BDe score

[ncullen93]

BDe score

[ncullen93]

I think this is because the network and the data don't match.. The andes network has these nodes: ['asia', 'smoke', 'tub', 'bronc', 'lung', 'either', 'dysp', 'xray'], whereas the lizards dataset only has 3 columns (nodes).. The BDe score measures how well a given BN fits a COMPATIBLE dataset (i.e. the nodes of the BN match up with the columns of the dataset). :)

[ncullen93]

Note, you can try LEARNING the structure from the lizards.csv dataset and check the BDe score.. OR you can generate your own random andes dataset and check the BDe score.

[sonujose123]

Thanks a lot for your quick response.

…

On Dec 4, 2016 8:43 PM, "Nicholas Cullen" ***@***.***> wrote: Note, you can try LEARNING the structure from the lizards.csv dataset and check the BDe score.. OR you can generate your own random andes dataset and check the BDe score. — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#20 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AQjW7cACYYtAtT-aHoMcVKIBMBtBEL6yks5rE5aPgaJpZM4LD0wr> .

[sonujose123]

Hi Nicholas,
I tried with modified csv with asia.bif . Then also I am facing the same issue.
I got this error -
python test.py
['asia', 'smoke', 'tub', 'bronc', 'lung', 'either', 'dysp', 'xray']
('asia', 'tub')
('smoke', 'bronc')
('smoke', 'lung')
('tub', 'either')
('bronc', 'dysp')
('lung', 'either')
('either', 'dysp')
('either', 'xray')
/home/sonu/Documents/pyBN/pyBN-master/pyBN/learning/parameter/mle.py:48: VisibleDeprecationWarning: using a non-integer number instead of an integer will result in an error in the future
F[rv]['cpt'] = nmp.histogram(data[:,rv], bins=bn.card(rv))[0]
Traceback (most recent call last):
File "test.py", line 20, in
print BDe(bn,data)
File "/home/sonu/Documents/pyBN/pyBN-master/pyBN/learning/structure/score/bayes_scores.py", line 61, in BDe
counts_dict = mle_fast(bn, data, counts=True, np=True)
File "/home/sonu/Documents/pyBN/pyBN-master/pyBN/learning/parameter/mle.py", line 48, in mle_fast
F[rv]['cpt'] = nmp.histogram(data[:,rv], bins=bn.card(rv))[0]
IndexError: only integers, slices (:), ellipsis (...), numpy.newaxis (None) and integer or boolean arrays are valid indices

Please help me.

Regards
asia.bif.zip

Sonu
lizards.csv.zip

[ncullen93]

Ok i think i fixed it... pandas must have changed their indexing since I wrote this. It should work if 'data' is a pandas dataframe whose columns are same as BN nodes.. but i think it will now be broken if data is numpy array.

[ncullen93]

Pull the repository and try again