def fit(self, X, y):
t = time() # get labels for test data
# build the graph result is the affinity matrix
if self.kernel is 'dbscan' or self.kernel is None:
affinity_matrix = self.dbscan(X, self.eps, self.minPts)
# it is possible to use other kernels -> as parameter
elif self.kernel is 'rbf':
affinity_matrix = rbf_kernel(X, X, gamma=self.gamma)
elif self.kernel is 'knn':
affinity_matrix = NearestNeighbors(self.naighbors).fit(X).kneighbors_graph(X, self.naighbors).toarray()
else:
raise
print( "praph(%s) time %2.3fms"%(self.kernel, (time() - t) *1000))
if affinity_matrix.max() == 0 :
print("no affinity matrix found")
return y
degree_martix = np.diag(affinity_matrix.sum(axis=0))
affinity_matrix = np.matrix(affinity_matrix)
try:
inserve_degree_matrix = np.linalg.inv(degree_martix)
except np.linalg.linalg.LinAlgError as err:
if 'Singular matrix' in err.args:
# use a pseudo inverse if it's not possible to make a normal of the degree matrix
inserve_degree_matrix = np.linalg.pinv(degree_martix)
else:
raise
matrix = inserve_degree_matrix * affinity_matrix
# split labels in different vectors to calculate the propagation for the separate label
labels = np.unique(y)
labels = [x for x in labels if x != self.unlabeledValue]
# init the yn1 and y0
y0 = [[1 if (x == l) else 0 for x in y] for l in labels]
yn1 = y0
# function to set the probability to 1 if it was labeled in the source
toOrgLabels = np.vectorize(lambda x, y : 1 if y == 1 else x , otypes=[np.int0])
# function to set the index's of the source labeled
toOrgLabelsIndex = np.vectorize(lambda x, y, z : z if y == 1 else x , otypes=[np.int0])
lastLabels = np.argmax(y0, axis=0)
while True:
yn1 = yn1 * matrix
#first matrix to labels
ynLablesIndex = np.argmax(yn1, axis=0)
# row-normalize
yn1 /= yn1.max()
yn1 = toOrgLabels(yn1, y0)
for x in y0:
ynLablesIndex = toOrgLabelsIndex(ynLablesIndex, x, y0.index(x))
#second original labels to result
if np.array_equiv(ynLablesIndex, lastLabels):
break
lastLabels = ynLablesIndex
# result is the index of the labels -> cast index to the given labels
toLabeles = np.vectorize(lambda x : labels[x])
return np.array(toLabeles(lastLabels))[0]
