Notebook

Alphalens - Open Source Factor Analysis¶

In [1]:
import numpy as np
import pandas as pd
import alphalens
from quantopian.research import run_pipeline
from quantopian.pipeline import Pipeline
from quantopian.pipeline.data.builtin import USEquityPricing
from quantopian.pipeline.data import morningstar
from quantopian.pipeline.factors import CustomFactor, Latest, Returns, RSI, EWMA as ewma, SimpleMovingAverage
from quantopian.pipeline.filters import Q1500US

Define the Factors¶

In [2]:
#Create the classes for many rav variables and factors

class LowVol(CustomFactor):
    inputs = [Returns(window_length=2)]
    window_length = 25
    
    def compute(self, today, assets, out, close):
        out[:] = -np.nanstd(close, axis=0)

class growth(CustomFactor):
    window_length = 1
    inputs = [morningstar.operation_ratios.revenue_growth]
    
    def compute(self, today, assets, out, growth):
        out[:] = growth
        
class sus_growth(CustomFactor):
    window_length = 1
    inputs = [morningstar.valuation_ratios.sustainable_growth_rate]
    
    def compute(self, today, assets, out, sustainable_growth_rate):
        out[:] = sustainable_growth_rate

#Quality
class turns(CustomFactor):
    window_length = 1
    inputs = [morningstar.operation_ratios.assets_turnover]
    
    def compute(self, today, assets, out, assets_turnover):
        out[:] = assets_turnover

class roic(CustomFactor):
    window_length = 1
    inputs = [morningstar.operation_ratios.roic]
    def compute(self, today, assets, out, roic):
        out[:] = roic

class margins(CustomFactor):
    window_length = 1
    inputs = [morningstar.operation_ratios.ebitda_margin]
    def compute(self, today, assets, out, ebitda_margin):
        out[:] = ebitda_margin

#Valuation
class peg_ratio(CustomFactor):
    window_length = 1
    inputs = [morningstar.valuation_ratios.peg_ratio]
    
    def compute(self, today, assets, out, peg_ratio):
        out[:] = np.where(peg_ratio <= 0, 0, 1/peg_ratio)
        
class pe_ratio(CustomFactor):
    window_length = 1
    inputs = [morningstar.valuation_ratios.pe_ratio]
    def compute(self, today, assets, out, pe_ratio):
        out[:] = np.where(pe_ratio <= 0, 0, 1/pe_ratio)

class pb_ratio(CustomFactor):
    window_length = 1
    inputs = [morningstar.valuation_ratios.pb_ratio]
    def compute(self, today, assets, out, pb_ratio):
        out[:] = np.where(pb_ratio <= 0, 0, 1/pb_ratio)

class total_yield(CustomFactor):
    window_length = 1
    inputs = [morningstar.valuation_ratios.total_yield]
    def compute(self, today, assets, out, total_yield):
        out[:] = total_yield
        
class ev_ebitda(CustomFactor):
    window_length = 1
    inputs = [morningstar.valuation_ratios.ev_to_ebitda]
    def compute(self, today, assets, out, ev_to_ebitda):
        out[:] = np.where(ev_to_ebitda <= 0, 0, 1/ev_to_ebitda)

class liquidity(CustomFactor):   
    inputs = [USEquityPricing.volume, USEquityPricing.close] 
    window_length = 21

    def compute(self, today, assets, out, volume, close): 
        out[:] = (volume * close).mean(axis=0)
        
class sector(CustomFactor):
    inputs = [morningstar.asset_classification.morningstar_sector_code]
    window_length = 1
    def compute(self, today, assets, out, morningstar_sector_code):
        out[:] = morningstar_sector_code[-1]
        
class AvgDailyDollarVolumeTraded(CustomFactor):
    
    inputs = [USEquityPricing.close, USEquityPricing.volume]
    window_length = 20
    
    def compute(self, today, assets, out, close_price, volume):
        out[:] = np.mean(close_price * volume, axis=0)

class PriceReturn(CustomFactor):  
    inputs = [USEquityPricing.close]
    window_length = 2
    
    def compute(self, today, assets, out, close):
        out[:] = close[-1]/close[0]

Set Universe¶

In [3]:
universe = Q1500US()

Create the Pipeline¶

In [4]:
pipe = Pipeline(
    columns={
        #'LowVol' : LowVol(mask=universe),
        #'ROIC': roic(mask=universe),
        'PE': pe_ratio(mask=universe),
        #'Growth': growth(mask=universe),
        #'SusGrowth': sus_growth(mask=universe),
        #'Turns': turns(mask=universe),
        #'Margins': margins(mask=universe),
        #'PEG': peg_ratio(mask=universe),
        #'PB': pb_ratio(mask=universe),
        #'TotalYield': total_yield(mask=universe),
        'EV_EBITDA': ev_ebitda(mask=universe),
        'PriceReturn': PriceReturn(mask=universe),
        'Sector': sector(mask=universe)
    },
    screen=universe
)

Run the Pipeline¶

In [5]:
results = run_pipeline(pipe, '2012-06-30', '2016-06-30')
In [6]:
results.head()
Out[6]:
EV_EBITDA PriceReturn Sector
2012-07-02 00:00:00+00:00 Equity(2 [ARNC]) 0.067388 1.028235 101.0
Equity(24 [AAPL]) 0.099307 1.026795 311.0
Equity(52 [ABM]) 0.121308 0.985880 310.0
Equity(53 [ABMD]) 0.008095 1.041534 206.0
Equity(62 [ABT]) 0.171444 1.024622 206.0
In [8]:
#Develop Factors for Testing
factor_name = 'EV_EBITDA'

results['factor'] = results.groupby([results.index.get_level_values(0),'Sector'])[factor_name].apply(lambda x: x.fillna(x.median()))

zscore = lambda x: (x - x.mean()) / x.std()
results['factor_score'] = results.groupby([results.index.get_level_values(0),'Sector'])['factor'].transform(zscore)

#Reset Factor to mean where abs(factor_score) > 3
results['factor_adj'] = np.where(abs(results['factor_score']) > 3,np.nan,results['factor'])
results['factor_adj'] = results.groupby([results.index.get_level_values(0),'Sector'])['factor_adj'].apply(lambda x: x.fillna(x.median()))
results['factor_score_adj'] = results.groupby([results.index.get_level_values(0),'Sector'])['factor_adj'].transform(zscore)

#Look ahead forward return
results['forward_return_1'] = results.groupby(results.index.get_level_values(1))['PriceReturn'].apply(lambda x: x.shift(-1))

Get pricing¶

In [12]:
assets = results.index.levels[1].unique()
# Make sure to extend the pricing a bit to get a full set of returns.
pricing = get_pricing(assets, start_date='2012-06-30', end_date='2016-07-31', fields='open_price')
In [21]:
results.head()
Out[21]:
EV_EBITDA PriceReturn Sector factor factor_score factor_adj factor_score_adj forward_return_1
2012-07-02 00:00:00+00:00 Equity(2 [ARNC]) 0.067388 1.028235 101.0 0.067388 -0.664975 0.067388 -0.664975 0.987414
Equity(24 [AAPL]) 0.099307 1.026795 311.0 0.099307 -0.090975 0.099307 -0.032519 1.014914
Equity(52 [ABM]) 0.121308 0.985880 310.0 0.121308 -0.082475 0.121308 -0.021833 0.992012
Equity(53 [ABMD]) 0.008095 1.041534 206.0 0.008095 -1.035993 0.008095 -1.186339 1.028046
Equity(62 [ABT]) 0.171444 1.024622 206.0 0.171444 0.901986 0.171444 1.221839 1.002172

Build Tearsheet¶

AlphaLens builds a single factor tearsheet.

In [20]:
#First, let's look at our standard factor
factor_data = alphalens.utils.get_clean_factor_and_forward_returns(results['EV_EBITDA'],
                                                                   pricing,
                                                                   quantiles=10,
                                                                   periods=(1,5,10))

alphalens.tears.create_full_tear_sheet(factor_data)
Quantiles Statistics
min max mean std count count %
factor_quantile
1 0.115815 1.008523 0.969218 0.028089 150204 10.033386
2 0.919959 1.016150 0.987489 0.010797 149678 9.998250
3 0.933965 1.020658 0.992675 0.009579 149602 9.993173
4 0.944708 1.025122 0.996145 0.009031 149720 10.001055
5 0.951937 1.028907 0.998994 0.008774 149739 10.002325
6 0.959253 1.033234 1.001705 0.008692 149476 9.984757
7 0.964623 1.038395 1.004591 0.008810 149394 9.979279
8 0.968305 1.044556 1.008080 0.009186 149654 9.996647
9 0.973426 1.056765 1.013330 0.010129 149513 9.987228
10 0.981000 8.983420 1.032713 0.039007 150062 10.023900
Returns Analysis
1 5 10
Ann. alpha 235.079 1.963 0.734
beta -0.058 -0.037 -0.028
Mean Period Wise Return Top Quantile (bps) 258.031 247.757 245.605
Mean Period Wise Return Bottom Quantile (bps) -252.796 -254.882 -262.501
Mean Period Wise Spread (bps) 510.936 100.644 50.926
Information Analysis
1 5 10
IC Mean 0.822 0.339 0.236
IC Std. 0.059 0.104 0.107
t-stat(IC) 437.814 103.106 70.102
p-value(IC) 0.000 0.000 0.000
IC Skew -3.815 -0.466 -0.320
IC Kurtosis 40.775 1.836 1.058
Ann. IR 219.233 51.630 35.103
Turnover Analysis
1 5 10
Quantile 1 Mean Turnover 0.825 0.836 0.840
Quantile 2 Mean Turnover 0.896 0.896 0.895
Quantile 3 Mean Turnover 0.896 0.897 0.897
Quantile 4 Mean Turnover 0.889 0.892 0.893
Quantile 5 Mean Turnover 0.881 0.887 0.888
Quantile 6 Mean Turnover 0.884 0.887 0.888
Quantile 7 Mean Turnover 0.890 0.891 0.891
Quantile 8 Mean Turnover 0.896 0.896 0.897
Quantile 9 Mean Turnover 0.896 0.896 0.898
Quantile 10 Mean Turnover 0.841 0.852 0.854
1 5 10
Mean Factor Rank Autocorrelation -0.008 0.001 0.005
<matplotlib.figure.Figure at 0x7f2e38a96450>