTree':context.model,'RandomForest':context.model4,'LogisticRegression':context.model1}
context.lookback = 350 # Look back 62 days
context.history_range = 350 # Only consider the past 400 days' history
context.threshold = 4.05
context.longprices = large_num
context.shortprices = least_num
context.time_series = 0
context.init = 0
set_long_only()
# Generate a new model every week
#schedule_function(create_model, date_rules.week_end(), time_rules.market_close(minutes=10))
"""
# Generate a new model every week
schedule_function(create_model1, date_rules.week_end(), time_rules.market_close(minutes=10))
"""
# Trade at the start of every day
schedule_function(rebalance, date_rules.every_day(), time_rules.market_open(minutes=1))
def initialize(context): # Stocks to trade stock_list = ['FB', 'AMZN', 'AAPL', 'NFLX', 'GOOGL'] context.stocks = [symbol(stock) for stock in stock_list] # How much of the portfolio is invested in each stock (20% each) context.target_pct_per_stock = 1 / len(context.stocks) # Transaction costs #context.set_commission(commission.PerShare(cost=0.0, min_trade_cost=0)) #context.set_commission(commission.PerDollar(cost=0.0015)) # default is 0.0015 #context.set_commission(commission.PerTrade(cost=0.0)) # Slippage #context.set_slippage(slippage.VolumeShareSlippage()) # Upper and Lower bound for RSI trading signals context.low_rsi = 30 context.high_rsi = 70 # Moving average window #context.index_average_window = 100 set_benchmark(False)
def initialize(context):
"""
Called once at the start of a backtest, and once per day at
the start of live trading. In live trading, the stored context
will be loaded *after* this function is called.
"""
# Rebalance every day, 1 hour after market open.
algo.schedule_function(
rebalance,
algo.date_rules.month_start(),
algo.time_rules.market_open(hours=1),
)
algo.schedule_function(
bonds,
algo.date_rules.month_start(days_offset=1),
algo.time_rules.market_open(hours=1),
)
algo.set_benchmark(algo.sid("FIBBG000BDTBL9"))
# Create a pipeline to select stocks each day.
algo.attach_pipeline(make_pipeline(), 'pipeline')
# algo.set_min_leverage(0, datetime.timedelta(30))
# algo.set_max_leverage(1.2)
context.trend_filter = False
def initialize(context):
# Set benchmark to short-term Treasury note ETF (SHY) since strategy is dollar neutral
set_benchmark(symbol('AAPL'))
# Schedule our rebalance function to run at the end of each day.
# Modified the timing to 5 mins earlier than the market close to reduce the fail to book warnings
# schedule_function(my_rebalance, date_rules.every_day(), time_rules.market_close(minutes=5))
# Try to change it to open and see what happened -- HY
schedule_function(my_rebalance, date_rules.every_day(),
time_rules.market_open(minutes=5))
# Record variables at the end of each day.
# schedule_function(my_record_vars, date_rules.every_day(), time_rules.market_close())
# Get intraday prices today before the close if you are not skipping the most recent data
# schedule_function(get_prices,date_rules.every_day(), time_rules.market_close(minutes=10))
# Try to get the price data when the market is opening -- HY
# schedule_function(get_prices, date_rules.every_day(), time_rules.market_open(minutes=1))
# Set commissions and slippage to 0 to determine pure alpha
set_commission(commission.PerShare(cost=0, min_trade_cost=0))
set_slippage(slippage.FixedSlippage(spread=0))
# Number of quantiles for sorting returns for mean reversion
context.nq = 5
# Number of quantiles for sorting volatility over five-day mean reversion period
context.nq_vol = 3
# Create our pipeline and attach it to our algorithm.
my_pipe = make_pipeline()
attach_pipeline(my_pipe, 'my_pipeline')
def initialize(context):
# List of Major World Indices Yahoo tickers - https://finance.yahoo.com/world-indices
with open('tickers.pickle', 'rb') as handle:
indices_tickers = pickle.load(handle) # load in tickers from pickle
os.remove('tickers.pickle') # delete tickers pickle file
context.indices = [symbol(ticker) for ticker in indices_tickers
] # create list of ticker symbols
context.days_of_correction = [
0 for _ in indices_tickers
] # create list of days since correction has begun
set_benchmark(symbol('^GSPC'))
set_commission(
commission.PerTrade(cost=15.0)
) # commission for IBKR, UK for Stocks, ETF's & Warrants - https://www.interactivebrokers.co.uk/en/index.php?f=39753&p=stocks1
'''-----------------------------PARAMETERS TO BE OPTIMISED--------------------------------'''
context.correction_margin = 0.1 # the percentage drawdown considered a correction
print('Drawdown percentage range from peak for correction: ' +
str(round(context.correction_margin * 100)) + '%')
context.upturn_coefficient = 0.24 # the ratio upturn from trough indicating end of correction - used in calculate_required_upturn function
print('Upturn Coefficient: ' + str(round(context.upturn_coefficient, 4)))
context.min_gain = 0.05 # the highest the price can be from peak and still be considered for ordering
print('Mainimum potential gain from peak to be considered: ' +
str(round(context.min_gain * 100, 0)) + '%')
context.state_threshold = -10.0 # 0.0002 threshold between bull and bear markets
print('Market state threshhold: ' +
str(round(context.state_threshold, 4)) + '%')
def initialize(context):
# List of Major World Indices Yahoo tickers - https://finance.yahoo.com/world-indices
with open('tickers.pickle', 'rb') as handle:
indices_tickers = pickle.load(handle) # load in tickers from pickle
os.remove('tickers.pickle') # delete tickers pickle file
context.indices = [symbol(ticker) for ticker in indices_tickers
] # create list of ticker symbols
context.days_of_correction = [
0 for _ in indices_tickers
] # create list of days since correction has begun
set_benchmark(symbol('^GSPC'))
'''-----------------------------PARAMETERS TO BE OPTIMISED--------------------------------'''
context.correction_margin = 0.1 # the percentage drawdown considered a correction
print('Drawdown percentage range from peak for correction: ' +
str(round(context.correction_margin * 100)) + '%')
context.upturn_coefficient = 0.22 # the ratio upturn from trough indicating end of correction - used in calculate_required_upturn function
print('Upturn Coefficient: ' + str(round(context.upturn_coefficient, 2)))
context.min_return = 0.26 # the minimum return required before changing positions
print('Minimum return per trade: ' + str(round(context.min_return * 100)) +
'%')
context.min_gain = 0.07 # the highest the price can be from peak and still be considered for ordering
print('Mainimum potential gain from peak to be considered: ' +
str(round(context.min_gain * 100, 0)) + '%')
context.stop_loss = 0.53 # lowest proportion of investment peak
print('Stop loss for investments: ' + str(round(context.stop_loss * 100)) +
'%')
def initialize(context):
context.set_commission(commission.PerShare(cost=0.0, min_trade_cost=0))
set_benchmark(symbol('SPY'))
context.asset = symbol('AAPL')
context.has_ordered = False
schedule_function(place_order, None, time_rules.market_open())
def initialize(context):
"""
Called once at the start of a backtest, and once per day at
the start of live trading.
"""
# Attach the pipeline to the algo
algo.attach_pipeline(make_pipeline(), 'pipeline')
# Set SPY as benchmark
algo.set_benchmark(algo.sid("FIBBG000BDTBL9"))
# identify down gaps immediately after the opening
algo.schedule_function(
find_down_gaps,
algo.date_rules.every_day(),
algo.time_rules.market_open(minutes=1),
)
# at 9:40, short stocks that gapped down
algo.schedule_function(
short_down_gaps,
algo.date_rules.every_day(),
algo.time_rules.market_open(minutes=10),
)
# close positions 5 minutes before the close
algo.schedule_function(
close_positions,
algo.date_rules.every_day(),
algo.time_rules.market_close(minutes=5),
)
# Set commissions and slippage
algo.set_commission(commission.PerShare(cost=0.0))
algo.set_slippage(slippage.FixedBasisPointsSlippage(basis_points=3.0))
def initialize(context):
context.time = 0
context.asset = symbol('SPY')
context.set_commission(
commission.PerShare(cost=0.001, min_trade_cost=0))
context.strategy_params_1 = ta_params
set_benchmark(symbol("SPY"))
def initialize(context):
"""
Called once at the start of the algorithm.
"""
feature_num = 11
context.orders_submitted = False
large_num = 9999999
least_num = 0
context.n_components = feature_num
context.security = symbol(SYMBOL) # Trade SPY
set_benchmark(symbol(SYMBOL)) # Set benchmarks
context.model = SVC(kernel='rbf', tol=1e-3, random_state=0, gamma=0.2, C=10.0, verbose=True) # 8.05 for SVM model
context.lookback = 350 # Look back 62 days
context.history_range = 350 # Only consider the past 400 days' history
context.threshold = 4.05
context.longprices = large_num
context.shortprices = least_num
set_long_only()
# Generate a new model every week
schedule_function(create_model, date_rules.week_end(), time_rules.market_close(minutes=10))
"""
# Generate a new model every week
schedule_function(create_model1, date_rules.week_end(), time_rules.market_close(minutes=10))
"""
# Trade at the start of every day
schedule_function(rebalance, date_rules.every_day(), time_rules.market_open(minutes=1))
def initialize(self, context):
set_benchmark(symbol(self.symbol))
context.set_slippage(slippage.NoSlippage())
context.scheduled_data = {}
def initialize(context):
# Benchmark against the Dow Jones Industrial Average (DIA)
api.set_benchmark(symbol('DIA'))
# stop when trying to handle missing data
api.set_nodata_policy(api.NoDataPolicy.EXCEPTION)
# These are the default commission and slippage settings. Change them to fit your
# brokerage fees. These settings only matter for backtesting. When you trade this
# algorithm, they are moot - the brokerage and real market takes over.
api.set_commission(api.commission.PerTrade(cost=0.03))
api.set_slippage(api.slippage.VolumeShareSlippage(volume_limit=0.25, price_impact=0.1))
# create an instance of the Dow30 class and set it within context
context.dow30 = dow_constituents
# next trade year
context.year = 0
# set to True to trigger a rebalance
context.trade = False
# for tracking max leverage
context.mx_lvrg = 0
# check for possible trades daily
api.schedule_function(func=rebalance, date_rule=api.date_rules.every_day(), time_rule=api.time_rules.market_open(hours=1))
def initialize(context):
context.security = symbol(SYMBOL) # Trade
set_benchmark(symbol(SYMBOL)) # Set benchmarks
#print(context.security)
context.start = True
set_long_only()
schedule_function(market_open, date_rules.every_day(),
time_rules.market_open(minutes=1))
context.orders_submitted = False
def initialize(context):
# attach_pipeline(make_pipeline(), 'my_pipeline')
context.longStock = symbol('SPY2')
context.shortStock = symbol('SH2')
context.turnover_count = 0
# etf stock
context.shorting_on = True
set_benchmark(symbol("SPY2"))
def initialize(self, context, stock_ids):
super().initialize(context, stock_ids)
context.portfolio_highest = {}
context.price_highest = {}
context.stock_shares = {}
context.set_commission(
commission.PerShare(cost=.0075, min_trade_cost=1.0))
context.set_slippage(slippage.VolumeShareSlippage())
set_benchmark(context.assets[0])
for asset in context.assets:
context.price_highest[asset] = 0.0
context.portfolio_highest[asset] = 0.0
context.stock_shares[asset] = 0
def initialize(context):
"""
Called once at the start of a backtest, and once per day at
the start of live trading.
"""
# Attach the pipeline to the algo
algo.attach_pipeline(make_pipeline(), 'pipeline')
algo.set_benchmark(algo.sid('FIBBG000BDTBL9'))
# Rebalance every day, 30 minutes before market close.
algo.schedule_function(
rebalance,
algo.date_rules.every_day(),
algo.time_rules.market_close(minutes=30),
)
def initialize(context):
attach_pipeline(make_pipeline(), 'my_pipeline')
# If Zipline has trouble pulling the default benchmark, try setting the
# benchmark to something already in your bundle
set_benchmark(symbol("SPY"))
# Rebalance each day. In daily mode, this is equivalent to putting
# `rebalance` in our handle_data, but in minute mode, it's equivalent to
# running at the start of the day each day.
schedule_function(rebalance, date_rules.every_day())
# Explicitly set the commission to the "old" value until we can
# rebuild example data.
# github.com/quantopian/zipline/blob/master/tests/resources/
# rebuild_example_data#L105
context.set_commission(commission.PerShare(cost=.0075, min_trade_cost=1.0))
def initialize(context):
attach_pipeline(make_pipeline(), 'data_pipeline')
context.technical_indicator_states = {}
context.window_length = 7
context.benchmark = deque(maxlen=context.window_length)
context.benchmark_asset = symbol('SPY')
context.benchmark_assets = symbols('QQQ', 'SPY')
#context.classifier = RandomForestClassifier() # Use a random forest classifier
context.classifier = DecisionTreeClassifier(max_depth=5, max_leaf_nodes=10)
# Clasifier training data
context.features = [
'RSI', 'EMA', 'MACD', 'SMA_5', 'SMA_10', 'bb_lower', 'bb_middle',
'bb_upper'
]
context.response = ['Class']
context.X = pd.DataFrame(
columns=context.features) # Independent, or input variables
context.Y = pd.DataFrame(
columns=context.response) # Dependent, or output variable
context.prediction = {} # Stores most recent prediction
context.tick = 0
context.total_buy = 0
context.positions = None
context.position_adjustment_days = 5 # Number of days to wait before adjusting positions
context.min_data_points = 500
context.max_data_points = 1500
schedule_function(rebalance, date_rules.every_day(),
time_rules.market_open(minutes=1))
schedule_function(record_vars, date_rules.every_day(),
time_rules.market_close())
set_benchmark(symbol('SPY'))
# 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))
def initialize(context):
set_benchmark(symbol("BTC"))
def initialize(context):
set_benchmark(symbol('MSFT'))
context.i = 0
context.asset = symbol('MSFT')
def initialize(context):
set_benchmark(symbol("PETR4"))
def initialize(cls, context):
context.i = 0
context.asset = symbol('MSFT')
context.assets = [symbol(asset) for asset in cls._portfolio.assets]
set_benchmark(symbol('benchmark'))
def intialize(context):
context.stock = symbol('SPY')
set_benchmark(context.stock)
def initialize(context):
set_benchmark(symbol(stock))
context.asset = symbol(stock)
context.i = 0
def initialize(context):
set_benchmark(symbol('SH00300'))
def initialize(context):
context.i = 0
set_benchmark(symbol('AAPL'))
context.asset = symbol('AAPL')
