def load_market_data(bm_symbol='^GSPC'):
bm_filepath = get_data_filepath(get_benchmark_filename(bm_symbol))
try:
saved_benchmarks = pd.Series.from_csv(bm_filepath)
except (OSError, IOError):
print("""
data files aren't distributed with source.
Fetching data from Yahoo Finance.
""".strip())
dump_benchmarks(bm_symbol)
saved_benchmarks = pd.Series.from_csv(bm_filepath)
saved_benchmarks = saved_benchmarks.tz_localize('UTC')
most_recent = pd.Timestamp('today', tz='UTC') - trading_day
most_recent_index = trading_days.searchsorted(most_recent)
days_up_to_now = trading_days[:most_recent_index + 1]
# Find the offset of the last date for which we have trading data in our
# list of valid trading days
last_bm_date = saved_benchmarks.index[-1]
last_bm_date_offset = days_up_to_now.searchsorted(
last_bm_date.strftime('%Y/%m/%d'))
# If more than 1 trading days has elapsed since the last day where
# we have data,then we need to update
if len(days_up_to_now) - last_bm_date_offset > 1:
benchmark_returns = update_benchmarks(bm_symbol, last_bm_date)
if (
benchmark_returns.index.tz is None
or
benchmark_returns.index.tz.zone != 'UTC'
):
benchmark_returns = benchmark_returns.tz_localize('UTC')
else:
benchmark_returns = saved_benchmarks
if (
benchmark_returns.index.tz is None
or
benchmark_returns.index.tz.zone != 'UTC'
):
benchmark_returns = benchmark_returns.tz_localize('UTC')
# Get treasury curve module, filename & source from mapping.
# Default to USA.
module, filename, source = INDEX_MAPPING.get(
bm_symbol, INDEX_MAPPING['^GSPC'])
tr_filepath = get_data_filepath(filename)
try:
saved_curves = pd.DataFrame.from_csv(tr_filepath)
except (OSError, IOError):
print("""
data files aren't distributed with source.
Fetching data from {0}
""".format(source).strip())
dump_treasury_curves(module, filename)
saved_curves = pd.DataFrame.from_csv(tr_filepath)
# Find the offset of the last date for which we have trading data in our
# list of valid trading days
last_tr_date = saved_curves.index[-1]
last_tr_date_offset = days_up_to_now.searchsorted(
last_tr_date.strftime('%Y/%m/%d'))
# If more than 1 trading days has elapsed since the last day where
# we have data,then we need to update
if len(days_up_to_now) - last_tr_date_offset > 1:
treasury_curves = dump_treasury_curves(module, filename)
else:
treasury_curves = saved_curves.tz_localize('UTC')
tr_curves = {}
for tr_dt, curve in treasury_curves.T.iterkv():
# tr_dt = tr_dt.replace(hour=0, minute=0, second=0, microsecond=0,
# tzinfo=pytz.utc)
tr_curves[tr_dt] = curve.to_dict()
tr_curves = OrderedDict(sorted(
((dt, c) for dt, c in iteritems(tr_curves)),
key=lambda t: t[0]))
return benchmark_returns, tr_curves
def load_market_data(bm_symbol='^GSPC'):
effective_days = trading_days[trading_days >= "2000-01-01"]
bm_filepath = get_data_filepath(get_benchmark_filename(bm_symbol))
try:
saved_benchmarks = pd.Series.from_csv(bm_filepath)
except (OSError, IOError):
print("""
data files aren't distributed with source.
Fetching data from Yahoo Finance.
""".strip())
#dump_benchmarks(bm_symbol)
#saved_benchmarks = pd.Series.from_csv(bm_filepath)
saved_benchmarks = pd.Series(data=0.00002,
index=effective_days).tz_localize(None)
saved_benchmarks = saved_benchmarks.tz_localize('UTC')
most_recent = pd.Timestamp('today', tz='UTC') - trading_day
most_recent_index = trading_days.searchsorted(most_recent)
days_up_to_now = trading_days[:most_recent_index + 1]
# Find the offset of the last date for which we have trading data in our
# list of valid trading days
last_bm_date = saved_benchmarks.index[-1]
last_bm_date_offset = days_up_to_now.searchsorted(
last_bm_date.strftime('%Y/%m/%d'))
# If more than 1 trading days has elapsed since the last day where
# we have data,then we need to update
if len(days_up_to_now) - last_bm_date_offset > 1:
benchmark_returns = update_benchmarks(bm_symbol, last_bm_date)
if (benchmark_returns.index.tz is None
or benchmark_returns.index.tz.zone != 'UTC'):
benchmark_returns = benchmark_returns.tz_localize('UTC')
else:
benchmark_returns = saved_benchmarks
if (benchmark_returns.index.tz is None
or benchmark_returns.index.tz.zone != 'UTC'):
benchmark_returns = benchmark_returns.tz_localize('UTC')
# Get treasury curve module, filename & source from mapping.
# Default to USA.
module, filename, source = INDEX_MAPPING.get(bm_symbol,
INDEX_MAPPING['^GSPC'])
tr_filepath = get_data_filepath(filename)
try:
saved_curves = pd.DataFrame.from_csv(tr_filepath)
except (OSError, IOError):
print("""
data files aren't distributed with source.
Fetching data from {0}
""".format(source).strip())
#dump_treasury_curves(module, filename)
#saved_curves = pd.DataFrame.from_csv(tr_filepath)
saved_curves = pd.DataFrame(0.0001,
index=effective_days,
columns=[
'10year', '1month', '1year', '20year',
'2year', '30year', '3month', '3year',
'5year', '6month', '7year', 'date', 'tid'
]).tz_localize(None)
# Find the offset of the last date for which we have trading data in our
# list of valid trading days
last_tr_date = saved_curves.index[-1]
last_tr_date_offset = days_up_to_now.searchsorted(
last_tr_date.strftime('%Y/%m/%d'))
# If more than 1 trading days has elapsed since the last day where
# we have data,then we need to update
if len(days_up_to_now) - last_tr_date_offset > 1:
treasury_curves = dump_treasury_curves(module, filename)
else:
treasury_curves = saved_curves.tz_localize('UTC')
tr_curves = {}
for tr_dt, curve in treasury_curves.T.iteritems():
# tr_dt = tr_dt.replace(hour=0, minute=0, second=0, microsecond=0,
# tzinfo=pytz.utc)
tr_curves[tr_dt] = curve.to_dict()
tr_curves = OrderedDict(
sorted(((dt, c) for dt, c in iteritems(tr_curves)),
key=lambda t: t[0]))
return benchmark_returns, tr_curves
def load_market_data(bm_symbol='^GSPC'):
try:
fp_bm = get_datafile(get_benchmark_filename(bm_symbol), "rb")
except IOError:
print("""
data files aren't distributed with source.
Fetching data from Yahoo Finance.
""").strip()
dump_benchmarks(bm_symbol)
fp_bm = get_datafile(get_benchmark_filename(bm_symbol), "rb")
saved_benchmarks = pd.Series.from_csv(fp_bm)
saved_benchmarks = saved_benchmarks.tz_localize('UTC')
fp_bm.close()
# Find the offset of the last date for which we have trading data in our
# list of valid trading days
last_bm_date = saved_benchmarks.index[-1]
last_bm_date_offset = trading_days.searchsorted(
last_bm_date.strftime('%Y/%m/%d'))
# If more than 1 trading days has elapsed since the last day where
# we have data,then we need to update
if len(trading_days) - last_bm_date_offset > 1:
benchmark_returns = update_benchmarks(bm_symbol, last_bm_date)
if benchmark_returns.index.tz.zone != 'UTC':
benchmark_returns = benchmark_returns.tz_localize('UTC')
else:
benchmark_returns = saved_benchmarks
if benchmark_returns.index.tz.zone != 'UTC':
benchmark_returns = benchmark_returns.tz_localize('UTC')
try:
fp_tr = get_datafile('treasury_curves.csv', "rb")
except IOError:
print("""
data files aren't distributed with source.
Fetching data from data.treasury.gov
""").strip()
dump_treasury_curves()
fp_tr = get_datafile('treasury_curves.csv', "rb")
saved_curves = pd.DataFrame.from_csv(fp_tr)
# Find the offset of the last date for which we have trading data in our
# list of valid trading days
last_tr_date = saved_curves.index[-1]
last_tr_date_offset = trading_days.searchsorted(
last_tr_date.strftime('%Y/%m/%d'))
# If more than 1 trading days has elapsed since the last day where
# we have data,then we need to update
if len(trading_days) - last_tr_date_offset > 1:
treasury_curves = dump_treasury_curves()
else:
treasury_curves = saved_curves.tz_localize('UTC')
tr_curves = {}
for tr_dt, curve in treasury_curves.T.iterkv():
# tr_dt = tr_dt.replace(hour=0, minute=0, second=0, microsecond=0,
# tzinfo=pytz.utc)
tr_curves[tr_dt] = curve.to_dict()
fp_tr.close()
tr_curves = OrderedDict(sorted(
((dt, c) for dt, c in tr_curves.iteritems()),
key=lambda t: t[0]))
return benchmark_returns, tr_curves
def load_market_data(bm_symbol='^GSPC'):
try:
fp_bm = get_datafile(get_benchmark_filename(bm_symbol), "rb")
except IOError:
print("""
data msgpacks aren't distributed with source.
Fetching data from Yahoo Finance.
""").strip()
dump_benchmarks(bm_symbol)
fp_bm = get_datafile(get_benchmark_filename(bm_symbol), "rb")
bm_list = msgpack.loads(fp_bm.read())
# Find the offset of the last date for which we have trading data in our
# list of valid trading days
last_bm_date = tuple_to_date(bm_list[-1][0])
last_bm_date_offset = trading_days.searchsorted(
last_bm_date.strftime('%Y/%m/%d'))
# If more than 1 trading days has elapsed since the last day where
# we have data,then we need to update
if len(trading_days) - last_bm_date_offset > 1:
update_benchmarks(bm_symbol, last_bm_date)
fp_bm = get_datafile(get_benchmark_filename(bm_symbol), "rb")
bm_list = msgpack.loads(fp_bm.read())
bm_returns = []
for packed_date, returns in bm_list:
event_dt = tuple_to_date(packed_date)
daily_return = DailyReturn(date=event_dt, returns=returns)
bm_returns.append(daily_return)
fp_bm.close()
bm_returns = sorted(bm_returns, key=attrgetter('date'))
try:
fp_tr = get_datafile('treasury_curves.msgpack', "rb")
except IOError:
print("""
data msgpacks aren't distributed with source.
Fetching data from data.treasury.gov
""").strip()
dump_treasury_curves()
fp_tr = get_datafile('treasury_curves.msgpack', "rb")
tr_list = msgpack.loads(fp_tr.read())
# Find the offset of the last date for which we have trading data in our
# list of valid trading days
last_tr_date = tuple_to_date(tr_list[-1][0])
last_tr_date_offset = trading_days.searchsorted(
last_tr_date.strftime('%Y/%m/%d'))
# If more than 1 trading days has elapsed since the last day where
# we have data,then we need to update
if len(trading_days) - last_tr_date_offset > 1:
update_treasury_curves(last_tr_date)
fp_tr = get_datafile('treasury_curves.msgpack', "rb")
tr_list = msgpack.loads(fp_tr.read())
tr_curves = {}
for packed_date, curve in tr_list:
tr_dt = tuple_to_date(packed_date)
# tr_dt = tr_dt.replace(hour=0, minute=0, second=0, microsecond=0,
# tzinfo=pytz.utc)
tr_curves[tr_dt] = curve
fp_tr.close()
tr_curves = OrderedDict(sorted(
((dt, c) for dt, c in tr_curves.iteritems()),
key=lambda t: t[0]))
return bm_returns, tr_curves
def load_market_data(bm_symbol='^GSPC'):
bm_filepath = get_data_filepath(get_benchmark_filename(bm_symbol))
try:
saved_benchmarks = pd.Series.from_csv(bm_filepath)
except (OSError, IOError):
print("""
data files aren't distributed with source.
Fetching data from Yahoo Finance.
""".strip())
dump_benchmarks(bm_symbol)
saved_benchmarks = pd.Series.from_csv(bm_filepath)
saved_benchmarks = saved_benchmarks.tz_localize('UTC')
most_recent = pd.Timestamp('today', tz='UTC') - trading_day
most_recent_index = trading_days.searchsorted(most_recent)
days_up_to_now = trading_days[:most_recent_index + 1]
# Find the offset of the last date for which we have trading data in our
# list of valid trading days
last_bm_date = saved_benchmarks.index[-1]
last_bm_date_offset = days_up_to_now.searchsorted(
last_bm_date.strftime('%Y/%m/%d'))
# If more than 1 trading days has elapsed since the last day where
# we have data,then we need to update
# We're doing "> 2" rather than "> 1" because we're subtracting an array
# _length_ from an array _index_, and therefore even if we had data up to
# and including the current day, the difference would still be 1.
if len(days_up_to_now) - last_bm_date_offset > 2:
benchmark_returns = update_benchmarks(bm_symbol, last_bm_date)
if benchmark_returns.index.tz is None or \
benchmark_returns.index.tz.zone != 'UTC':
benchmark_returns = benchmark_returns.tz_localize('UTC')
else:
benchmark_returns = saved_benchmarks
if benchmark_returns.index.tz is None or\
benchmark_returns.index.tz.zone != 'UTC':
benchmark_returns = benchmark_returns.tz_localize('UTC')
# Get treasury curve module, filename & source from mapping.
# Default to USA.
module, filename, source = INDEX_MAPPING.get(bm_symbol,
INDEX_MAPPING['^GSPC'])
tr_filepath = get_data_filepath(filename)
try:
saved_curves = pd.DataFrame.from_csv(tr_filepath)
except (OSError, IOError):
print("""
data files aren't distributed with source.
Fetching data from {0}
""".format(source).strip())
dump_treasury_curves(module, filename)
saved_curves = pd.DataFrame.from_csv(tr_filepath)
# Find the offset of the last date for which we have trading data in our
# list of valid trading days
last_tr_date = saved_curves.index[-1]
last_tr_date_offset = days_up_to_now.searchsorted(
last_tr_date.strftime('%Y/%m/%d'))
# If more than 1 trading days has elapsed since the last day where
# we have data,then we need to update
# Comment above explains why this is "> 2".
if len(days_up_to_now) - last_tr_date_offset > 2:
treasury_curves = dump_treasury_curves(module, filename)
else:
treasury_curves = saved_curves.tz_localize('UTC')
tr_curves = {}
for tr_dt, curve in treasury_curves.T.iteritems():
# tr_dt = tr_dt.replace(hour=0, minute=0, second=0, microsecond=0,
# tzinfo=pytz.utc)
tr_curves[tr_dt] = curve.to_dict()
tr_curves = OrderedDict(
sorted(((dt, c) for dt, c in iteritems(tr_curves)),
key=lambda t: t[0]))
return benchmark_returns, tr_curves