Janez Demšar

I agree with @markotoplak. Why would anyone want to use LR without regularization? It would not not look professional at all.

Note to whomever implements this: just change `compute_score` and `compute_stat` to return tuple `(p, -F)` instead of just `p` (where F is the value of ANOVA statistic). For tests, mock...

@markotoplak, please confirm design before I start indulging in the single greatest joy of my life, writing tests.

@VesnaT, see prints I added to the code. #### Test for naive Bayes My machine (and, probably yours) prints ``` val=12.173463707365983, p=None, k=[11.72533296 7.25521762], cls_index=0, d_=30.796719820629992 nnp 0.6101947116490711 val=374.90275104235775, p=None,...

Thanks for this suggestion, because it revived the discussion about #5655 and resulted in an interesting idea: outputs could be lazy. A widget could offer a function to compute the...

Lazy signals do not seem difficult to implement. A quick and dirty solution (which probably breaks something) is to have ```python class LazyValue: NoValue = object() def __init__(self, callable): self.callable...

On the other hand ... What if you have some data instance on the input, but then you'd like to see what would happen if some value was different? Hm,...

You're right, the result of `compute_value` should be reshaped. `compute_value` is currently called in domain conversion, which (for dense arrays) goes through `assure_column_dense`, which calls `reshape(-1)`. What about sparse data?...

The widget uses `PythonConsole`, which does `patch('sys.stdout', self)`, and calling `sys.stdout.flush`: ```python def flush(self): pass ``` `PythonConsole.write` already adds show the output without any flushing, but Qt doesn't update the...

When does ipython output commands?