# First, import your uploaded dataset:
## from quantopian.pipeline.data.user_[user_ID] import [dataset name]
from quantopian.pipeline.data.user_[user_ID] import campaign_contributions

from quantopian.pipeline import Pipeline
from quantopian.pipeline.data import Fundamentals
from quantopian.research import run_pipeline
from quantopian.pipeline.factors import BusinessDaysSincePreviousEvent, SimpleMovingAverage
from quantopian.pipeline.filters import QTradableStocksUS
import pandas as pd

# Set up the Pipeline:
def make_pipeline():
    
    base_universe = QTradableStocksUS()
    
    # Factor for number of business days since data was last updated.
    days_since_last_update = BusinessDaysSincePreviousEvent(
        inputs=[campaign_contributions.asof_date.latest]
    )
    
    # A pipeline screen that ensures uploaded data are not 3 or more business days old.
    has_recent_update = (days_since_last_update < 3)
    universe = (has_recent_update & base_universe)
    
    # Factor for 6-month simple moving average of campaign contributions count:
    score = SimpleMovingAverage(
        inputs=[campaign_contributions.count], 
        window_length= 252/2
    )
    
    # Factor for sector code:
    sector = Fundamentals.morningstar_sector_code.latest
    
    # Filter out NaNs and 0s
    screen_null = score.notnull()
    screen_zeros = (score != 0.0)
    
    pipe = Pipeline(
        columns={
            'Score': score,
            'Sector': sector
        }, 
        screen= screen_null & screen_zeros & universe
    )
    
    return pipe

# Define a time range over which to run the pipeline:
start_date = '2017-01-01'
end_date = '2017-12-31'
results = run_pipeline(make_pipeline(), start_date, end_date)

results.head()

# Import Alphalens:
import alphalens as al

# Retrieve list of assets from Pipeline output:
asset_list = results.index.levels[1].unique()

# Define time range over which to analyze the factor over:
start_date = '2017-01-01'
end_date = '2018-05-31'

# Obtain pricing information on list of assets for input to alphalens:
prices = get_pricing(
    asset_list,
    start_date=start_date,
    end_date=end_date,
    fields='open_price'
)

# Define sector labels for factor analysis grouping:
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' ,    
}

# First, we get our factor categorized by sector code and calculate our forward returns. 
# The forward returns are the returns that we would have received for holding each security over 
# the day periods ending on the given date, passed in through the periods parameter.
factor_data = al.utils.get_clean_factor_and_forward_returns(
    results['Score'],
    prices=prices,
    groupby=results['Sector'],
    binning_by_group=True,
    groupby_labels=MORNINGSTAR_SECTOR_CODES,
    quantiles=5,
    periods=(10, 21, 63)
)

# Use composed factor data to create full tearsheet
al.tears.create_full_tear_sheet(factor_data, by_group=True);