Modified "How to Get an Allocation" to better suit Sentdex¶

import matplotlib.pyplot as plt
import pandas as pd

# http://blaze.readthedocs.io/en/latest/index.html
import blaze as bz

from zipline.utils.tradingcalendar import get_trading_days

from quantopian.interactive.data.sentdex import sentiment

type(sentiment)

aapl_sid = symbols('BAC').sid

# Look at a sample of AAPL sentiment data starting from 2013-12-01.
sentiment[(sentiment.sid == aapl_sid) & (sentiment.asof_date >= '2013-12-01')].peek()

num_sids = bz.compute(sentiment.sid.distinct().count())
print 'Number of sids in the data: %d' % num_sids

# Mask for trading days.
date_mask = sentiment.asof_date.isin(
    get_trading_days(pd.Timestamp('2014-06-01'), pd.Timestamp('2014-12-01'))
)

# Mask for AAPL.
stock_mask = (sentiment.sid == aapl_sid)

# Blaze expression for AAPL sentiment on trading days between 12/2013 and 12/2014
sentiment_2014_expr = sentiment[date_mask & stock_mask].sort('asof_date')

sentiment_2014_df = bz.compute(sentiment_2014_expr)

pd.rolling_mean(sentiment_2014_df.set_index('asof_date').sentiment_signal, window=5).plot()

from quantopian.pipeline import Pipeline
from quantopian.research import run_pipeline

from quantopian.pipeline.factors import SimpleMovingAverage
from quantopian.pipeline.filters.morningstar import Q1500US

# Sentdex Sentiment free from 15 Oct 2012 to 1 month ago.
from quantopian.pipeline.data.sentdex import sentiment

# EventVestor Earnings Calendar free from 01 Feb 2007 to 1 year ago.
from quantopian.pipeline.factors.eventvestor import (
    BusinessDaysUntilNextEarnings,
    BusinessDaysSincePreviousEarnings,
)

# EventVestor Mergers & Acquisitions free from 01 Feb 2007 to 1 year ago.
from quantopian.pipeline.filters.eventvestor import IsAnnouncedAcqTarget

from quantopian.pipeline.factors import BusinessDaysSincePreviousEvent

def make_pipeline():
    
    # 5-day sentiment moving average factor.
    sentiment_factor = SimpleMovingAverage(inputs=[sentiment.sentiment_signal], window_length=5)
    
    # Filter for stocks that are not within 2 days of an earnings announcement.
    not_near_earnings_announcement = ~((BusinessDaysUntilNextEarnings() <= 2)
                                | (BusinessDaysSincePreviousEarnings() <= 2))
    
    # Filter for stocks that are announced acquisition target.
    not_announced_acq_target = ~IsAnnouncedAcqTarget()
    
    # Filter for stocks that had their sentiment signal updated in the last day.
    new_info = (BusinessDaysSincePreviousEvent(inputs=[sentiment.asof_date.latest]) <= 1)
    
    # Our universe is made up of stocks that have a non-null sentiment signal that was updated in
    # the last day, are not within 2 days of an earnings announcement, are not announced acquisition
    # targets, and are in the Q1500US.
    universe = (Q1500US() 
                & sentiment_factor.notnull() 
                & not_near_earnings_announcement
                & not_announced_acq_target
                & new_info)
    
    # Our pipeline is defined to have the rank of the sentiment_factor as the only column. It is
    # screened by our universe filter.
    pipe = Pipeline(
        columns={
            'sentiment': sentiment_factor.rank(mask=universe, method='average'),
        },
        screen=universe
    )
    
    return pipe

result = run_pipeline(make_pipeline(), start_date='2015-01-01', end_date='2016-01-01')

# All assets that were returned in the pipeline result.
assets = result.index.levels[1].unique()

# We need to get a little more pricing data than the length of our factor so we 
# can compare forward returns. We'll tack on another month in this example.
pricing = get_pricing(assets, start_date='2015-01-01', end_date='2016-02-01', fields='open_price')

import alphalens

alphalens.tears.create_factor_tear_sheet(factor=result['sentiment'],
                                         prices=pricing,
                                         quantiles=3,
                                         periods=(1,5,10))

def make_pipeline():
    
    # 5-day sentiment moving average factor.
    sentiment_factor = sentiment.sentiment_signal.latest
    
     # Filter for stocks that are not within 2 days of an earnings announcement.
    #not_near_earnings_announcement = ~((BusinessDaysUntilNextEarnings() <= 2)
    #                            | (BusinessDaysSincePreviousEarnings() <= 2))
    
    # Filter for stocks that are announced acquisition target.
    #not_announced_acq_target = ~IsAnnouncedAcqTarget()
    
    # Filter for stocks that had their sentiment signal updated in the last day.
    new_info = (BusinessDaysSincePreviousEvent(inputs=[sentiment.asof_date.latest]) <= 1)
    
    # Our universe is made up of stocks that have a non-null sentiment signal that was updated in
    # the last day, are not within 2 days of an earnings announcement, are not announced acquisition
    # targets, and are in the Q1500US.
    universe = (Q1500US() 
                & sentiment_factor.notnull() 
                & new_info)
    
    # A classifier to separate the stocks into quantiles based on sentiment rank.

    
    # Go short the stocks in the 0th quantile, and long the stocks in the 2nd quantile.
    pipe = Pipeline(
        columns={
            'sentiment': sentiment_factor,
            'longs': (sentiment_factor >=4),
            'shorts': (sentiment_factor<=2),
        },
        screen=universe
    )
    
    return pipe

bt = get_backtest('5882a4b48aab61619ac8b0ba')

bt.create_full_tear_sheet()