def xval(self, nfold=5, nrep=10, pairwiseGTA=None, pairwiseViral=None, cluster_type='farthest', d=0.03):
"""n-fold cross validation of
the test set.
Input:
n (int): number of folds for xval
Returns:
(fpr, fnr): false positive and false
negative rates from the n xvals
"""
# keep track of label classification
score0 = 0.0
score1 = 0.0
gta_as_phage = []
phage_as_gta = []
# repeat xval results nrep times
for i in range(nrep):
if not mini:
sys.stdout.flush()
sys.stdout.write("Starting rep: %d\r" % (i+1))
# randomly sort profiles
random.shuffle(self.profiles)
# split into folds
split = [self.profiles[i::nfold] for i in range(nfold)]
# cross val
for j in range(nfold):
# Build train and test sets
train_fold = np.array([x for sublist in (split[:j]+split[j+1:]) for x in sublist])
test_fold = split[j]
trainX = np.array([x.features for x in train_fold])
testX = np.array([x.features for x in test_fold])
trainY = np.array([-1.0 if y.label == self.label0 else 1.0 for y in train_fold])
testY = np.array([-1.0 if y.label == self.label0 else 1.0 for y in test_fold])
testNames = np.array([x.org_name for x in test_fold])
# randomize labels
# random.shuffle(trainY)
# Get training set weights
if pairwiseGTA:
# Reweight based on training set
# GTA
GTA_weight = Weight([x for x in train_fold if x.label == self.label0], pairwiseGTA)
GTA_clusters = GTA_weight.cluster(cluster_type, d)
GTA_weight.weight(GTA_clusters)
# Virus
virus_weight = Weight([x for x in train_fold if x.label != self.label0], pairwiseViral)
virus_clusters = virus_weight.cluster(cluster_type, d)
virus_weight.weight(virus_clusters)
# Grab updated weights
weights = np.array([x.weight for x in train_fold])
else:
weights = np.array([1 for x in train_fold])
# evaluate results
predictor = SVMTrain(self.kernel, self.c).train(trainX, trainY, weights)
for r in range(len(testX)):
# Positive product is correct classification
if predictor.predict(testX[r]) * testY[r] > 0:
# Update label0 if negative, label1 otherwise
if testY[r] < 0:
score0 += 1
else:
score1 += 1
else: # predicted incorrectly
if testY[r] > 0: #virus as GTA
phage_as_gta.append(testNames[r])
else: #gta as virus
gta_as_phage.append(testNames[r])
if not mini:
print("\nPhages (%d) misclassified over %d reps: %s" % (len(phage_as_gta), nrep, phage_as_gta))
print("\nGTA (%d) misclassified over %d reps: %s\n" % (len(gta_as_phage), nrep, gta_as_phage))
return (score0/nrep, score1/nrep)
def xval(self,
nfold=5,
nrep=10,
pairwiseGTA=None,
pairwiseViral=None,
cluster_type='farthest',
d=0.03):
"""n-fold cross validation of
the test set.
Input:
n (int): number of folds for xval
Returns:
(fpr, fnr): false positive and false
negative rates from the n xvals
"""
# keep track of label classification
score0 = 0.0
score1 = 0.0
gta_as_phage = []
phage_as_gta = []
# repeat xval results nrep times
for i in range(nrep):
if not mini:
sys.stdout.flush()
sys.stdout.write("Starting rep: %d\r" % (i + 1))
# randomly sort profiles
random.shuffle(self.profiles)
# split into folds
split = [self.profiles[i::nfold] for i in range(nfold)]
# cross val
for j in range(nfold):
# Build train and test sets
train_fold = np.array([
x for sublist in (split[:j] + split[j + 1:])
for x in sublist
])
test_fold = split[j]
trainX = np.array([x.features for x in train_fold])
testX = np.array([x.features for x in test_fold])
trainY = np.array([
-1.0 if y.label == self.label0 else 1.0 for y in train_fold
])
testY = np.array([
-1.0 if y.label == self.label0 else 1.0 for y in test_fold
])
testNames = np.array([x.org_name for x in test_fold])
# randomize labels
# random.shuffle(trainY)
# Get training set weights
if pairwiseGTA:
# Reweight based on training set
# GTA
GTA_weight = Weight(
[x for x in train_fold if x.label == self.label0],
pairwiseGTA)
GTA_clusters = GTA_weight.cluster(cluster_type, d)
GTA_weight.weight(GTA_clusters)
# Virus
virus_weight = Weight(
[x for x in train_fold if x.label != self.label0],
pairwiseViral)
virus_clusters = virus_weight.cluster(cluster_type, d)
virus_weight.weight(virus_clusters)
# Grab updated weights
weights = np.array([x.weight for x in train_fold])
else:
weights = np.array([1 for x in train_fold])
# evaluate results
predictor = SVMTrain(self.kernel,
self.c).train(trainX, trainY, weights)
for r in range(len(testX)):
# Positive product is correct classification
if predictor.predict(testX[r]) * testY[r] > 0:
# Update label0 if negative, label1 otherwise
if testY[r] < 0:
score0 += 1
else:
score1 += 1
else: # predicted incorrectly
if testY[r] > 0: #virus as GTA
phage_as_gta.append(testNames[r])
else: #gta as virus
gta_as_phage.append(testNames[r])
if not mini:
print("\nPhages (%d) misclassified over %d reps: %s" %
(len(phage_as_gta), nrep, phage_as_gta))
print("\nGTA (%d) misclassified over %d reps: %s\n" %
(len(gta_as_phage), nrep, gta_as_phage))
return (score0 / nrep, score1 / nrep)
if args.kmer == None and args.pseaac == None and not args.physico:
print("You must specify at least one feature type (-k, -p, -y).")
else:
# Weight if needed
if args.weight:
# Get distance threshold
d = args.dist[0]
# Get cluster type
cluster_type = args.cluster_type[0]
# Weight GTA
pairwiseGTA = Weight.load(args.weight[0])
GTA_weight = Weight(gta_profs, pairwiseGTA)
GTA_clusters = GTA_weight.cluster(cluster_type, d)
GTA_weight.weight(GTA_clusters)
# Weight Virus
pairwiseViral = Weight.load(args.weight[1])
virus_weight = Weight(viral_profs, pairwiseViral)
virus_clusters = virus_weight.cluster(cluster_type, d)
virus_weight.weight(virus_clusters)
# Create SVM
c = args.c[0]
kernel = args.kernel[0]
kernel_var = float(args.kernel[1])
svm = SVM(gta_profs, viral_profs, c, kernel, kernel_var)
# Print support vectors
if args.svs:
if args.kmer == None and args.pseaac == None and not args.physico:
print("You must specify at least one feature type (-k, -p, -y).")
else:
# Weight if needed
if args.weight:
# Get distance threshold
d = args.dist[0]
# Get cluster type
cluster_type = args.cluster_type[0]
# Weight GTA
pairwiseGTA = Weight.load(args.weight[0])
GTA_weight = Weight(gta_profs, pairwiseGTA)
GTA_clusters = GTA_weight.cluster(cluster_type, d)
GTA_weight.weight(GTA_clusters)
# Weight Virus
pairwiseViral = Weight.load(args.weight[1])
virus_weight = Weight(viral_profs, pairwiseViral)
virus_clusters = virus_weight.cluster(cluster_type, d)
virus_weight.weight(virus_clusters)
# Create SVM
c = args.c[0]
kernel = args.kernel[0]
kernel_var = float(args.kernel[1])
svm = SVM(gta_profs, viral_profs, c, kernel, kernel_var)
# Print support vectors
if args.svs:
