def data_loader_builder(verbose: bool = True):
msci_prices_from_feather = pd.read_feather(
'../../data/clean/msci_world_prices.feather')
if verbose:
print("MSCI World Prices:")
msci_prices_from_feather.info()
msci_mv_from_feather = pd.read_feather(
'../../data/clean/msci_world_mv.feather')
if verbose:
print("\nMSCI World Market Values:")
msci_mv_from_feather.info()
# 1-Month Treasury Constant Maturity Rate (GS1M)
rf_ = DataReader('GS1M', 'fred',
start=datetime.datetime(1990, 1,
1)).resample('MS').mean()
# We bring the annual rate to a monthly one
rf_m = rf_.div(100).div(12)
dl = DataLoader(prices=msci_prices_from_feather,
mv=msci_mv_from_feather,
rf=rf_m)
prices, mv, rf = dl.get_prices(), dl.get_mv(), dl.get_rf()
if verbose:
print(f'\n\'prices\' shape: {prices.shape}')
print(f'\'mv\' shape: {mv.shape}')
print(f'\'rf\' shape: {rf.shape}')
return rf, prices, mv, dl
def __update(self):
"""Updates class attributes."""
p, mv, rf = self.__prices, self.__mv, self.__rf
# Select attributes different from 'None'
li = [x for x in (p, mv, rf) if x is not None]
# if there is no element in the list, i.e., if all attributes are 'None'
if len(li) == 0:
self.__date = None
# if there is only one element not 'None' in the list, 'self.__date' should be equal to its index
elif len(li) == 1:
self.__date: np.ndarray = li[0].index.to_numpy()
# if there is at least 2 attributes that are not 'None' we must verify if rows match in length and in values
else:
# if lengths match (to prevent ValueError)
if self.__check_index_length_match(li):
# if length and values are the same
if self.__check_index_values_match(li):
self.__date = li[0].index.to_numpy().copy()
# if lengths are equal among each dataset index, but not the values
else:
# if values do not match, we force them to take the same
print(
"Lengths of rows match, but not they have different values."
)
self.__date = li[0].index.to_numpy().copy()
self.__make_indices_values_match()
assert self.__check_index_values_match(li)
# if any length mismatch, we truncate all DataFrames or Series
else:
# Get the oldest date among the list of DataFrames
min_date = min([df.index.min() for df in li])
# In the case there is a risk-free rate and that it begins after the other series: try
# to complete it with the 3 month proxy
if (self.__rf is not None) & (self.__rf.index[0] > min_date):
# Get initial date of the risk-free rate series
end = rf.index[0]
# 3-Month Treasury Constant Maturity Rate (GS3M)
rf3m = DataReader('GS3M', 'fred', start=min_date,
end=end).resample('MS').mean()
# We have to drop the last row to prevent overlapping
# We couldn't have used timedelta to go back 1 month as some have 31 days while others 30
rf3m.drop(rf3m.tail(1).index, inplace=True)
rf3m.columns = rf.columns
rf3m = rf3m.div(100).div(12)
# Concatenate both risk-free rates pd.Series
rf_concat = pd.concat([rf3m, self.__rf], sort=True)
errmsg: str = f"Got {rf_concat.shape} shape, but ({len(li[0].index)}, 1) expected."
assert rf_concat.shape[1] == 1, errmsg
self.__rf = rf_concat
# Join both series in a sole one
# self.__rf = rf_concat.iloc[:, 0].add(rf_concat.iloc[:, 1], fill_value=0)
else:
# Truncate rows of different length according to their dates
self.__truncate_rows()
# Verify if the rows were correctly truncated
not_none_attributes_list = self.__among_not_none_attributes(
)
err_message = "Rows were not correctly truncated"
assert self.__check_index_length_match(
not_none_attributes_list), err_message
# Update the 'self.__date' attribute with the first item
self.__date = not_none_attributes_list[0].index.to_numpy(
).copy()
# Propagate same indexes to the other datasets to force a perfect match
self.__make_indices_values_match()
# Verify that indices have same indexes
err_message = "Values do not match among not 'None' attributes."
assert self.__check_index_values_match(
self.__among_not_none_attributes()), err_message
self.__update()
