Fitting on residuals
Another method of detecting outliers from time series is fitting a classifier to the residuals from decomposition. This is also a univariate approach with the advantage of being much faster than other multivariate methods.
The apple dataset has been loaded, along with MAD estimator and the seasonal_decompose function.
Deze oefening maakt deel uit van de cursus
Anomaly Detection in Python
Praktische interactieve oefening
Probeer deze oefening eens door deze voorbeeldcode in te vullen.
results = seasonal_decompose(apple['Volume'], period=365)
# Extract and reshape the residuals
residuals = ____
residuals = ____