def make_pipeline():
value = Fundamentals.ebit.latest / Fundamentals.enterprise_value.latest
sentiment_score = SimpleMovingAverage(
inputs=[stocktwits.total_scanned_messages],
window_length=21,
)
ty = Fundamentals.total_yield.latest
wps = Fundamentals.working_capital_per_share.latest
gro = Fundamentals.growth_score.latest
dollar_volume = AverageDollarVolume(window_length=63)
universe = QTradableStocksUS()
dollar_winsorize = dollar_volume.winsorize(min_percentile=0.2, max_percentile=0.8)
value_winsorized = value.winsorize(min_percentile=0.05, max_percentile=0.95)
sentiment_score_winsorized = sentiment_score.winsorize(min_percentile=0.05, max_percentile=0.95)
eps_wisorized = wps.winsorize(min_percentile=0.05, max_percentile=0.95)
ty_winsorized = ty.winsorize(min_percentile=0.05, max_percentile=0.95)
gro_winsorize = gro.winsorize(min_percentile=0.05, max_percentile=0.95)
combined_factor = (
value_winsorized.zscore() *0.15
+ gro_winsorize.zscore() *0.25
+ sentiment_score_winsorized.zscore()* 0.15
+ eps_wisorized.zscore() *0.15
+ ty_winsorized.zscore() *0.15
+ dollar_winsorize.zscore() *0.15
)
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():
"""
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,
)
sentiment_week = SimpleMovingAverage(
inputs=[stocktwits.bull_minus_bear],
window_length=7,
)
sentiment_2weeks = SimpleMovingAverage(
inputs=[stocktwits.bull_minus_bear],
window_length=15,
)
dollar_volume = AverageDollarVolume(window_length=15)
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)
sentiment_week_winsorized = sentiment_week.winsorize(min_percentile=0.05, max_percentile=0.95)
sentiment_2weeks_winsorized = sentiment_2weeks.winsorize(min_percentile=0.05, max_percentile=0.95)
dollar_volume_winsorized = dollar_volume.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() +
dollar_volume_winsorized.zscore() +
sentiment_score_winsorized.zscore()/sentiment_2weeks_winsorized.zscore() +
sentiment_week_winsorized.zscore()/sentiment_2weeks_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