def demo_44():
close = get_tick('AAL')
vol = get_daily_vol(close)
sampled_idx = cusum_filter(close, vol)
t1 = get_t1(close, sampled_idx, num_days=1)
trgt = vol
events = get_3barriers(close,
t_events=sampled_idx,
trgt=trgt,
ptsl=1,
t1=t1)
print(events.head())
num_threads = 24
num_co_events = mp_pandas_obj(get_num_co_events,
('molecule', events.index),
num_threads,
close_idx=close.index,
t1=events['t1'])
num_co_events = num_co_events.loc[~num_co_events.index.duplicated(
keep='last')]
num_co_events = num_co_events.reindex(close.index).fillna(0)
num_threads = 24
tw = mp_pandas_obj(get_sample_tw, ('molecule', events.index),
num_threads,
t1=events['t1'],
num_co_events=num_co_events)
exp_decay = get_time_decay(tw, last_w=.1, is_exp=True)
print(exp_decay.head())
def avg_active_signals(signals, num_threads):
# Compute the average signal
# 1) time points where singal changes
t_pnts = set(signals['t1'].dropna().values)
t_pnts = t_pnts.union(signals.index.values)
t_pnts = list(t_pnts)
t_pnts.sort()
out = mp_pandas_obj(mp_avg_active_signals, ('molecule', t_pnts),
num_threads,
signals=signals)
return out
def demo():
close = get_tick('AAL')
vol = get_daily_vol(close)
sampled_idx = cusum_filter(close, vol)
t1 = get_t1(close, sampled_idx, num_days=5)
trgt = vol
events = get_3barriers(close,
t_events=sampled_idx,
trgt=trgt,
ptsl=1,
t1=t1)
print(events.head())
num_threads = 1
num_co_events = mp_pandas_obj(get_num_co_events,
('molecule', events.index),
num_threads,
close_idx=close.index,
t1=events['t1'])
fig, ax1 = plt.subplots(figsize=(16, 8))
ax1.set_xlabel('time (s)')
ax1.set_ylabel('num_co_events', color='red')
ax1.plot(num_co_events, color='red')
ax1.tick_params(axis='y', labelcolor='red')
ax2 = ax1.twinx() # instantiate a second axes that shares the same x-axis
ax2.set_ylabel('volatility',
color='blue') # we already handled the x-label with ax1
ax2.plot(vol, color='blue')
ax2.tick_params(axis='y', labelcolor='blue')
fig.tight_layout() # otherwise the right y-label is slightly clipped
plt.savefig(PNG_PATH + "num_co_events.png")
plt.close()
fig, ax1 = plt.subplots(figsize=(16, 8))
ax1.set_xlabel('time')
ax1.set_ylabel('num_co_events', color='red')
ax1.scatter(num_co_events.index, num_co_events.values, color='red')
ax2 = ax1.twinx()
ret = close.pct_change().dropna()
ax2.set_ylabel('return', color='blue')
ax2.scatter(ret.index, ret.values, color='blue')
plt.savefig(PNG_PATH + "num_co_events_scatter.png")
plt.close()
def feat_importance(X,
cont,
clf=None,
n_estimators=1000,
n_splits=10,
max_samples=1.,
num_threads=24,
pct_embargo=0.,
scoring='accuracy',
method='SFI',
min_w_leaf=0.,
**kwargs):
"""
takes in a classifier and type of importance score and runs through the cross validation score
"""
n_jobs = (-1 if num_threads > 1 else 1)
# Build classifiers
if clf is None:
base_clf = DecisionTreeClassifier(criterion='entropy',
max_features=1,
class_weight='balanced',
min_weight_fraction_leaf=min_w_leaf)
clf = BaggingClassifier(base_estimator=base_clf,
n_estimators=n_estimators,
max_features=1.,
max_samples=max_samples,
oob_score=True,
n_jobs=n_jobs)
fit_clf = clf.fit(X, cont['bin'], sample_weight=cont['w'].values)
if hasattr(fit_clf, 'oob_score_'):
oob = fit_clf.oob_score_
else:
oob = None
# cv score will use true out of sample training sets
if method == 'MDI':
imp = feat_imp_MDI(fit_clf, feat_names=X.columns)
oos = cv_score(clf,
X=X,
y=cont['bin'],
n_splits=n_splits,
sample_weight=cont['w'],
t1=cont['t1'],
pct_embargo=pct_embargo,
scoring=scoring).mean()
elif method == 'MDA':
imp, oos = feat_imp_MDA(clf,
X=X,
y=cont['bin'],
n_splits=n_splits,
sample_weight=cont['w'],
t1=cont['t1'],
pct_embargo=pct_embargo,
scoring=scoring)
elif method == 'SFI':
cv_gen = PurgedKFold(n_splits=n_splits,
t1=cont['t1'],
pct_embargo=pct_embargo)
oos = cv_score(clf,
X=X,
y=cont['bin'],
sample_weight=cont['w'],
scoring=scoring,
cv_gen=cv_gen)
clf.n_jobs = 24
imp = mp_pandas_obj(aux_feat_imp_SFI, ('feat_names', X.columns),
num_threads,
clf=clf,
X=X,
cont=cont,
scoring=scoring,
cv_gen=cv_gen)
return imp, oob, oos