def fit(self, dataValues, dataLabels=None):
arrAcc = []
classes = list(set(dataLabels))
initialDataLength = 0
finalDataLength = self.initialLabeledData
# ***** Box 1 *****
#Initial labeled data
X, y = util.loadLabeledData(dataValues, dataLabels, initialDataLength,
finalDataLength, self.usePCA)
for t in range(self.batches):
#print("passo: ",t)
initialDataLength = finalDataLength
finalDataLength = finalDataLength + self.sizeOfBatch
# ***** Box 2 *****
Ut, yt = util.loadLabeledData(dataValues, dataLabels,
initialDataLength, finalDataLength,
self.usePCA)
# ***** Box 3 *****
clf = classifiers.labelPropagation(X, y, self.K)
#classifiers.classifier(X, y, self.K, self.clfName)
predicted = clf.predict(Ut)
# Evaluating classification
arrAcc.append(metrics.evaluate(yt, predicted))
# ***** Box 4 *****
#pdfs from each new points from each class applied on new arrived points
indexesByClass = util.slicingClusteredData(y, classes)
bestModelSelectedByClass = util.loadBestModelByClass(
X, indexesByClass)
# ***** Box 5 *****
predictedByClass = util.slicingClusteredData(predicted, classes)
#p% smallest distances per class, based on paper
selectedIndexes = util.mahalanobisCoreSupportExtraction(
Ut, predictedByClass, bestModelSelectedByClass, self.p)
#selectedIndexes = np.hstack([selectedIndexes[0],selectedIndexes[1]])
stackedIndexes = selectedIndexes[0]
for i in range(1, len(selectedIndexes)):
stackedIndexes = np.hstack(
[stackedIndexes, selectedIndexes[i]])
selectedIndexes = stackedIndexes
# ***** Box 6 *****
X, y = util.selectedSlicedData(Ut, predicted, selectedIndexes)
# returns accuracy array and last selected points
self.threshold_ = arrAcc
return self
def cuttingPercentageByClass(Xt_1, Xt, yt_1, yt, classes, t=None):
x = np.sqrt(2)
reset = False
hellinger_distance_by_class = {}
similarityByClass = {}
indexes_Xt_1_ByClass = util.slicingClusteredData(yt_1, classes)
indexes_Xt_ByClass = util.slicingClusteredData(yt, classes)
for c in classes:
res = []
for i in range(Xt_1.shape[1]):
P = Xt_1[indexes_Xt_1_ByClass[c], i]
Q = Xt[indexes_Xt_ByClass[c], i]
bins = int(np.sqrt(len(indexes_Xt_1_ByClass[c])))
hP = np.histogram(P + (-np.min(P)), bins=bins)
hQ = np.histogram(Q + (-np.min(Q)), bins=bins)
res.append(hellinger(hP[1], hQ[1]))
res = np.mean(res)
similarity = 1 - (
((100 * res) / x) / 100) #(100 - ((100 * res)/x))/100
#print(t,res, similarity)
if similarity < 0:
reset = True
elif similarity > 0:
reset = False
similarity = 0.5 + ((res / x) / 10)
if similarity > 0.9:
similarity = 0.9
similarityByClass.update({c: similarity})
#print(t,c,similarity)
return similarityByClass, reset #percentage of similarity
def countInstances(datasetID, dataLabels):
classes = list(set(dataLabels))
inst = util.slicingClusteredData(dataLabels, classes)
for i in range(len(inst)):
print("{}: class {} -> {} instances.".format(datasetID, i,
len(inst[i])))
def start(**kwargs):
dataValues = kwargs["dataValues"]
dataLabels = kwargs["dataLabels"]
initialLabeledData = kwargs["initialLabeledData"]
sizeOfBatch = kwargs["sizeOfBatch"]
classes = kwargs["classes"]
batches = kwargs["batches"]
sizeOfBatch = kwargs["sizeOfBatch"]
p = kwargs["excludingPercentage"]
K = kwargs["K_variation"]
clfName = kwargs["clfName"]
densityFunction='gmmBIC'
distanceMetric = 'mahalanobis'
print("METHOD: {} as classifier and GMM with BIC and Mahalanobis as core support extraction".format(clfName))
usePCA=False
arrAcc = []
arrX = []
arrY = []
arrUt = []
arrYt = []
arrClf = []
arrPredicted = []
initialDataLength = 0
finalDataLength = initialLabeledData #round((initialLabeledDataPerc)*sizeOfBatch)
# ***** Box 1 *****
#Initial labeled data
X, y = util.loadLabeledData(dataValues, dataLabels, initialDataLength, finalDataLength, usePCA)
#predicted = classifiers.classify(X, y, Ut, K, classes, clfName)
clf = classifiers.labelPropagation(X, y, K)
#Starting the process
for t in range(batches):
#print("Step: ", t)
initialDataLength=finalDataLength
finalDataLength=finalDataLength+sizeOfBatch
# ***** Box 2 *****
Ut, yt = util.loadLabeledData(dataValues, dataLabels, initialDataLength, finalDataLength, usePCA)
# for decision boundaries plot
arrClf.append(clf)
arrX.append(X)
arrY.append(y)
arrUt.append(np.array(Ut))
arrYt.append(yt)
#predict test data
predicted = clf.predict(Ut)
arrPredicted.append(predicted)
# Evaluating classification
arrAcc.append(metrics.evaluate(yt, predicted))
# ***** Box 4 *****
indexesByClass = util.slicingClusteredData(y, classes)
bestModelSelectedByClass = util.loadBestModelByClass(X, indexesByClass)
# ***** Box 5 *****
predictedByClass = util.slicingClusteredData(predicted, classes)
selectedIndexes = util.mahalanobisCoreSupportExtraction(Ut, predictedByClass, bestModelSelectedByClass, p)
#selectedIndexes = np.hstack([selectedIndexes[0],selectedIndexes[1]])
stackedIndexes=selectedIndexes[0]
for i in range(1, len(selectedIndexes)):
stackedIndexes = np.hstack([stackedIndexes,selectedIndexes[i]])
selectedIndexes = stackedIndexes
X, y = util.selectedSlicedData(Ut, yt, selectedIndexes)
#training data
clf = classifiers.labelPropagation(X, y, K)
return "COMPOSE GMM", arrAcc, X, y, arrX, arrY, arrUt, arrYt, arrClf, arrPredicted