from quantopian.pipeline import Pipeline
from quantopian.pipeline.data.alpha_vertex import (
    # Top 100 Securities
    precog_top_100 as dataset_100,
    # Top 500 Securities|
    precog_top_500 as dataset_500
)
from quantopian.research import run_pipeline
import alphalens
from quantopian.pipeline.filters.morningstar import Q1500US
from quantopian.pipeline.data.builtin import USEquityPricing
from quantopian.pipeline.factors import SimpleMovingAverage,RSI
from quantopian.interactive.data.zacks import earnings_surprises_free as dataset
from odo import odo
import pandas as pd

def make_pipeline():

    sma_10 = SimpleMovingAverage(inputs=[USEquityPricing.close], window_length=10)
    sma_20 = SimpleMovingAverage(inputs=[USEquityPricing.close], window_length=20)
    EPS_mean_estimate = dataset.eps_mean_est
    EPS_std_est = dataset.eps_std_dev_est
    eps_act = dataset.eps_act
    
    
    percent_diff = (sma_10 - sma_20)/sma_20
    
    top_bottom_scores = (
        percent_diff.top(350) | percent_diff.bottom(350)
    )                           
    
    universe = (Q1500US &
                top_bottom_scores & 
                dataset.eps_mean_est.notnull() &
                dataset.eps_std_dev_est.notnull() &
                dataset.eps_act.notnull())
    return Pipeline(
        columns={
            "percent diff" : percent_diff,
            'EPS mean estimate': EPS_mean_estimate,
            'EPS std est': EPS_std_est,
            'eps_act':eps_act,
            'SUE': (eps_act - EPS_mean_estimate)/EPS_std_est,
            'score': percent_diff
        },
        screen=universe
    )

results = run_pipeline(make_pipeline(), start_date='2007-01-01', end_date='2010-01-01')


TypeErrorTraceback (most recent call last)
<ipython-input-90-47f1bf42d04f> in <module>()
----> 1 results = run_pipeline(make_pipeline(), start_date='2007-01-01', end_date='2010-01-01')

<ipython-input-89-ab5917bf44fc> in make_pipeline()
     17                 top_bottom_scores &
     18                 dataset.eps_mean_est.notnull() &
---> 19                 dataset.eps_std_dev_est.notnull() &
     20                 dataset.eps_act.notnull())
     21     return Pipeline(

/build/src/qexec_repo/zipline_repo/zipline/pipeline/filters/filter.pyc in binary_operator(self, other)
     75         if isinstance(self, NumericalExpression):
     76             self_expr, other_expr, new_inputs = self.build_binary_op(
---> 77                 op, other,
     78             )
     79             return NumExprFilter.create(

/build/src/qexec_repo/zipline_repo/zipline/pipeline/expression.pyc in build_binary_op(self, op, other)
    308             new_inputs = self.inputs
    309         else:
--> 310             raise BadBinaryOperator(op, other)
    311         return self_expr, other_expr, new_inputs
    312 

TypeError: __init__() takes exactly 4 arguments (3 given)

results.head()


NameErrorTraceback (most recent call last)
<ipython-input-86-0f9ba5b4964d> in <module>()
----> 1 results.head()

NameError: name 'results' is not defined

assets = results.index.levels[1].unique()
pricing = get_pricing(assets, start_date='2005-12-01', end_date='2012-02-01', fields='open_price')

factor_data = alphalens.utils.get_clean_factor_and_forward_returns(factor = results['percent diff'], 
                                                     prices = pricing, 
                                                     quantiles=3, 
                                                     periods=(5,10,20,30),
                                                     max_loss = 0.60)
alphalens.tears.create_full_tear_sheet(factor_data)

Dropped 55.9% entries from factor data: 0.0% in forward returns computation and 55.9% in binning phase (set max_loss=0 to see potentially suppressed Exceptions).
max_loss is 60.0%, not exceeded: OK!
Quantiles Statistics

Returns Analysis

<matplotlib.figure.Figure at 0x7ff8b5d31190>

Information Analysis

Turnover Analysis

	min	max	mean	std	count	count %
factor_quantile
1.0	-0.319945	0.213576	-0.081035	0.151293	59	46.825397
2.0	-0.200952	0.224897	0.079853	0.166307	13	10.317460
3.0	-0.218304	0.332132	0.089737	0.155898	54	42.857143

	5D	10D	20D	30D
Ann. alpha	-0.043	-0.142	0.165	-0.180
beta	-0.271	-0.433	-0.323	0.038
Mean Period Wise Return Top Quantile (bps)	-137.188	-91.487	-12.206	-16.881
Mean Period Wise Return Bottom Quantile (bps)	103.833	124.519	16.983	12.794
Mean Period Wise Spread (bps)	-221.080	-264.679	-53.337	-25.347

	5D	10D	20D	30D
IC Mean	-0.008	-0.185	0.006	-0.136
IC Std.	0.923	0.901	0.934	0.927
Risk-Adjusted IC	-0.008	-0.205	0.006	-0.147
t-stat(IC)	-0.060	-1.493	0.044	-1.067
p-value(IC)	0.953	0.141	0.965	0.291
IC Skew	0.023	0.319	-0.061	0.289
IC Kurtosis	-1.856	-1.746	-1.870	-1.777

	10D	20D	30D	5D
Quantile 1 Mean Turnover	0.965	1.00	1.000	0.854
Quantile 2 Mean Turnover	1.000	NaN	NaN	0.750
Quantile 3 Mean Turnover	1.000	0.97	0.957	0.938