def _compare_clusters(**datasets):
for name, dataset in datasets.items():
pca = RandomizedPCA(2)
pca.fit(dataset)
X = pca.transform(dataset)
instances = _kmeans()
for instance in instances:
instance.fit(dataset)
# reduce to 2d for visualisation
draw_cluster_2d(instance, X,
filename="%s-kmeans-%s.png" % (name, instance.k))
ms_instances = _meanshift(dataset)
for instance in ms_instances:
instance.fit(dataset)
compare_pies(
[_get_distribution(i) for i in instances] +
[_get_distribution(i) for i in ms_instances],
["KMeans(%s)" % i.k for i in instances] +
["MeanShift(%s)" % round(i.bandwidth) for i in ms_instances],
filename="%s-pie.png" % name)
def compare_pca(self):
"""Compare the clusters generated with different values for the dimensions
of the PCA
"""
processors = (TextProcessor(N=50, algorithms=["kmeans"]),
TextProcessor(N=100, algorithms=["kmeans"]),
TextProcessor(N=200, algorithms=["kmeans"]))
users_cluster = defaultdict(list)
for processor in processors:
# don't use random centers for kmeans to be able to compare them
processor._particular_user = "******"
processor.run()
for user, cluster in processor.clusters['kmeans'].items():
users_cluster[user].append(np.bincount(cluster.labels_))
for user, bincounts in users_cluster.items():
compare_pies(bincounts, "compare_%s.png" % user, self.output_path)
def compare_pca(self):
"""Compare the clusters generated with different values for the dimensions
of the PCA
"""
processors = (
TextProcessor(N=50, algorithms=["kmeans"]),
TextProcessor(N=100, algorithms=["kmeans"]),
TextProcessor(N=200, algorithms=["kmeans"])
)
users_cluster = defaultdict(list)
for processor in processors:
# don't use random centers for kmeans to be able to compare them
processor._particular_user = "******"
processor.run()
for user, cluster in processor.clusters['kmeans'].items():
users_cluster[user].append(np.bincount(cluster.labels_))
for user, bincounts in users_cluster.items():
compare_pies(bincounts, "compare_%s.png" % user, self.output_path)
def _compare_clusters(**datasets):
for name, dataset in datasets.items():
pca = RandomizedPCA(2)
pca.fit(dataset)
X = pca.transform(dataset)
instances = _kmeans()
for instance in instances:
instance.fit(dataset)
# reduce to 2d for visualisation
draw_cluster_2d(instance,
X,
filename="%s-kmeans-%s.png" %
(name, instance.k))
ms_instances = _meanshift(dataset)
for instance in ms_instances:
instance.fit(dataset)
compare_pies(
[_get_distribution(i) for i in instances] +
[_get_distribution(i) for i in ms_instances],
["KMeans(%s)" % i.k for i in instances] +
["MeanShift(%s)" % round(i.bandwidth) for i in ms_instances],
filename="%s-pie.png" % name)
