(2019-06-12)
- Tensor Building and RCLR transformation in
preprocessing.rclr
andpreprocessing.build
- N-mode tensor building and transformation
- Mean of counts for subject-conditional pairs with several samples
- In
preprocessing.build
:- pervious -> current
- build().sample_order -> build().subject_order
- build().temporal_order -> build().condition_orders
- as a list for N possible condition(s)
- build().tensor -> build().counts
- tensor building and transformation
-
line 369-360 in
factorization.tenals
causes np.nan(s) in solution- fixed by added pseudocount if any nan in solution
-
line 178-179 in
factorization.TenAls
- was previously checking if all missing/zero not if there were no missing/zero as intended
- In
preprocessing.rclr
andpreprocessing.build
:- build().transform() ->
preprocessing.rclr
as standalone function
- build().transform() ->
- line 175 in
factorization.TenAls
to send ValueError if input is not numpy array
(2019-05-17)
-
Tensor factorization in
factorization.tenals
andfactorization.TenALS
- Accomplished by turning hard-coded operations into for loops and generalizing vectorization using tensor contractions
-
Khatri Rao Product
factorization.tenals
returns a list of matricesloadings
instead ofu1, u2, u3
tuple, along with other arguments
- tensor contraction
- various type and spacing fixes
Original "working" code