New QC Tests to Add

[kenkehoe]

This is to track what QC tests need to be added. I added all the numpy masked array options and two more, persistence and single variable comparison.

[kenkehoe]

Need to add a more than two variable comparison. I'm thinking of a three or more variable comparison where it can narrow down which variable is incorrect so a variable is not flagged when the other variable is the issue.

[kenkehoe]

Need to add some normal distribution tests. Maybe a Grubbs test, or Grubbs expanded like the DQ Office currently employes.

[kenkehoe]

Will need something along the lines of a statistical covariance.

[AdamTheisen]

Have you checked to see what python libraries are already out there? Could we build what we need based on the scipy stats functions? https://docs.scipy.org/doc/scipy/reference/stats.html

[AdamTheisen]

One other thought is how we would want to implement these. Not sure if adding as method or variable makes more sense.

[kenkehoe]

I prefer the method way as it allows for passing different keywords for each test. Different tests will need different inputs.

[AdamTheisen]

@kenkehoe not sure if you looked, but I did not add the FFT test to the same class as the others. Since it was instrument specific, I thought it would be best to leave as a separate function that one has to call. Sound good?

[kenkehoe]

Yeah that is fine @AdamTheisen.

[AdamTheisen]

@kenkehoe Converting this issue to the discussion board since it's more idea gathering.