if 'new' in testable:
with open(os.path.join(outdir, 'index.html'), 'wt') as f:
f.write('<h1>Quant Factors Zoo</h1><br>')
f.write(' <br>')
f.write('<p>\n')
# Momentum and divyld from CRSP monthly
if 'monthly' in testable:
if regenerate:
beg, end = 19251231, LAST_DATE
intervals = {'mom12m': (2,12), 'mom36m': (13,36),
'mom6m': (2,6), 'mom1m': (1,1)}
for label, past in intervals.items():
out = DataFrame()
for rebaldate in bd.date_range(bd.endmo(beg, past[1]), end, 'endmo'):
start = bd.endmo(rebaldate, -past[1])
beg1 = bd.offset(start, 1)
end1 = bd.endmo(rebaldate, 1-past[0])
df = crsp.get_universe(end1)
df['start'] = crsp.get_section(dataset='monthly', fields=['ret'],
date_field='date', date=start)\
.reindex(df.index)
df[label] = crsp.get_ret(beg1, end1).reindex(df.index)
df['permno'] = df.index
df['rebaldate'] = rebaldate
df = df.dropna(subset=['start'])
out = out.append(df[['rebaldate', 'permno', label]],
ignore_index=True) # append rows
n = signals.write(out, label, overwrite=True)
plt.show()
# Construct monthly BEA industry returns for the same period of years
codes = Sectoring(sql, f"bea{vintage}", fillna='')
naics = pstat.build_lookup('lpermno', 'naics', fillna=0)
caps, counts, rets = [], [], []
for year in years:
date = bd.endyr(year - 1)
univ = crsp.get_universe(date)
univ['bea'] = codes[naics(univ.index, date)]
univ = univ[univ['bea'].ne('')]
grouped = univ.groupby('bea')
caps.append(grouped['cap'].sum().rename(year))
counts.append(grouped['cap'].count().rename(year))
months = bd.date_range(date, bd.endyr(year), 'endmo')
for rebaldate, end in zip(months[:-1], months[1:]):
r = pd.concat([crsp.get_ret(bd.begmo(end), end),
crsp.get_cap(rebaldate, use_permco=False),
univ['bea']], axis=1, join='inner').dropna()
grp = r.groupby('bea') # industry ret is sum of weighted rets
r['wtdret'] = r['ret'].mul(r['cap'].div(grp['cap'].transform('sum')))
rets.append(grp['wtdret'].sum(min_count=1).rename(end))
print(end, len(r), r['wtdret'].sum() / len(grp))
# collect and average market caps, counts and returns
caps = pd.concat(caps, axis=1).mean(axis=1) # average cap over years
counts = pd.concat(counts, axis=1).mean(axis=1) # average count
rets = pd.concat(rets, axis=1)
# create node variables: count and cap (will take logs of)
signals = chunk_signal(df)
holdings = famafrench_sorts(crsp,
'hml',
signals,
rebalbeg,
LAST_DATE,
window=12,
months=[6],
rebals=rebals)['holdings']
# Compute MOM momentum factor
label = 'mom'
past = (2, 12)
df = [] # collect each month's momentum signal values
rebalend = bd.endmo(LAST_DATE, -1)
for rebaldate in bd.date_range(rebalbeg, rebalend, 'endmo'):
beg = bd.endmo(rebaldate, -past[1]) # require price at this date
start = bd.offset(beg, 1) # start date, inclusive, of signal
end = bd.endmo(rebaldate, 1 - past[0]) # end date of signal
p = [
crsp.get_universe(rebaldate), # retrieve prices and construct signal
crsp.get_ret(start, end)['ret'].rename(label),
crsp.get_section('monthly', ['prc'], 'date', beg)['prc'].rename('beg'),
crsp.get_section('monthly', ['prc'], 'date', end)['prc'].rename('end')
]
q = pd.concat(p, axis=1, join='inner').reset_index().dropna()
q['rebaldate'] = rebaldate
df.append(q[['permno', 'rebaldate', label]])
print(rebaldate, len(df), len(q))
df = pd.concat(df)
signals = chunk_signal(df)