def run(self, **kwargs):
self.run_parameters = kwargs
data = self.database.get_pyml_dataset(self.features, **kwargs)
data.attachKernel('gaussian', gamma=kwargs['gamma'], normalization='cosine') # normalization='cosine'
if self.classifier == Classifier.SVM:
# svm = SVM()
svm = SVM(optimizer='pegasos')
training, testing = self.database.get_cv_folds(kwargs['folds'])
self.pyml_result = cvFromFolds(svm, data, training, testing, numFolds=kwargs['folds'], verbose=False)
self.get_rfpp()
if kwargs['save']:
self.__save_results()
def learn(classified, histograms):
clf = SVM()
total_samples = 0
for c in classified.keys():
cim = classified[c]
total_samples = total_samples + len(cim)
samples = []
labels = []
for c in classified.keys():
cim = classified[c]
for im in cim:
hist = histograms[im]
row = []
for j in range(NUM_BINS):
row.append(cv.QueryHistValue_1D(hist, j))
samples.append(row)
labels.append(c)
data = VectorDataSet(samples, L=labels)
print str(data)
clf.train(data)
return clf
from PyML import SparseDataSet, SVM
__author__ = 'basir'
data = SparseDataSet('data/heartSparse.data', labelsColumn=-1)
svm = SVM()
res = svm.cv(data, 5)
for fold in res:
print fold
print res
# print data
# help(sequenceData.spectrum_data)
def init():
'''Inits classifier with optimal options.'''
return SVM(C=10, optimization='liblinear')
def svm_prediction(peptides, job_id, input_train="SVM_POS_NEG.fasta"):
"""
Makes a final prediction based on SVM training files.
This code is used for prediciton of blind datasets, based on the training
datasets of positives and negatives.
:param peptides: input peptides
:param job_id: random job id assigned prior to start predicting
:param input_train: input positive and negative examples used in training
:return: returns SVM scores for each inputed peptide
"""
print("Begin SVM")
# from methods import load_sqlite, store_sqlite
global PATH
global TMP_PATH
# suppress SVM output
devnull = open(os.devnull, 'w')
sys.stdout, sys.stderr = devnull, devnull
svm_scores = []
# query the database
# for peptide in peptides:
# try:
# score = load_sqlite(peptide, method="SVM", unique=True)
# svm_scores.append(score)
# except:
# pass
if len(peptides) == len(svm_scores):
pass
else:
# generate a svm input from the peptides
rand = job_id
input_svm = "%s_svm.fasta" % rand
output_tmp = open(os.path.join(TMP_PATH, input_svm), "w")
count = 0
for peptide in peptides:
count += 1
output_tmp.write("> %i label=%s\n%s\n" % (count, 1, peptide))
for peptide in peptides:
count += 1
output_tmp.write("> %i label=%s\n%s\n" % (count, -1, peptide))
output_tmp.close()
# outputs
model_svm = "%s_svm_model.txt" % rand
# train data
train_data = SequenceData(os.path.join(PATH, input_train),
mink=1,
maxk=1,
maxShift=0,
headerHandler=svm_process_header)
train_data.attachKernel('cosine')
cval = 1
s = SVM(C=cval)
s.train(train_data)
s.save(os.path.join(TMP_PATH, model_svm))
# load trained SVM
loaded_svm = loadSVM(os.path.join(TMP_PATH, model_svm), train_data)
# test data
test_data = SequenceData(os.path.join(TMP_PATH, input_svm),
mink=1,
maxk=1,
maxShift=0,
headerHandler=svm_process_header)
test_data.attachKernel('cosine')
results = loaded_svm.test(test_data)
# print results out
output_svm = "%s_svm.txt" % rand
results.toFile(os.path.join(TMP_PATH, output_svm))
# load results process output (positives + negatives)
infile = open(os.path.join(TMP_PATH, output_svm), "r")
inlines = infile.readlines()
infile.close()
scores = list()
for line in inlines:
line = line.rstrip("\r\n")
try:
entry = int(line.split("\t")[0])
score = float(line.split("\t")[1])
label = int(line.split("\t")[3])
if label != "-1":
scores.append([entry, score])
except:
pass
# order list
sorted_scores = sorted(scores, key=lambda scores: scores[0])
svm_scores = list()
for score in sorted_scores:
svm_score = score[1]
svm_scores.append(svm_score)
# remove the temporary model files and results
try:
os.remove(os.path.join(TMP_PATH, input_svm))
os.remove(os.path.join(TMP_PATH, model_svm))
os.remove(os.path.join(TMP_PATH, output_svm))
except:
pass
# save the peptides in db
# for peptide, score in zip(peptides, svm_scores):
# store_sqlite(peptide, method="SVM", information=score, save=True)
# restore normal output
sys.stdout = sys.__stdout__
sys.stderr = sys.__stderr__
print("End SVM")
return svm_scores
def __init__(self):
self.Features = SVMFeatures()
self.TDFeatures = SVMTDFeatures()
self.svminstance = SVM()
