# 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)
nodevars = pd.concat([caps.rename('cap'), counts.rename('count')], axis=1)
rets = rets.T[nodevars.index] # ensure same order of industries
end = wd.endwk(beg) # ending date of holding week
prcdate = bd.offset(start, -1) # require price available at start of week
prcyear = (prcdate // 10000) * 10000
if prcyear != year: # retrieve new batch of prices each new year
year = prcyear
prc = crsp.get_range('daily',
'prc',
'date',
year + 101,
year + 1231,
use_cache=True)
X = prc[prc.index.get_level_values('date') == prcdate]\
.reset_index()\
.set_index('permno')\
.join(crsp.get_ret(start,rebaldate).reindex(univ.index))\
.dropna() # retrieve prior week's returns, require start price
Y = crsp.get_ret(beg, end).reindex(X.index).fillna(0) # gross return
Z = crsp.get_ret(bd.offset(beg, 1),
end).reindex(X.index).fillna(0) # net ret
z = Z['ret']
y = Y['ret']
x = (X['ret'].mean() - X['ret']) / (X['ret'].std(ddof=0) * len(X)
) # standardize
res = res.append(
DataFrame(
{
'ret': x.dot(y),
'ic': x.corr(y),
'n': len(Y),
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)
beg, end = 19270101, LAST_DATE
columns = ['chmom', 'divyld', 'indmom']
out = DataFrame()
for rebaldate in bd.date_range(beg, end, 'endmo'):
start = bd.endmo(rebaldate, -12)
beg1 = bd.offset(start, 1)
end1 = bd.endmo(rebaldate, -6)
beg2 = bd.offset(end1, 1)
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)
holdings[label] = famafrench_sorts(crsp,
label,
signals,
rebalbeg,
rebalend,
window=0,
- same year filings [yr]0101:[yr]1231 = bd.begyr(caldate) to caldate
- lagged [yr+1]0401:[yr+2]0331 = bd.begmo(caldate,4) - bd.endmo(caldate,15)
"""
for ifig, key in enumerate(['mdasent', 'mdachg', 'mdacos']):
ret1 = {} # to collect year-ahead spread returns
ret0 = {} # to collect current-year spread returns
for year in sorted(np.unique(data['year'])): # loop over years
# compute current year spread returns
beg = bd.begyr(year)
end = bd.endyr(year)
univ = data[data['year'] == year]\
.dropna(subset=[key])\
.set_index('permno')\
.join(crsp.get_cap(bd.offset(beg, -1)), how='inner')\
.join(crsp.get_ret(beg, end, delist=True), how='left')
if len(univ):
sub = fractiles(univ[key], [20, 80])
pos = weighted_average(univ.loc[sub == 1, ['cap', 'ret']],
'cap')['ret']
neg = weighted_average(univ.loc[sub == 3, ['cap', 'ret']],
'cap')['ret']
ret0[end] = {
'ret': pos - neg,
'npos': sum(sub == 1),
'nneg': sum(sub == 3)
}
if ECHO:
print(end, len(univ), pos, neg)
# compute year ahead spread returns
## Construct Mom
# Load monthly universe and stock returns from CRSP.
# Signal is stocks' total return from 12 months ago, skipping most recent month
# Construct 2-way portfolio sorts, and backtest returns
label, benchname, past, leverage = 'mom', 'Mom(mo)', (2, 12), 1
rebalbeg, rebalend = 19260101, LAST_DATE
df = [] # collect each month's momentum signal values
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.write(df, label, overwrite=True)
portfolios = famafrench_sorts(crsp,
label,
signals,
rebalbeg,
rebalend,
window=0,