

In [1]:

    
%pylab inline









    



Populating the interactive namespace from numpy and matplotlib

Scores (`pyannote.core.scores.Scores`)



In [2]:

    
from pyannote.core import Scores

Scores instances are used to describe classification scores. For instance, one can use a Scores to store the result of speaker identification approach applied on an episode of The Big Bang Theory TV series.



In [3]:

    
scores = Scores(
    uri='TheBigBangTheory.Season01.Episode01', 
    modality='speaker'
)

For instance, to represent a dialogue between Penny and Leonard, we could do the following:



In [4]:

    
from pyannote.core import Segment
scores[Segment(3, 5), '_', 'Penny'] = 8
scores[Segment(3, 5), '_', 'Leonard'] = 0.15
scores[Segment(3, 5), '_', 'Sheldon'] = 0.05
scores[Segment(5.5, 7), '_', 'Penny'] = 0.4
scores[Segment(5.5, 7), '_', 'Leonard'] = 0.5
scores[Segment(5.5, 7), '_', 'Sheldon'] = 0.1
scores[Segment(8, 10), '_', 'Penny'] = 0.4
scores[Segment(8, 10), '_', 'Leonard'] = 0.25
scores[Segment(8, 10), '_', 'Sheldon'] = -12
scores









    Out[4]:



In [5]:

    
scores.to_annotation()









    Out[5]:



In [6]:

    
from pyannote.core import notebook
subplot(211)
notebook(scores, time=False)
subplot(212)
notebook(scores.to_annotation(), legend=False)

Scores (pyannote.core.scores.Scores)

Scores (`pyannote.core.scores.Scores`)