def estimate(self, nparrays: List[np.recarray]):
"""Compute the book leverage
Parameters
----------
nparrays : List[np.recarray]
Input datasets, same order as specified in `DATASETS_REQUIRED`
Returns
-------
Tuple[pd.DataFrame, Dict[str, str]]
Output dataset and the `VARIABLE_LABELS`
"""
nparray = filter_funda(nparrays[0])
# debts = long-term debt + debt in current liabilities
debts = np.nansum([nparray.dltt, nparray.dlc], axis=0)
# assets = debts + common equity
assets = np.nansum([debts, nparray.ceq], axis=0)
# book leverage = debts / assets
bleverage = np.true_divide(debts, assets, where=(assets != 0))
# set book leverage to missing if common equity is somehow missing
bleverage[np.isnan(nparray.ceq)] = np.nan
# add book leverage to the result
nparray = rfn.rec_append_fields(nparray, NAME, bleverage)
# keep only useful columns
cols = set(rfn.get_names_flat(nparray.dtype))
nparray.sort(order=(keys := ["gvkey", "datadate"]))
def estimate(self, nparrays: List[np.recarray]):
funda = pd.DataFrame.from_records(filter_funda(nparrays[0]))
anncomp = pd.DataFrame.from_records(nparrays[1])
work = anncomp.merge(funda,
left_on=["gvkey", "year"],
right_on=["gvkey", "fyear"])
# CSHO is in millions and SHROWN_TOT is in thousands
work["ExecSharePct"] = work.shrown_tot / work.csho / 10
work["ExecSharePctExclOpt"] = work.shrown_excl_opts / work.csho / 10
work["ExecOptPct"] = work.opt_exer_num / work.csho / 10
work["ExecShareVestPct"] = work.shrs_vest_num / work.csho / 10
work["ExecIncentivePct"] = ((work.opt_exer_val + work.shrs_vest_num) /
work.tdc1 / 10)
# Replace infinity with nan
work["ExecSharePctExclOpt"].replace(np.inf, np.nan, inplace=True)
work["ExecOptPct"].replace(np.inf, np.nan, inplace=True)
work["ExecShareVestPct"].replace(np.inf, np.nan, inplace=True)
work["ExecIncentivePct"].replace(np.inf, np.nan, inplace=True)
keys = ["gvkey", "datadate"]
cols = [*keys, *(VARIABLE_LABELS.keys())]
result = work[cols].drop_duplicates().sort_values(by=keys)
return result, VARIABLE_LABELS
def estimate(self, nparrays: List[np.recarray]):
nparray = filter_funda(nparrays[0])
size = np.log(nparray.at, where=(nparray.at > 0))
size[np.isnan(nparray.at)] = np.nan
nparray = rfn.rec_append_fields(nparray, NAME, size)
# keep only useful columns
cols = set(rfn.get_names_flat(nparray.dtype))
nparray.sort(order=(keys := ["gvkey", "datadate"]))
def estimate(self, nparrays: List[np.recarray]):
nparray = filter_funda(nparrays[0])
roa = np.true_divide(nparray.ib, nparray.at, where=(nparray.at != 0))
roa[np.isnan(nparray.at)] = np.nan
nparray = rfn.rec_append_fields(nparray, NAME, roa)
# keep only useful columns
cols = set(rfn.get_names_flat(nparray.dtype))
nparray.sort(order=(keys := ["gvkey", "datadate"]))
def estimate(
self, nparrays: List[np.recarray]
) -> Tuple[pd.DataFrame, Dict[str, str]]:
"""Counts the numer of restatements during the past fiscal year(s)
Parameters
----------
nparrays : List[np.recarray]
Input datasets, same order as specified in `DATASETS_REQUIRED`
Returns
-------
Tuple[pd.DataFrame, Dict[str, str]]
Output dataset and the `VARIABLE_LABELS`
"""
# Note that the order of dataset is preseved
rests = pd.DataFrame.from_records(nparrays[0])
funda = pd.DataFrame.from_records(filter_funda(nparrays[1]))
# Inner join funda and restatements
work = funda.merge(rests, left_on="cik", right_on="company_fkey")
# Filing date must be in the past year(s) relative the datadate
time_delta = work.datadate - work.file_date
years = np.timedelta64(self._years, "Y")
cond = (time_delta < years) & (work.datadate >= work.file_date)
# Forget about the non-matched
cond = cond & (work.cik != "")
# Apply the filtering condition
work.where(cond, inplace=True)
# Count by gvkey and datadate/fyear
keys = ["gvkey", "datadate"]
work = work.groupby((keys), as_index=False).sum()
# Rename columns to match output variable labels
work.rename(
columns={
"res_accounting": "NumResAcct",
"res_fraud": "NumResFraud",
"res_adverse": "NumResAdver",
"res_cler_err": "NumResClerErr",
"res_sec_invest": "NumResSECInvest",
},
inplace=True,
)
# Left join with funda so to retain the missing values
result = funda[keys].merge(work, how="left", on=keys, copy=False)
# Keep only useful columns
cols = [*keys, *(VARIABLE_LABELS.keys())]
# Some cosmetic issues
result = result[cols].drop_duplicates().sort_values(by=keys)
if self._years > 1:
for k, v in VARIABLE_LABELS.items():
VARIABLE_LABELS.update({
k:
v.replace("fiscal year",
f"past {self._years} fiscal years")
})
return result, VARIABLE_LABELS
def estimate(self, nparrays: List[np.recarray]):
nparray = filter_funda(nparrays[0])
# market value at fiscal year
mv = nparray.prcc_f * nparray.csho
# market-to-book = market value of equity / common equity
mtb = np.true_divide(mv, nparray.ceq, where=(nparray.ceq != 0))
# set mtb to missing if common equity is somehow missing
mtb[np.isnan(nparray.ceq)] = np.nan
# add book leverage to the result
nparray = rfn.rec_append_fields(nparray, NAME, mtb)
# keep only useful columns
cols = set(rfn.get_names_flat(nparray.dtype))
nparray.sort(order=(keys := ["gvkey", "datadate"]))
def estimate(
self, nparrays: List[np.recarray]
) -> Tuple[pd.DataFrame, Dict[str, str]]:
company = pd.DataFrame.from_records(nparrays[0])
compositon = pd.DataFrame.from_records(nparrays[1])
funda = pd.DataFrame.from_records(
filter_funda(nparrays[2]),
columns=["gvkey", "datadate", "cik", "fyear"],
)
tmp = (company.merge(compositon,
left_on=["boardid"],
right_on=["companyid"
]).merge(funda,
left_on=["cikcode"],
right_on=["cik"
]).drop_duplicates())
cond = (((tmp.datestartrole <= tmp.datadate)
& (tmp.datadate <= tmp.dateendrole))
| (pd.isnull(tmp.dateendrole) &
(tmp.datestartrole <= tmp.datadate))
| (pd.isnull(tmp.datestartrole) &
(tmp.datadate <= tmp.dateendrole))) & np.in1d(
tmp.seniority,
("Executive Director", "Supervisory Director"))
tmp = tmp.where(cond)
tmp.fillna({"rolename": ""}, inplace=True)
keys = ["gvkey", "datadate"]
board_size = (tmp.groupby(keys,
as_index=False)["directorid"].count().rename(
columns={"directorid": "BoardSize"}))
independent_dirs = (
tmp[tmp.rolename.str.lower().str.contains("independent")].groupby(
keys, as_index=False)["directorid"].count().rename(
columns={"directorid": "IndependentMembers"}))
result = board_size.merge(independent_dirs, on=keys, how="left")
if self._missing_as_zero:
result.fillna({"IndependentMembers": 0}, inplace=True)
result["BoardIndependence"] = (result.IndependentMembers /
result.BoardSize * 100)
cols = [*keys, *(VARIABLE_LABELS.keys())]
result = result[cols].drop_duplicates()
return result, VARIABLE_LABELS
def estimate(self, nparrays: List[np.recarray]):
"""Compute the capital expenditures scaled by total assets
Parameters
----------
nparrays : List[np.recarray]
Input datasets, same order as specified in `DATASETS_REQUIRED`
Returns
-------
Tuple[pd.DataFrame, Dict[str, str]]
Output dataset and the `VARIABLE_LABELS`
"""
nparray = filter_funda(nparrays[0])
capx = np.true_divide(nparray.capx,
nparray.at,
where=(nparray.at != 0))
capx[np.isnan(nparray.at)] = np.nan
nparray = rfn.rec_append_fields(nparray, NAME, capx)
# keep only useful columns
cols = set(rfn.get_names_flat(nparray.dtype))
nparray.sort(order=(keys := ["gvkey", "datadate"]))