Alphalens boilerplate¶
In [1]:
from quantopian.research import run_pipeline
from quantopian.pipeline import Pipeline
from quantopian.pipeline import factors, filters, classifiers
from quantopian.pipeline.filters import StaticAssets
from quantopian.pipeline.factors import CustomFactor, Returns, AverageDollarVolume, SimpleMovingAverage
from quantopian.pipeline.data.builtin import USEquityPricing
from quantopian.pipeline.classifiers.morningstar import Sector
from quantopian.pipeline.filters.morningstar import Q500US, Q1500US, Q3000US
import math
import datetime
import numpy as np
import pandas as pd
MORNINGSTAR_SECTOR_CODES = {
-1: 'Misc',
101: 'Basic Materials',
102: 'Consumer Cyclical',
103: 'Financial Services',
104: 'Real Estate',
205: 'Consumer Defensive',
206: 'Healthcare',
207: 'Utilities',
308: 'Communication Services',
309: 'Energy',
310: 'Industrials',
311: 'Technology' ,
}
## Helper functions
def high_volume_universe(top_liquid, min_price = None, min_volume = None):
"""
Computes a security universe of liquid stocks and filtering out
hard to trade ones
Returns
-------
high_volume_tradable - zipline.pipeline.filter
"""
if top_liquid == 500:
universe = Q500US()
elif top_liquid == 1500:
universe = Q1500US()
elif top_liquid == 3000:
universe = Q3000US()
else:
universe = filters.make_us_equity_universe(
target_size=top_liquid,
rankby=factors.AverageDollarVolume(window_length=200),
mask=filters.default_us_equity_universe_mask(),
groupby=Sector(),
max_group_weight=0.3,
smoothing_func=lambda f: f.downsample('month_start'),
)
if min_price is not None:
price = SimpleMovingAverage(inputs=[USEquityPricing.close],
window_length=21, mask=universe)
universe &= (price >= min_price)
if min_volume is not None:
volume = SimpleMovingAverage(inputs=[USEquityPricing.volume],
window_length=21, mask=universe)
universe &= (volume >= min_volume)
return universe
def construct_factor_history(factor_cls, start_date='2015-10-1', end_date='2016-2-1',
factor_name='factor', top_liquid=500,
sector_column=None):
"""
Creates a DataFrame containing daily factor values and sector codes for a liquidity
constrained universe. The returned DataFrame is can be used in the factor tear sheet.
"""
ok_universe = high_volume_universe(top_liquid)
factor = factor_cls(mask=ok_universe)
sector = Sector(mask=ok_universe)
pipe = Pipeline()
pipe.add(factor, factor_name)
if sector_column is not None: # this is very slow too
pipe.add(sector, sector_column)
pipe.set_screen(ok_universe)
daily_factor = run_pipeline(pipe, start_date=start_date, end_date=end_date, chunksize=250)
return daily_factor.dropna()
def get_daily_price(sid_universe, start_date, end_date, extra_days_before=0, extra_days_after=0):
"""
Creates a DataFrame containing daily percentage returns and price
"""
extra_days = math.ceil(extra_days_before * 365.0/252.0) + 3 # just to be sure
start_date = datetime.datetime.strptime(start_date, "%Y-%m-%d") - datetime.timedelta(days=extra_days)
start_date = start_date.strftime("%Y-%m-%d")
extra_days = math.ceil(extra_days_after * 365.0/252.0) + 3 # just to be sure
end_date = datetime.datetime.strptime(end_date, "%Y-%m-%d") + datetime.timedelta(days=extra_days)
end_date = end_date.strftime("%Y-%m-%d")
pricing = get_pricing(sid_universe, start_date=start_date, end_date=end_date, fields='open_price')
return pricing
#
# 'run_tear_sheet' glues all the function together to make life easier to run the tear sheet on a pipeline factor
#
import alphalens
import alphalens.performance as perf
import alphalens.utils as utils
def run_tear_sheet(factor,
factor_name,
start_date,
end_date,
top_liquid,
show_sector_plots,
avgretplot,
periods,
quantiles,
bins,
filter_zscore,
long_short,
prices_cache = None):
sector_column = 'sector_code' if show_sector_plots else None
days_before, days_after = (0,0)
if avgretplot is not None:
days_before, days_after = avgretplot
days_after = max(days_after, max(periods) + 1)
#
## Run the Pipeline
#
print 'construct factor history'
factor = construct_factor_history(factor, start_date=start_date, end_date=end_date,
factor_name=factor_name, top_liquid=top_liquid,
sector_column=sector_column)
#
## Get prices
#
sid_universe = set( factor.index.levels[1].unique() )
if prices_cache is not None:
cached_sids = set(prices_cache.columns)
sid_universe -= cached_sids
print 'Get pricing for %d entries' % len(sid_universe)
if sid_universe:
prices = get_daily_price(sid_universe, start_date=start_date, end_date=end_date,
extra_days_before=days_before, extra_days_after=days_after)
if prices_cache is not None:
prices = pd.concat([prices, prices_cache], axis=1)
else:
prices = prices_cache
#
## Use Alphalens to create a factor tear sheet
#
print 'Alphalens'
if len(np.isinf(factor[factor_name])) > 0:
print 'Dropping inf or -inf values from factor'
factor[factor_name] = factor[factor_name].replace([np.inf, -np.inf], np.nan)
sectors_series = factor[sector_column] if show_sector_plots else None
factor_data = alphalens.utils.get_clean_factor_and_forward_returns(factor=factor[factor_name],
prices=prices,
groupby=sectors_series,
by_group=False,
quantiles=quantiles,
bins=bins,
periods=periods,
filter_zscore=filter_zscore,
groupby_labels=MORNINGSTAR_SECTOR_CODES)
if avgretplot:
alphalens.tears.create_event_returns_tear_sheet(factor_data=factor_data,
prices=prices,
avgretplot=avgretplot,
long_short=long_short,
by_group=show_sector_plots)
#alphalens.tears.create_full_tear_sheet(factor_data=factor_data,
# long_short=long_short,
# group_adjust=False,
# by_group=show_sector_plots)
alphalens.plotting.plot_quantile_statistics_table(factor_data)
alphalens.tears.create_returns_tear_sheet(factor_data=factor_data,
long_short=long_short,
by_group=show_sector_plots)
return prices
Define our factor¶
In [2]:
#
# Many technical indicators are already defined in Pipeline but we can build our own CustomFactor too
#
from quantopian.pipeline.factors import RSI, BollingerBands, Aroon, FastStochasticOscillator
from quantopian.pipeline.factors import IchimokuKinkoHyo, RateOfChangePercentage, TrueRange
from quantopian.pipeline.factors import MovingAverageConvergenceDivergenceSignal, AnnualizedVolatility
Define settings¶
In [3]:
factor_name = 'factor'
start_date = '2009-01-01'
end_date = '2014-05-01'
top_liquid = 500
show_sector_plots = False
# alphalens specific
periods = (1, 3)
quantiles = 5
bins = None
avgretplot = (1, 10) # use None to avoid plotting or (days_before, days_after)
filter_zscore = None
long_short = True
prices_cache = None # this saves lots of time when running tear sheet multiple times
Run the tear sheet¶
In [4]:
def factor(mask):
return -RSI(mask=mask, window_length=15)
prices_cache = \
run_tear_sheet( factor = factor,
factor_name = factor_name,
start_date = start_date,
end_date = end_date,
top_liquid = top_liquid,
show_sector_plots = show_sector_plots,
avgretplot = avgretplot,
periods = periods,
quantiles = quantiles,
bins = bins,
filter_zscore = filter_zscore,
long_short = long_short,
prices_cache = prices_cache)
