Alpha research - Quality companies¶

# Research-specific imports
from quantopian.research import run_pipeline
from alphalens.utils import get_clean_factor_and_forward_returns
from alphalens.tears import create_summary_tear_sheet, create_full_tear_sheet


from quantopian.pipeline import Pipeline
from quantopian.pipeline.factors import CustomFactor
from quantopian.pipeline.data.builtin import EquityPricing
from quantopian.pipeline.data import Fundamentals
from quantopian.pipeline.data import factset


from quantopian.pipeline.filters import QTradableStocksUS

import numpy as np
import pandas as pd
from datetime import datetime, timedelta

# Pipeline parameters
USE_SECTORS = True
PIPE_NORMALIZE = True
TRAIN_START="2010-01-01"
TEST_START="2015-01-01"
VAL_START="2018-01-01"

# Utility functions

def price_data(pipeline_output, start=TRAIN_START, end=TEST_START):
    tickerlist = pipeline_output.index.levels[1].unique()
    # Subtract/add one month from bounds
    start_minus_one = datetime.strftime(datetime.strptime(start, "%Y-%m-%d") - timedelta(30), "%Y-%m-%d")
    end_plus_one = datetime.strftime(datetime.strptime(end, "%Y-%m-%d") + timedelta(30), "%Y-%m-%d")
    
    return get_pricing(symbols=tickerlist, start_date=start_minus_one, end_date=end_plus_one, fields="open_price"
    )

def make_pipeline():
    # Measures a company's asset growth rate.
    sector = factset.RBICSFocus.l1_name.latest
    mask = (sector != "Finance")
    
    roic = Fundamentals.roic.latest
    ltd_to_eq = Fundamentals.long_term_debt_equity_ratio.latest
    fcf_yield = Fundamentals.fcf_yield.latest
    
    factor = roic.rank(mask=mask) + \
                ltd_to_eq.rank(ascending=False, mask=mask) + \
                fcf_yield.rank(mask=mask)
        
    return Pipeline(
        columns={'signal': factor.rank(),
                 'sector':sector},screen=(QTradableStocksUS()) & mask)


pipeline_out = run_pipeline(pipeline=make_pipeline(), start_date=TRAIN_START, end_date=TEST_START)
factor_data = pipeline_out["signal"]
sector = pipeline_out["sector"]
factor_data.head()

prices = price_data(factor_data)

merged_data = get_clean_factor_and_forward_returns(
  factor=factor_data, 
  prices=prices,
  groupby=sector,
  periods=(5, 10, 20)
)
merged_data.head()

create_full_tear_sheet(merged_data, by_group=True)