Zipline algorithm analysis example in pyfolio

Here's an example where we run an algorithm with zipline, then produce tear sheets for that algorithm.

Imports

Import pyfolio and zipline, and ingest the pricing data for backtesting.

import sys
sys.path.append('/Users/george/Desktop/pyfolio/')

import pyfolio as pf
%matplotlib inline

# silence warnings
import warnings
warnings.filterwarnings('ignore')

import zipline
%load_ext zipline
!zipline ingest

[?25lDownloading Bundle: quantopian-quandl  [------------------------------------]    0%

Run our zipline algorithm

This algorithm can also be adjusted to execute a modified, or completely different, trading strategy.

%%zipline --start 2004-1-1 --end 2010-1-1 -o results.pickle

# Zipline trading algorithm
# Taken from zipline.examples.olmar

import numpy as np

from zipline.finance import commission, slippage

STOCKS = ['AMD', 'CERN', 'COST', 'DELL', 'GPS', 'INTC', 'MMM']


# On-Line Portfolio Moving Average Reversion

# More info can be found in the corresponding paper:
# http://icml.cc/2012/papers/168.pdf
def initialize(algo, eps=1, window_length=5):
    algo.stocks = STOCKS
    algo.sids = [algo.symbol(symbol) for symbol in algo.stocks]
    algo.m = len(algo.stocks)
    algo.price = {}
    algo.b_t = np.ones(algo.m) / algo.m
    algo.eps = eps
    algo.window_length = window_length

    algo.set_commission(commission.PerShare(cost=0))
    algo.set_slippage(slippage.FixedSlippage(spread=0))


def handle_data(algo, data):
    m = algo.m

    x_tilde = np.zeros(m)
    b = np.zeros(m)

    # find relative moving average price for each asset
    mavgs = data.history(algo.sids, 'price', algo.window_length, '1d').mean()
    for i, sid in enumerate(algo.sids):
        price = data.current(sid, "price")
        # Relative mean deviation
        x_tilde[i] = mavgs[sid] / price

    ###########################
    # Inside of OLMAR (algo 2)
    x_bar = x_tilde.mean()

    # market relative deviation
    mark_rel_dev = x_tilde - x_bar

    # Expected return with current portfolio
    exp_return = np.dot(algo.b_t, x_tilde)
    weight = algo.eps - exp_return
    variability = (np.linalg.norm(mark_rel_dev)) ** 2

    # test for divide-by-zero case
    if variability == 0.0:
        step_size = 0
    else:
        step_size = max(0, weight / variability)

    b = algo.b_t + step_size * mark_rel_dev
    b_norm = simplex_projection(b)
    np.testing.assert_almost_equal(b_norm.sum(), 1)

    rebalance_portfolio(algo, data, b_norm)

    # update portfolio
    algo.b_t = b_norm


def rebalance_portfolio(algo, data, desired_port):
    # rebalance portfolio
    for i, sid in enumerate(algo.sids):
        algo.order_target_percent(sid, desired_port[i])


def simplex_projection(v, b=1):
    """Projection vectors to the simplex domain
    Implemented according to the paper: Efficient projections onto the
    l1-ball for learning in high dimensions, John Duchi, et al. ICML 2008.
    Implementation Time: 2011 June 17 by Bin@libin AT pmail.ntu.edu.sg
    Optimization Problem: min_{w}\| w - v \|_{2}^{2}
    s.t. sum_{i=1}^{m}=z, w_{i}\geq 0
    Input: A vector v \in R^{m}, and a scalar z > 0 (default=1)
    Output: Projection vector w
    :Example:
    >>> proj = simplex_projection([.4 ,.3, -.4, .5])
    >>> print(proj)
    array([ 0.33333333, 0.23333333, 0. , 0.43333333])
    >>> print(proj.sum())
    1.0
    Original matlab implementation: John Duchi (jduchi@cs.berkeley.edu)
    Python-port: Copyright 2013 by Thomas Wiecki (thomas.wiecki@gmail.com).
    """

    v = np.asarray(v)
    p = len(v)

    # Sort v into u in descending order
    v = (v > 0) * v
    u = np.sort(v)[::-1]
    sv = np.cumsum(u)

    rho = np.where(u > (sv - b) / np.arange(1, p + 1))[0][-1]
    theta = np.max([0, (sv[rho] - b) / (rho + 1)])
    w = (v - theta)
    w[w < 0] = 0
    return w

Extract metrics

Get the returns, positions, and transactions from the zipline backtest object.

import pandas as pd

results = pd.read_pickle('results.pickle')
returns, positions, transactions = pf.utils.extract_rets_pos_txn_from_zipline(results)

Single plot example

Make one plot of the top 5 drawdown periods.

pf.plot_drawdown_periods(returns, top=5).set_xlabel('Date')

<matplotlib.text.Text at 0x1207c8050>

Full tear sheet example

Create a full tear sheet for our algorithm. As an example, set the live start date to something arbitrary.

pf.create_full_tear_sheet(returns, positions=positions, transactions=transactions,
                          live_start_date='2009-10-22', round_trips=True)

/Users/georgeho/pyfolio/pyfolio/utils.py:251: UserWarning: Yahoo Finance read failed: HTTPConnectionPool(host='ichart.finance.yahoo.com', port=80): Max retries exceeded with url: /table.csv?a=0&ignore=.csv&s=SPY&b=1&e=13&d=7&g=d&f=2017&c=1970 (Caused by NewConnectionError('<requests.packages.urllib3.connection.HTTPConnection object at 0x12372a750>: Failed to establish a new connection: [Errno 8] nodename nor servname provided, or not known',)), falling back to Google
  UserWarning)


Entire data start date: 2004-01-02
Entire data end date: 2009-12-31
In-sample months: 69
Out-of-sample months: 2

/Users/georgeho/anaconda/lib/python2.7/site-packages/numpy/lib/function_base.py:4269: RuntimeWarning: Invalid value encountered in percentile
  interpolation=interpolation)

Suppressing symbol output

When sharing tear sheets it might be undesirable to display which symbols where used by a strategy. To suppress these in the tear sheet you can pass hide_positions=True.

pf.create_full_tear_sheet(returns, positions=positions, transactions=transactions,
                          live_start_date='2009-10-22', hide_positions=True)

Entire data start date: 2004-01-02
Entire data end date: 2009-12-31
In-sample months: 69
Out-of-sample months: 2