m=args.period,
information_criterion="aicc",
seasonal=args.seasonal,
error_action="ignore",
suppress_warnings=True,
)
elif args.fit:
with warnings.catch_warnings():
warnings.simplefilter("ignore")
arima = ARIMA(order=args.order,
seasonal_order=args.seasonal_order)
arima.fit(train)
print(arima.summary())
residuals = arima.resid()
print("train lengths: data={} resid={}".format(
train_len, residuals.shape[0]))
len_delta = train_len - residuals.shape[0]
# Diagnostics plot
arima.plot_diagnostics(lags=50)
box_ljung(residuals, nlags=20).format()
plt.gcf().suptitle('Diagnostics Plot')
plt.figure()
plt.plot(df.value.index[len_delta:train_len],
np.abs(residuals), label="abs(residuals)")
plt.plot(df.value, label="data", alpha=0.5)
# fig, axes = plt.subplots(3, 1, sharex=True)
# axes[0].plot(arima.resid(), label="residuals")
# axes[1].plot(arima.resid()**2, label="residuals^2")
plt.gcf().suptitle('Diagnostics Plot', fontsize=14)
# !! not necessary !! Everything already plotted
# Plot Residuals and fitted values
# plt.figure()
# fitted_values = arima.predict_in_sample()
# plt.plot(df.index[:train_len - 1], fitted_values,
# color='C0', label="Fitted values")
# plt.plot(pd.to_datetime(df.index), data, color='C1', label="Data")
# plt.plot(df.index[:train_len - 1], arima.resid(),
# color='C2', label="Residuals")
# plt.gca().grid(which='both', axis='x', linestyle='--')
# plt.title("Residuals and fitted values")
# plt.legend()
print("SSE: {}".format((arima.resid()**2).sum()))
# Plot fitted values and forecasts
predictions = arima.predict(n_periods=test.shape[0])
fitted_values = arima.predict_in_sample()
plt.figure()
plt.plot(df.index[train_len:], test, '--', color='C0', label="test set")
plt.plot(df.index[train_len:],
predictions,
'--',
color='C1',
label="forecasted values")
plt.plot(df.index[:train_len], train, color='C0', label="train set")
plt.plot(df.index[:train_len - 1],
fitted_values,
color='C1',
joblib.dump(arima, fpath, compress=3)
else:
print("Reading model from disk")
arima = joblib.load(fpath)
gt_pred, gt_windows = get_gt_arrays(
df.index, df.index, labels, labels_windows
)
# Compute metrics
metrics_columns = ["precision", "recall", "f_score", "nab_score"]
Metrics = collections.namedtuple("Metrics", metrics_columns)
window_size = 30
alpha = 0.15
pred = get_arima_predictions(arima.resid(), window_size, alpha)
print("Anomalies number:", pred[pred == -1].shape[0])
len_delta = len(df.value) - pred.shape[0]
nab_score = get_nab_score(gt_windows, pred)
simple_metrics = get_simple_metrics(gt_pred[len_delta:], pred)
metrics = simple_metrics + (nab_score,)
metrics = Metrics(*metrics)
anomalies = df.value[len_delta:][pred == -1]
ax = make_predictions_plots(
whole_df, df, labels, labels_windows, "", anomalies, ""
)
line = "& {} & {:.2f} & {:.2f} & {:.2f} & {:.2f} \\\\".format(
"\\emph{ARIMA}",
metrics.nab_score,
