def benchmark_build_rank_with_group(n_samples: int, n_loops: int,
n_included: int, n_groups: int) -> None:
print("-" * 60)
print(
"Starting portfolio construction by rank with group-by values benchmarking"
)
print(
"Parameters(n_samples: {0}, n_included: {1}, n_loops: {2}, n_groups: {3})"
.format(n_samples, n_included, n_loops, n_groups))
n_portfolio = 10
x = np.random.randn(n_samples, n_portfolio)
groups = np.random.randint(n_groups, size=n_samples)
start = dt.datetime.now()
for _ in range(n_loops):
calc_weights = rank_build(x, n_included, groups=groups)
impl_model_time = dt.datetime.now() - start
print('{0:20s}: {1}'.format('Implemented model', impl_model_time))
start = dt.datetime.now()
for _ in range(n_loops):
grouped_ordering = pd.DataFrame(-x).groupby(groups).rank()
exp_weights = np.zeros((len(x), n_portfolio))
masks = (grouped_ordering <= n_included).values
for j in range(n_portfolio):
exp_weights[masks[:, j], j] = 1.
benchmark_model_time = dt.datetime.now() - start
np.testing.assert_array_almost_equal(calc_weights, exp_weights)
print('{0:20s}: {1}'.format('Benchmark model', benchmark_model_time))
def benchmark_build_rank(n_samples: int, n_loops: int,
n_included: int) -> None:
print("-" * 60)
print("Starting portfolio construction by rank benchmarking")
print("Parameters(n_samples: {0}, n_included: {1}, n_loops: {2})".format(
n_samples, n_included, n_loops))
n_portfolio = 10
x = np.random.randn(n_samples, n_portfolio)
start = dt.datetime.now()
for _ in range(n_loops):
calc_weights = rank_build(x, n_included)
impl_model_time = dt.datetime.now() - start
print('{0:20s}: {1}'.format('Implemented model', impl_model_time))
start = dt.datetime.now()
for _ in range(n_loops):
exp_weights = np.zeros((len(x), n_portfolio))
choosed_index = (-x).argsort(axis=0).argsort(axis=0) < n_included
for j in range(n_portfolio):
exp_weights[choosed_index[:, j], j] = 1.
benchmark_model_time = dt.datetime.now() - start
np.testing.assert_array_almost_equal(calc_weights, exp_weights)
print('{0:20s}: {1}'.format('Benchmark model', benchmark_model_time))
def test_rank_build_with_masks(self):
for n_portfolio in self.n_portfolio:
x = np.random.randn(self.n_samples, n_portfolio)
choices = np.random.choice(self.n_samples,
self.n_mask,
replace=False)
masks = np.full(self.n_samples, True, dtype=bool)
masks[choices] = False
calc_weights = rank_build(x, self.n_included, masks=masks)
expected_weights = np.zeros((len(x), n_portfolio))
filtered_index = np.arange(len(x))[masks]
filtered_x = x[masks]
big_boolen = np.full(x.shape, False, dtype=bool)
chosen = (-filtered_x).argsort(axis=0).argsort(
axis=0) < self.n_included
big_boolen[filtered_index] = chosen
for j in range(x.shape[1]):
expected_weights[big_boolen[:, j], j] = 1.
np.testing.assert_array_almost_equal(calc_weights,
expected_weights)
def test_rank_build(self):
for n_portfolio in self.n_portfolio:
x = np.random.randn(self.n_samples, n_portfolio)
calc_weights = rank_build(x, self.n_included)
expected_weights = np.zeros((len(x), n_portfolio))
chosen = (-x).argsort(axis=0).argsort(axis=0) < self.n_included
for j in range(x.shape[1]):
expected_weights[chosen[:, j], j] = 1.
np.testing.assert_array_almost_equal(calc_weights,
expected_weights)
def test_rank_build_with_group(self):
n_include = int(self.n_included / self.n_groups)
for n_portfolio in self.n_portfolio:
x = np.random.randn(self.n_samples, n_portfolio)
groups = np.random.randint(self.n_groups, size=self.n_samples)
calc_weights = rank_build(x, n_include, groups)
grouped_ordering = pd.DataFrame(-x).groupby(groups).rank()
expected_weights = np.zeros((len(x), n_portfolio))
chosen = (grouped_ordering <= n_include).values
for j in range(x.shape[1]):
expected_weights[chosen[:, j], j] = 1.
np.testing.assert_array_almost_equal(calc_weights,
expected_weights)
def build_portfolio(er: np.ndarray,
builder: Optional[str] = 'long_short',
**kwargs) -> np.ndarray:
builder = builder.lower()
if builder == 'ls' or builder == 'long_short':
return long_short_build(er, **kwargs).flatten()
elif builder == 'rank':
return rank_build(er, **kwargs).flatten()
elif builder == 'percent':
return percent_build(er, **kwargs).flatten()
elif builder == 'linear_prog' or builder == 'linear':
status, _, weight = linear_build(er, **kwargs)
if status != 'optimal':
raise ValueError(
'linear programming optimizer in status: {0}'.format(status))
else:
return weight
def er_portfolio_analysis(
er: np.ndarray,
industry: np.ndarray,
dx_return: np.ndarray,
constraints: Optional[Union[LinearConstraints, Constraints]] = None,
detail_analysis=True,
benchmark: Optional[np.ndarray] = None,
is_tradable: Optional[np.ndarray] = None,
method='risk_neutral',
**kwargs) -> Tuple[pd.DataFrame, Optional[pd.DataFrame]]:
er = er.flatten()
def create_constraints(benchmark, **kwargs):
if 'lbound' in kwargs:
lbound = kwargs['lbound'].copy()
del kwargs['lbound']
else:
lbound = np.maximum(0., benchmark - 0.01)
if 'ubound' in kwargs:
ubound = kwargs['ubound'].copy()
del kwargs['ubound']
else:
ubound = 0.01 + benchmark
if is_tradable is not None:
ubound[~is_tradable] = np.minimum(lbound, ubound)[~is_tradable]
risk_lbound, risk_ubound = constraints.risk_targets()
cons_exp = constraints.risk_exp
return lbound, ubound, cons_exp, risk_lbound, risk_ubound
if method == 'risk_neutral':
lbound, ubound, cons_exp, risk_lbound, risk_ubound = create_constraints(
benchmark, **kwargs)
turn_over_target = kwargs.get('turn_over_target')
current_position = kwargs.get('current_position')
status, _, weights = linear_builder(er,
risk_constraints=cons_exp,
lbound=lbound,
ubound=ubound,
risk_target=(risk_lbound,
risk_ubound),
turn_over_target=turn_over_target,
current_position=current_position)
if status != 'optimal':
raise ValueError(
'linear programming optimizer in status: {0}'.format(status))
elif method == 'rank':
weights = rank_build(
er, use_rank=kwargs['use_rank'],
masks=is_tradable).flatten() * benchmark.sum() / kwargs['use_rank']
elif method == 'ls' or method == 'long_short':
weights = long_short_builder(er).flatten()
elif method == 'mv' or method == 'mean_variance':
lbound, ubound, cons_exp, risk_lbound, risk_ubound = create_constraints(
benchmark, **kwargs)
cov = kwargs['cov']
if 'lam' in kwargs:
lam = kwargs['lam']
else:
lam = 1.
status, _, weights = mean_variance_builder(er,
cov=cov,
bm=benchmark,
lbound=lbound,
ubound=ubound,
risk_exposure=cons_exp,
risk_target=(risk_lbound,
risk_ubound),
lam=lam)
if status != 'optimal':
raise ValueError(
'mean variance optimizer in status: {0}'.format(status))
elif method == 'tv' or method == 'target_vol':
lbound, ubound, cons_exp, risk_lbound, risk_ubound = create_constraints(
benchmark, **kwargs)
cov = kwargs['cov']
if 'target_vol' in kwargs:
target_vol = kwargs['target_vol']
else:
target_vol = 1.
status, _, weights = target_vol_builder(er,
cov=cov,
bm=benchmark,
lbound=lbound,
ubound=ubound,
risk_exposure=cons_exp,
risk_target=(risk_lbound,
risk_ubound),
vol_low=0,
vol_high=target_vol)
else:
raise ValueError("Unknown building type ({0})".format(method))
if detail_analysis:
analysis = simple_settle(weights, dx_return, industry, benchmark)
else:
analysis = None
return pd.DataFrame({'weight': weights,
'industry': industry,
'er': er}), \
analysis