def returns_plot(dates: List[str], time_step: str) -> None:
"""Plots the returns of five stocks.
:param dates: List of the interval of dates to be analyzed
(i.e. ['1980-01', '2020-12']).
:param time_step: time step of the data (i.e. '1m', '2m', '5m', ...).
:return: None -- The function saves the plot in a file and does not return
a value.
"""
function_name: str = returns_plot.__name__
exact_distributions_correlation_tools.function_header_print_plot(
function_name, dates, time_step
)
try:
# Load data
returns_data: pd.DataFrame = pickle.load(
open(
f"../data/exact_distributions_correlation/returns_data"
+ f"_{dates[0]}_{dates[1]}_step_{time_step}.pickle",
"rb",
)
).iloc[:, :5]
plot: np.ndarray = returns_data.plot(
subplots=True, sharex=True, figsize=(16, 16), grid=True, sort_columns=True
)
_ = [ax.set_ylabel("Returns", fontsize=20) for ax in plot]
_ = [plot.legend(loc=1, fontsize=20) for plot in plt.gcf().axes]
plt.xlabel(f"Date - {time_step}", fontsize=20)
plt.tight_layout(pad=0.5)
figure: plt.Figure = plot[0].get_figure()
# Plotting
exact_distributions_correlation_tools.save_plot(
figure, function_name, dates, time_step
)
plt.close()
del returns_data
del figure
gc.collect()
except FileNotFoundError as error:
print("No data")
print(error)
print()
def aggregated_dist_returns_market_plot(dates: List[str], time_step: str) -> None:
"""Plots the aggregated distribution of returns for a market.
:param dates: List of the interval of dates to be analyzed
(i.e. ['1980-01', '2020-12']).
:param time_step: time step of the data (i.e. '1m', '2m', '5m', ...).
:return: None -- The function saves the plot in a file and does not return
a value.
"""
function_name: str = aggregated_dist_returns_market_plot.__name__
exact_distributions_correlation_tools.function_header_print_plot(
function_name, dates, time_step
)
try:
# Load data
agg_returns_data: pd.Series = pickle.load(
open(
"../data/exact_distributions_correlation/aggregated_dist_returns"
+ f"_market_data_{dates[0]}_{dates[1]}_step_{time_step}.pickle",
"rb",
)
)
agg_returns_data = agg_returns_data.rename("Agg. returns")
x_gauss: np.ndarray = np.arange(-10, 10, 0.1)
gaussian: np.ndarray = (
exact_distributions_correlation_tools.gaussian_distribution(0, 1, x_gauss)
)
# Log plot
plot_log = agg_returns_data.plot(
kind="density", style="-", logy=True, figsize=(16, 9), legend=True, lw=3
)
plt.semilogy(x_gauss, gaussian, "o", lw=3, label="Gaussian")
plt.legend(fontsize=20)
plt.title(
f"Aggregated distribution returns from {dates[0]} to"
+ f" {dates[1]} - {time_step}",
fontsize=30,
)
plt.xlabel("Aggregated returns", fontsize=25)
plt.ylabel("PDF", fontsize=25)
plt.xticks(fontsize=15)
plt.yticks(fontsize=15)
plt.xlim(-10, 10)
plt.ylim(10 ** -9, 1)
plt.grid(True)
plt.tight_layout()
figure_log: plt.Figure = plot_log.get_figure()
left, bottom, width, height = [0.36, 0.13, 0.35, 0.3]
ax2 = figure_log.add_axes([left, bottom, width, height])
agg_returns_data.plot(kind="density", style="-", legend=False, lw=3)
ax2.plot(x_gauss, gaussian, "o")
plt.xlim(-2, 2)
plt.ylim(0, 0.6)
plt.grid(True)
# Plotting
exact_distributions_correlation_tools.save_plot(
figure_log, function_name + "_log", dates, time_step
)
plt.close()
del agg_returns_data
del figure_log
del plot_log
gc.collect()
except FileNotFoundError as error:
print("No data")
print(error)
print()
def pdf_log_all_distributions_plot(dates: List[str], time_step: str) -> None:
"""Plots all the distributions and compares with agg. returns of a market.
:param dates: List of the interval of dates to be analyzed
(i.e. ['1980-01', '2020-12']).
:param time_step: time step of the data (i.e. '1m', '2m', '5m', ...).
:return: None -- The function saves the plot in a file and does not return
a value.
"""
function_name: str = pdf_log_all_distributions_plot.__name__
exact_distributions_correlation_tools.function_header_print_plot(
function_name, dates, time_step
)
try:
# Load data
agg_returns_data: pd.Series = pickle.load(
open(
"../data/exact_distributions_correlation/aggregated_dist_returns"
+ f"_market_data_{dates[0]}_{dates[1]}_step_{time_step}.pickle",
"rb",
)
)
agg_returns_data = agg_returns_data.rename("Agg. returns")
x_val: np.ndarray = np.arange(-10, 10, 0.1)
# Log plot
plot_log = agg_returns_data.plot(
kind="density", style="-", logy=True, figsize=(16, 9), legend=True, lw=3
)
if dates[0] == "1972-01":
N = 5.5
N_aa = 6
K = 23
L = 55
l = 55
gg_distribution: np.ndarray = (
exact_distributions_correlation_tools.pdf_gaussian_gaussian(x_val, N, 1)
)
plt.semilogy(x_val, gg_distribution, "o", lw=3, label=f"GG - N = {N}")
ga_distribution: np.ndarray = (
exact_distributions_correlation_tools.pdf_gaussian_algebraic(
x_val, K, L, N, 1
)
)
plt.semilogy(
x_val,
ga_distribution,
"o",
lw=3,
label=f"GA - N = {N} - K = {K} - L = {L}",
)
ag_distribution: np.ndarray = (
exact_distributions_correlation_tools.pdf_algebraic_gaussian(
x_val, K, l, N, 1
)
)
plt.semilogy(
x_val,
ag_distribution,
"o",
lw=3,
label=f"AG - N = {N} - K = {K} - l = {l}",
)
aa_distribution: np.ndarray = (
exact_distributions_correlation_tools.pdf_algebraic_algebraic(
x_val, K, L, l, N_aa, 1
)
)
plt.semilogy(
x_val,
aa_distribution,
"o",
lw=3,
label=f"AA - N = {N_aa} - K = {K} - L = {L}" + f" - l = {l}",
)
elif dates[0] == "1992-01":
N = 6
N_gg = 5
N_aa = 9
K = 277
L = 150
l = 150
gg_distribution: np.ndarray = (
exact_distributions_correlation_tools.pdf_gaussian_gaussian(
x_val, N_gg, 1
)
)
plt.semilogy(x_val, gg_distribution, "o", lw=3, label=f"GG - N = {N_gg}")
ga_distribution: np.ndarray = (
exact_distributions_correlation_tools.pdf_gaussian_algebraic(
x_val, K, L, N, 1
)
)
plt.semilogy(
x_val,
ga_distribution,
"o",
lw=3,
label=f"GA - N = {N} - K = {K} - L = {L}",
)
ag_distribution: np.ndarray = (
exact_distributions_correlation_tools.pdf_algebraic_gaussian(
x_val, K, l, N, 1
)
)
plt.semilogy(
x_val,
ag_distribution,
"o",
lw=3,
label=f"AG - N = {N} - K = {K} - l = {l}",
)
aa_distribution: np.ndarray = (
exact_distributions_correlation_tools.pdf_algebraic_algebraic(
x_val, K, L, l, N_aa, 1
)
)
plt.semilogy(
x_val,
aa_distribution,
"o",
lw=3,
label=f"AA - N = {N_aa} - K = {K} - L = {L}" + f" - l = {l}",
)
else:
N = 7
N_aa = 8
K = 461
L = 280
l = 280
gg_distribution: np.ndarray = (
exact_distributions_correlation_tools.pdf_gaussian_gaussian(x_val, N, 1)
)
plt.semilogy(x_val, gg_distribution, "o", lw=3, label=f"GG - N = {N}")
ga_distribution: np.ndarray = (
exact_distributions_correlation_tools.pdf_gaussian_algebraic(
x_val, K, L, N, 1
)
)
plt.semilogy(
x_val,
ga_distribution,
"o",
lw=3,
label=f"GA - N = {N} - K = {K} - L = {L}",
)
ag_distribution: np.ndarray = (
exact_distributions_correlation_tools.pdf_algebraic_gaussian(
x_val, K, l, N, 1
)
)
plt.semilogy(
x_val,
ag_distribution,
"o",
lw=3,
label=f"AG - N = {N} - K = {K} - l = {l}",
)
aa_distribution: np.ndarray = (
exact_distributions_correlation_tools.pdf_algebraic_algebraic(
x_val, K, L, l, N_aa, 1
)
)
plt.semilogy(
x_val,
aa_distribution,
"o",
lw=3,
label=f"AA - N = {N_aa} - K = {K} - L = {L}" + f" - l = {l}",
)
plt.legend(fontsize=20)
plt.title(
f"Aggregated distribution returns from {dates[0]} to"
+ f" {dates[1]} - {time_step}",
fontsize=30,
)
plt.xlabel("Aggregated returns", fontsize=25)
plt.ylabel("PDF", fontsize=25)
plt.xticks(fontsize=15)
plt.yticks(fontsize=15)
plt.xlim(-10, 10)
plt.ylim(10 ** -9, 1)
plt.grid(True)
plt.tight_layout()
figure_log: plt.Figure = plot_log.get_figure()
# Plotting
exact_distributions_correlation_tools.save_plot(
figure_log, function_name, dates, time_step
)
plt.close()
del agg_returns_data
del figure_log
del plot_log
gc.collect()
except FileNotFoundError as error:
print("No data")
print(error)
print()