def make_pipeline(context): """ A function to create our dynamic stock selector (pipeline). Documentation on pipeline can be found here: https://www.quantopian.com/help#pipeline-title """ rsi_filter = SidInList(sid_list = context.stock_traded.sid) close = Latest( inputs = [USEquityPricing.close], mask = rsi_filter, ) rsi_9 = RSI( inputs = [USEquityPricing.close], window_length = 9, mask = rsi_filter, ) pipe = Pipeline() pipe.add(close, 'close') pipe.add(rsi_9, 'rsi_9') pipe.set_screen(rsi_filter) return pipe
def pipeline(context): # create pipeline pipe = Pipeline() # Add market cap pipe.add(mkt_cap(), 'Market Cap') return pipe
def initialize(context): # Define the instruments in the portfolio: context.sidsLongVol = {sid(38054): +1.0} context.sidsShortVol = {sid(40516): +1.0} context.sidsShortSPY = {sid(22887): +1.0} context.sidsLongSPY = {sid(8554): +1.0} context.spy = symbol('SPY') context.hedge = symbol('IWM') context.vxx = symbol('VXX') context.epsilon = .01 context.ivts=[] context.ivts_medianfiltered = [] pipe = Pipeline() attach_pipeline(pipe, 'vix_pipeline') pipe.add(GetVol(inputs=[cboe_vix.vix_close]), 'vix') pipe.add(GetVol(inputs=[cboe_vxv.close]), 'vxv') vxstUrl = 'http://www.cboe.com/publish/scheduledtask/mktdata/datahouse/vxstcurrent.csv' vx1Url = 'http://www.quandl.com/api/v1/datasets/CHRIS/CBOE_VX1.csv' vx2Url = 'http://www.quandl.com/api/v1/datasets/CHRIS/CBOE_VX2.csv' fetch_csv(vxstUrl, symbol='VXST', skiprows=3,date_column='Date', pre_func=addFieldsVXST) fetch_csv(vx1Url, date_column='Trade Date',date_format='%Y-%m-%d', symbol='v1', post_func=rename_col) fetch_csv(vx2Url, date_column='Trade Date',date_format='%Y-%m-%d', symbol='v2', post_func=rename_col) # Calculating the contango ratio of the front and second month VIX Futures settlements context.threshold = 0.90 #contango ratio threshold schedule_function(ordering_logic,date_rule=date_rules.every_day(),time_rule=time_rules.market_open(hours=0, minutes=1)) # Rebalance every day, 1 hour after market open. context.wait_trigger=False context.vixpipe = None start_date = context.spy.security_start_date end_date = context.spy.security_end_date context.algo_hist={} context.returns_df = pd.DataFrame() # Get the dates when the market closes early: context.early_closes = get_early_closes(start_date, end_date).date context.slopes = Series() context.betas = Series()
def initialize(context): log.info("here") context.x = 100 # Create, register and name a pipeline in initialize. pipe = Pipeline() attach_pipeline(pipe, 'example') # Construct a simple moving average factor and add it to the pipeline. simple_return = Returns(inputs=[USEquityPricing.close], window_length=365) pipe.add(simple_return, 'simple_return') # Set a screen on the pipelines to filter out securities. pipe.set_screen(simple_return > 1.0) schedule_function(func=rebalance, date_rule = date_rules.every_day(), time_rule = time_rules.market_open(hours = 1))
def initialize(context): # Create, register and name a pipeline in initialize. pipe = Pipeline() attach_pipeline(pipe, 'dollar_volume_10m_pipeline') # Construct a 100-day average dollar volume factor and add it to the pipeline. dollar_volume = AverageDollarVolume(window_length=100) pipe.add(dollar_volume, 'dollar_volume') #Create high dollar-volume filter to be the top 2% of stocks by dollar volume. high_dollar_volume = dollar_volume.percentile_between(99, 100) # Set the screen on the pipelines to filter out securities. pipe.set_screen(high_dollar_volume) context.dev_multiplier = 2 context.max_notional = 1000000 context.min_notional = -1000000 context.days_traded = 0 schedule_function(func=process_data_and_order, date_rule=date_rules.every_day())
def make_pipeline(): """ Create and return our pipeline. We break this piece of logic out into its own function to make it easier to test and modify in isolation. In particular, this function can be copy/pasted into research and run by itself. """ pipe = Pipeline() initial_screen = Q500US() factors = { "Message": MessageVolume(mask=initial_screen), #"Momentum": Momentum(mask=initial_screen), "Value": Value(mask=initial_screen), } clean_factors = None for name, factor in factors.items(): if not clean_factors: clean_factors = factor.isfinite() else: clean_factors = clean_factors & factor.isfinite() combined_rank = None for name, factor in factors.items(): if not combined_rank: combined_rank = factor.rank(mask=clean_factors) else: combined_rank += factor.rank(mask=clean_factors) pipe.add(combined_rank, 'factor') # Build Filters representing the top and bottom 200 stocks by our combined ranking system. # We'll use these as our tradeable universe each day. longs = combined_rank.percentile_between(90, 100) shorts = combined_rank.percentile_between(0, 10) pipe.set_screen(longs | shorts) pipe.add(longs, 'longs') pipe.add(shorts, 'shorts') return pipe
def Data_Pull(): """ Attach all CustomFactors to the Pipeline returns ------- Pipeline (numpy.array) An array containing all data needed for the algorithm """ # create the pipeline for the data pull Data_Pipe = Pipeline() # attach SPY proxy Data_Pipe.add(SPY_proxy(), 'SPY Proxy') """ ADD COMPOSITE FACTORS with Data_Pipe.add(CUSTOMFACTOR) HERE """ return Data_Pipe
def initialize(context): set_commission(commission.PerShare(cost=0.005, min_trade_cost=1.00)) schedule_function(func=monthly_rebalance, date_rule=date_rules.month_start(days_offset=10), time_rule=time_rules.market_open(), half_days=True) schedule_function(func=daily_rebalance, date_rule=date_rules.every_day(), time_rule=time_rules.market_close(hours=1)) set_do_not_order_list(security_lists.leveraged_etf_list) context.canary = sid(8554) context.acc_leverage = 1.00 context.min_holdings = 50 context.profit_taking_factor = 0.01 context.profit_target={} context.profit_taken={} context.entry_date={} context.stop_pct = 0.75 context.stop_price = defaultdict(lambda:0) context.no_trade_yet = True context.buy_stocks = False # context.fct_window_length_1 = 20 # context.fct_window_length_2 = 60 # context.fct_window_length_3 = 125 # context.fct_window_length_4 = 252 context.safe = [ sid(23870), #IEF sid(23921), #TLT sid(25485) #AGG ] pipe = Pipeline() attach_pipeline(pipe, 'ranked_stocks') # factor1 = momentum_factor_1() factor1 = Returns(window_length=fct_window_length_1) pipe.add(factor1, 'factor_1') ''' # factor2 = momentum_factor_2() factor2 = Returns(window_length=context.fct_window_length_2) pipe.add(factor2, 'factor_2') # factor3 = momentum_factor_3() factor3 = Returns(window_length=context.fct_window_length_3) pipe.add(factor3, 'factor_3') # factor4 = momentum_factor_4() factor4 = Returns(window_length=context.fct_window_length_4) pipe.add(factor4, 'factor_4') ''' factor5=efficiency_ratio() pipe.add(factor5, 'factor_5') factor6 = AverageDollarVolume(window_length=20) pipe.add(factor6, 'factor_6') mkt_screen = market_cap() stocks = mkt_screen.top(3000) factor_5_filter = factor5 > 0.0 factor_6_filter = factor6 > 0.5e6 # only consider stocks trading >$500k per day total_filter = (stocks & factor_5_filter & factor_6_filter) pipe.set_screen(total_filter) ''' factor1_rank = factor1.rank(mask=total_filter, ascending=False) # pipe.add(factor1_rank, 'f1_rank') factor2_rank = factor2.rank(mask=total_filter, ascending=False) # pipe.add(factor2_rank, 'f2_rank') factor3_rank = factor3.rank(mask=total_filter, ascending=False) # pipe.add(factor3_rank, 'f3_rank') factor4_rank = factor4.rank(mask=total_filter, ascending=False) # pipe.add(factor4_rank, 'f4_rank') ''' # combo_raw = (factor1_rank+factor2_rank+factor3_rank+factor4_rank)/4 # pipe.add(combo_raw, 'combo_raw') combo_rank = MomentumRanking(mask=total_filter) pipe.add(combo_rank, 'combo_rank')
def make_pipeline(): # The factors we create here are based on fundamentals data and a moving # average of sentiment data value = Fundamentals.ebit.latest / Fundamentals.enterprise_value.latest quality = Fundamentals.roe.latest sentiment_score = SimpleMovingAverage( inputs=[stocktwits.bull_minus_bear], window_length=3, ) growthh = Fundamentals.growth_score.latest value_score = Fundamentals.value_score.latest profitability_grade = Fundamentals.profitability_grade.latest basic_average_shares = Fundamentals.basic_average_shares_earnings_reports.latest a = Fundamentals.current_ratio.latest b = Fundamentals.accumulated_depreciation.latest c = Fundamentals.ps_ratio.latest d = Fundamentals.style_score.latest #e = Fundamentals2.turn_rate_af.latest #f = Fundamentals. #g = Fundamentals. universe = QTradableStocksUS() # We winsorize our factor values in order to lessen the impact of outliers # For more information on winsorization, please see # https://en.wikipedia.org/wiki/Winsorizing value_winsorized = value.winsorize(min_percentile=0.0, max_percentile=1) quality_winsorized = quality.winsorize(min_percentile=0.00, max_percentile=1) sentiment_score_winsorized = sentiment_score.winsorize(min_percentile=0.05, max_percentile=0.95) growthh_winsorized = growthh.winsorize(min_percentile=0.05, max_percentile=0.95) value_score_winsorized = value_score.winsorize(min_percentile=0.05, max_percentile=0.95) basic_average_shares_winzorized = basic_average_shares.winsorize( min_percentile=0.05, max_percentile=0.95) a_winso = a.winsorize(min_percentile=0.05, max_percentile=0.95) b_winso = b.winsorize(min_percentile=0.05, max_percentile=0.95) c_winso = c.winsorize(min_percentile=0.05, max_percentile=0.95) d_winso = d.winsorize(min_percentile=0.05, max_percentile=0.95) #e_winso = e.winsorize(min_percentile=0.05, max_percentile=0.95) #f_winso = f.winsorize(min_percentile=0.05, max_percentile=0.95) #g_winso = g.winsorize(min_percentile=0.05, max_percentile=0.95) #profitability_grade_winsorized = profitability_grade.winsorize(min_percentile=0.05,max_percentile=0.95) # Here we combine our winsorized factors, z-scoring them to equalize their influence combined_factor = ( #(1*value_winsorized.zscore() ) #(-1.1*quality_winsorized.zscore() )+ #(1*sentiment_score_winsorized.zscore()) (1.4 * growthh_winsorized.zscore()) + (-1.6 * value_score_winsorized.zscore()) + (0.6 * a_winso.zscore()) + (0.8 * b_winso.zscore()) + (2.3 * c_winso.zscore()) + (0.75 * d_winso.zscore()) #(1*e_winso.zscore()) #(f_winso.zscore()) #(-0.1*basic_average_shares_winzorized.zscore( ) ) ) # Build Filters representing the top and bottom baskets of stocks by our # combined ranking system. We'll use these as our tradeable universe each # day. longs = combined_factor.top(TOTAL_POSITIONS // 2, mask=universe) shorts = combined_factor.bottom(2 * TOTAL_POSITIONS // 2, mask=universe) # The final output of our pipeline should only include # the top/bottom 300 stocks by our criteria long_short_screen = (longs | shorts) # Create pipeline pipe = Pipeline(columns={ 'longs': longs, 'shorts': shorts, 'combined_factor': combined_factor }, screen=long_short_screen) return pipe
def make_pipeline(): """ A function that creates and returns our pipeline. We break this piece of logic out into its own function to make it easier to test and modify in isolation. In particular, this function can be copy/pasted into research and run by itself. Returns ------- pipe : Pipeline Represents computation we would like to perform on the assets that make it through the pipeline screen. """ # The factors we create here are based on fundamentals data and a moving # average of sentiment data total_revenue = FundaMorningstar.total_revenue.latest yesterday_close = EquityPricing.close.latest yesterday_volume = EquityPricing.volume.latest yesterday = yesterday_close / yesterday_volume quarterly_sales = FundaFactset.sales_qf.latest amortization_income = FundaMorningstar.amortization_income_statement.latest administrative_expense = FundaMorningstar.administrative_expense.latest value = Fundamentals.ebit.latest / Fundamentals.enterprise_value.latest quality = Fundamentals.roe.latest sentiment_score = SimpleMovingAverage( inputs=[stocktwits.bull_minus_bear], window_length=3, ) universe = QTradableStocksUS() # We winsorize our factor values in order to lessen the impact of outliers # For more information on winsorization, please see # https://en.wikipedia.org/wiki/Winsorizing total_revenue_winsorized = total_revenue.winsorize(min_percentile=0.05, max_percentile=0.95) yesterday_winsorize = yesterday.winsorize(min_percentile=0.05, max_percentile=0.95) quarterly_sales_winsorize = quarterly_sales.winsorize(min_percentile=0.05, max_percentile=0.95) amortization_winsorize = amortization_income.winsorize(min_percentile=0.05, max_percentile=0.95) administrative_expense_winsorize = administrative_expense.winsorize( min_percentile=0.05, max_percentile=0.95) value_winsorized = value.winsorize(min_percentile=0.05, max_percentile=0.95) quality_winsorized = quality.winsorize(min_percentile=0.05, max_percentile=0.95) sentiment_score_winsorized = sentiment_score.winsorize(min_percentile=0.05, max_percentile=0.95) # Here we combine our winsorized factors, z-scoring them to equalize their influence combined_factor = (value_winsorized.zscore() + quality_winsorized.zscore() + sentiment_score_winsorized.zscore() + total_revenue_winsorized.zscore() + yesterday_winsorize.zscore() + quarterly_sales_winsorize.zscore() + administrative_expense_winsorize.zscore() + amortization_winsorize.zscore()) # Build Filters representing the top and bottom baskets of stocks by our # combined ranking system. We'll use these as our tradeable universe each # day. longs = combined_factor.top(TOTAL_POSITIONS // 2, mask=universe) shorts = combined_factor.bottom(TOTAL_POSITIONS // 2, mask=universe) # The final output of our pipeline should only include # the top/bottom 300 stocks by our criteria long_short_screen = (longs | shorts) # Create pipeline pipe = Pipeline(columns={ 'longs': longs, 'shorts': shorts, 'combined_factor': combined_factor }, screen=long_short_screen) return pipe
def initialize(context): schedule_function( func=periodic_rebalance, date_rule=date_rules.every_day(), #week_start(days_offset=1), time_rule=time_rules.market_open(hours=.5)) schedule_function(my_rebalance, date_rules.every_day(), time_rules.market_open(hours=0, minutes=1)) #schedule_function(my_rebalance, date_rules.every_day(), time_rules.market_open(hours=1, minutes=1)) schedule_function(my_rebalance, date_rules.every_day(), time_rules.market_open(hours=2, minutes=1)) #schedule_function(my_rebalance, date_rules.every_day(), time_rules.market_open(hours=3, minutes=1)) schedule_function(my_rebalance, date_rules.every_day(), time_rules.market_open(hours=4, minutes=1)) #schedule_function(my_rebalance, date_rules.every_day(), time_rules.market_open(hours=5, minutes=1)) schedule_function(my_rebalance, date_rules.every_day(), time_rules.market_open(hours=6, minutes=1)) #schedule_function( # do_portfolio_construction, # date_rule=algo.date_rules.week_start(), # time_rule=algo.time_rules.market_open(minutes=30), # half_days=False, # ) for hours_offset in range(7): schedule_function(my_rebalance, date_rules.every_day(), time_rules.market_open(hours=hours_offset, minutes=10), half_days=True) # # set portfolis parameters # set_asset_restrictions(security_lists.restrict_leveraged_etfs) context.acc_leverage = 1.00 context.min_holdings = 20 context.s_min_holdings = 10 # # set profit taking and stop loss parameters # context.profit_taking_factor = 0.01 context.profit_taking_target = 100.0 #set much larger than 1.0 to disable context.profit_target = {} context.profit_taken = {} context.stop_pct = 0.97 # set to 0.0 to disable context.stop_price = defaultdict(lambda: 0) # # Set commission model to be used # set_slippage( slippage.VolumeShareSlippage(volume_limit=0.025, price_impact=0.1)) # Default set_commission(commission.PerShare(cost=0.005, min_trade_cost=1.0)) # FSC for IB # Define safe set (of bonds) #sid(32268) #SH context.safe = [ sid(23870), #IEF sid(23921), #TLT #sid(8554), #SPY ] # # Define proxy to be used as proxy for overall stock behavior # set default position to be in safe set (context.buy_stocks = False) # context.canary = sid(22739) #why not spy context.buy_stocks = False # # Establish pipeline # pipe = Pipeline() attach_pipeline(pipe, 'ranked_stocks') # # Define the four momentum factors used in ranking stocks # factor1 = simple_momentum(window_length=1) pipe.add(factor1, 'factor_1') factor2 = simple_momentum(window_length=60) / Volatility(window_length=60) pipe.add(factor2, 'factor_2') factor3 = simple_momentum(window_length=252) pipe.add(factor3, 'factor_3') factor4 = ((Momentum() / Volatility()) + Momentum()) #or Downside_Risk() pipe.add(factor4, 'factor_4') factor8 = earning_yield() pipe.add(factor8, 'factor8') factor9 = roe() + roic() + roa() pipe.add(factor9, 'factor9') factor10 = cash_return() pipe.add(factor10, 'factor10') factor11 = fcf_yield() pipe.add(factor11, 'factor11') factor12 = current_ratio() pipe.add(factor12, 'factor12') factor13 = Quality() pipe.add(factor13, 'factor13') factor14 = market_cap() pipe.add(factor14, 'factor14') factor15 = RnD_to_market() + capex() pipe.add(factor15, 'factor15') factor18 = EPS_Growth_3M() pipe.add(factor18, 'factor18') factor19 = Piotroski4() pipe.add(factor19, 'factor19') factor20 = capex() pipe.add(factor20, 'factor20') # # Define other factors that may be used in stock screening # #factor5 = get_fcf_per_share() #pipe.add(factor5, 'factor_5') factor6 = AverageDollarVolume(window_length=60) pipe.add(factor6, 'factor_6') factor7 = get_last_close() pipe.add(factor7, 'factor_7') #factor_4_filter = factor4 > 1.03 # only consider stocks with positive 1y growth #factor_5_filter = factor5 > 0.0 # only consider stocks with positive FCF factor_6_filter = factor6 > .5e6 # only consider stocks trading >$500k per day #factor_7_filter = factor7 > 3.00 # only consider stocks that close above this value factor_12_filter = factor12 > .99 #factor_8_filter = factor8 > 0 #factor_15_filter = factor15 > factor6 #factor_1_filter = factor1 > 1.1 #factor_2_filter = factor2 > 1 #factor_20_filter = factor20 > 0 utilities_filter = Sector() != 207 materials_filter = Sector() != 101 energy_filter = Sector() != 309 industrial_filter = Sector() != 310 health_filter = Sector() != 206 staples_filter = Sector() != 205 real_estate_filter = Sector() != 104 #sentiment_filter = ((0.5*st.bull_scored_messages.latest)>(st.bear_scored_messages.latest)) & (st.bear_scored_messages.latest > 10) consumer_cyclical_filter = Sector() != 102 financial_filter = Sector() != 103 communication_filter = Sector() != 308 technology_filter = Sector != 311 #Basic_Materials = context.output[context.output.sector == 101] #Consumer_Cyclical = context.output[context.output.sector == 102] #Financial_Services = context.output[context.output.sector == 103] #Real_Estate = context.output[context.output.sector == 104] #Consumer_Defensive = context.output[context.output.sector == 205] #Healthcare = context.output[context.output.sector == 206] #Utilities = context.output[context.output.sector == 207] #Communication_Services = context.output[context.output.sector == 308] #Energy = context.output[context.output.sector == 309] #Industrials = context.output[context.output.sector == 310] #Technology = context.output[context.output.sector == 311] # # Establish screen used to establish candidate stock list # mkt_screen = market_cap() cash_flow = factor10 + factor11 price = factor14 profitability = factor9 #earning_quality = factor15 stocks = QTradableStocksUS( ) #mkt_screen.top(3500)&profitability.top(3500)&factor19.top(2000)#&factor8.top(2000)#&price.top(2000)#&factor15.top(3000)# total_filter = ( stocks & factor_6_filter #& factor_15_filter #& factor_8_filter #& factor_9_filter #& factor_1_filter #& factor_20_filter #& communication_filter #& consumer_cyclical_filter #& financial_filter #& staples_filter #& materials_filter #& industrial_filter #& factor_12_filter #& technology_filter ) pipe.set_screen(total_filter) # # Establish ranked stock list # factor1_rank = factor1.rank(mask=total_filter, ascending=False) pipe.add(factor1_rank, 'f1_rank') factor2_rank = factor2.rank(mask=total_filter, ascending=False) pipe.add(factor2_rank, 'f2_rank') factor3_rank = factor3.rank(mask=total_filter, ascending=False) #significant effect pipe.add(factor3_rank, 'f3_rank') factor4_rank = factor4.rank(mask=total_filter, ascending=False) #significant effect pipe.add(factor4_rank, 'f4_rank') factor8_rank = factor8.rank(mask=total_filter, ascending=False) #significant effect pipe.add(factor8_rank, 'f8_rank') factor9_rank = factor9.rank(mask=total_filter, ascending=False) #very big effect pipe.add(factor9_rank, 'f9_rank') factor10_rank = factor10.rank(mask=total_filter, ascending=False) pipe.add(factor10_rank, 'f10_rank') factor11_rank = factor11.rank(mask=total_filter, ascending=False) pipe.add(factor11_rank, 'f11_rank') factor13_rank = factor13.rank(mask=total_filter, ascending=False) #may want to remove pipe.add(factor13_rank, 'f13_rank') factor14_rank = factor14.rank(mask=total_filter, ascending=True) pipe.add(factor14_rank, 'f14_rank') factor15_rank = factor15.rank(mask=total_filter, ascending=False) pipe.add(factor15_rank, 'f15_rank') factor18_rank = factor18.rank(mask=total_filter, ascending=False) pipe.add(factor18_rank, 'f18_rank') factor19_rank = factor19.rank(mask=total_filter, ascending=False) pipe.add(factor19_rank, 'f19_rank') factor20_rank = factor20.rank(mask=total_filter, ascending=False) pipe.add(factor20_rank, 'f20_rank') combo_raw = (factor8_rank + factor18_rank + factor1_rank + factor4_rank + factor10_rank + factor11_rank + factor15_rank + factor9_rank + factor19_rank) #+factor14_rank*.5) pipe.add(combo_raw, 'combo_raw') pipe.add(combo_raw.rank(mask=total_filter), 'combo_rank')
def initialize(context): set_commission(commission.PerShare(cost=0.005, min_trade_cost=1.00)) schedule_function(func=monthly_rebalance, date_rule=date_rules.month_start(days_offset=5), time_rule=time_rules.market_open(), half_days=True) schedule_function(func=daily_rebalance, date_rule=date_rules.every_day(), time_rule=time_rules.market_close(hours=1)) set_do_not_order_list(security_lists.leveraged_etf_list) context.acc_leverage = 1.00 context.holdings = 10 context.profit_taking_factor = 0.01 context.profit_target = {} context.profit_taken = {} context.entry_date = {} context.stop_pct = 0.75 context.stop_price = defaultdict(lambda: 0) pipe = Pipeline() attach_pipeline(pipe, 'ranked_stocks') factor1 = momentum_factor_1() pipe.add(factor1, 'factor_1') factor2 = momentum_factor_2() pipe.add(factor2, 'factor_2') factor3 = momentum_factor_3() pipe.add(factor3, 'factor_3') factor4 = momentum_factor_4() pipe.add(factor4, 'factor_4') factor5 = efficiency_ratio() pipe.add(factor5, 'factor_5') mkt_cap = morningstar.valuation.market_cap.latest mkt_cap_rank = mkt_cap.rank(ascending=True) pipe.add(mkt_cap_rank, 'mkt_cap_rank') stocks = mkt_cap_rank.top(3000) factor_5_filter = factor5 > 0.031 total_filter = (stocks & factor_5_filter) pipe.set_screen(total_filter) factor1_rank = factor1.rank(mask=total_filter, ascending=False) pipe.add(factor1_rank, 'f1_rank') factor2_rank = factor2.rank(mask=total_filter, ascending=False) pipe.add(factor2_rank, 'f2_rank') factor3_rank = factor3.rank(mask=total_filter, ascending=False) pipe.add(factor3_rank, 'f3_rank') factor4_rank = factor4.rank(mask=total_filter, ascending=False) pipe.add(factor4_rank, 'f4_rank') combo_raw = (factor1_rank + factor2_rank + factor3_rank + factor4_rank) / 4 pipe.add(combo_raw, 'combo_raw') pipe.add(combo_raw.rank(mask=total_filter), 'combo_rank')
def initialize(context): pipe = Pipeline() pipe = attach_pipeline(pipe, name='factors') pipe.add(Value(), "value") pipe.add(Momentum(), "momentum") pipe.add(Quality(), "quality") pipe.add(Volatility(), "volatility") sma_200 = SimpleMovingAverage(inputs=[USEquityPricing.close], window_length=200) dollar_volume = AvgDailyDollarVolumeTraded() # Screen out penny stocks and low liquidity securities. pipe.set_screen((sma_200 > 5) & (dollar_volume > 10**7)) context.spy = sid(8554) context.shorts = None context.longs = None schedule_function(rebalance, date_rules.month_start()) schedule_function(cancel_open_orders, date_rules.every_day(), time_rules.market_close())
def make_pipeline(): """ A function that creates and returns our pipeline. We break this piece of logic out into its own function to make it easier to test and modify in isolation. In particular, this function can be copy/pasted into research and run by itself. Returns ------- pipe : Pipeline Represents computation we would like to perform on the assets that make it through the pipeline screen. """ # The factors we create here are based on fundamentals data and a moving # average of sentiment data value = Fundamentals.ebit.latest / Fundamentals.enterprise_value.latest quality = Fundamentals.roe.latest foo = Fundamentals.diluted_cont_eps_growth.latest var = Fundamentals.size_score.latest aux = Fundamentals.value_score.latest res = Fundamentals.accounts_payable.latest x = Fundamentals.accumulated_depreciation.latest y = Fundamentals.book_value_per_share.latest s = Fundamentals.working_capital_per_share.latest sentiment_score = SimpleMovingAverage( inputs=[stocktwits.bull_minus_bear], window_length=3, ) universe = QTradableStocksUS() # We winsorize our factor values in order to lessen the impact of outliers # For more information on winsorization, please see # https://en.wikipedia.org/wiki/Winsorizing value_winsorized = value.winsorize(min_percentile=0.05, max_percentile=0.95) quality_winsorized = quality.winsorize(min_percentile=0.05, max_percentile=0.95) sentiment_score_winsorized = sentiment_score.winsorize(min_percentile=0.05, max_percentile=0.95) foo_winsorized = foo.winsorize(min_percentile=0.05, max_percentile=0.95) var_winsorized = var.winsorize(min_percentile=0.05, max_percentile=0.95) aux_winsorized = aux.winsorize(min_percentile=0.05, max_percentile=0.95) res_winsorized = res.winsorize(min_percentile=0.05, max_percentile=0.95) x_winsorized = x.winsorize(min_percentile=0.05, max_percentile=0.95) y_winsorized = y.winsorize(min_percentile=0.05, max_percentile=0.95) s_winsorized = s.winsorize(min_percentile=0.05, max_percentile=0.95) # Here we combine our winsorized factors, z-scoring them to equalize their influence combined_factor = (value_winsorized.zscore() + quality_winsorized.zscore() + sentiment_score_winsorized.zscore() - foo_winsorized.zscore() + var_winsorized.zscore() + aux_winsorized.zscore() - res_winsorized.zscore() - x_winsorized.zscore() + y_winsorized.zscore() - s_winsorized.zscore()) # Build Filters representing the top and bottom baskets of stocks by our # combined ranking system. We'll use these as our tradeable universe each # day. longs = combined_factor.top(TOTAL_POSITIONS // 2, mask=universe) shorts = combined_factor.bottom(TOTAL_POSITIONS // 2, mask=universe) # The final output of our pipeline should only include # the top/bottom 300 stocks by our criteria long_short_screen = (longs | shorts) # Create pipeline pipe = Pipeline(columns={ 'longs': longs, 'shorts': shorts, 'combined_factor': combined_factor }, screen=long_short_screen) return pipe
def make_pipeline(): base_universe = QTradableStocksUS() latest_close = USEquityPricing.close.latest latest_volume = USEquityPricing.volume.latest latest_close = USEquityPricing.close.latest mkt_cap = morningstar.valuation.market_cap.latest symbol_float1 = morningstar.Fundamentals.shares_outstanding.latest symbol_float2 = morningstar.Fundamentals.ordinary_shares_number.latest morningstar_sector = Sector() volume_3_months = AverageDollarVolume( window_length=66, mask=base_universe & (mkt_cap < 5000000000) #masking ) volume_1_day = AverageDollarVolume( window_length=1, mask=base_universe & (mkt_cap < 5000000000) #masking ) mean_close_30 = SimpleMovingAverage( inputs=[USEquityPricing.close], window_length=30, mask=base_universe & (mkt_cap < 5000000000) #masking ) rv = volume_1_day / volume_3_months high_52_w = High252() high_3_m = High66() low_52_w = Low252() # price at 30%, 50%, 60% and 90% respectively of the yearly price range third_range = (high_52_w - low_52_w) * (1 / 3) + low_52_w half_range = (high_52_w - low_52_w) * 0.5 + low_52_w sixty_range = (high_52_w - low_52_w) * 0.6 + low_52_w ninty_range = (high_52_w - low_52_w) * 0.9 + low_52_w fifteen_range = (high_52_w - low_52_w) * 0.15 + low_52_w #create the price range for potential longs long_range = (latest_close <= sixty_range) & (latest_close >= third_range) #take profit range tp_range = latest_close >= ninty_range #stop loss range sl_range = latest_close <= fifteen_range valid_open_position_range = (latest_close <= ninty_range) & (latest_close >= fifteen_range) #filters (the data type is a zipline pipeline filter not a df) # returns True or False per row (per symbol): close_price_filter = (latest_close < 15) price_under_30mva = latest_close < mean_close_30 #price under 30 mva #create a list of stocks for potential longs universe = close_price_filter & base_universe & (mkt_cap < 5000000000) # create the "go long" critera longs = price_under_30mva & long_range return Pipeline(columns={ 'latest_close': latest_close, 'rv': rv, 'stop_loss': sl_range, 'take_profit': tp_range, 'valid_open_position': valid_open_position_range, 'longs': longs }, screen=universe)
def Data_Pull(): # create the pipeline for the data pull Data_Pipe = Pipeline() # create SPY proxy Data_Pipe.add(SPY_proxy(), "SPY Proxy") # Div Yield Data_Pipe.add(Div_Yield(), "Dividend Yield") # Price to Book Data_Pipe.add(Price_to_Book(), "Price to Book") # Price / TTM Sales Data_Pipe.add(Price_to_TTM_Sales(), "Price / TTM Sales") # Price / TTM Cashflows Data_Pipe.add(Price_to_TTM_Cashflows(), "Price / TTM Cashflow") return Data_Pipe
def make_pipeline(): """ A function that creates and returns our pipeline. We break this piece of logic out into its own function to make it easier to test and modify in isolation. In particular, this function can be copy/pasted into research and run by itself. Returns ------- pipe : Pipeline Represents computation we would like to perform on the assets that make it through the pipeline screen. """ # The factors we create here are based on fundamentals data and a moving # average of sentiment data value = Fundamentals.ebit.latest / Fundamentals.enterprise_value.latest quality = Fundamentals.roe.latest sentiment_score = SimpleMovingAverage( inputs=[stocktwits.bull_minus_bear], window_length=3, ) ppe = Fundamentals.sale_of_ppe.latest cap_mercado = Fundamentals.market_cap.latest assets = Fundamentals.assets_turnover.latest expenses = Fundamentals.administrative_expense.latest gr_loan = Fundamentals.gross_loan.latest universe = QTradableStocksUS() income_tax = Fundamentals.income_tax_payable.latest # We winsorize our factor values in order to lessen the impact of outliers # For more information on winsorization, please see # https://en.wikipedia.org/wiki/Winsorizing value_winsorized = value.winsorize(min_percentile=0.05, max_percentile=0.95) quality_winsorized = quality.winsorize(min_percentile=0.05, max_percentile=0.95) sentiment_score_winsorized = sentiment_score.winsorize(min_percentile=0.05, max_percentile=0.95) ppe_winsorized = ppe.winsorize(min_percentile=0.05, max_percentile=0.95) cap_mercado_winsorized = cap_mercado.winsorize(min_percentile=0.05, max_percentile=0.95) assets_winsorized = assets.winsorize(min_percentile=0.05, max_percentile=0.95) expenses_winsorized = expenses.winsorize(min_percentile=0.05, max_percentile=0.95) gr_loan_winsorized = gr_loan.winsorize(min_percentile=0.05, max_percentile=0.95) income_tax_winsorized = income_tax.winsorize(min_percentile=0.05, max_percentile=0.95) value_weight = 0.14 quality_weight = 0.14 sentiment_score_weight = 0.14 ppe_weight = 0.10 cap_mercado_weight = 0.4 assets_weight = 0.5 expenses_weight = 0.2 gr_loan_weight = 0.5 income_tax_weight = 0.3 #weights # Here we combine our winsorized factors, z-scoring them to equalize their influence combined_factor = ( value_winsorized.zscore() * value_weight + quality_winsorized.zscore() * quality_weight + sentiment_score_winsorized.zscore() * sentiment_score_weight + ppe_winsorized.zscore() * ppe_weight + cap_mercado_winsorized.zscore() * cap_mercado_weight + assets_winsorized.zscore() * assets_weight + expenses_winsorized.zscore() * expenses_weight + gr_loan_winsorized.zscore() * gr_loan_weight + income_tax_winsorized.zscore() * income_tax_weight ) # Build Filters representing the top and bottom baskets of stocks by our # combined ranking system. We'll use these as our tradeable universe each # day. longs = combined_factor.top(TOTAL_POSITIONS//2, mask=universe) shorts = combined_factor.bottom(TOTAL_POSITIONS//2, mask=universe) # The final output of our pipeline should only include # the top/bottom 300 stocks by our criteria long_short_screen = (longs | shorts) # Create pipeline pipe = Pipeline( columns={ 'longs': longs, 'shorts': shorts, 'combined_factor': combined_factor }, screen=long_short_screen ) return pipe
def make_pipeline(): """ Create our pipeline. """ # Filter for primary share equities. IsPrimaryShare is a built-in filter. primary_share = IsPrimaryShare() # Equities listed as common stock (as opposed to, say, preferred stock). # 'ST00000001' indicates common stock. common_stock = morningstar.share_class_reference.security_type.latest.eq('ST00000001') # Non-depositary receipts. Recall that the ~ operator inverts filters, # turning Trues into Falses and vice versa not_depositary = ~morningstar.share_class_reference.is_depositary_receipt.latest # Equities not trading over-the-counter. not_otc = ~morningstar.share_class_reference.exchange_id.latest.startswith('OTC') # Not when-issued equities. not_wi = ~morningstar.share_class_reference.symbol.latest.endswith('.WI') # Equities without LP in their name, .matches does a match using a regular # expression not_lp_name = ~morningstar.company_reference.standard_name.latest.matches('.* L[. ]?P.?$') # Equities with a null value in the limited_partnership Morningstar # fundamental field. not_lp_balance_sheet = morningstar.balance_sheet.limited_partnership.latest.isnull() # Equities whose most recent Morningstar market cap is not null have # fundamental data and therefore are not ETFs. have_market_cap = morningstar.valuation.market_cap.latest.notnull() # Filter for stocks that pass all of our previous filters. tradeable_stocks = ( primary_share & common_stock & not_depositary & not_otc & not_wi & not_lp_name & not_lp_balance_sheet & have_market_cap ) # High dollar volume filter. base_universe = AverageDollarVolume(window_length=20, mask=tradeable_stocks).percentile_between(70, 100) # 10-day close price average. mean_10 = SimpleMovingAverage(inputs=[USEquityPricing.close], window_length=10, mask=base_universe) # 30-day close price average. mean_30 = SimpleMovingAverage(inputs=[USEquityPricing.close], window_length=30, mask=base_universe) percent_difference = (mean_10 - mean_30) / mean_30 # Filter to select securities to short. shorts = percent_difference.top(25) # Filter to select securities to long. longs = percent_difference.bottom(25) # Filter for all securities that we want to trade. securities_to_trade = (shorts | longs) return Pipeline( columns={ 'longs': longs, 'shorts': shorts }, screen=(securities_to_trade), )
def make_pipeline(): """ Create and return our pipeline. We break this piece of logic out into its own function to make it easier to test and modify in isolation. In particular, this function can be copy/pasted into research and run by itself. """ # Create our sentiment, value, and quality factors sentiment = Sentiment() # By appending .latest to the imported morningstar data, we get builtin Factors # so there's no need to define a CustomFactor value = morningstar.income_statement.ebit.latest / morningstar.valuation.enterprise_value.latest quality = morningstar.operation_ratios.roe.latest # Classify all securities by sector so that we can enforce sector neutrality later sector = Sector() # Screen out non-desirable securities by defining our universe. # Removes ADRs, OTCs, non-primary shares, LP, etc. # Also sets a minimum $500MM market cap filter and $5 price filter mkt_cap_filter = morningstar.valuation.market_cap.latest >= 500000000 price_filter = USEquityPricing.close.latest >= 5 universe = Q1500US() & price_filter & mkt_cap_filter # Construct a Factor representing the rank of each asset by our sentiment, # value, and quality metrics. We aggregate them together here using simple # addition. # # By applying a mask to the rank computations, we remove any stocks that failed # to meet our initial criteria **before** computing ranks. This means that the # stock with rank 10.0 is the 10th-lowest stock that was included in the Q1500US. combined_rank = (sentiment.rank(mask=universe).zscore() + value.rank(mask=universe).zscore() + quality.rank(mask=universe).zscore()) # Build Filters representing the top and bottom 150 stocks by our combined ranking system. # We'll use these as our tradeable universe each day. longs = combined_rank.top(NUM_LONG_POSITIONS) shorts = combined_rank.bottom(NUM_SHORT_POSITIONS) # The final output of our pipeline should only include # the top/bottom 300 stocks by our criteria long_short_screen = (longs | shorts) # Define any risk factors that we will want to neutralize # We are chiefly interested in market beta as a risk factor so we define it using # Bloomberg's beta calculation # Ref: https://www.lib.uwo.ca/business/betasbydatabasebloombergdefinitionofbeta.html beta = 0.66 * RollingLinearRegressionOfReturns( target=sid(8554), returns_length=5, regression_length=260, mask=long_short_screen).beta + 0.33 * 1.0 # Create pipeline pipe = Pipeline(columns={ 'longs': longs, 'shorts': shorts, 'combined_rank': combined_rank, 'quality': quality, 'value': value, 'sentiment': sentiment, 'sector': sector, 'market_beta': beta }, screen=long_short_screen) return pipe
def make_pipeline(): return Pipeline()
def make_pipeline(context): # Create a pipeline object. pipe = Pipeline() # Create a dollar_volume factor using default inputs and window_length. # This is a builtin factor. dollar_volume = AverageDollarVolume(window_length=1) pipe.add(dollar_volume, 'dollar_volume') # Create a recent_returns factor with a 5-day returns lookback. This is # a custom factor defined below (see RecentReturns class). recent_returns = Returns(window_length=context.returns_lookback) pipe.add(recent_returns, 'recent_returns') # Define high dollar-volume filter to be the top 5% of stocks by dollar volume. high_dollar_volume = dollar_volume.percentile_between(95, 100) # Define high and low returns filters to be the bottom 10% and top 10% of # securities in the high dollar volume group. low_returns = recent_returns.percentile_between(0,10,mask=high_dollar_volume) high_returns = recent_returns.percentile_between(90,100,mask=high_dollar_volume) # Factors return a scalar value for each security in the entire universe # of securities. Here, we add the recent_returns rank factor to our pipeline # and we provide it with a mask such that securities that do not pass the mask # (i.e. do not have high dollar volume), are not considered in the ranking. pipe.add(recent_returns.rank(mask=high_dollar_volume), 'recent_returns_rank') # Add a filter to the pipeline such that only high-return and low-return # securities are kept. pipe.set_screen((low_returns | high_returns) & high_dollar_volume) # Add the low_returns and high_returns filters as columns to the pipeline so # that when we refer to securities remaining in our pipeline later, we know # which ones belong to which category. pipe.add(low_returns, 'low_returns') pipe.add(high_returns, 'high_returns') return pipe
def make_pipeline(): """ A function that creates and returns our pipeline. We break this piece of logic out into its own function to make it easier to test and modify in isolation. In particular, this function can be copy/pasted into research and run by itself. Returns ------- pipe : Pipeline Represents computation we would like to perform on the assets that make it through the pipeline screen. """ # The factors we create here are based on fundamentals data and a moving # average of sentiment data value = Fundamentals.ebit.latest / Fundamentals.enterprise_value.latest quality = Fundamentals.roe.latest sentiment_score = SimpleMovingAverage( inputs=[stocktwits.bull_minus_bear], window_length=3, ) mean_close_10 = SimpleMovingAverage( inputs=[USEquityPricing.close], window_length=10 ) mean_close_30 = SimpleMovingAverage( inputs=[USEquityPricing.close], window_length=30 ) percent_difference = (mean_close_10 - mean_close_30) / mean_close_30 universe = QTradableStocksUS() # We winsorize our factor values in order to lessen the impact of outliers # For more information on winsorization, please see # https://en.wikipedia.org/wiki/Winsorizing value_winsorized = value.winsorize(min_percentile=0.05, max_percentile=0.95) quality_winsorized = quality.winsorize(min_percentile=0.05, max_percentile=0.95) sentiment_score_winsorized = sentiment_score.winsorize( min_percentile=0.05, max_percentile=0.95 ) percent_difference_winsorized = percent_difference.winsorize( min_percentile=0.1, max_percentile=0.9 ) recent_returns = Returns(window_length=5) fq1_eps_cons = fe.PeriodicConsensus.slice('EPS', 'qf', 2) fq1_eps_cons_up = fq1_eps_cons.up.latest fq1_eps_cons_down = fq1_eps_cons.down.latest fq_tot = fq1_eps_cons_up - fq1_eps_cons_down fq_tot_windsorized = fq_tot.winsorize(min_percentile=0.01, max_percentile=0.99) # Here we combine our winsorized factors, z-scoring them to equalize their influence combined_factor = ( value_winsorized.zscore() + quality_winsorized.zscore() + sentiment_score_winsorized.zscore() + 0.05 * percent_difference_winsorized.zscore() + 0.05 * fq_tot_windsorized.zscore() + 0.1 * recent_returns.zscore() ) # Build Filters representing the top and bottom baskets of stocks by our # combined ranking system. We'll use these as our tradeable universe each # day. longs = combined_factor.top(TOTAL_POSITIONS // 2, mask=universe) shorts = combined_factor.bottom(TOTAL_POSITIONS // 2, mask=universe) # The final output of our pipeline should only include # the top/bottom 300 stocks by our criteria long_short_screen = (longs | shorts) # Create pipeline pipe = Pipeline( columns={ 'longs': longs, 'shorts': shorts, 'combined_factor': combined_factor }, screen=long_short_screen ) return pipe
def my_pipeline(context): """ A function to create our dynamic stock selector (pipeline). Documentation on pipeline can be found here: https://www.quantopian.com/help#pipeline-title """ pipe = Pipeline() # span stands for past 120 days, need doulbe window length to get 120 data point. ewma120 = EWMA.from_span([USEquityPricing.close], window_length=2 * context.look_back_long, span=context.look_back_long) pipe.add(ewma120, "ewma120") ewma60 = EWMA.from_span([USEquityPricing.close], window_length=2 * context.look_back_middle, span=context.look_back_middle) pipe.add(ewma60, "ewma60") ewma15 = EWMA.from_span([USEquityPricing.close], window_length=2 * context.look_back_short, span=context.look_back_short) pipe.add(ewma15, "ewma15") pipe.add(Latest(inputs=[USEquityPricing.close]), "yes_price") momentum = (ewma120 - ewma60).abs() + (ewma60 - ewma15).abs() middle_momentum = momentum.percentile_between(0, 5) # Create a dollar volume factor. dollar_volume = AverageDollarVolume(window_length=1, mask=middle_momentum) pipe.add(dollar_volume, 'dollar_volume') # Pick the top 10% of stocks ranked by dollar volume. high_dollar_volume = dollar_volume.percentile_between(90, 100) pipe.set_screen(high_dollar_volume) return pipe
def make_pipeline(context): """ Create our pipeline. """ # Filter for primary share equities. IsPrimaryShare is a built-in filter. primary_share = IsPrimaryShare() # Equities listed as common stock (as opposed to, say, preferred stock). # 'ST00000001' indicates common stock. common_stock = morningstar.share_class_reference.security_type.latest.eq( 'ST00000001') # Non-depositary receipts. Recall that the ~ operator inverts filters, # turning Trues into Falses and vice versa not_depositary = ~morningstar.share_class_reference.is_depositary_receipt.latest # Equities not trading over-the-counter. not_otc = ~morningstar.share_class_reference.exchange_id.latest.startswith( 'OTC') # Not when-issued equities. not_wi = ~morningstar.share_class_reference.symbol.latest.endswith('.WI') # Equities without LP in their name, .matches does a match using a regular # expression not_lp_name = ~morningstar.company_reference.standard_name.latest.matches( '.* L[. ]?P.?$') # Equities with a null value in the limited_partnership Morningstar # fundamental field. not_lp_balance_sheet = morningstar.balance_sheet.limited_partnership.latest.isnull( ) # Equities whose most recent Morningstar market cap is not null have # fundamental data and therefore are not ETFs. have_market_cap = morningstar.valuation.market_cap.latest.notnull() # At least a certain price price = USEquityPricing.close.latest AtLeastPrice = (price >= context.MyLeastPrice) AtMostPrice = (price <= context.MyMostPrice) # Filter for stocks that pass all of our previous filters. tradeable_stocks = (primary_share & common_stock & not_depositary & not_otc & not_wi & not_lp_name & not_lp_balance_sheet & have_market_cap & AtLeastPrice & AtMostPrice) LowVar = 6 HighVar = 40 log.info(''' Algorithm initialized variables: context.MaxCandidates %s LowVar %s HighVar %s''' % (context.MaxCandidates, LowVar, HighVar)) # High dollar volume filter. base_universe = AverageDollarVolume( window_length=20, mask=tradeable_stocks).percentile_between(LowVar, HighVar) # Short close price average. ShortAvg = SimpleMovingAverage(inputs=[USEquityPricing.close], window_length=3, mask=base_universe) # Long close price average. LongAvg = SimpleMovingAverage(inputs=[USEquityPricing.close], window_length=45, mask=base_universe) percent_difference = (ShortAvg - LongAvg) / LongAvg # Filter to select securities to long. stocks_worst = percent_difference.bottom(context.MaxCandidates) securities_to_trade = (stocks_worst) return Pipeline( columns={'stocks_worst': stocks_worst}, screen=(securities_to_trade), )
def make_pipeline(): """ A function that creates and returns our pipeline. We break this piece of logic out into its own function to make it easier to test and modify in isolation. In particular, this function can be copy/pasted into research and run by itself. Returns ------- pipe : Pipeline Represents computation we would like to perform on the assets that make it through the pipeline screen. """ # The factors we create here are based on fundamentals data and a moving # average of sentiment data value = Fundamentals.ebit.latest * 0.6/ Fundamentals.enterprise_value.latest quality = Fundamentals.roe.latest + Fundamentals.ebit.latest sentiment_score = SimpleMovingAverage( inputs=[stocktwits.bull_minus_bear], window_length= 21, ) growth_score = Fundamentals.growth_score.latest #print(value) gross_profit = Fundamentals.gross_profit.latest equity_per_share_growth = Fundamentals.equity_per_share_growth.latest #dps_growth = Fundamentals.dps_growth.latest universe = QTradableStocksUS() # We winsorize our factor values in order to lessen the impact of outliers # For more information on winsorization, please see # https://en.wikipedia.org/wiki/Winsorizing # 0.05 - 0.95 #dps_growth_winsorized = dps_growth.winsorize(min_percentile=0.05, max_percentile=0.95) eps_growth_winsorized = equity_per_share_growth.winsorize(min_percentile=0.05, max_percentile=0.95) gross_profit_winsorized = gross_profit.winsorize(min_percentile=0.05, max_percentile=0.95) value_winsorized = value.winsorize(min_percentile=0.05, max_percentile=0.95) quality_winsorized = quality.winsorize(min_percentile=0.05, max_percentile=0.95) sentiment_score_winsorized = sentiment_score.winsorize(min_percentile=0.05, max_percentile=0.95) growth_score_winsorized = growth_score.winsorize(min_percentile=0.05, max_percentile=0.95) # Here we combine our winsorized factors, z-scoring them to equalize their influence combined_factor = ( value_winsorized.zscore() + quality_winsorized.zscore() * 0.8 + sentiment_score_winsorized.zscore() * 0.5 + growth_score_winsorized * 0.8 + gross_profit_winsorized * 0.3 + #rth eps_growth_winsorized * 0.8 ) # Build Filters representing the top and bottom baskets of stocks by our # combined ranking system. We'll use these as our tradeable universe each # day. #longs = combined_factor.top(TOTAL_POSITIONS//2, mask=universe) #shorts = combined_factor.bottom(TOTAL_POSITIONS//2, mask=universe) ''' longs = combined_factor.top(0.45*TOTAL_POSITIONS//2, mask=universe) shorts = combined_factor.bottom(0.35*TOTAL_POSITIONS//2, mask=universe) longs = combined_factor.top(0.35*TOTAL_POSITIONS//2, mask=universe) shorts = combined_factor.bottom(0.35*TOTAL_POSITIONS//2, mask=universe) ''' longs = combined_factor.top(0.8*TOTAL_POSITIONS//2, mask=universe) shorts = combined_factor.bottom(0.85*TOTAL_POSITIONS//2, mask=universe) # The final output of our pipeline should only include # the top/bottom 300 stocks by our criteria long_short_screen = (longs | shorts) # Create pipeline pipe = Pipeline( columns={ 'longs': longs, 'shorts': shorts, 'combined_factor': combined_factor }, screen=long_short_screen ) return pipe
def make_pipeline(): """ A function that creates and returns our pipeline. We break this piece of logic out into its own function to make it easier to test and modify in isolation. In particular, this function can be copy/pasted into research and run by itself. Returns ------- pipe : Pipeline Represents computation we would like to perform on the assets that make it through the pipeline screen. """ # The factors we create here are based on fundamentals data and a moving # average of sentiment data value = Fundamentals.ebit.latest quality = Fundamentals.roe.latest sentiment_score = SimpleMovingAverage( inputs=[stocktwits.bull_minus_bear], window_length=3, ) total_revenue = Fundamentals.total_revenue.latest positive_sentiment_pct = (twitter_sentiment.bull_scored_messages.latest / twitter_sentiment.total_scanned_messages.latest) positive_sentiment_pctt = ( twitter_sentiment2.bull_scored_messages.latest / twitter_sentiment2.total_scanned_messages.latest) value_morning = Fundamentals.ebit.latest universe = QTradableStocksUS() # We winsorize our factor values in order to lessen the impact of outliers # For more information on winsorization, please see # https://en.wikipedia.org/wiki/Winsorizing value_winsorized = value.winsorize(min_percentile=0.05, max_percentile=0.95) quality_winsorized = quality.winsorize(min_percentile=0.05, max_percentile=0.95) sentiment_score_winsorized = sentiment_score.winsorize(min_percentile=0.05, max_percentile=0.95) total_revenue_winsorized = total_revenue.winsorize(min_percentile=0.05, max_percentile=0.95) positive_sentiment_pct_winsorized = positive_sentiment_pct.winsorize( min_percentile=0.05, max_percentile=0.95) positive_sentiment_pctt_winsorized = positive_sentiment_pctt.winsorize( min_percentile=0.05, max_percentile=0.95) value_morning_winsorized = value_morning.winsorize(min_percentile=0.05, max_percentile=0.95) # Here we combine our winsorized factors, z-scoring them to equalize their influence combined_factor = (0.2 * value_winsorized.zscore() + 0.2 * quality_winsorized.zscore() + 0.2 * sentiment_score_winsorized.zscore() + 0.1 * total_revenue_winsorized.zscore() + 0.1 * positive_sentiment_pct_winsorized + 0.1 * positive_sentiment_pctt_winsorized + value_morning_winsorized) # Build Filters representing the top and bottom baskets of stocks by our # combined ranking system. We'll use these as our tradeable universe each # day. longs = combined_factor.top(TOTAL_POSITIONS // 2, mask=universe) shorts = combined_factor.bottom(TOTAL_POSITIONS // 2, mask=universe) # The final output of our pipeline should only include # the top/bottom 300 stocks by our criteria long_short_screen = (longs | shorts) # Create pipeline pipe = Pipeline(columns={ 'longs': longs, 'shorts': shorts, 'combined_factor': combined_factor, 'total_revenue': total_revenue, 'positive_sentiment_pct': positive_sentiment_pct, 'positive_sentiment_pctt': positive_sentiment_pctt, 'value_morning_winsorized': value_morning }, screen=long_short_screen) return pipe
def initialize(context): context.long_leverage = 0.50 context.short_leverage = -0.50 pipe = Pipeline() attach_pipeline(pipe, 'ranked_2000') #add the two factors defined to the pipeline factor1 = Factor1() pipe.add(factor1, 'factor_1') factor2 = Factor2() pipe.add(factor2, 'factor_2') # Create and apply a filter representing the top 2000 equities by MarketCap every day # This is an approximation of the Russell 2000 mkt_cap = MarketCap() top_2000 = mkt_cap.top(2000) pipe.set_screen(top_2000) # Rank factor 1 and add the rank to our pipeline factor1_rank = factor1.rank(mask=top_2000) pipe.add(factor1_rank, 'f1_rank') # Rank factor 2 and add the rank to our pipeline factor2_rank = factor2.rank(mask=top_2000) pipe.add(factor2_rank, 'f2_rank') # Take the average of the two factor rankings, add this to the pipeline combo_raw = (factor1_rank + factor2_rank) pipe.add(combo_raw, 'combo_raw') # Rank the combo_raw and add that to the pipeline pipe.add(combo_raw.rank(mask=top_2000), 'combo_rank') # Scedule my rebalance function schedule_function(func=rebalance, date_rule=date_rules.month_start(days_offset=0), time_rule=time_rules.market_open(hours=0, minutes=30), half_days=True)
def make_pipeline(): Universe = Q500US() pipe = Pipeline(screen=Universe) return pipe