def main_predict(model_initializer, args):
iterator = model_initializer.load_data(args)
from itertools import tee
iterator, iterator_ = tee(iterator)
from eden.model import ActiveLearningBinaryClassificationModel
model = ActiveLearningBinaryClassificationModel()
model.load(args.model_file)
logger.info(model.get_parameters())
predictions = model.decision_function(iterator)
text = []
for p in predictions:
text.append(str(p) + "\n")
save_output(text=text, output_dir_path=args.output_dir_path, out_file_name='predictions.txt')
text = []
for p in predictions:
if p > 0:
prediction = 1
else:
prediction = -1
text.append(str(prediction) + "\n")
save_output(text=text, output_dir_path=args.output_dir_path, out_file_name='classifications.txt')
text = []
from itertools import izip
info_iterator = model.get_info(iterator_)
for p, info in izip(predictions, info_iterator):
text.append("%.4f\t%s\n" % (p, info))
save_output(text=text, output_dir_path=args.output_dir_path, out_file_name='info.txt')
def main_feature(model_initializer, args):
iterator = model_initializer.load_data(args)
from eden.model import ActiveLearningBinaryClassificationModel
model = ActiveLearningBinaryClassificationModel()
model.load(args.model_file)
logger.info(model.get_parameters())
X = model._data_matrix(iterator)
store_matrix(matrix=X, output_dir_path=args.output_dir_path, out_file_name='data_matrix', output_format=args.output_format)
def main_estimate(model_initializer, args):
pos_test_iterator = model_initializer.load_positive_data(args)
neg_test_iterator = model_initializer.load_negative_data(args)
from eden.model import ActiveLearningBinaryClassificationModel
model = ActiveLearningBinaryClassificationModel()
model.load(args.model_file)
logger.info(model.get_parameters())
apr, rocauc = model.estimate(pos_test_iterator, neg_test_iterator)
def main_matrix(model_initializer, args):
iterator = model_initializer.load_data(args)
from eden.model import ActiveLearningBinaryClassificationModel
model = ActiveLearningBinaryClassificationModel()
model.load(args.model_file)
logger.info(model.get_parameters())
X = model._data_matrix(iterator)
K = metrics.pairwise.pairwise_kernels(X, metric='linear')
store_matrix(matrix=K, output_dir_path=args.output_dir_path, out_file_name='Gram_matrix', output_format=args.output_format)
def main_feature(model_initializer, args):
iterator = model_initializer.load_data(args)
from eden.model import ActiveLearningBinaryClassificationModel
model = ActiveLearningBinaryClassificationModel()
model.load(args.model_file)
logger.info(model.get_parameters())
X = model._data_matrix(iterator)
store_matrix(matrix=X,
output_dir_path=args.output_dir_path,
out_file_name='data_matrix',
output_format=args.output_format)
def main_matrix(model_initializer, args):
iterator = model_initializer.load_data(args)
from eden.model import ActiveLearningBinaryClassificationModel
model = ActiveLearningBinaryClassificationModel()
model.load(args.model_file)
logger.info(model.get_parameters())
X = model._data_matrix(iterator)
K = metrics.pairwise.pairwise_kernels(X, metric='linear')
store_matrix(matrix=K,
output_dir_path=args.output_dir_path,
out_file_name='Gram_matrix',
output_format=args.output_format)
def main_predict(model_initializer, args):
iterator = model_initializer.load_data(args)
from itertools import tee
iterator, iterator_ = tee(iterator)
from eden.model import ActiveLearningBinaryClassificationModel
model = ActiveLearningBinaryClassificationModel()
model.load(args.model_file)
logger.info(model.get_parameters())
text = []
for margin, graph_info in model.decision_function_info(iterator, key='id'):
if margin > 0:
prediction = 1
else:
prediction = -1
text.append("%d\t%s\t%s\n" % (prediction, margin, graph_info))
save_output(text=text, output_dir_path=args.output_dir_path, out_file_name='predictions.txt')
def main_predict(model_initializer, args):
iterator = model_initializer.load_data(args)
from itertools import tee
iterator, iterator_ = tee(iterator)
from eden.model import ActiveLearningBinaryClassificationModel
model = ActiveLearningBinaryClassificationModel()
model.load(args.model_file)
logger.info(model.get_parameters())
text = []
for margin, graph_info in model.decision_function_info(iterator, key='id'):
if margin > 0:
prediction = 1
else:
prediction = -1
text.append("%d\t%s\t%s\n" % (prediction, margin, graph_info))
save_output(text=text,
output_dir_path=args.output_dir_path,
out_file_name='predictions.txt')
def main_predict(model_initializer, args):
iterator = model_initializer.load_data(args)
from itertools import tee
iterator, iterator_ = tee(iterator)
from eden.model import ActiveLearningBinaryClassificationModel
model = ActiveLearningBinaryClassificationModel()
model.load(args.model_file)
logger.info(model.get_parameters())
predictions = model.decision_function(iterator)
text = []
for p in predictions:
text.append(str(p) + "\n")
save_output(text=text,
output_dir_path=args.output_dir_path,
out_file_name='predictions.txt')
text = []
for p in predictions:
if p > 0:
prediction = 1
else:
prediction = -1
text.append(str(prediction) + "\n")
save_output(text=text,
output_dir_path=args.output_dir_path,
out_file_name='classifications.txt')
text = []
from itertools import izip
info_iterator = model.get_info(iterator_)
for p, info in izip(predictions, info_iterator):
text.append("%.4f\t%s\n" % (p, info))
save_output(text=text,
output_dir_path=args.output_dir_path,
out_file_name='info.txt')
def get_stem(seqs,window_c,model_c_name,window_d, model_d_name,flank_size_l,flank_size_r):
from itertools import izip
import re
from itertools import tee,islice
#1)c_finder
seqs_c = get_Cbox(seqs,window_c)
#2)submit the Cbox candidates to the model
from eden.model import ActiveLearningBinaryClassificationModel
model = ActiveLearningBinaryClassificationModel()
model.load(model_c_name)
seqs_c_pred = list()
cands_c = list()
max_count = 0
for seq_c in seqs_c:
max_count +=1
cands_c.append(seq_c)
if (max_count == 10000): #in order to not generate memory leak I've restricted the number of samples to be submited to the model
preds = model.decision_function(cands_c)
seqs_c_pred = seqs_c_pred + zip(cands_c,preds)
cands_c = list()
max_count = 0
if (max_count != 0):
preds = model.decision_function(cands_c)
seqs_c_pred = seqs_c_pred + zip(cands_c,preds)
#discard sequences with pred < 0
seqs_c = list()
for cand in seqs_c_pred:
if (cand[1] >= 0.0):
seqs_c.append(cand)
#D_finder
seqs_cd = get_Dbox(seqs_c,window_d)
#submit Dboxes candidate to its model
model = ActiveLearningBinaryClassificationModel()
model.load(model_d_name)
seqs_d_pred = list()
cands_d = list()
max_count = 0
for seq_d in seqs_cd:
max_count +=1
cands_d.append(seq_d)
if (max_count == 10000): #in order to not generate memory leak I've restricted the number of samples to be submited to the model
preds = model.decision_function(cands_d)
seqs_d_pred = seqs_d_pred + zip(cands_d,preds)
cands_d = list()
max_count = 0
if (max_count != 0):
preds = model.decision_function(cands_d)
seqs_d_pred = seqs_d_pred + zip(cands_d,preds)
#Get the stem region from the sequences
stem_cands=[]
stem_info =[]
#(([[(header, seq), pos_c], cand_c, pred_c, pos_d], 'UAAxCUGAyGAU'), 77.000434164559792)
for ([[(header,nts),pos_c],cand_c,pred_c,pos_d],cand_d),pred_d in seqs_d_pred:
#print header,'\t',seq,pos_c,'\t',cand_c,'\t',pred_c,'\t',cand_d,'\t',pred_d,"\n---\n"
if ( int(pos_c) - 10 < 0):
if (int(pos_d)+10 > len(nts)):
stem_cands.append([[header,pos_c,pos_d],nts[0:int(pos_c)+6]+"&"+nts[int(pos_d)-1:len(nts)]])
else:
stem_cands.append([[header,pos_c,pos_d],nts[0:int(pos_c)+6]+"&"+nts[int(pos_d)-1:int(pos_d)+3+10]])
else:
if (int(pos_d)+10 > len(nts)):
stem_cands.append([[header,pos_c,pos_d],nts[int(pos_c)-10:int(pos_c)+6]+"&"+nts[int(pos_d)-1:len(nts)]])
else:
stem_cands.append([[header,pos_c,pos_d],nts[int(pos_c)-10:int(pos_c)+6]+"&"+nts[int(pos_d)-1:int(pos_d)+3+10]])
return stem_cands
