In [1]:

    

%cd ~/NetBeansProjects/ExpLosion/
from notebooks.common_imports import *
from gui.output_utils import *

sns.timeseries.algo.bootstrap = my_bootstrap
sns.categorical.bootstrap = my_bootstrap


    

    




/Users/miroslavbatchkarov/NetBeansProjects/ExpLosion

In [2]:

    

ids = Experiment.objects.filter(labelled__in=['movie-reviews-tagged', 'aclImdb-tagged'],
                                clusters__isnull=False).values_list('id', flat=True)
print(ids)
df = dataframe_from_exp_ids(ids, {'id':'id',
                                  'labelled': 'labelled',
                                  'algo': 'clusters__vectors__algorithm',
                                  'unlab': 'clusters__vectors__unlabelled',
                                  'num_cl': 'clusters__num_clusters'}).convert_objects(convert_numeric=True)
performance_table(df)


    

    




[385, 386, 387, 388, 389]
folds has 2500 values
Accuracy has 2500 values
id has 2500 values
unlab has 2500 values
num_cl has 2500 values
algo has 2500 values
labelled has 2500 values
keeping {'unlab', 'num_cl', 'algo', 'labelled'}






    
Out[2]:






  

    

      

      

      

      

      
mean
      
ci_width
    
    

      
algo
      
labelled
      
num_cl
      
unlab
      

      

    
  
  

    

      
glove
      
aclImdb-tagged
      
100
      
wiki
      
62.794289
      
1.326575
    
    

      
w2v
      
aclImdb-tagged
      
100
      
cwiki
      
62.226928
      
1.303602
    
    

      
wiki
      
62.255558
      
1.229679
    
    

      
500
      
wiki
      
66.200386
      
1.206691
    
    

      
2000
      
wiki
      
68.837472
      
1.041709
    
  

In [ ]: