def load(name, environ=os.environ, timestamp=None):
"""Loads a previously ingested bundle.
Parameters
----------
name : str
The name of the bundle.
environ : mapping, optional
The environment variables. Defaults of os.environ.
timestamp : datetime, optional
The timestamp of the data to lookup.
Defaults to the current time.
Returns
-------
bundle_data : BundleData
The raw data readers for this bundle.
"""
if timestamp is None:
timestamp = pd.Timestamp.utcnow()
timestr = most_recent_data(name, timestamp, environ=environ)
return BundleData(
asset_finder=AssetFinder(
asset_db_path(name, timestr, environ=environ), ),
equity_minute_bar_reader=BcolzMinuteBarReader(
minute_equity_path(name, timestr, environ=environ), ),
equity_daily_bar_reader=CNBcolzDailyBarReader(
daily_equity_path(name, timestr, environ=environ), ),
adjustment_reader=SQLiteAdjustmentReader(
adjustment_db_path(name, timestr, environ=environ), ),
fundamental_reader=SQLiteFundamentalsReader(
fundamentals_db_path(name, timestr, environ=environ), ),
)
def load_sharadar_bundle(name=SHARADAR_BUNDLE_NAME,
timestr=SHARADAR_BUNDLE_DIR,
environ=os.environ):
return BundleData(
asset_finder=SQLiteAssetFinder(
asset_db_path(name, timestr, environ=environ), ),
equity_minute_bar_reader=None,
equity_daily_bar_reader=SQLiteDailyBarReader(
daily_equity_path(name, timestr, environ=environ), ),
adjustment_reader=SQLiteAdjustmentReader(
adjustment_db_path(name, timestr, environ=environ), ),
)
def component_dataframes(self, convert_dates=True):
with SQLiteAdjustmentReader(self.db_path) as r:
return r.unpack_db_to_component_dfs(convert_dates=convert_dates)
def calc_dividend_ratios(self, dividends):
"""
Calculate the ratios to apply to equities when looking back at pricing
history so that the price is smoothed over the ex_date, when the market
adjusts to the change in equity value due to upcoming dividend.
Returns
-------
DataFrame
A frame in the same format as splits and mergers, with keys
- sid, the id of the equity
- effective_date, the date in seconds on which to apply the ratio.
- ratio, the ratio to apply to backwards looking pricing data.
"""
if dividends is None or dividends.empty:
return pd.DataFrame(np.array(
[],
dtype=[
('sid', uint64_dtype),
('effective_date', uint32_dtype),
('ratio', float64_dtype),
],
))
pricing_reader = self._equity_daily_bar_reader
input_sids = dividends.sid.values
unique_sids, sids_ix = np.unique(input_sids, return_inverse=True)
dates = pricing_reader.sessions.values
start = pd.Timestamp(dates[0], tz='UTC')
end = pd.Timestamp(dates[-1], tz='UTC')
calendar = self._equity_daily_bar_reader.trading_calendar
data_portal = DataPortal(self._asset_finder,
trading_calendar=calendar,
first_trading_day=start,
equity_daily_reader=self._equity_daily_bar_reader,
adjustment_reader= SQLiteAdjustmentReader(self._filename))
close = data_portal.get_history_window(assets=unique_sids,
end_dt=end,
bar_count=calendar.session_distance(start, end),
frequency='1d',
field='close',
data_frequency='daily').values
date_ix = np.searchsorted(dates, dividends.ex_date.values)
mask = date_ix > 0
date_ix = date_ix[mask]
sids_ix = sids_ix[mask]
input_dates = dividends.ex_date.values[mask]
# subtract one day to get the close on the day prior to the merger
previous_close = close[date_ix - 1, sids_ix]
input_sids = input_sids[mask]
amount = dividends.amount.values[mask]
ratio = 1.0 - amount / previous_close
non_nan_ratio_mask = ~np.isnan(ratio)
for ix in np.flatnonzero(~non_nan_ratio_mask):
ex_date = pd.Timestamp(input_dates[ix], tz='UTC')
start_date = self._asset_finder.retrieve_asset(input_sids[ix]).start_date
if ex_date != start_date:
log.warn(
"Couldn't compute ratio for dividend"
" sid={sid}, ex_date={ex_date:%Y-%m-%d}, start_date={start_date:%Y-%m-%d}, amount={amount:.3f}",
sid=input_sids[ix],
ex_date=ex_date,
amount=amount[ix],
start_date=start_date
)
valid_ratio_mask = non_nan_ratio_mask > 0
for ix in np.flatnonzero(~valid_ratio_mask):
log.warn(
"Dividend ratio <= 0 for dividend"
" sid={sid}, ex_date={ex_date:%Y-%m-%d}, amount={amount:.3f}",
sid=input_sids[ix],
ex_date=pd.Timestamp(input_dates[ix]),
amount=amount[ix],
)
return pd.DataFrame({
'sid': input_sids[valid_ratio_mask],
'effective_date': input_dates[valid_ratio_mask],
'ratio': ratio[valid_ratio_mask],
})