def RunAllKnnShogun(q):
totalTimer = Timer()
# Load input dataset.
# If the dataset contains two files then the second file is the query
# file.
try:
Log.Info("Loading dataset", self.verbose)
if len(self.dataset) == 2:
referenceData = np.genfromtxt(self.dataset[0],
delimiter=',')
queryData = np.genfromtxt(self.dataset[1], delimiter=',')
queryFeat = RealFeatures(queryFeat.T)
else:
referenceData = np.genfromtxt(self.dataset, delimiter=',')
# Labels are the last row of the dataset.
labels = MulticlassLabels(
referenceData[:, (referenceData.shape[1] - 1)])
referenceData = referenceData[:, :-1]
with totalTimer:
# Get all the parameters.
k = re.search("-k (\d+)", options)
if not k:
Log.Fatal(
"Required option: Number of furthest neighbors to find."
)
q.put(-1)
return -1
else:
k = int(k.group(1))
if (k < 1 or k > referenceData.shape[0]):
Log.Fatal("Invalid k: " + k.group(1) +
"; must be greater than 0" +
" and less or equal than " +
str(referenceData.shape[0]))
q.put(-1)
return -1
referenceFeat = RealFeatures(referenceData.T)
distance = EuclideanDistance(referenceFeat, referenceFeat)
# Perform All K-Nearest-Neighbors.
model = SKNN(k, distance, labels)
model.train()
if len(self.dataset) == 2:
out = model.apply(queryFeat).get_labels()
else:
out = model.apply(referenceFeat).get_labels()
except Exception as e:
q.put(-1)
return -1
time = totalTimer.ElapsedTime()
q.put(time)
return time
def assign_labels(data, centroids):
from shogun.Classifier import KNN
from numpy import arange
labels = Labels(arange(1., 11.))
fea = RealFeatures(data)
fea_centroids = RealFeatures(centroids)
distance = EuclidianDistance(fea_centroids, fea_centroids)
knn = KNN(1, distance, labels)
knn.train()
return knn.apply(fea)
def assign_labels(data, centroids):
from shogun.Classifier import KNN
from numpy import arange
labels = Labels(arange(1.,11.))
fea = RealFeatures(data)
fea_centroids = RealFeatures(centroids)
distance = EuclidianDistance(fea_centroids, fea_centroids)
knn = KNN(1, distance, labels)
knn.train()
return knn.apply(fea)
def knn_train(train_data=None, train_label = None, k=1):
train_data = RealFeatures(train_data)
distance = EuclidianDistance(train_data, train_data)
try:
train_label = Labels(array(train_label.tolist(), dtype=float64))
except Exception as e:
print e
raise Exception
knn_model = KNN(k, distance, train_label)
knn_train = knn_model.train()
return knn_model
def RunAllKnnShogun(q):
totalTimer = Timer()
# Load input dataset.
# If the dataset contains two files then the second file is the query
# file.
try:
Log.Info("Loading dataset", self.verbose)
if len(self.dataset) == 2:
referenceData = np.genfromtxt(self.dataset[0], delimiter=',')
queryData = np.genfromtxt(self.dataset[1], delimiter=',')
queryFeat = RealFeatures(queryFeat.T)
else:
referenceData = np.genfromtxt(self.dataset, delimiter=',')
# Labels are the last row of the dataset.
labels = MulticlassLabels(referenceData[:, (referenceData.shape[1] - 1)])
referenceData = referenceData[:,:-1]
with totalTimer:
# Get all the parameters.
k = re.search("-k (\d+)", options)
if not k:
Log.Fatal("Required option: Number of furthest neighbors to find.")
q.put(-1)
return -1
else:
k = int(k.group(1))
if (k < 1 or k > referenceData.shape[0]):
Log.Fatal("Invalid k: " + k.group(1) + "; must be greater than 0"
+ " and less or equal than " + str(referenceData.shape[0]))
q.put(-1)
return -1
referenceFeat = RealFeatures(referenceData.T)
distance = EuclideanDistance(referenceFeat, referenceFeat)
# Perform All K-Nearest-Neighbors.
model = SKNN(k, distance, labels)
model.train()
if len(self.dataset) == 2:
out = model.apply(queryFeat).get_labels()
else:
out = model.apply(referenceFeat).get_labels()
except Exception as e:
q.put(-1)
return -1
time = totalTimer.ElapsedTime()
q.put(time)
return time
def assign_labels(data, centroids, ncenters): from shogun.Distance import EuclideanDistance from shogun.Features import RealFeatures, MulticlassLabels from shogun.Classifier import KNN from numpy import arange labels = MulticlassLabels(arange(0.,ncenters)) fea = RealFeatures(data) fea_centroids = RealFeatures(centroids) distance = EuclideanDistance(fea_centroids, fea_centroids) knn = KNN(1, distance, labels) knn.train() return knn.apply(fea)
def assign_labels(data, centroids, ncenters):
from shogun.Distance import EuclideanDistance
from shogun.Features import RealFeatures, MulticlassLabels
from shogun.Classifier import KNN
from numpy import arange
labels = MulticlassLabels(arange(0., ncenters))
fea = RealFeatures(data)
fea_centroids = RealFeatures(centroids)
distance = EuclideanDistance(fea_centroids, fea_centroids)
knn = KNN(1, distance, labels)
knn.train()
return knn.apply(fea)
def classifier_knn_modular(fm_train_real=traindat,fm_test_real=testdat,label_train_multiclass=label_traindat, k=3 ): from shogun.Features import RealFeatures, Labels from shogun.Classifier import KNN from shogun.Distance import EuclidianDistance feats_train=RealFeatures(fm_train_real) feats_test=RealFeatures(fm_test_real) distance=EuclidianDistance(feats_train, feats_train) labels=Labels(label_train_multiclass) knn=KNN(k, distance, labels) knn_train = knn.train() output=knn.apply(feats_test).get_labels() return knn,knn_train,output
def classifier_knn_modular(fm_train_real=traindat,fm_test_real=testdat,label_train_multiclass=label_traindat, k=3 ): from shogun.Features import RealFeatures, Labels from shogun.Classifier import KNN from shogun.Distance import EuclidianDistance feats_train=RealFeatures(fm_train_real) feats_test=RealFeatures(fm_test_real) distance=EuclidianDistance(feats_train, feats_train) labels=Labels(label_train_multiclass) knn=KNN(k, distance, labels) knn_train = knn.train() output=knn.apply(feats_test).get_labels() multiple_k=knn.classify_for_multiple_k() return knn,knn_train,output,multiple_k
def knn (): print 'KNN' from shogun.Features import RealFeatures, Labels from shogun.Classifier import KNN from shogun.Distance import EuclidianDistance feats_train=RealFeatures(fm_train_real) feats_test=RealFeatures(fm_test_real) distance=EuclidianDistance(feats_train, feats_train) k=3 labels=Labels(label_train_multiclass) knn=KNN(k, distance, labels) knn.train() output=knn.classify(feats_test).get_labels()
trainData = trainData.reshape(-1, 10000) f.close() f = open(os.path.dirname(__file__) + '../data/arcene_train.label') trainLabel = np.fromfile(f, dtype=np.int32, sep=' ') f.close() # Load test data. f = open(os.path.dirname(__file__) + '../data/arcene_test.data') testData = np.fromfile(f, dtype=np.float64, sep=' ') testData = testData.reshape(-1, 10000) f.close() f = open(os.path.dirname(__file__) + '../data/arcene_test.label') testLabel = np.fromfile(f, dtype=np.float64, sep=' ') f.close() # Construct a KNN classifier with a neighborhood size of 9. feat = RealFeatures(trainData.T) distance = EuclideanDistance(feat, feat) labels = BinaryLabels(trainLabel.astype(np.float64)) testFeat = RealFeatures(testData.T) knn = KNN(9, distance, labels) knn.train() # Predict the classification. output = knn.apply(testFeat).get_labels() # Validate the classification. print output == testLabel
