def train_model_agg( self, bags, y, cv_split_bags=None, sample_weight=None, param_search=True ):
"""Train instance aggregation function using quantile function."""
# figure out number of quantiles and where to set them
ninst = int( np.round( sum( [ len(bag) for bag in bags ] ) / float(len(bags)) ) )
if self.quantiles is not None:
nq = self.quantiles
else:
nq = 16
if ninst <= nq:
quantiles = np.linspace(0,100,ninst)
else:
quantiles = np.linspace(100.0/nq/2,100-100.0/nq/2,nq)
p = []
test_y = []
if cv_split_bags is None:
# train/test split
skf = sklearn.model_selection.StratifiedKFold( n_splits=5, shuffle=True )
cv_split_bags = list(skf.split(bags,y))
# compute quantile function
for f in range(5):
train_idx,test_idx = cv_split_bags[f]
for i in test_idx:
pi = super(SIL,self).predict( bags[i], cv=f )
if pi.shape[1] == 2:
q = np.percentile( pi[:,1], quantiles )
else:
q = np.hstack( [ np.percentile( pi[:,c], quantiles ) for c in range(pi.shape[1]) ] )
p.append( q )
test_y.append( y[i] )
p = np.vstack(p)
test_y = np.array(test_y)
# train model
model_agg = LinearClassifier( classifier='svm' )
self.C_agg,self.gamma_agg = model_agg.param_search( p, test_y, sample_weight=sample_weight, quick=False )
model_agg.C = self.C_agg
model_agg.fit( p, test_y, sample_weight=sample_weight, param_search=param_search, calibrate=self._calibrate )
self._model_agg = (model_agg,quantiles)
y_train = labels[idx_train, c]
y_sw = y_train + len(label_names[c]) * labels_sw[idx_train]
uniq = np.unique(y_sw).tolist()
counts = np.array([(y_sw == l).sum() for l in uniq])
counts = counts.sum().astype(float) / (counts * len(counts))
sw = np.array([counts[uniq.index(y)] for y in y_sw])
else:
sw = None
if mi_type is None:
model = LinearClassifier(n_jobs=n_jobs, **options)
model.fit(X_train,
y_train,
calibrate=calibrate,
param_search=True,
sample_weight=sw)
elif mi_type in ['median', 'max']:
model = SIL(n_jobs=n_jobs, **options)
model.fit(X_train,
y_train,
calibrate=calibrate,
param_search=True,
sample_weight=sw)
elif mi_type == 'quantile':
if quantiles is not None:
options['quantiles'] = int(quantiles)
model = SIL(n_jobs=n_jobs, **options)
model.fit(X_train,
y_train,
