def make_SVM_1(sw, dssp, x, dataset):
inputs_train = []
outputs_train = []
#read dataset file
f = open(dataset, 'r')
for i in range(x):
desc = f.readline().strip()
primlen = int(desc.split('#')[1])
prim = []
for j in range(primlen):
prim.append(f.readline().strip())
sec = f.readline().strip()
#prim = prim[-2:]
primx = inOutFunctions.merge_sequences(prim)
ins, outs = inOutFunctions.prepare_input_forX(sec, primx, sw, dssp)
for q in ins:
inputs_train.append(q)
for q in outs:
outputs_train.append(q)
f.close()
clf = svm.SVC(C=2.5, gamma=0.05)
clf.fit(inputs_train, outputs_train)
return clf
def test_SMV_1(sw, dssp, w, clfx, z):
f = open('rs126.fa', 'r')
cq = 0
cqp = 0
for i in range(z+w):
desc = f.readline().strip()
primlen = int(desc.split('#')[1])
prim = []
for j in range(primlen):
prim.append(f.readline().strip())
sec = f.readline().strip()
#prim = prim[-2:]
if i >= z:
primx = inOutFunctions.merge_sequences(prim)
ins, outs = inOutFunctions.prepare_input_forX(sec, primx, sw, dssp)
pred = inOutFunctions.display_result(clfx.predict(np.array(ins, np.float32)), {0:'X', 1:dssp})
print sec
print pred
print "\n"
cq += measurePrediction.calcQ(pred, sec, dssp)
cqp += measurePrediction.calcQpred(pred, sec, dssp)
return (cq/w, cqp/w)
def make_SVM_2(sw, dataset, groups, without, struct):
inputs_train = []
outputs_train = []
protCodes = []
for i in range(len(groups)):
if i == without:
continue
else:
for s in groups[i]:
protCodes.append(s)
for p in protCodes:
sec = dataset[p]['sec']
prim = dataset[p]['prim']
#prim = prim[-2:]
primx = inOutFunctions.merge_sequences(prim)
ins, outs = inOutFunctions.prepare_input_forX(sec, primx, sw, struct)
for q in ins:
inputs_train.append(q)
for q in outs:
outputs_train.append(q)
clf = svm.SVC(C=1.5, gamma=0.1)
clf.fit(inputs_train, outputs_train)
return clf
def test_SMV_2(clf, sw, dataset, groups, without, dssp):
cq = 0
cqp = 0
cc = 0
sov = 0
q = 18
qq = 0
protCodes = []
for s in groups[without]:
protCodes.append(s)
for p in protCodes:
sec = dataset[p]['sec']
prim = dataset[p]['prim']
#prim = prim[-2:]
primx = inOutFunctions.merge_sequences(prim)
ins, outs = inOutFunctions.prepare_input_forX(sec, primx, sw, dssp)
pred = inOutFunctions.display_result(clf.predict(np.array(ins, np.float32)), {0:'X', 1:dssp})
# print sec
# print pred
# print "\n"
cq += measurePrediction.calcQ(pred, sec, dssp)
cqp += measurePrediction.calcQpred(pred, sec, dssp)
cc += measurePrediction.calcC(pred, sec, dssp)
sovx = measurePrediction.calcSOV(pred, sec, dssp)
if sovx != None:
sov += sovx
qq += 1
return (cq/q, cqp/q, cc/q, sov/qq)
