def my_pipeline(context):
pipe = Pipeline()
"""
The original algorithm used the following filters:
1. common stock
2 & 3. not limited partnership - name and database check
4. database has fundamental data
5. not over the counter
6. not when issued
7. not depository receipts
8. primary share
9. high dollar volume
Check Scott's notebook for more details.
This updated version uses Q1500US, one of the pipeline's built-in base universes.
Lesson 11 from the Pipeline tutorial offers a great overview of using multiple
filters vs using the built-in base universes:
https://www.quantopian.com/tutorials/pipeline#lesson11
More detail on the selection criteria of this filter can be found here:
https://www.quantopian.com/posts/the-q500us-and-q1500us
"""
base_universe = Q1500US()
# The example algorithm - mean reversion. Note the tradable filter used as a mask.
sma_10 = SimpleMovingAverage(inputs=[USEquityPricing.close],
window_length=10,
mask=base_universe)
sma_30 = SimpleMovingAverage(inputs=[USEquityPricing.close],
window_length=30,
mask=base_universe)
rel_diff = (sma_10 - sma_30) / sma_30
top_rel_diff = rel_diff.top(context.num_short)
pipe.add(top_rel_diff, 'top_rel_diff')
bottom_rel_diff = rel_diff.bottom(context.num_long)
pipe.add(bottom_rel_diff, 'bottom_rel_diff')
return pipe
def make_pipeline():
#context.features = ['RSI', 'MACD', 'EMA','SMA_5','SMA_10','ADX']
base_universe = Q1500US()
sector = mstar.asset_classification.morningstar_sector_code.latest
sectors_311 = sector.eq(311)
returns_5 = Returns(window_length=5)
rsi = RSI(inputs=[USEquityPricing.close])
macd = MovingAverageConvergenceDivergenceSignal(mask=base_universe)
ema = ExponentialWeightedMovingAverage(mask=base_universe,
inputs=[USEquityPricing.close],
window_length=30,
decay_rate=(1 - (2.0 / (1 + 15.0))))
mean_5 = SimpleMovingAverage(inputs=[USEquityPricing.close],
window_length=5,
mask=base_universe)
mean_10 = SimpleMovingAverage(inputs=[USEquityPricing.close],
window_length=10,
mask=base_universe)
bb = BollingerBands(inputs=[USEquityPricing.close], window_length=20, k=2)
diluted_eps = Fundamentals.diluted_eps_earnings_reports.latest
growth_score = Fundamentals.growth_score.latest
tangible_bv = Fundamentals.tangible_book_value.latest
return Pipeline(
columns={
'returns_5': returns_5,
'RSI': rsi,
'MACD': macd,
'EMA': ema,
'SMA_5': mean_5,
'SMA_10': mean_10,
'bb_upper': bb.upper,
'bb_middle': bb.middle,
'bb_lower': bb.lower,
'diluted_eps': diluted_eps,
'growth_score': growth_score,
'tangible_bv': tangible_bv
},
screen=(base_universe & sectors_311),
)
def make_pipeline():
"""
A function to create our dynamic stock selector (pipeline). Used to calculate
SMA and latest close price then filter on SID.
"""
# n = [1, 5, 15, 25, 35, 45, 50, 100, 200]
sma_short = 1
sma_long = 100
short_sma = SimpleMovingAverage(inputs=[USEquityPricing.close], window_length=sma_short)
long_sma = SimpleMovingAverage(inputs=[USEquityPricing.close], window_length=sma_long)
symbol = SidInList(sid_list=(8554)) # Only show values for the S&P500
return Pipeline(
columns={
'SMA_short': short_sma,
'SMA_long': long_sma,
'symbol': symbol,
},
screen=symbol,
)
def initialize(context):
context.max_notional = 100000.1
context.min_notional = -100000.0
context.stockpct = 0.1
pipe = Pipeline()
attach_pipeline(pipe, name='my_pipeline')
pvol_factor = Parkinson(window_length=30)
pvol_filter = pvol_factor.bottom(500)
sma_30 = SimpleMovingAverage(inputs=[USEquityPricing.close],
window_length=30)
sma_10 = SimpleMovingAverage(inputs=[USEquityPricing.close],
window_length=10)
sma_5 = SimpleMovingAverage(inputs=[USEquityPricing.close],
window_length=5)
priceclose = PriceRange(window_length=1)
price_filter = (priceclose > 10)
dollar_volume = AvgDailyDollarVolumeTraded(window_length=30)
dv_filter = dollar_volume > 100 * 10**5
context.account.leverage = 1
positive_movement = (sma_5 > sma_10)
positive_movement_long = (sma_10 > sma_30)
pipe.add(dv_filter, 'dv_filter')
pipe.add(pvol_factor, 'pvol_factor')
pipe.add(pvol_filter, 'pvol_filter')
pipe.add(price_filter, 'price_filter')
pipe.add(positive_movement, 'positive_movement')
pipe.add(positive_movement_long, 'positive_movement_long')
pipe.set_screen(price_filter & dv_filter & positive_movement & pvol_filter
& positive_movement_long)
schedule_function(func=trader,
date_rule=date_rules.every_day(),
time_rule=time_rules.market_open(hours=0, minutes=5))
schedule_function(func=liquidate,
date_rule=date_rules.every_day(),
time_rule=time_rules.market_open(hours=0, minutes=1))
def make_pipeline():
value = Fundamentals.ebit.latest / Fundamentals.enterprise_value.latest
quality = Fundamentals.roe.latest
positived_sentiment = (twitter_sentiment.bull_scored_messages.latest /
twitter_sentiment.total_scanned_messages.latest)
sentiment_3day = SimpleMovingAverage(inputs=[sentiment.sentiment_signal],
window_length=3)
universe = QTradableStocksUS()
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_winsorized = sentiment_3day.winsorize(min_percentile=0.05,
max_percentile=0.95)
combined_factor = (
value_winsorized.zscore() + quality_winsorized.zscore() +
((positived_sentiment.zscore() + sentiment_winsorized.zscore()) / 2))
longs = combined_factor.top(TOTAL_POSITIONS // 2, mask=universe)
shorts = combined_factor.bottom(TOTAL_POSITIONS // 2, mask=universe)
long_short_screen = (longs | shorts)
pipe = Pipeline(columns={
'longs': longs,
'shorts': shorts,
'combined_factor': combined_factor
},
screen=long_short_screen)
return pipe
def make_pipeline(context):
year_high = ATH()
apr = APR()
price1 = USEquityPricing.close.latest
sma_100 = SimpleMovingAverage(inputs=[USEquityPricing.close],
window_length=100)
sma_filter = (price1 > sma_100)
spy = Q500US()
momentum = (Latest(inputs=[USEquityPricing.close]) / SimpleMovingAverage(
inputs=[USEquityPricing.close], window_length=252)) - 1
apr_filter = (apr > 0.005)
new_high = (year_high <= price1)
dollar_volume = AverageDollarVolume(window_length=30)
high_dv = dollar_volume.percentile_between(90, 100)
mkt_cap = MarketCap().top(UniverseSize)
mo_filter = (momentum > 0)
universe = (new_high & spy & apr_filter & mkt_cap & mo_filter & high_dv
& sma_filter)
mo_rank = momentum.rank(mask=universe, ascending=False)
pipe=Pipeline(
columns={#"year high": year_high ,
# "price" : price1,
"mo_rank" : mo_rank,
"apr" : apr,
},
screen=spy
)
return pipe
def make_pipeline():
# Create Filters for Masks First
latest_close = USEquityPricing.close.latest
small_price = latest_close < 5
# Classifier
nyse_filter = exchange.eq('NYS')
# Pass in the mask
mean_close_10 = SimpleMovingAverage(inputs=[USEquityPricing.close],
window_length=10,
mask=small_price)
mean_close_30 = SimpleMovingAverage(inputs=[USEquityPricing.close],
window_length=30,
mask=small_price)
percent_difference = (mean_close_10 - mean_close_30) / mean_close_30
perc_diff_check = percent_difference > 0
final_filter = perc_diff_check & nyse_filter
return Pipeline(columns={
'Percent Difference': percent_difference,
'30 Day Mean Close': mean_close_30,
'Latest Close': latest_close,
'Positive Percent Diff': perc_diff_check
},
screen=final_filter)
def custom_pipeline(context):
sma_10 = SimpleMovingAverage(inputs = [USEquityPricing.close], window_length=10)
sma_50 = SimpleMovingAverage(inputs = [USEquityPricing.close], window_length=50)
# for testing only
small_universe = SidInList(sid_list = (24))
#changed to be easier to read.
my_screen = (Q500US() & \
(sma_10 > sma_50) & \
(st.bull_scored_messages.latest > 10))
prediction = Prediction(inputs=[st.bull_scored_messages, st.bear_scored_messages, \
USEquityPricing.close, USEquityPricing.open],\
window_length=200, mask=small_universe)
return Pipeline(
columns={
'sma10': sma_10,
'close': USEquityPricing.close.latest,
'prediction': prediction
},
screen=my_screen)
def make_pipeline():
"""
A function to create our dynamic stock selector (pipeline). Documentation
on pipeline can be found here:
https://www.quantopian.com/help#pipeline-title
"""
# Set universe to our filter (the same as Q1500US())
base_universe = filter_universe()
# Basic mean reversion strategy
# 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
# Top and bottom 75 filters using percent_difference
shorts = percent_difference.top(75)
longs = percent_difference.bottom(75)
# Combine these filters into a pipeline screen
securities_to_trade = (shorts | longs)
pipe = Pipeline(columns={
'longs': longs,
'shorts': shorts
},
screen=securities_to_trade)
return pipe
def make_pipeline():
# Base universe set to the QTradableStocksUS
base_universe = QTradableStocksUS()
# Count 10 day min
mean_10 = SimpleMovingAverage(
inputs=[USEquityPricing.close],
window_length=10,
mask=base_universe
)
# Count 30 day max
mean_30 = SimpleMovingAverage(
inputs=[USEquityPricing.close],
window_length=30,
mask=base_universe
)
percent_difference = (mean_10 - mean_30) / mean_30
shorts = percent_difference.top(75)
longs = percent_difference.bottom(75)
# use the model
pipe = Pipeline(
columns={
'longs': longs,
'shorts': shorts,
'Model': Predictor(
window_length=days_for_analysis
,mask=base_universe
)
}
,screen = base_universe
)
return pipe
def make_pipeline(context):
base_universe = Q500US()
rsi_factor = RSI(window_length=5)
fso_factor = FastStochasticOscillator()
beta = SimpleBeta(target=sid(8554), regression_length=260)
pipe = Pipeline(columns={
'rsi': rsi_factor,
'fso': fso_factor,
'beta': beta
},
screen=base_universe & rsi_factor.notnull()
& fso_factor.notnull())
context.sma_short = SimpleMovingAverage(inputs=[USEquityPricing.close],
window_length=20)
pipe.add(context.sma_short, "sma_short")
context.sma_long = SimpleMovingAverage(inputs=[USEquityPricing.close],
window_length=50)
pipe.add(context.sma_long, "sma_long")
return pipe
def make_pipeline():
base_universe = QTradableStocksUS()
sentiment_score = SimpleMovingAverage(
inputs=[stocktwits.bull_minus_bear],
window_length=3,
)
return Pipeline(
columns={
'sentiment_score': sentiment_score,
},
screen=base_universe
)
def make_pipeline():
"""
Create our pipeline.
"""
# Base universe set to the QTradableStocksUS.
base_universe = QTradableStocksUS()
# 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(75)
# Filter to select securities to long.
longs = percent_difference.bottom(75)
# 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():
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
dollar_volume = AverageDollarVolume(window_length=30)
# percentile_between: Factor method returning a Filter
high_dollar_volume = dollar_volume.percentile_between(90, 100)
# above_20: a filter
latest_close = USEquityPricing.close.latest
above_20 = latest_close > 20
# Combine filters
is_tradeable = high_dollar_volume & above_20
return Pipeline(
columns={'percent_difference': percent_difference},
# Apply the filter
screen=is_tradeable)
def make_pipeline():
base_universe = Q500US()
price_moving_average_20 = SimpleMovingAverage(
inputs=[USEquityPricing.close], window_length=20, mask=base_universe)
current_price = USEquityPricing.close.latest
twenty_day_momentum = (current_price -
price_moving_average_20) / price_moving_average_20
# '''
wiki_views = wikipedia_pageviews.views.latest
wiki_views_sma10 = SimpleMovingAverage(inputs=[wikipedia_pageviews.views],
window_length=10,
mask=base_universe)
last_open = USEquityPricing.open.latest
one_day_momentum = (current_price - last_open) / last_open
views_spike_filter = (wiki_views -
wiki_views_sma10) / wiki_views_sma10 > .2
# '''
factor1 = twenty_day_momentum + 5 * one_day_momentum
longs = factor1.top(75)
shorts = factor1.bottom(75)
securities_to_trade = (shorts | longs) & views_spike_filter
return Pipeline(columns={
'longs': longs,
'shorts': shorts
},
screen=securities_to_trade)
def make_pipeline():
"""
A function to create our dynamic stock selector (pipeline). Documentation on
pipeline can be found here: https://www.quantopian.com/help#pipeline-title
"""
sma_short = 35
sma_long = 50
short_sma = SimpleMovingAverage(inputs=[USEquityPricing.close], window_length=sma_short)
long_sma = SimpleMovingAverage(inputs=[USEquityPricing.close], window_length=sma_long)
rsi = RSI(inputs=[USEquityPricing.close], window_length=10)
symbol = SidInList(sid_list=(8554)) # SPY 500
return Pipeline(
columns={
'RSI': rsi,
'SMA_short': short_sma,
'SMA_long': long_sma,
'symbol': symbol,
},
screen=symbol,
)
def make_pipeline():
base_universe = MYQ500US() # Q500US()
# 一週間のリターンをとりあえず過去５日間のリターンと考える
fiveday_return = Returns(window_length=5)
sma30 = SimpleMovingAverage(inputs=[USEquityPricing.close],
window_length=30)
remove_penny_stocks = sma30 > 10.0
remove_expensive_stocks = sma30 < 100.0
pipe = Pipeline(screen=base_universe & remove_penny_stocks
& remove_expensive_stocks,
columns={
'fiveday_return': fiveday_return,
})
return pipe
def make_pipeline():
# Get latest closing price
close_price = USEquityPricing.close.latest
# Calculate 3 day average of bull_minus_bear scores
sentiment_score = SimpleMovingAverage(
inputs=[stocktwits.bull_minus_bear],
window_length=3,
)
# Return Pipeline containing close_price
# and sentiment_score
return Pipeline(columns={
'close_price': close_price,
'sentiment_score': sentiment_score,
})
def make_pipeline():
universe = QTradableStocksUS()
dma_200 = SimpleMovingAverage(inputs=[USEquityPricing.close],
window_length=200,
mask=universe)
close = USEquityPricing.close.latest
longs = close > dma_200
securities_to_trade = (longs)
return Pipeline(
columns={'longs': longs},
screen=(securities_to_trade),
)
def make_pipeline():
universe = StaticAssets((symbols('NFLX')))
sma = SimpleMovingAverage(inputs=[USEquityPricing.close],
window_length = 50)
close = USEquityPricing.close.latest
signal = sma > close
return Pipeline(
columns = {
'sma':sma,
'close':close,
'signal':signal
}, screen = universe
)
def initialize(context):
context.spy = sid(8554)
set_benchmark(context.spy)
# define momentum as latest/SMA, same as to market (SPY) filter
momentum = (Latest(inputs=[USEquityPricing.close]) / SimpleMovingAverage(
inputs=[USEquityPricing.close], window_length=Lookback)) - 1
#mkt_cap = Latest(inputs=[morningstar.valuation.market_cap]) #very slow
#universe = mkt_cap.top(UniverseSize)
dollar_volume = AvgDailyDollarVolumeTraded(window_length=100)
universe = dollar_volume.top(UniverseSize)
momentum_rank = momentum.rank(mask=universe, ascending=False)
long_filter = momentum_rank <= 0.2 * UniverseSize
short_filter = momentum_rank > 0.8 * UniverseSize
apr = APR()
apr_filter = apr > 0.005
pipe = Pipeline()
#pipe.add(momentum, 'momentum') # include for debugging
pipe.add(momentum_rank, 'momentum_rank')
pipe.add(apr, 'apr')
pipe.add(long_filter, 'long')
pipe.add(short_filter, 'short')
pipe.set_screen(universe & apr_filter & (long_filter | short_filter))
pipe = attach_pipeline(pipe, name='equitylongshort')
schedule_function(func=rebalance_positions,
date_rule=date_rules.week_start(days_offset=2),
time_rule=time_rules.market_open(hours=2),
half_days=True)
schedule_function(func=cancel_all,
date_rule=date_rules.week_start(days_offset=2),
time_rule=time_rules.market_close(),
half_days=True)
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
def make_pipeline():
# Create a reference to our trading universe
base_universe = QTradableStocksUS()
# get latest closing price
close_price = USEquityPricing.close.latest
# calculate 3 day MA of bull-minus-bear scores
sentiment_score = SimpleMovingAverage(
inputs=[stocktwits.bull_minus_bear],
window_length=3,
)
# Return Pipeline containing close_price and sentiment_score
return Pipeline(
columns={'close_price': close_price,
'sentiment_score': sentiment_score,
}
screen=base_universe
)
def custom_pipe(context):
pipe = Pipeline()
# bull_1 = st.bullish_intensity.latest
# bear_1 = st.bearish_intensity.latest
# volume = USEquityPricing.volume.latest
sma_scan_7 = SimpleMovingAverage(inputs = [st.total_scanned_messages], window_length=7)
# sma_scan_6 = SimpleMovingAverage(inputs = [st.total_scanned_messages], window_length=6)
# sma_scan_5 = SimpleMovingAverage(inputs = [st.total_scanned_messages], window_length=5)
# sma_scan_4 = SimpleMovingAverage(inputs = [st.total_scanned_messages], window_length=4)
# sma_scan_3 = SimpleMovingAverage(inputs = [st.total_scanned_messages], window_length=3)
# sma_scan_2 = SimpleMovingAverage(inputs = [st.total_scanned_messages], window_length=2)
scan_1 = st.total_scanned_messages.latest
# pipe.add(bull_1, 'bullish_intensity')
# pipe.add(bear_1, 'bearish_intensity')
# pipe.add(st.bear_scored_messages.latest, 'bear_scored_messages')
# pipe.add(st.bull_scored_messages.latest, 'bull_scored_messages')
pipe.add(scan_1, 'scan_1')
# pipe.add(sma_scan_2, 'sma_scan_2')
# pipe.add(sma_scan_3, 'sma_scan_3')
# pipe.add(sma_scan_4, 'sma_scan_4')
# pipe.add(sma_scan_5, 'sma_scan_5')
# pipe.add(sma_scan_6, 'sma_scan_6')
pipe.add(sma_scan_7, 'sma_scan_7')
# pricing = USEquityPricing.close.latest
# Base universe set to the Q500US
base_universe = Q1500US()
pipe.set_screen(
(base_universe)
# (scan_1 < 10)
# (pricing < 15.00) &
# (pricing > 5.00) &
# (volume > 1000000) &
# (
# (bull_1 > 0) |
# (bear_1 > 0)
# )
# (scan_1 < sma_scan_7)
)
return pipe
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 initialize(context):
"""
Called once at the start of the algorithm.
"""
context.stocks = [sid(8554), sid(38054), sid(40516)] # spy, vxx, xiv
context.spy = sid(8554)
context.xiv = sid(40516)
context.vxx = sid(38054)
context.sell_price = 0
context.vix_last_price = 0
set_benchmark(sid(40516))
context.allocation = [0,0,0]
# Rebalance every day, 1 hour after market open.
schedule_function(my_rebalance, date_rules.every_day(), time_rules.market_open(minutes=1))
#schedule_function(check_xiv, date_rules.every_day(), time_rules.market_close(minutes=60))
# Record tracking variables at the end of each day.
schedule_function(my_record_vars, date_rules.every_day(), time_rules.market_close())
#Set slippage and commission
#set_slippage(slippage.VolumeShareSlippage(volume_limit=0.025, price_impact=0.1))
#set_commission(commission.PerShare(cost=0.0075, min_trade_cost=1))
# fetch VIX data
pipe = Pipeline()
attach_pipeline(pipe, 'my_pipeline')
#get VIX at market open
pipe.add(GetVIX(inputs=[cboe_vix.vix_close]), 'VixOpen')
pipe.add(GetVIX(inputs=[cboe_vvix.vvix]), 'Vvix')
pipe.add(GetVIXma(inputs=[cboe_vvix.vvix], window_length = 5), 'Vvix_ma5')
#get VIX average in the last 2 days
pipe.add(SimpleMovingAverage(inputs=[cboe_vix.vix_close], window_length=2), 'vix_mean')
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
def make_pipeline():
base_universe = Q500US()
# 一週間のリターンをとりあえず過去５日間のリターンと考える
# 本当は，休日の事も考えなくては行けないが，とりあえず決め打ち．
fiveday_return = Returns(window_length=5)
# 過去30日の移動平均を取得
sma30 = SimpleMovingAverage(inputs=[USEquityPricing.close],
window_length=30)
# 移動平均が10ドル以上
remove_penny_stocks = sma30 > 10.0
# 過去30日の売買高
dollar_volume = AverageDollarVolume(window_length=30)
# 上位１０％だけを対象
high_dollar_volume = dollar_volume.percentile_between(90, 100)
pipe = Pipeline(screen=base_universe & remove_penny_stocks
& high_dollar_volume,
columns={
'fiveday_return': fiveday_return,
})
return pipe
def make_pipeline():
universe = StaticAssets(symbols('SPY'))
close = USEquityPricing.close.latest
sma_200 = SimpleMovingAverage(
inputs = [USEquityPricing.close],
window_length = 200,
mask = universe
)
logic = close > sma_200
return Pipeline(
columns = {
'close':close,
'sma_200':sma_200,
'logic':logic
}, screen = universe
)
def make_pipeline():
"""
A function to create our dynamic stock selector (pipeline). Documentation
on pipeline can be found here:
https://www.quantopian.com/help#pipeline-title
"""
# Base universe set to the QTradableStocksUS
base_universe = StaticAssets(SYMBOLS)
n = 10
ma = SimpleMovingAverage(inputs=[USEquityPricing.close],
window_length=n,
mask=base_universe)
# Factor of yesterday's close price.
yesterday_close = USEquityPricing.close.latest
pipe = Pipeline(columns={
'close': yesterday_close,
'ma': ma,
},
screen=base_universe)
return pipe
def make_pipeline():
"""
pipeline を作る
make_pipeline を作ったほうが，research にもコピペして使えるし，テストや修正も簡単に出来るので，幸せになれます
"""
# クロスモメンタム
cross_momentum = CrossSectionalMomentum()
# Returns で過去252分全てのクローズベースのリターンを取得
abs_momentum = Returns(input=[USEquityPricing.close], window_length = 252)
# 流動性がある株式だけ取引する.過去20日間，平均1千万ドル平均の取引高（price*volume）があるものだけを取引
dollar_volume = AverageDollarVolume(window_length=20)
is_liquid = (dollar_volume > le7)
# 過去200日平均で株価5ドル以下のペニーストックはトレードしない．
sma_200 = SimpleMovingAverage(inputs = [USEquityPricing.close], window_length=200)
not_a_penny_stock = (sma_200 > 5)
# 不必要な銘柄は取り除く
initial_screen = (is_liquid & not_a_penny_stock)
# cross momentum を適用したあとに，ランク付けをする
combined_rank = (cross_momentum.rank(mask=initial_screen) + abs_momentum.rank(mask=initial_screen))
# top 5 % をロング
longs = combined_rank.percentile_between(95, 100)
shorts = combined_rank.percentile_between(0, 5)
# パイプラインにロングショートする銘柄を取得
pipe_screen = (longs | shorts)
pipe_columns = {
'longs': longs,
'shorts': shorts,
'combined_rank': combined_rank,
'abs_momentum': abs_momentum,
'cross_momentum': cross_momentum,
}
# パイプ作成
pipe = Pipeline(columns=pipe_columns, screen=pipe_screen)
return pipe
def public_opinion():
qtu = QTradableStocksUS()
sentiment_stocktwits = SimpleMovingAverage(
inputs=[stocktwits.bull_minus_bear],
window_length=2,
)
sentiment_news = SimpleMovingAverage(
inputs=[sentiment.sentiment_signal],
window_length=2
)
sentiment_factor = sentiment_stocktwits + sentiment_news
sentiment_factor_winsorized = sentiment_factor.winsorize(
min_percentile=0.10,
max_percentile=0.90)
sentiment_factor_rank = sentiment_factor_winsorized.rank().zscore()
screen = qtu & ~sentiment_stocktwits.isnull() & ~sentiment_news.isnull() & sentiment_factor.isfinite()
return sentiment_factor_rank, screen
