def arima(l_args, s_ticker, df_stock):
parser = argparse.ArgumentParser(
prog="arima",
description="""
In statistics and econometrics, and in particular in time series analysis, an
autoregressive integrated moving average (ARIMA) model is a generalization of an
autoregressive moving average (ARMA) model. Both of these models are fitted to time
series data either to better understand the data or to predict future points in the
series (forecasting). ARIMA(p,d,q) where parameters p, d, and q are non-negative
integers, p is the order (number of time lags) of the autoregressive model, d is the
degree of differencing (the number of times the data have had past values subtracted),
and q is the order of the moving-average model.
""",
)
parser.add_argument(
"-d",
"--days",
action="store",
dest="n_days",
type=check_positive,
default=5,
help="prediction days.",
)
parser.add_argument(
"-i",
"--ic",
action="store",
dest="s_ic",
type=str,
default="aic",
choices=["aic", "aicc", "bic", "hqic", "oob"],
help="information criteria.",
)
parser.add_argument(
"-s",
"--seasonal",
action="store_true",
default=False,
dest="b_seasonal",
help="Use weekly seasonal data.",
)
parser.add_argument(
"-o",
"--order",
action="store",
dest="s_order",
type=str,
help="arima model order (p,d,q) in format: pdq.",
)
parser.add_argument(
"-r",
"--results",
action="store_true",
dest="b_results",
default=False,
help="results about ARIMA summary flag.",
)
try:
ns_parser = parse_known_args_and_warn(parser, l_args)
# Machine Learning model
if ns_parser.s_order:
t_order = tuple([int(ord) for ord in list(ns_parser.s_order)])
model = ARIMA(df_stock["5. adjusted close"].values, order=t_order).fit()
l_predictions = model.predict(
start=len(df_stock["5. adjusted close"]) + 1,
end=len(df_stock["5. adjusted close"]) + ns_parser.n_days,
)
else:
if ns_parser.b_seasonal:
model = pmdarima.auto_arima(
df_stock["5. adjusted close"].values,
error_action="ignore",
seasonal=True,
m=5,
information_criteria=ns_parser.s_ic,
)
else:
model = pmdarima.auto_arima(
df_stock["5. adjusted close"].values,
error_action="ignore",
seasonal=False,
information_criteria=ns_parser.s_ic,
)
l_predictions = model.predict(n_periods=ns_parser.n_days)
# Prediction data
l_pred_days = get_next_stock_market_days(
last_stock_day=df_stock["5. adjusted close"].index[-1],
n_next_days=ns_parser.n_days,
)
df_pred = pd.Series(l_predictions, index=l_pred_days, name="Price")
if ns_parser.b_results:
print(model.summary())
print("")
# Plotting
plt.figure()
plt.plot(df_stock.index, df_stock["5. adjusted close"], lw=2)
if ns_parser.s_order:
plt.title(
f"ARIMA {str(t_order)} on {s_ticker} - {ns_parser.n_days} days prediction"
)
else:
plt.title(
f"ARIMA {model.order} on {s_ticker} - {ns_parser.n_days} days prediction"
)
plt.xlim(
df_stock.index[0], get_next_stock_market_days(df_pred.index[-1], 1)[-1]
)
plt.xlabel("Time")
plt.ylabel("Share Price ($)")
plt.grid(b=True, which="major", color="#666666", linestyle="-")
plt.minorticks_on()
plt.grid(b=True, which="minor", color="#999999", linestyle="-", alpha=0.2)
plt.plot(
[df_stock.index[-1], df_pred.index[0]],
[df_stock["5. adjusted close"].values[-1], df_pred.values[0]],
lw=1,
c="tab:green",
linestyle="--",
)
plt.plot(df_pred.index, df_pred, lw=2, c="tab:green")
plt.axvspan(
df_stock.index[-1], df_pred.index[-1], facecolor="tab:orange", alpha=0.2
)
_, _, ymin, ymax = plt.axis()
plt.vlines(
df_stock.index[-1], ymin, ymax, linewidth=1, linestyle="--", color="k"
)
plt.ion()
plt.show()
# Print prediction data
print_pretty_prediction(df_pred, df_stock["5. adjusted close"].values[-1])
print("")
except Exception as e:
print(e)
print("")
def exponential_smoothing(l_args, s_ticker, df_stock):
parser = argparse.ArgumentParser(
add_help=False,
prog="ets",
description="""
Exponential Smoothing, see https://otexts.com/fpp2/taxonomy.html
Trend='N', Seasonal='N': Simple Exponential Smoothing
Trend='N', Seasonal='A': Exponential Smoothing
Trend='N', Seasonal='M': Exponential Smoothing
Trend='A', Seasonal='N': Holt’s linear method
Trend='A', Seasonal='A': Additive Holt-Winters’ method
Trend='A', Seasonal='M': Multiplicative Holt-Winters’ method
Trend='Ad', Seasonal='N': Additive damped trend method
Trend='Ad', Seasonal='A': Exponential Smoothing
Trend='Ad', Seasonal='M': Holt-Winters’ damped method
Trend component: N: None, A: Additive, Ad: Additive Damped
Seasonality component: N: None, A: Additive, M: Multiplicative
""",
)
parser.add_argument(
"-d",
"--days",
action="store",
dest="n_days",
type=check_positive,
default=5,
help="prediction days.",
)
parser.add_argument(
"-t",
"--trend",
action="store",
dest="trend",
type=check_valid_trend,
default="N",
help="Trend component: N: None, A: Additive, Ad: Additive Damped.",
)
parser.add_argument(
"-s",
"--seasonal",
action="store",
dest="seasonal",
type=check_valid_seasonal,
default="N",
help="Seasonality component: N: None, A: Additive, M: Multiplicative.",
)
parser.add_argument(
"-p",
"--periods",
action="store",
dest="seasonal_periods",
type=check_positive,
default=5,
help="Seasonal periods.",
)
try:
ns_parser = parse_known_args_and_warn(parser, l_args)
if not ns_parser:
return
model, title = get_exponential_smoothing_model(
df_stock["5. adjusted close"].values,
ns_parser.trend,
ns_parser.seasonal,
ns_parser.seasonal_periods,
)
if model.mle_retvals.success:
forecast = model.forecast(ns_parser.n_days)
l_pred_days = get_next_stock_market_days(
last_stock_day=df_stock["5. adjusted close"].index[-1],
n_next_days=ns_parser.n_days,
)
df_pred = pd.Series(forecast, index=l_pred_days, name="Price")
if ~np.isnan(forecast).any():
print(f"\n{title}")
print("\nFit model parameters:")
for key, value in model.params.items():
print(f"{key} {' '*(18-len(key))}: {value}")
print("\nAssess fit model:")
print(f"AIC: {round(model.aic, 2)}")
print(f"BIC: {round(model.bic, 2)}")
print(f"SSE: {round(model.sse, 2)}\n")
# Plotting
plt.figure()
plt.plot(df_stock.index, df_stock["5. adjusted close"], lw=2)
plt.title(f"{title} on {s_ticker}")
plt.xlim(
df_stock.index[0],
get_next_stock_market_days(df_pred.index[-1], 1)[-1],
)
plt.xlabel("Time")
plt.ylabel("Share Price ($)")
plt.grid(b=True, which="major", color="#666666", linestyle="-")
plt.minorticks_on()
plt.grid(
b=True, which="minor", color="#999999", linestyle="-", alpha=0.2
)
plt.plot(
[df_stock.index[-1], df_pred.index[0]],
[df_stock["5. adjusted close"].values[-1], df_pred.values[0]],
lw=1,
c="tab:green",
linestyle="--",
)
plt.plot(df_pred.index, df_pred, lw=2, c="tab:green")
plt.axvspan(
df_stock.index[-1],
df_pred.index[-1],
facecolor="tab:orange",
alpha=0.2,
)
_, _, ymin, ymax = plt.axis()
plt.vlines(
df_stock.index[-1],
ymin,
ymax,
linewidth=1,
linestyle="--",
color="k",
)
plt.ion()
plt.show()
# Print prediction data
print_pretty_prediction(
df_pred, df_stock["5. adjusted close"].values[-1]
)
print("")
else:
print("RuntimeWarning: invalid value encountered in double_scalars.")
else:
print("ConvergenceWarning: Optimization failed to converge.")
except Exception as e:
print(e)
print("")
def k_nearest_neighbors(l_args, s_ticker, df_stock):
parser = argparse.ArgumentParser(
prog="knn",
description="""
K nearest neighbors is a simple algorithm that stores all
available cases and predict the numerical target based on a similarity measure
(e.g. distance functions).
""",
)
parser.add_argument(
"-i",
"--input",
action="store",
dest="n_inputs",
type=check_positive,
default=40,
help="number of days to use for prediction.",
)
parser.add_argument(
"-d",
"--days",
action="store",
dest="n_days",
type=check_positive,
default=5,
help="prediction days.",
)
parser.add_argument(
"-j",
"--jumps",
action="store",
dest="n_jumps",
type=check_positive,
default=1,
help="number of jumps in training data.",
)
parser.add_argument(
"-n",
"--neighbors",
action="store",
dest="n_neighbors",
type=check_positive,
default=20,
help="number of neighbors to use on the algorithm.",
)
try:
ns_parser = parse_known_args_and_warn(parser, l_args)
# Split training data
stock_x, stock_y = splitTrain.split_train(
df_stock["5. adjusted close"].values,
ns_parser.n_inputs,
ns_parser.n_days,
ns_parser.n_jumps,
)
# Machine Learning model
knn = neighbors.KNeighborsRegressor(n_neighbors=ns_parser.n_neighbors)
knn.fit(stock_x, stock_y)
# Prediction data
l_predictions = knn.predict(
df_stock["5. adjusted close"].values[-ns_parser.n_inputs:].reshape(
1, -1))[0]
l_pred_days = get_next_stock_market_days(
last_stock_day=df_stock["5. adjusted close"].index[-1],
n_next_days=ns_parser.n_days,
)
df_pred = pd.Series(l_predictions, index=l_pred_days, name="Price")
# Plotting
plt.figure()
plt.plot(df_stock.index, df_stock["5. adjusted close"], lw=2)
plt.title(
f"{ns_parser.n_neighbors}-Nearest Neighbors on {s_ticker} - {ns_parser.n_days} days prediction"
)
plt.xlim(df_stock.index[0],
get_next_stock_market_days(df_pred.index[-1], 1)[-1])
plt.xlabel("Time")
plt.ylabel("Share Price ($)")
plt.grid(b=True, which="major", color="#666666", linestyle="-")
plt.minorticks_on()
plt.grid(b=True,
which="minor",
color="#999999",
linestyle="-",
alpha=0.2)
plt.plot(
[df_stock.index[-1], df_pred.index[0]],
[df_stock["5. adjusted close"].values[-1], df_pred.values[0]],
lw=1,
c="tab:green",
linestyle="--",
)
plt.plot(df_pred.index, df_pred, lw=2, c="tab:green")
plt.axvspan(df_stock.index[-1],
df_pred.index[-1],
facecolor="tab:orange",
alpha=0.2)
_, _, ymin, ymax = plt.axis()
plt.vlines(df_stock.index[-1],
ymin,
ymax,
linewidth=1,
linestyle="--",
color="k")
plt.ion()
plt.show()
# Print prediction data
print_pretty_prediction(df_pred,
df_stock["5. adjusted close"].values[-1])
print("")
except Exception as e:
print(e)
print("")
def simple_moving_average(l_args, s_ticker, df_stock):
parser = argparse.ArgumentParser(
prog="sma",
description="""
Moving Averages are used to smooth the data in an array to
help eliminate noise and identify trends. The Simple Moving Average is literally
the simplest form of a moving average. Each output value is the average of the
previous n values. In a Simple Moving Average, each value in the time period carries
equal weight, and values outside of the time period are not included in the average.
This makes it less responsive to recent changes in the data, which can be useful for
filtering out those changes.
""",
)
parser.add_argument(
"-l",
"--length",
action="store",
dest="n_length",
type=check_positive,
default=20,
help="length of SMA window.",
)
parser.add_argument(
"-d",
"--days",
action="store",
dest="n_days",
type=check_positive,
default=5,
help="prediction days.",
)
try:
ns_parser = parse_known_args_and_warn(parser, l_args)
# Prediction data
l_predictions = list()
for pred_day in range(ns_parser.n_days):
if pred_day < ns_parser.n_length:
l_ma_stock = df_stock["5. adjusted close"].values[
-ns_parser.n_length + pred_day:]
else:
l_ma_stock = list()
l_predictions.append(np.mean(np.append(l_ma_stock, l_predictions)))
l_pred_days = get_next_stock_market_days(
last_stock_day=df_stock["5. adjusted close"].index[-1],
n_next_days=ns_parser.n_days,
)
df_pred = pd.Series(l_predictions, index=l_pred_days, name="Price")
# Plotting
plt.plot(df_stock.index, df_stock["5. adjusted close"], lw=2)
plt.title(
f"{ns_parser.n_length} Moving Average on {s_ticker} - {ns_parser.n_days} days prediction"
)
plt.xlim(df_stock.index[0],
get_next_stock_market_days(df_pred.index[-1], 1)[-1])
plt.xlabel("Time")
plt.ylabel("Share Price ($)")
plt.grid(b=True, which="major", color="#666666", linestyle="-")
plt.minorticks_on()
plt.grid(b=True,
which="minor",
color="#999999",
linestyle="-",
alpha=0.2)
df_ma = df_stock["5. adjusted close"].rolling(
window=ns_parser.n_length).mean()
plt.plot(df_ma.index, df_ma, lw=2, linestyle="--", c="tab:orange")
plt.plot(
[df_stock.index[-1], df_pred.index[0]],
[df_stock["5. adjusted close"].values[-1], df_pred.values[0]],
lw=1,
c="tab:green",
linestyle="--",
)
plt.plot(df_pred.index, df_pred, lw=2, c="tab:green")
plt.axvspan(df_stock.index[-1],
df_pred.index[-1],
facecolor="tab:orange",
alpha=0.2)
_, _, ymin, ymax = plt.axis()
plt.vlines(df_stock.index[-1],
ymin,
ymax,
linewidth=1,
linestyle="--",
color="k")
plt.ion()
plt.show()
# Print prediction data
print_pretty_prediction(df_pred,
df_stock["5. adjusted close"].values[-1])
print("")
except Exception as e:
print(e)
print("")
def regression(l_args, s_ticker, df_stock, polynomial):
parser = argparse.ArgumentParser(
prog="regression",
description="""
Regression attempts to model the relationship between
two variables by fitting a linear/quadratic/cubic/other equation to
observed data. One variable is considered to be an explanatory variable,
and the other is considered to be a dependent variable.
""",
)
parser.add_argument(
"-i",
"--input",
action="store",
dest="n_inputs",
type=check_positive,
default=40,
help="number of days to use for prediction.",
)
parser.add_argument(
"-d",
"--days",
action="store",
dest="n_days",
type=check_positive,
default=5,
help="prediction days.",
)
parser.add_argument(
"-j",
"--jumps",
action="store",
dest="n_jumps",
type=check_positive,
default=1,
help="number of jumps in training data.",
)
if polynomial == USER_INPUT:
parser.add_argument(
"-p",
"--polynomial",
action="store",
dest="n_polynomial",
type=check_positive,
required=True,
help="polynomial associated with regression.",
)
try:
ns_parser = parse_known_args_and_warn(parser, l_args)
# Split training data
stock_x, stock_y = splitTrain.split_train(
df_stock["5. adjusted close"].values,
ns_parser.n_inputs,
ns_parser.n_days,
ns_parser.n_jumps,
)
# Machine Learning model
if polynomial == LINEAR:
model = linear_model.LinearRegression(n_jobs=-1)
else:
if polynomial == USER_INPUT:
polynomial = ns_parser.n_polynomial
model = pipeline.make_pipeline(
preprocessing.PolynomialFeatures(polynomial),
linear_model.Ridge())
model.fit(stock_x, stock_y)
l_predictions = model.predict(
df_stock["5. adjusted close"].values[-ns_parser.n_inputs:].reshape(
1, -1))[0]
# Prediction data
l_pred_days = get_next_stock_market_days(
last_stock_day=df_stock["5. adjusted close"].index[-1],
n_next_days=ns_parser.n_days,
)
df_pred = pd.Series(l_predictions, index=l_pred_days, name="Price")
# Plotting
plt.figure()
plt.plot(df_stock.index, df_stock["5. adjusted close"], lw=2)
plt.title(
f"Regression (polynomial {polynomial}) on {s_ticker} - {ns_parser.n_days} days prediction"
)
plt.xlim(df_stock.index[0],
get_next_stock_market_days(df_pred.index[-1], 1)[-1])
plt.xlabel("Time")
plt.ylabel("Share Price ($)")
plt.grid(b=True, which="major", color="#666666", linestyle="-")
plt.minorticks_on()
plt.grid(b=True,
which="minor",
color="#999999",
linestyle="-",
alpha=0.2)
plt.plot(
[df_stock.index[-1], df_pred.index[0]],
[df_stock["5. adjusted close"].values[-1], df_pred.values[0]],
lw=1,
c="tab:green",
linestyle="--",
)
plt.plot(df_pred.index, df_pred, lw=2, c="tab:green")
plt.axvspan(df_stock.index[-1],
df_pred.index[-1],
facecolor="tab:orange",
alpha=0.2)
_, _, ymin, ymax = plt.axis()
plt.vlines(df_stock.index[-1],
ymin,
ymax,
linewidth=1,
linestyle="--",
color="k")
plt.ion()
plt.show()
# Print prediction data
print_pretty_prediction(df_pred,
df_stock["5. adjusted close"].values[-1])
print("")
except Exception as e:
print(e)
print("")
def mlp(l_args, s_ticker, df_stock):
parser = argparse.ArgumentParser(prog="mlp",
description="""Multilayer Perceptron. """)
parser.add_argument(
"-d",
"--days",
action="store",
dest="n_days",
type=check_positive,
default=5,
help="prediction days.",
)
parser.add_argument(
"-i",
"--input",
action="store",
dest="n_inputs",
type=check_positive,
default=40,
help="number of days to use for prediction.",
)
parser.add_argument(
"-e",
"--epochs",
action="store",
dest="n_epochs",
type=check_positive,
default=200,
help="number of training epochs.",
)
parser.add_argument(
"-j",
"--jumps",
action="store",
dest="n_jumps",
type=check_positive,
default=1,
help="number of jumps in training data.",
)
parser.add_argument(
"-p",
"--pp",
action="store",
dest="s_preprocessing",
default="normalization",
choices=["normalization", "standardization", "none"],
help="pre-processing data.",
)
parser.add_argument(
"-o",
"--optimizer",
action="store",
dest="s_optimizer",
default="adam",
choices=[
"adam",
"adagrad",
"adadelta",
"adamax",
"ftrl",
"nadam",
"optimizer",
"rmsprop",
"sgd",
],
help="optimization technique.",
)
parser.add_argument(
"-l",
"--loss",
action="store",
dest="s_loss",
default="mae",
choices=["mae", "mape", "mse", "msle"],
help="loss function.",
)
try:
ns_parser = parse_known_args_and_warn(parser, l_args)
# Pre-process data
if ns_parser.s_preprocessing == "standardization":
scaler = StandardScaler()
stock_train_data = scaler.fit_transform(
np.array(df_stock["5. adjusted close"].values.reshape(-1, 1)))
elif ns_parser.s_preprocessing == "normalization":
scaler = MinMaxScaler()
stock_train_data = scaler.fit_transform(
np.array(df_stock["5. adjusted close"].values.reshape(-1, 1)))
else: # No pre-processing
stock_train_data = np.array(
df_stock["5. adjusted close"].values.reshape(-1, 1))
# Split training data for the neural network
stock_x, stock_y = splitTrain.split_train(
stock_train_data,
ns_parser.n_inputs,
ns_parser.n_days,
numJumps=ns_parser.n_jumps,
)
stock_x = np.array(stock_x)
stock_x = np.reshape(stock_x, (stock_x.shape[0], stock_x.shape[1]))
stock_y = np.array(stock_y)
stock_y = np.reshape(stock_y, (stock_y.shape[0], stock_y.shape[1]))
# Build Neural Network model
model = build_neural_network_model(cfg_nn_models.MultiLayer_Perceptron,
ns_parser.n_inputs,
ns_parser.n_days)
model.compile(optimizer=ns_parser.s_optimizer, loss=ns_parser.s_loss)
# Train our model
model.fit(stock_x, stock_y, epochs=ns_parser.n_epochs, verbose=1)
print("")
print(model.summary())
print("")
# Prediction
yhat = model.predict(
stock_train_data[-ns_parser.n_inputs:].reshape(
1, ns_parser.n_inputs),
verbose=0,
)
# Re-scale the data back
if (ns_parser.s_preprocessing
== "standardization") or (ns_parser.s_preprocessing
== "normalization"):
y_pred_test_t = scaler.inverse_transform(yhat.tolist())
else:
y_pred_test_t = yhat
l_pred_days = get_next_stock_market_days(
last_stock_day=df_stock["5. adjusted close"].index[-1],
n_next_days=ns_parser.n_days,
)
df_pred = pd.Series(y_pred_test_t[0].tolist(),
index=l_pred_days,
name="Price")
# Plotting
plt.figure()
plt.plot(df_stock.index, df_stock["5. adjusted close"], lw=3)
plt.title(f"MLP on {s_ticker} - {ns_parser.n_days} days prediction")
plt.xlim(df_stock.index[0],
get_next_stock_market_days(df_pred.index[-1], 1)[-1])
plt.xlabel("Time")
plt.ylabel("Share Price ($)")
plt.grid(b=True, which="major", color="#666666", linestyle="-")
plt.minorticks_on()
plt.grid(b=True,
which="minor",
color="#999999",
linestyle="-",
alpha=0.2)
plt.plot(
[df_stock.index[-1], df_pred.index[0]],
[df_stock["5. adjusted close"].values[-1], df_pred.values[0]],
lw=1,
c="tab:green",
linestyle="--",
)
plt.plot(df_pred.index, df_pred, lw=2, c="tab:green")
plt.axvspan(df_stock.index[-1],
df_pred.index[-1],
facecolor="tab:orange",
alpha=0.2)
_, _, ymin, ymax = plt.axis()
plt.vlines(
df_stock.index[-1],
ymin,
ymax,
colors="k",
linewidth=3,
linestyle="--",
color="k",
)
plt.ion()
plt.show()
# Print prediction data
print_pretty_prediction(df_pred,
df_stock["5. adjusted close"].values[-1])
print("")
except Exception as e:
print(e)
print("")