This operator learns deviation of (each point of a) sequence. The sequence needs a counter so that the operator can distinguish multiple sequences and the values within a sequence. The operator uses the online-learn algorithm of the DeviationLearn operator.
The operator gets the following input:
This were two sequences, because a new sequence starts if the counter of the next tuple is smaller than the previous counter. Every sequence had three tuples. The output on port 1 would be the following:
- attribute Name of the attribute which should be analysed
- sequencesToLearn The number of (correct) sequencesto learn from. The first x sequences will define the perfect sequence the others are compared to. If set to 0, the operator will not stop to learn (learn infinity sequences). Default is 0.
- GROUP_BY To group the tuples into the single parts of the sequence.
- fastGrouping Use hash code instead of tuple compare to create group. Potentially unsafe!
The example PQL code shows, how to use the operator. The GROUP_BY parameter is very important because it is used to distinguish the single values within one sequence.