In [1]:

    

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

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


    

    




/Volumes/LocalDataHD/m/mm/mmb28/NetBeansProjects/ExpLosion

In [2]:

    

s = {'document_features_ev': 'J+N+AN+NN',
     'document_features_tr': 'J+N+AN+NN',
     'expansions__allow_overlap': 0,
     'expansions__decode_handler': 'SignifiedOnlyFeatureHandler',
     'expansions__entries_of_id': None,
     'expansions__k': 3,
     'expansions__neighbour_strategy': 'linear',
     'expansions__noise': 0.0,
     'expansions__use_random_neighbours': 0,
     'expansions__use_similarity': 0,
     'expansions__vectors__algorithm': 'word2vec',
#      'expansions__vectors__composer': 'Add',
     'expansions__vectors__dimensionality': 100,
     'expansions__vectors__rep': 0,
     'expansions__vectors__unlabelled__in': ['gigaw', 'wiki'],
     'expansions__vectors__unlabelled_percentage__in': [15, 100],
     'labelled': 'amazon_grouped-tagged'}
ids = list(Experiment.objects.filter(**s).values_list('id', flat=True))
s['document_features_ev'] = 'AN+NN'
ids += list(Experiment.objects.filter(**s).values_list('id', flat=True))
# s['document_features_ev'] = 'AN'
# ids += list(Experiment.objects.filter(**s).values_list('id', flat=True))
# s['document_features_ev'] = 'NN'
# ids += list(Experiment.objects.filter(**s).values_list('id', flat=True))
print(ids, 'total', len(ids))

fields = {  'unlab': 'expansions__vectors__unlabelled',
            'percent': 'expansions__vectors__unlabelled_percentage',
            'Composer': 'expansions__vectors__composer',
            'feats': 'document_features_ev'}
df = dataframe_from_exp_ids(ids, fields)
df['corpus'] = ['%s-%s'%(a,b) for a,b in zip(df.unlab, df.percent)]
with sns.color_palette("cubehelix", 4):
    g= sns.factorplot(y='Accuracy', x='corpus', col='Composer', hue='feats', 
                       x_order=sort_df_by(df, 'corpus'),
                       col_wrap=2, ci=68, aspect=1.5,
                       data=df, kind='bar');

for ax in g.axes.flat:
    ax.axhline(random_vect_baseline(), c='k');
plt.savefig('plot-nps-at-decode-time.pdf', format='pdf', dpi=300, bbox_inches='tight', pad_inches=0.1)


    

    




[195, 196, 197, 198, 199, 200, 201, 202, 203, 204, 205, 206, 19, 20, 21, 22, 34, 35, 36, 37, 75, 76, 77, 78] total 24
Calculating CI for exp 195
Calculating CI for exp 196
Calculating CI for exp 197
Calculating CI for exp 198
Calculating CI for exp 199
Calculating CI for exp 200
Calculating CI for exp 201
Calculating CI for exp 202
Calculating CI for exp 203
Calculating CI for exp 204
Calculating CI for exp 205
Calculating CI for exp 206






    




/home/m/mm/mmb28/anaconda3/lib/python3.4/site-packages/seaborn/categorical.py:2653: UserWarning: The `x_order` parameter has been renamed `order`
  UserWarning)

WARNING:py.warnings:/home/m/mm/mmb28/anaconda3/lib/python3.4/site-packages/seaborn/categorical.py:2653: UserWarning: The `x_order` parameter has been renamed `order`
  UserWarning)







    




Accuracy has 12000 values
percent has 12000 values
folds has 12000 values
feats has 12000 values
Composer has 12000 values
unlab has 12000 values






    

In [ ]: