def generate_splits(task_config,hash,colname):
base_query = SON([('__hash__',hash)])
ntrain = task_config['ntrain']
ntest = task_config['ntest']
ntrain_pos = task_config.get('ntrain_pos')
ntest_pos = task_config.get('ntest_pos')
N = task_config.get('N',10)
query = task_config['query']
base_query.update(reach_in('config',task_config.get('universe',SON([]))))
cquery = reach_in('config',query)
print('q',cquery)
print('u',base_query)
return traintest.generate_split2(DB_NAME,colname,cquery,N,ntrain,ntest,ntrain_pos=ntrain_pos,ntest_pos = ntest_pos,universe=base_query,use_negate = True)
def train_test_loop(outfile,extract_creates,task_config,feature_config_path,hash):
feature_config = get_config(feature_config_path)
base_query = SON([('__config_hash__',hash)])
image_params = SON([('image',feature_config['image'])])
models_params = feature_config['models']
ntrain = task_config['ntrain']
ntest = task_config['ntest']
ntrain_pos = task_config.get('ntrain_pos')
N = task_config.get('N',10)
query = task_config['query']
base_query.update(reach_in('config',task_config.get('universe',SON([]))))
print('\n')
print('BASE',base_query)
print('\n')
conn = pm.Connection(document_class=SON)
db = conn['v1']
fs = gridfs.GridFS(db, collection = 'model_performance')
cquery = reach_in('config',query)
for m in models_params:
base_query_copy = base_query.copy()
base_query_copy.update(reach_in('config.model',m))
splitdata, results = train_test(cquery,'v1','features',ntrain,ntest,ntrain_pos=ntrain_pos,N=N,universe=base_query_copy)
splitpickle = cPickle.dumps(splitdata)
data = SON([('feature_config_path',feature_config_path),
('model',m),
('task',son_escape(task_config)),
('image__aggregate__',son_escape(feature_config['image']))])
filename = get_filename(data)
data.update(results)
data['filename'] = filename
fs.put(splitpickle,**data)
createCertificateDict(outfile,{'task_config':task_config,'feature_config':feature_config,'feature_config_path':feature_config_path})