from quantopian.interactive.data.sentdex import sentiment
from quantopian.pipeline.filters.morningstar import Q500US, Q1500US, Q3000US

from quantopian.pipeline import Pipeline
from quantopian.pipeline.data import USEquityPricing
from quantopian.pipeline.filters import QTradableStocksUS
from quantopian.pipeline.factors import SimpleMovingAverage
from quantopian.pipeline.data.psychsignal import stocktwits
from quantopian.pipeline.domain import US_EQUITIES

def make_pipeline():
    return Pipeline()

from quantopian.research import run_pipeline

result = run_pipeline(make_pipeline(), start_date = '2002-02-01', end_date = '2020-01-01')

len(result)

assets = result.index.levels[1].unique()
len(assets)

result.head()

from quantopian.pipeline.data.sentdex import sentiment

def make_pipeline():
    # Create a reference to our trading universe
    base_universe = USEquityPricing.specialize(US_EQUITIES)

    # 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 that has our trading universe as screen
    return Pipeline(
        columns={
            'close_price': close_price,
            'sentiment_score': sentiment_score,
        },
        screen=base_universe
    )

result = run_pipeline(make_pipeline(), start_date = '2003-01-01', end_date = '2019-12-31')

result.head()

assets = result.index.levels[1].unique()
len(assets)

pricing = get_pricing(assets, start_date = '2003-01-01', end_date = '2019-12-31', fields = 'open_price')

result.tail(10)

import alphalens

factor_data = alphalens.utils.get_clean_factor_and_forward_returns(factor=result['sentiment'],
                                                                   prices = pricing,
                                                                   quantiles = 2,
#quantiles: a factor that is going to range from low to high(eg. so cannot use price to book ratio(a company might be worth less than its tangible assets))
#quantiles: have to use 2 quantiles because if we use more it will evenly distribute by sample number(meaning it will relicate numbers rather than use -3,-2,-1 etc to 6, it will eg. -3,-3,-3,-1,-1,1,1,2,4,6,6)
                                                                   periods = (20,40,60)
                                                                  )

factor_data.head()

alphalens.tears.create_full_tear_sheet(factor_data, long_short=True )