Running process and method calling convention
There are a few parts of the logic that you need to be familiar with.
fit command, when
partial_fit=f (default), first the algorithm's
fit method is called. If it returns a DataFrame, we return that to the search. If it doesn't, we will call
apply later, then return whatever DataFrame
apply gives us.
Fit command partial_fit=t
partial_fit=t, the algorithm's
partial_fit method is called on each chunk of 50,000 events. Then
apply is called on those events. We continue this process until we run out of data.
apply command, things are much simpler. We reconstruct the python object by using its codec, then call
apply on the events, chunk by chunk.
summary command, things are similar to
apply. We reconstruct the python object by using its codec, then call
Write an algorithm class
This documentation applies to the following versions of Splunk® Machine Learning Toolkit: 2.3.0, 2.4.0, 3.0.0, 3.1.0, 3.2.0, 3.3.0, 3.4.0, 4.0.0, 4.1.0, 4.2.0, 4.3.0