def test_hierarchical(self):
# Assert cluster contains nested clusters and/or vectors.
def _test_cluster(cluster):
for nested in cluster:
if isinstance(nested, vector.Cluster):
v1 = set((v.id for v in nested.flatten()))
v2 = set((v.id for v in cluster.flatten()))
self.assertTrue(nested.depth < cluster.depth)
self.assertTrue(v1.issubset(v2))
else:
self.assertTrue(isinstance(nested, vector.Vector))
self.assertTrue(isinstance(cluster, list))
self.assertTrue(isinstance(cluster.depth, int))
self.assertTrue(isinstance(cluster.flatten(), list))
n = 50
m = dict((d.vector.id, d.type) for d in self.model[:n])
h = vector.hierarchical([d.vector for d in self.model[:n]], k=2)
h.traverse(_test_cluster)
# Assert the accuracy of hierarchical clustering (shallow test).
# Assert that cats are separated from dogs.
v = (
vector.Vector({"feline": 1, " lion": 1, "mane": 1}),
vector.Vector({"feline": 1, "tiger": 1, "stripe": 1}),
vector.Vector({"canine": 1, "wolf": 1, "howl": 1}),
vector.Vector({"canine": 1, "dog": 1, "bark": 1})
)
h = vector.hierarchical(v)
self.assertTrue(len(h[0][0]) == 2)
self.assertTrue(len(h[0][1]) == 2)
self.assertTrue(
v[0] in h[0][0] and v[1] in h[0][0] or v[0] in h[0][1] and v[1] in h[0][1])
self.assertTrue(
v[2] in h[0][0] and v[3] in h[0][0] or v[2] in h[0][1] and v[3] in h[0][1])
print("pattern.vector.Cluster()")
print("pattern.vector.hierarchical()")
def test_hierarchical(self):
# Assert cluster contains nested clusters and/or vectors.
def _test_cluster(cluster):
for nested in cluster:
if isinstance(nested, vector.Cluster):
v1 = set((v.id for v in nested.flatten()))
v2 = set((v.id for v in cluster.flatten()))
self.assertTrue(nested.depth < cluster.depth)
self.assertTrue(v1.issubset(v2))
else:
self.assertTrue(isinstance(nested, vector.Vector))
self.assertTrue(isinstance(cluster, list))
self.assertTrue(isinstance(cluster.depth, int))
self.assertTrue(isinstance(cluster.flatten(), list))
n = 50
m = dict((d.vector.id, d.type) for d in self.model[:n])
h = vector.hierarchical([d.vector for d in self.model[:n]], k=2)
h.traverse(_test_cluster)
# Assert the accuracy of hierarchical clustering (shallow test).
# Assert that cats are separated from dogs.
v = (
vector.Vector({"feline":1, " lion":1, "mane":1}),
vector.Vector({"feline":1, "tiger":1, "stripe":1}),
vector.Vector({"canine":1, "wolf":1, "howl":1}),
vector.Vector({"canine":1, "dog":1, "bark":1})
)
h = vector.hierarchical(v)
self.assertTrue(len(h[0][0]) == 2)
self.assertTrue(len(h[0][1]) == 2)
self.assertTrue(v[0] in h[0][0] and v[1] in h[0][0] or v[0] in h[0][1] and v[1] in h[0][1])
self.assertTrue(v[2] in h[0][0] and v[3] in h[0][0] or v[2] in h[0][1] and v[3] in h[0][1])
print("pattern.vector.Cluster()")
print("pattern.vector.hierarchical()" )
return len(questions)
def elaboration(questions):
return sum(min(len(parsetree(a)[0].pnp), 2) for a in questions)
def variance(cluster):
return avg([distance(centroid(cluster), v) for v in cluster])
vectors = []
for q in all_q:
v = count(words(q), stemmer='lemma')
v = Vector(v)
vectors.append(v)
clusters = hierarchical(vectors, k=250, distance='cosine')
clusters = [isinstance(v, Vector) and [v] or v.flatten() for v in clusters]
clusters = sorted(clusters, key=variance)
categories = {}
for i, cluster in enumerate(clusters):
for v in cluster:
categories[row[vectors.index(v)]] = i
def flex(questions):
ml_categories = []
for q in questions:
q_uri = classifier_uri + q
j = requests.get(q_uri, auth=(watson_user, watson_pass))
ml_categories.append(j.json()['top_class'])