def returns_data(dates: List[str], time_step: str) -> None:
"""Computes the returns of the time series.
:param dates: List of the interval of dates to be analyzed
(i.e. ['1980-01-01', '2020-12-01']).
:param time_step: time step of the data (i.e. '1m', '1h', '1d', 'wk',
'1mo').
:return: None -- The function saves the data in a file and does not return
a value.
"""
function_name: str = returns_data.__name__
epochs_tools.function_header_print_data(function_name, dates, time_step, "", "")
try:
# Load data
data: pd.DataFrame = pickle.load(
open(
f"../data/original_data/original_data_{dates[0]}_{dates[1]}_step"
+ f"_{time_step}.pickle",
"rb",
)
)
returns_df: pd.DataFrame = data.pct_change().dropna()
returns_df = returns_df.iloc[:, :200]
# Saving data
epochs_tools.save_data(returns_df, function_name, dates, time_step, "", "")
except FileNotFoundError as error:
print("No data")
print(error)
print()
def normalized_returns_data(dates: List[str], time_step: str) -> None:
"""Normalizes the returns of the time series to mean zero and std deviation one.
:param dates: List of the interval of dates to be analyzed
(i.e. ['1980-01-01', '2020-12-31']).
:param time_step: time step of the data (i.e. '1m', '1h', '1d', 'wk',
'1mo').
:param window: window time to compute the volatility (i.e. '60').
:return: None -- The function saves the data in a file and does not return
a value.
"""
function_name: str = normalized_returns_data.__name__
epochs_tools.function_header_print_data(function_name, dates, time_step, "", "")
try:
# Load data
data: pd.DataFrame = pickle.load(
open(
f"../data/epochs/returns_data_{dates[0]}_{dates[1]}_step_{time_step}"
+ "_win__K_.pickle",
"rb",
)
)
normalized_df: pd.DataFrame = (data - data.mean()) / data.std()
# Saving data
epochs_tools.save_data(normalized_df, function_name, dates, time_step, "", "")
except FileNotFoundError as error:
print("No data")
print(error)
print()
def epochs_rolling_avg_correlation_matrix_data(
dates: List[str], time_step: str, window: str
) -> None:
"""Computes the correlation matrix of the normalized returns and average each column.
:param dates: List of the interval of dates to be analyzed
(i.e. ['1980-01-01', '2020-12-31']).
:param time_step: time step of the data (i.e. '1m', '1h', '1d', '1wk',
'1mo').
:param window: window time to compute the volatility (i.e. '25').
:return: None -- The function saves the data in a file and does not return
a value.
"""
function_name: str = epochs_rolling_avg_correlation_matrix_data.__name__
epochs_tools.function_header_print_data(function_name, dates, time_step, window, "")
try:
# Load data
data: pd.DataFrame = pickle.load(
open(
f"../data/epochs/normalized_returns_data_{dates[0]}"
+ f"_{dates[1]}_step_{time_step}_win__K_.pickle",
"rb",
)
)
_, k = data.shape
corr_matrix_df: pd.DataFrame = data.rolling(window=int(window)).corr().dropna()
avg_data = []
dates_series = []
for idx in set(corr_matrix_df.index.get_level_values(0)):
avg_data.append(corr_matrix_df.loc[idx].values.sum() / (k * k))
dates_series.append(idx)
series = pd.Series(data=avg_data, index=dates_series)
series = series.sort_index()
# Saving data
epochs_tools.save_data(series, function_name, dates, time_step, window, "")
except FileNotFoundError as error:
print("No data")
print(error)
print()
except TypeError as error:
print("To compute the correlation is needed at least to stocks")
print(error)
print()
def epochs_correlation_matrix_data(
dates: List[str], time_step: str, window: str
) -> None:
"""uses local normalization to compute the correlation matrix of the
normalized returns.
:param dates: List of the interval of dates to be analyzed
(i.e. ['1980-01-01', '2020-12-31']).
:param time_step: time step of the data (i.e. '1m', '1h', '1d', '1wk',
'1mo').
:param window: window time to compute the volatility (i.e. '25').
:return: None -- The function saves the data in a file and does not return
a value.
"""
function_name: str = epochs_correlation_matrix_data.__name__
epochs_tools.function_header_print_data(function_name, dates, time_step, window)
try:
# Load data
data: pd.DataFrame = pickle.load(
open(
f"../data/epochs/epochs_normalized_returns_data_{dates[0]}"
+ f"_{dates[1]}_step_{time_step}_win_{window}.pickle",
"rb",
)
)
corr_matrix_df: pd.DataFrame = data.corr()
# Saving data
epochs_tools.save_data(corr_matrix_df, function_name, dates, time_step, window)
except FileNotFoundError as error:
print("No data")
print(error)
print()
except TypeError as error:
print("To compute the correlation is needed at least to stocks")
print(error)
print()
def epochs_rolling_volatility_data(
dates: List[str], time_step: str, window: str
) -> None:
"""Uses local normalization to compute the volatility of the time series.
:param dates: List of the interval of dates to be analyzed
(i.e. ['1980-01-01', '2020-12-31']).
:param time_step: time step of the data (i.e. '1m', '1h', '1d', '1wk',
'1mo').
:param window: window time to compute the volatility (i.e. '25').
:return: None -- The function saves the data in a file and does not return
a value.
"""
function_name: str = epochs_rolling_volatility_data.__name__
epochs_tools.function_header_print_data(function_name, dates, time_step, window, "")
try:
# Load data
data: pd.DataFrame = pickle.load(
open(
f"../data/epochs/normalized_returns_data_{dates[0]}_{dates[1]}_step"
+ f"_{time_step}_win__K_.pickle",
"rb",
)
)
std_df: pd.DataFrame = data.rolling(window=int(window)).std().dropna()
# Saving data
epochs_tools.save_data(std_df, function_name, dates, time_step, window, "")
except FileNotFoundError as error:
print("No data")
print(error)
print()
def epochs_aggregated_dist_returns_market_data(
dates: List[str], time_step: str, window: str, K_value: str, norm: str = "long"
) -> None:
"""Computes the aggregated distribution of returns for a market.
:param dates: List of the interval of dates to be analyzed
(i.e. ['1980-01-01', '2020-12-31']).
:param time_step: time step of the data (i.e. '1m', '1h', '1d', '1wk',
'1mo').
:param window: window time to compute the volatility (i.e. '25').
:param K_value: number of companies to be used (i.e. '80', 'all').
:norm: define if the normalization is made in the complete time series or
in each epoch. Default 'long', 'short' is the other option.
:return: None -- The function saves the data in a file and does not return
a value.
"""
function_name: str = epochs_aggregated_dist_returns_market_data.__name__
epochs_tools.function_header_print_data(
function_name, dates, time_step, window, K_value
)
try:
# Load name of the stocks
if K_value == "all":
stocks_name: pd.DataFrame = pickle.load(
open(
f"../data/epochs/returns_data_{dates[0]}_{dates[1]}_step"
+ f"_{time_step}_win__K_.pickle",
"rb",
)
)[:200]
else:
stocks_name = pickle.load(
open(
f"../data/epochs/returns_data_{dates[0]}_{dates[1]}_step"
+ f"_{time_step}_win__K_.pickle",
"rb",
)
).sample(n=int(K_value), axis="columns")
agg_ret_mkt_list: List[List[float]] = []
# Combination of stock pairs
stocks_comb: Iterable[Tuple[Any, ...]] = icomb(stocks_name, 2)
args_prod: Iterable[Any] = iprod(
[dates], [time_step], stocks_comb, [window], [norm]
)
# Parallel computing
with mp.Pool(processes=mp.cpu_count()) as pool:
agg_ret_mkt_list.extend(
pool.starmap(epochs_aggregated_dist_returns_pair_data, args_prod)
)
# Flatten the list
agg_ret_mkt_list_flat: List[float] = [
val for sublist in agg_ret_mkt_list for val in sublist
]
agg_ret_mkt_series: pd.Series = pd.Series(agg_ret_mkt_list_flat)
print(f"mean = {agg_ret_mkt_series.mean()}")
print(f"std = {agg_ret_mkt_series.std()}")
# Saving data
epochs_tools.save_data(
agg_ret_mkt_series,
function_name + "_" + norm,
dates,
time_step,
window,
K_value,
)
del agg_ret_mkt_list
del agg_ret_mkt_series
except FileNotFoundError as error:
print("No data")
print(error)
print()