data = (
(
seq_x, pos, create_annotation(ann_x),
seq_y, pos, create_annotation(ann_y),
)
for seq_x in itertools.product('ACGT', repeat=window_size)
for seq_y in itertools.product('ACGT', repeat=window_size)
for ann_x in itertools.product('01', repeat=window_size)
for ann_y in itertools.product('01', repeat=window_size)
)
else:
data = (
(
seq_x, pos, create_annotation(ann_x),
seq_y, pos, create_annotation(ann_y),
)
for seq_x in 'ACGT'
for seq_y in 'ACGT'
for ann_x in '01'
for ann_y in '01'
)
s = sum(clf.multi_prepare_predict(data))
return s
if __name__ == '__main__':
dp = DataPreparer(window_size)
clf = PairClassifier(dp, filename='data/randomforest1.clf')
print('Normalization constant:', compute_norm_constant(clf))
def _get_classifier(self):
return PairClassifier(self.dp,
filename=self.clf_fname,
inverted=config.same_classifier,
use_global_classifier=config.same_classifier)
