def _test_k_means(self, seed):
# Assert k-means clustering accuracy.
A = []
n = 100
m = dict((d.vector.id, d.type) for d in self.model[:n])
for i in range(30):
# Create two clusters of vectors.
k = vector.kmeans([d.vector for d in self.model[:n]], k=2, seed=seed)
# Measure the number of spam in each clusters.
# Ideally, we have a cluster without spam and one with only spam.
i = len([1 for v in k[0] if m[v.id] == False])
j = len([1 for v in k[1] if m[v.id] == False])
A.append(max(i,j) * 2.0 / n)
# Return average accuracy after 10 tests.
return sum(A) / 30.0
def _test_k_means(self, seed):
# Assert k-means clustering accuracy.
A = []
n = 100
m = dict((d.vector.id, d.type) for d in self.model[:n])
for i in range(30):
# Create two clusters of vectors.
k = vector.kmeans([d.vector for d in self.model[:n]], k=2, seed=seed)
# Measure the number of spam in each clusters.
# Ideally, we have a cluster without spam and one with only spam.
i = len([1 for v in k[0] if m[v.id] == False])
j = len([1 for v in k[1] if m[v.id] == False])
A.append(max(i,j) * 2.0 / n)
# Return average accuracy after 10 tests.
return sum(A) / 30.0
