Add new timeseries anomaly detection primitives

[itinawi]

X-Sigma primitive:
This primitive computes the absolute error of a prediction and checks to see if its magnitude is larger than a factor of x-sigma where x is a positive integer.

Edit the timeseries_errors.py file so that it has methods from only the NASA paper. It should be given a different name like dynamic_error_thresholding.py

For the new primitive, I will call it sigma_error_thresholding.py

Methods needed for this primitive:

• To compute the error for this method, we could use the get_forecast_errors() method similarly implemented in the current timeseries_errors.py

• detect_sigma_outliers(errors, num_sigmas) returns a list of contiguous sequences of anomalies, where each an anomaly has errors[i] > x*sigma_error and sigma_error = np.std(errors).