def generate_signals(context, data):
try:
pipeline_results = pipeline_output('strategy_pipeline')
except NoFurtherDataError:
context.long_securities = []
context.short_securities = []
return
p = context.params['percentile']
momentum = pipeline_results
long_candidates = momentum[momentum > 0].dropna().sort_values('momentum')
short_candidates = momentum[momentum < 0].dropna().sort_values('momentum')
n_long = len(long_candidates)
n_short = len(short_candidates)
n = int(min(n_long, n_short) * p)
if n == 0:
print("{}, no signals".format(get_datetime()))
context.long_securities = []
context.short_securities = []
context.long_securities = long_candidates.index[-n:]
context.short_securities = short_candidates.index[:n]
def generate_signals(context, data):
try:
pipeline_results = pipeline_output('strategy_pipeline')
except NoFurtherDataError:
context.weights = {}
return
# return if the filtered universe is too short
n = int(context.params['universe'])
rets = pipeline_results.dropna()
if len(rets) < n:
context.weights = {}
return
# select top n assets as universe by liquidity factor
rets = rets.sort_values('liquidity')
rets = rets.iloc[-n:]
# calculate the 1-week broad market return
spx = data.history(symbol('SPY'),'close',10,'1d').dropna()
mkt_ret = spx[-1]/spx[-5] - 1
# calculate mean reversion weights
rets['weight'] = -(rets['momentum']-mkt_ret)
rets['weight'] = rets['weight']/rets['weight'].abs().sum()
context.weights = rets['weight'].to_dict()
def generate_signals(context, data):
try:
pipeline_results = pipeline_output('strategy_pipeline')
except NoFurtherDataError:
context.long_securities = []
context.short_securities = []
return
p = context.params['percentile']
pipeline_results = pipeline_results[pipeline_results.vol > 0].dropna()
vol_threshold_hi = pipeline_results.vol.quantile(0.75)
vol_threshold_lo = pipeline_results.vol.quantile(0.25)
high_vol = pipeline_results[pipeline_results.vol > vol_threshold_hi]
low_vol = pipeline_results[pipeline_results.vol < vol_threshold_lo]
long_candidates = high_vol.sort_values('skew', ascending=True)
short_candidates = low_vol.sort_values('skew', ascending=True)
available = min(len(long_candidates), len(short_candidates))
n = int(available * p)
print('total candidates {}'.format(n))
if n == 0:
print("{}, no signals".format(get_datetime()))
context.long_securities = []
context.short_securities = []
context.long_securities = long_candidates.index[:n]
context.short_securities = short_candidates.index[:n]
def generate_signals(context, data):
try:
results = pipeline_output('strategy_pipeline')
except:
return
# use other columns to print other indicators scanning results
results = results.sort_values('rsi', ascending=True)
print('{}{}'.format(get_datetime(), '-' * 30))
print(results.head())
print(results.tail())
def compute_signal(context,data):
try:
pipeline_results = pipeline_output('strategy_pipeline')
except NoFurtherDataError:
print(f'{get_datetime()}: error in pipeline output.')
context.candidates = []
return
momentum = pipeline_results
momentum['z_score'] = momentum['momentum']/momentum['vol']
candidates = momentum[momentum['z_score'] > 0].dropna().sort_values('momentum')
if len(candidates) < context.size:
print(f'{get_datetime()}:no assets passed screening.')
context.candidates = []
context.candidates = candidates.index[-context.size:].tolist()
def generate_signals(context, data):
try:
pipeline_results = pipeline_output('strategy_pipeline')
except NoFurtherDataError:
context.long_securities = []
context.short_securities = []
return
p = context.params['percentile']
momentum = pipeline_results.dropna().sort_values('momentum')
n = int(len(momentum) * p)
if n == 0:
print("{}, no signals".format(get_datetime()))
context.long_securities = []
context.short_securities = []
context.long_securities = momentum.index[-n:]
context.short_securities = momentum.index[:n]
def generate_signals(context, data):
try:
pipeline_results = pipeline_output('strategy_pipeline')
except:
context.long_securities = []
context.short_securities = []
return
p = context.params['percentile']
rsi_factor = pipeline_results
candidates = rsi_factor[rsi_factor > 0].dropna().sort_values('rsi')
n = int(len(candidates) * p)
if n == 0:
print("{}, no signals".format(get_datetime()))
context.long_securities = []
context.short_securities = []
context.long_securities = candidates.index[-n:]
context.short_securities = candidates.index[:n]
def generate_signals(context, data):
try:
pipeline_results = pipeline_output('strategy_pipeline')
except NoFurtherDataError:
context.long_securities = []
context.short_securities = []
return
p = context.params['percentile']
vol_factor = pipeline_results
candidates = vol_factor[vol_factor > 0].dropna().sort_values('vol')
n = int(len(candidates) * p)
if n == 0:
print("{}, no signals".format(data.current_dt))
context.long_securities = []
context.short_securities = []
context.long_securities = candidates.index[:n]
context.short_securities = candidates.index[-n:]
def compute_signal(context, data):
try:
pipeline_results = pipeline_output('strategy_pipeline')
except NoFurtherDataError:
print(f'{get_datetime()}: error in pipeline output.')
context.candidates = []
return
candidates = pipeline_results.dropna()
if len(candidates) < context.size:
print(f'{get_datetime()}:no assets passed screening.')
context.candidates = []
candidates = candidates.tail(context.size)
candidates['weight'] = 1 / candidates.vol
total = candidates.weight.sum()
candidates['weight'] = candidates['weight'] / total
# naive risk parity - inverse vol weights
context.weight = candidates['weight'].to_dict()
context.candidates = candidates.index.tolist()
