def main(tickers='AAPL', start=None, end=None, n_steps=21):
data = OrderedDict()
pred_data = OrderedDict()
forecast_data = OrderedDict()
for ticker in tickers:
data[ticker] = fc.get_time_series(ticker, start, end)
# log_returns
data[ticker]['log_returns'] = np.log(
data[ticker]['adj_close'] / data[ticker]['adj_close'].shift(1))
data[ticker]['log_returns'].dropna(inplace=True)
# plotting the histogram of returns
fc.plot_histogram(data[ticker]['log_returns'])
fc.plot_time_series(data[ticker]['log_returns'], lags=30)
print("{} Series\n"
"-------------\n"
"mean: {:.3f}\n"
"median: {:.3f}\n"
"maximum: {:.3f}\n"
"minimum: {:.3f}\n"
"variance: {:.3f}\n"
"standard deviation: {:.3f}\n"
"skewness: {:.3f}\n"
"kurtosis: {:.3f}".format(ticker,
data[ticker]['adj_close'].mean(),
data[ticker]['adj_close'].median(),
data[ticker]['adj_close'].max(),
data[ticker]['adj_close'].min(),
data[ticker]['adj_close'].var(),
data[ticker]['adj_close'].std(),
data[ticker]['adj_close'].skew(),
data[ticker]['adj_close'].kurtosis()))
adfstat, pvalue, critvalues, resstore, dagostino_results, shapiro_results, ks_results, anderson_results, kpss_results = fc.get_stationarity_statistics(
data[ticker]['log_returns'].values)
print(
"{} Stationarity Statistics\n"
"-------------\n"
"Augmented Dickey-Fuller unit root test: {}\n"
"MacKinnon’s approximate p-value: {}\n"
"Critical values for the test statistic at the 1 %, 5 %, and 10 % levels: {}\n"
"D’Agostino and Pearson’s normality test: {}\n"
"Shapiro-Wilk normality test: {}\n"
"Kolmogorov-Smirnov goodness of fit test: {}\n"
"Anderson-Darling test: {}\n"
"Kwiatkowski, Phillips, Schmidt, and Shin (KPSS) stationarity test: {}"
.format(ticker, adfstat, pvalue, critvalues, dagostino_results,
shapiro_results, ks_results, anderson_results,
kpss_results))
# Fit ARMA model to AAPL returns
res_tup = fc.get_best_arma_model(data[ticker]['log_returns'])
res_tup[2].summary()
# verify stationarity
adfstat, pvalue, critvalues, resstore, dagostino_results, shapiro_results, ks_results, anderson_results, kpss_results = fc.get_stationarity_statistics(
res_tup[2].resid.values)
print(
"Stationarity Statistics\n"
"-------------\n"
"Augmented Dickey-Fuller unit root test: {}\n"
"MacKinnon’s approximate p-value: {}\n"
"Critical values for the test statistic at the 1 %, 5 %, and 10 % levels: {}\n"
"D’Agostino and Pearson’s normality test: {}\n"
"Shapiro-Wilk normality test: {}\n"
"Kolmogorov-Smirnov goodness of fit test: {}\n"
"Anderson-Darling test: {}\n"
"Kwiatkowski, Phillips, Schmidt, and Shin (KPSS) stationarity test: {}"
.format(adfstat, pvalue, critvalues, dagostino_results,
shapiro_results, ks_results, anderson_results,
kpss_results))
fc.plot_histogram(y=res_tup[2].resid, ticker=ticker, title='ARMA')
fc.plot_time_series(y=res_tup[2].resid,
lags=30,
ticker=ticker,
title='ARMA')
# cross-validation testing
split = rand.uniform(0.60, 0.80)
train_size = int(len(data[ticker]) * split)
train, test = data[ticker][0:train_size], data[ticker][
train_size:len(data[ticker])]
# in-sample prediction
pred_data[ticker] = res_tup[2].predict(start=len(train),
end=len(train) + len(test) - 1)
pred_results = pd.DataFrame(data=dict(
original=test['log_returns'], prediction=pred_data[ticker].values),
index=test.index)
print('{} Original Sharpe Ratio:'.format(ticker),
fc.get_sharpe_ratio(returns=pred_results['original']))
print('{} Prediction Sharpe Ratio:'.format(ticker),
fc.get_sharpe_ratio(returns=pred_results['prediction']))
# prediction plot
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(pred_results['original'])
ax.plot(pred_results['prediction'])
ax.set(title='{} ARMA{} In-Sample Return Prediction'.format(
ticker, res_tup[1]),
xlabel='time',
ylabel='$')
ax.legend(['Original', 'Prediction'])
fig.tight_layout()
fig.savefig(
'charts/{}-ARMA-In-Sample-Return-Prediction'.format(ticker))
# out-of-sample forecast
forecast_data[ticker] = res_tup[2].forecast(steps=n_steps)
# forecast plot
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(forecast_data[ticker][0])
ax.set(
title='{} Day {} ARMA{} Out-of-Sample Return Forecast.png'.format(
n_steps, ticker, res_tup[1]),
xlabel='time',
ylabel='$')
ax.legend(['Forecast'])
fig.tight_layout()
fig.savefig(
'charts/{}-Day-{}-ARMA-Out-of-Sample-Return-Forecast.png'.format(
n_steps, ticker))
# end of day plot of all tickers
fig = plt.figure()
ax = fig.add_subplot(111)
for ticker in tickers:
ax.plot(data[ticker]['adj_close'])
ax.set(title='Time series plot', xlabel='time', ylabel='$')
ax.legend(tickers)
fig.tight_layout()
fig.savefig('charts/stocks.png')
return forecast_data
def main(tickers=['AAPL'], n_steps=21):
"""
Main entry point of the app
"""
data = OrderedDict()
pred_data = OrderedDict()
forecast_data = OrderedDict()
for ticker in tickers:
data[ticker] = fc.get_time_series(ticker)[-500:]
print("{} Series\n"
"-------------\n"
"mean: {:.3f}\n"
"median: {:.3f}\n"
"maximum: {:.3f}\n"
"minimum: {:.3f}\n"
"variance: {:.3f}\n"
"standard deviation: {:.3f}\n"
"skewness: {:.3f}\n"
"kurtosis: {:.3f}".format(ticker,
data[ticker]['adj_close'].mean(),
data[ticker]['adj_close'].median(),
data[ticker]['adj_close'].max(),
data[ticker]['adj_close'].min(),
data[ticker]['adj_close'].var(),
data[ticker]['adj_close'].std(),
data[ticker]['adj_close'].skew(),
data[ticker]['adj_close'].kurtosis()))
data[ticker]['log_returns'] = np.log(
data[ticker]['adj_close'] / data[ticker]['adj_close'].shift(1))
data[ticker]['log_returns'].dropna(inplace=True)
adfstat, pvalue, critvalues, resstore, dagostino_results, shapiro_results, ks_results, anderson_results, kpss_results = fc.get_stationarity_statistics(
data[ticker]['log_returns'].values)
print(
"{} Stationarity Statistics\n"
"-------------\n"
"Augmented Dickey-Fuller unit root test: {}\n"
"MacKinnon’s approximate p-value: {}\n"
"Critical values for the test statistic at the 1 %, 5 %, and 10 % levels: {}\n"
"D’Agostino and Pearson’s normality test: {}\n"
"Shapiro-Wilk normality test: {}\n"
"Kolmogorov-Smirnov goodness of fit test: {}\n"
"Anderson-Darling test: {}\n"
"Kwiatkowski, Phillips, Schmidt, and Shin (KPSS) stationarity test: {}"
.format(ticker, adfstat, pvalue, critvalues, dagostino_results,
shapiro_results, ks_results, anderson_results,
kpss_results))
train, test = np.arange(0, 450), np.arange(
451, len(data[ticker]['log_returns']))
n = len(train)
with pm.Model() as model:
sigma = pm.Exponential('sigma', 1. / .02, testval=.1)
mu = pm.Normal('mu', 0, sd=5, testval=.1)
nu = pm.Exponential('nu', 1. / 10)
logs = pm.GaussianRandomWalk('logs', tau=sigma**-2, shape=n)
# lam uses variance in pymc3, not sd like in scipy
r = pm.StudentT('r',
nu,
mu=mu,
lam=1 / np.exp(-2 * logs),
observed=data[ticker]['log_returns'].values[train])
with model:
start = pm.find_MAP(vars=[logs], fmin=sp.optimize.fmin_l_bfgs_b)
with model:
step = pm.NUTS(vars=[logs, mu, nu, sigma],
scaling=start,
gamma=.25)
start2 = pm.sample(100, step, start=start)[-1]
# Start next run at the last sampled position.
step = pm.NUTS(vars=[logs, mu, nu, sigma],
scaling=start2,
gamma=.55)
trace = pm.sample(2000, step, start=start2)
pred_data[ticker], vol = fc.generate_proj_returns(
1000, trace, len(test))
pred_results = pd.DataFrame(
data=dict(original=data[ticker]['log_returns'][test],
prediction=pred_data[ticker][1, :]),
index=data[ticker]['log_returns'][test].index)
print('{} Original Sharpe Ratio:'.format(ticker),
fc.get_sharpe_ratio(returns=pred_results['original']))
print('{} Prediction Sharpe Ratio:'.format(ticker),
fc.get_sharpe_ratio(returns=pred_results['prediction']))
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(data[ticker]['log_returns'].values, color='blue')
ax.plot(1 + len(train) + np.arange(0, len(test)),
pred_data[ticker][1, :],
color='red')
ax.set(title='{} NUTS In-Sample Returns Prediction'.format(ticker),
xlabel='time',
ylabel='%')
ax.legend(['Original', 'Prediction'])
fig.tight_layout()
fig.savefig(
'charts/{}-NUTS-In-Sample-Returns-Prediction.png'.format(ticker))
# out-of-sample test
forecast_data[ticker], vol = fc.generate_proj_returns(
1000, trace,
len(test) + n_steps)
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(forecast_data[ticker][1, :][-n_steps:])
ax.set(title='{} Day {} NUTS Out-of-Sample Returns Forecast'.format(
n_steps, ticker),
xlabel='time',
ylabel='%')
ax.legend(['Forecast'])
fig.tight_layout()
fig.savefig(
'charts/{}-Day-{}-NUTS-Out-of-Sample-Returns-Forecast.png'.format(
n_steps, ticker))
fig = plt.figure()
ax = fig.add_subplot(111)
for ticker in tickers:
ax.plot(data[ticker]['adj_close'])
ax.set(title='Time series plot', xlabel='time', ylabel='$')
ax.legend(tickers)
fig.tight_layout()
fig.savefig('charts/stocks-close-price.png')
fig = plt.figure()
ax = fig.add_subplot(111)
for ticker in tickers:
ax.plot(data[ticker]['log_returns'])
ax.set(title='Time series plot', xlabel='time', ylabel='%')
ax.legend(tickers)
fig.tight_layout()
fig.savefig('charts/stocks-close-returns.png')
return forecast_data