def test_apply_offset(self):
ans = datetime(2016, 8, 2)
self.assertEqual(date_shift(self.t, "+1bd"), ans)
ans = datetime(2016, 7, 25)
self.assertEqual(date_shift(self.t, "-Mon"), ans)
ans = datetime(2016, 8, 8)
self.assertEqual(date_shift(self.t, "+Mon"), ans)
def load_eur():
""" Return cash rate for EUR and DEM prior to the introduction of EUR """
bank_rate = quandl.get(CashFile.GER_BANKRATE.value, api_key=quandl_token)
ww2_data = pd.DataFrame([4.0, 3.5, 5.0],
index=[
datetime(1936, 6, 30),
datetime(1940, 4, 9),
datetime(1948, 6, 28)
])
ww2_month = pd.date_range('1936-06-01', '1948-06-01', freq='M')
ww2_month = pd.DataFrame(index=ww2_month)
ww2_data = pd.concat((ww2_data, ww2_month), axis=1).fillna(method="pad")
parser = lambda d: date_shift(datetime.strptime(d, "%Y-%m"), "+BMonthEnd")
filename = join(DATA_DIRECTORY, 'cash_rate', 'eur', 'BBK01.SU0112.csv')
discount_rate = pd.read_csv(filename,
index_col=0,
skiprows=[1, 2, 3, 4],
usecols=[0, 1],
engine="python",
skipfooter=95,
parse_dates=True,
date_parser=parser)
ib_rate = DataReader(CashFile.EUR_3M_IB_RATE.value, "fred", START_DATE)
libor = quandl.get(CashFile.EUR_3M_EURIBOR.value, api_key=quandl_token)
data = (pd.concat(
(bank_rate[:"1936-06"].fillna(method="pad"), ww2_data,
discount_rate[:"1959"].fillna(method="pad"),
to_monthend(ib_rate['1960':"1998"].fillna(method="pad")),
libor['1999':].fillna(method="pad")),
axis=1).sum(axis=1).rename("cash_rate_eur"))
return data
def data_to_mongo(symbol, data):
metadata = {'last_datetime': data.index[-1]}
if library.has_symbol(symbol):
# only append non-overlapping part
existing_up_to = library.read(symbol).metadata['last_datetime']
last_existing_data = library.read(symbol,
date_range=DateRange(existing_up_to))
if len(last_existing_data.data) != 1:
raise ValueError('metadata and database are not consistent.')
save_from = date_shift(existing_up_to, data_frequency)
save_data = data.loc[save_from:, :]
library.append(symbol, save_data, metadata=metadata)
else:
library.write(symbol, data, metadata=metadata)
def load_jpy():
""" Return cash rate for JPY """
libor = DataReader(CashFile.JPY_3M_LIBOR.value, 'fred', START_DATE)
parser = lambda d: date_shift(datetime.strptime(d, "%Y/%m"), "+BMonthEnd")
filename = join(DATA_DIRECTORY, 'cash_rate', 'jpy', 'discount_rate.csv')
discount_rate = pd.read_csv(filename,
index_col=0,
usecols=[0, 1],
parse_dates=True,
date_parser=parser)
data = (pd.concat(
(discount_rate["1882-10":"1985-12"].astype("float").fillna(
method="pad"), libor['1986':].fillna(method="pad")),
axis=1).sum(axis=1).rename("cash_rate_jpy"))
return data
raise ValueError('metadata and database are not consistent.')
save_from = date_shift(existing_up_to, data_frequency)
save_data = data.loc[save_from:, :]
logger.debug('Append {} rows'.format(len(save_data)))
library.append(symbol, save_data, metadata=metadata)
else:
logger.debug('Write {} rows'.format(len(data)))
library.write(symbol, data, metadata=metadata)
if __name__ == '__main__':
for ccy_pair in ccy_pairs:
logger.info('Updating {}'.format(ccy_pair))
last_update = get_last_update(ccy_pair)
download_date = date_shift(last_update, '+MonthBegin')
last_month = date_shift(datetime.today(), '-MonthEnd')
while download_date < last_month:
logger.info('Downloading {}-{}'.format(download_date.year,
download_date.month))
download_url = get_download_url(ccy_pair, download_date)
filename = download_url.split('/')[-1].replace('zip', 'csv')
logger.debug('Try download: {}'.format(download_url))
download_zip_from_url(download_url, download_to)
logger.debug('Loading csv: {}'.format(filename))
csv_filepath = join(download_to, filename)
data = get_df_from_csv(csv_filepath)
# remove duplicate rows, also sometimes csv contains NaNs.
def test_multi_apply(self):
ans = datetime(2016, 8, 26)
self.assertEqual(date_shift(self.t, "+MonthEnd-3bd"), ans)
def test_apply_offset_without_int(self):
ans = datetime(2016, 8, 31)
self.assertEqual(date_shift(self.t, "+MonthEnd"), ans)
