def predict(self, future_points: int = 1) -> List[Prediction]:
train_X, train_Y, test_X = self.build_train_test(future_points)
df = self.build_df(train_X, train_Y)
model = Prophet(uncertainty_samples=2000)
model.fit(df)
future = pd.DataFrame({"ds": test_X})
forecast = model.predictive_samples(future)
posterior_pred = forecast["yhat"]
pred_mean = np.mean(posterior_pred, axis=1)
pred_var = np.var(posterior_pred, axis=1)
return [Prediction(pred_mean[i],pred_var[i]) for i in np.arange(len(posterior_pred))]
plt.ylabel('Number of Passengers')
plt.axvline(x=131, c='k', linestyle='dashed', linewidth=0.5)
plt.plot(may_1960_index,
forecast['yhat'][may_1960_index],
'ro',
fillstyle='none',
color='c')
plt.annotate(s='',
xy=(may_1960_index, forecast_new.iloc[may_1960_index]),
xytext=(may_1960_index, forecast['yhat'][may_1960_index]),
arrowprops=dict(arrowstyle='simple', color='g'))
plt.legend()
plt.show()
# Extract the samples from the posterior predictive distribution for may 1960
pred_samples = m.predictive_samples(future)
pred_samples_df = pd.DataFrame(pred_samples['yhat'])
prior_samples = pred_samples_df.iloc[may_1960_index, :]
print(
"We introduce th optinion of an expert: \n This May we had 420.000 Passengers and we will definitely not have fewer in May 1960 (['-inf', 420] has probability 1%).\n Furthermore, given the numbers of the last three years, I am sure that a growth rate compared to this May between 7.5% and 15% is extremely probable ([451, 483] has probability 80%). \n However, an increase of 15% or more compared to this May, in my opinion, is unrealistic ([483, 'inf'] has probability 1%)."
)
input("Press Enter to continue...")
# Define the constraints for may 1960
rules = [['-inf', 420, 0.01], [451, 483, 0.80], [483, 'inf', 0.01]]
# Calculate the Maximum Entropy Distribution for may 1960
points, weights, prior, max_ent_dist = me.opt_max_ent(rules, prior_samples)
# Plot prior and the Maximum Entropy Distribution for may 1960
#loop over each state. Parallelise?
#initialise model
m = Prophet(mcmc_samples=100, growth='logistic')
df_prophet['y'] = cases[state].values[:-truncation]
df_prophet['cap'] = pop[state]
df_prophet['floor'] = 0
m.fit(df_prophet)
future = m.make_future_dataframe(periods=truncation + forecast_length,
include_history=False)
future['cap'] = pop[state]
future['floor'] = 0
df_forecast = m.predict(future)
forecast = m.predictive_samples(future)
fig1 = m.plot(df_forecast,
ax=ax[i // 2, i % 2],
plot_cap=False,
xlabel='Date of Symptom Onset',
ylabel='Local cases')
fig2 = m.plot_components(df_forecast, plot_cap=False)
fig2.savefig("./results/prophet/" + data_date.strftime("%m-%d") + "/" +
state + "components.png",
dpi=144)
samples = m.predictive_samples(future)
temp = pd.DataFrame(samples['yhat'])
temp['state'] = state
def main(timey, fcst_type):
location = "886-limited"
timestring = time.strftime("%Y-%m-%d")
sql = r"C:\Users\uxkp\sql_queries\inventory\avg_bal_daily.sql"
df = daily_time_series(data_prep(read_sql_to_df(sql)))
print(df.columns)
df.rename(columns={"DATETIME": "ds", "INVENTORY": "y"}, inplace=True)
print(df.dtypes)
print(df.tail)
df.reset_index(drop=True)
# m = Prophet()
df["y"] = np.log(df["y"].replace(0, np.nan))
df.to_csv(r"c:\users\uxkp\desktop\filetest.csv", index=False)
df["cap"] = 24.5
df["floor"] = 0
m = Prophet(
mcmc_samples=100,
growth="logistic",
uncertainty_samples=100,
interval_width=0.9,
changepoint_range=0.90,
changepoint_prior_scale=0.01,
weekly_seasonality=False,
)
m.fit(df)
future = m.make_future_dataframe(periods=60, freq="d")
future["cap"] = 24.5
future["floor"] = 0
forecast = m.predict(future)
psf = m.predictive_samples(future)
# m.plot(psf).show()
forecast.to_csv(
f"c:\\users\\uxkp\\desktop\\{timey}_{fcst_type}_forecast_{location}_{timestring}.csv",
index=False)
dcv = cross_validation(m,
initial="30 days",
period="7 days",
horizon="60 days")
performance_metrics_results = performance_metrics(dcv)
performance_metrics_results.to_csv(
f"c:\\users\\uxkp\\desktop\\{timey}_{fcst_type}_performance_metrics_{location}_{timestring}.csv",
index=False)
fig1 = plot_cross_validation_metric(dcv, metric="mape")
plt.savefig(
f"c:\\users\\uxkp\\desktop\\{timey}_{fcst_type}_cross validation_{location}_{timestring}.png",
format="png")
fig2 = m.plot(forecast, xlabel=f"Time Series Forecast")
plt.savefig(
f"c:\\users\\uxkp\\desktop\\{timey}_{fcst_type}_forecast_{location}_{timestring}.png",
format="png")
fig3 = m.plot_components(forecast)
a = add_changepoints_to_plot(fig3.gca(), m, forecast)
plt.savefig(
f"c:\\users\\uxkp\\desktop\\{timey}_{fcst_type}_components_{location}_{timestring}.png",
format="png")
fig1.show()
fig2.show()
fig3.show()
