def test_es_return_sample():
df = get_data()
mu = expected_returns.mean_historical_return(df)
S = risk_models.sample_cov(df)
# Generate a 1y sample of daily data
np.random.seed(0)
mu_daily = (1 + mu)**(1 / 252) - 1
S_daily = S / 252
sample_rets = pd.DataFrame(np.random.multivariate_normal(
mu_daily, S_daily, 300),
columns=mu.index)
cd = EfficientCDaR(mu, sample_rets)
w = cd.efficient_return(0.2)
assert isinstance(w, dict)
assert set(w.keys()) == set(cd.tickers)
np.testing.assert_almost_equal(cd.weights.sum(), 1)
assert all([i >= -1e-5 for i in w.values()])
np.testing.assert_allclose(
cd.portfolio_performance(),
(0.20, 0.045414),
rtol=1e-4,
atol=1e-4,
)
# Cover verbose param case
np.testing.assert_equal(cd.portfolio_performance(verbose=True),
cd.portfolio_performance())
def test_cdar_example():
beta = 0.95
df = get_data()
mu = expected_returns.mean_historical_return(df)
historical_rets = expected_returns.returns_from_prices(df).dropna()
cd = EfficientCDaR(mu, historical_rets, beta=beta)
w = cd.min_cdar()
assert isinstance(w, dict)
assert set(w.keys()) == set(cd.tickers)
np.testing.assert_almost_equal(cd.weights.sum(), 1)
assert all([i >= -1e-5 for i in w.values()])
np.testing.assert_allclose(
cd.portfolio_performance(),
(0.21502, 0.056433),
rtol=1e-4,
atol=1e-4,
)
cdar = cd.portfolio_performance()[1]
portfolio_rets = historical_rets @ cd.weights
cum_rets = portfolio_rets.cumsum(0)
drawdown = cum_rets.cummax() - cum_rets
dar_hist = drawdown.quantile(beta)
cdar_hist = drawdown[drawdown > dar_hist].mean()
np.testing.assert_almost_equal(cdar_hist, cdar, decimal=3)
def test_efficient_return_short():
cd = EfficientCDaR(*setup_efficient_cdar(data_only=True),
weight_bounds=(-3.0, 3.0))
w = cd.efficient_return(0.28)
assert isinstance(w, dict)
assert set(w.keys()) == set(cd.tickers)
np.testing.assert_almost_equal(cd.weights.sum(), 1)
np.testing.assert_allclose(
cd.portfolio_performance(),
(0.28, 0.045999),
rtol=1e-4,
atol=1e-4,
)
cdar = cd.portfolio_performance()[1]
ef_long_only = EfficientCDaR(*setup_efficient_cdar(data_only=True),
weight_bounds=(0.0, 1.0))
ef_long_only.efficient_return(0.26)
long_only_cdar = ef_long_only.portfolio_performance()[1]
assert long_only_cdar > cdar
def test_efficient_risk_market_neutral():
cd = EfficientCDaR(*setup_efficient_cdar(data_only=True),
weight_bounds=(-1, 1))
w = cd.efficient_risk(0.025, market_neutral=True)
assert isinstance(w, dict)
assert set(w.keys()) == set(cd.tickers)
np.testing.assert_almost_equal(cd.weights.sum(), 0)
assert (cd.weights < 1).all() and (cd.weights > -1).all()
np.testing.assert_allclose(
cd.portfolio_performance(),
(0.219306, 0.025),
rtol=1e-4,
atol=1e-4,
)
def test_cdar_example_weekly():
beta = 0.90
df = get_data()
df = df.resample("W").first()
mu = expected_returns.mean_historical_return(df, frequency=52)
historical_rets = expected_returns.returns_from_prices(df).dropna()
cd = EfficientCDaR(mu, historical_rets, beta=beta)
cd.efficient_return(0.21)
np.testing.assert_allclose(
cd.portfolio_performance(),
(0.21, 0.045085),
rtol=1e-4,
atol=1e-4,
)
cdar = cd.portfolio_performance()[1]
portfolio_rets = historical_rets @ cd.weights
cum_rets = portfolio_rets.cumsum(0)
drawdown = cum_rets.cummax() - cum_rets
dar_hist = drawdown.quantile(beta)
cdar_hist = drawdown[drawdown > dar_hist].mean()
np.testing.assert_almost_equal(cdar_hist, cdar, decimal=3)
def test_cdar_example_short():
df = get_data()
mu = expected_returns.mean_historical_return(df)
historical_rets = expected_returns.returns_from_prices(df).dropna()
cd = EfficientCDaR(
mu,
historical_rets,
weight_bounds=(-1, 1),
)
w = cd.efficient_return(0.2, market_neutral=True)
assert isinstance(w, dict)
assert set(w.keys()) == set(cd.tickers)
np.testing.assert_almost_equal(cd.weights.sum(), 0)
np.testing.assert_allclose(
cd.portfolio_performance(),
(0.2, 0.047152),
rtol=1e-4,
atol=1e-4,
)