def _fit(self, num_iters=10):
scores = []
start = time.time()
for i in range(num_iters):
print('Starting sklearn KMeans: %d' % i)
sklearn_kmeans = SklearnKMeans(n_clusters=self.num_clusters,
init='k-means++',
max_iter=50, n_init=1, tol=1e-4,
random_state=i * 42)
sklearn_kmeans.fit(self.points)
scores.append(sklearn_kmeans.inertia_)
self._report(num_iters, start, time.time(), scores)
def fit(self, X, K, sample_labels=None, estimator_params=None):
self._reset()
# Note: previously set n_init=50
self.model_ = SklearnKMeans(K)
if estimator_params is not None:
assert isinstance(estimator_params, dict)
self.model_.set_params(**estimator_params)
# Compute Kmeans model
self.model_.fit(X)
if sample_labels is None:
#print("INSIDE")
sample_labels = ["sample_{}".format(i) for i in range(X.shape[0])]
print("sample labels:",len(sample_labels)," ",X.shape)
assert len(sample_labels) == X.shape[0]
self.sample_labels_ = np.array(sample_labels)
self.n_clusters_ = K
# Record sample label/distance from its cluster center
self.sample_distances_ = OrderedDict()
for cluster_label in range(self.n_clusters_):
assert cluster_label not in self.sample_distances_
member_rows = X[self.cluster_labels_ == cluster_label, :]
member_labels = self.sample_labels_[self.cluster_labels_ == cluster_label]
centroid = np.expand_dims(self.cluster_centers_[cluster_label], axis=0)
# "All clusters must have at least 1 member!"
if member_rows.shape[0] == 0:
return None
# Calculate distance between each member row and the current cluster
dists = np.empty(member_rows.shape[0])
dist_labels = []
for j, (row, label) in enumerate(zip(member_rows, member_labels)):
dists[j] = cdist(np.expand_dims(row, axis=0), centroid, "euclidean").squeeze()
dist_labels.append(label)
# Sort the distances/labels in ascending order
sort_order = np.argsort(dists)
dists = dists[sort_order]
dist_labels = np.array(dist_labels)[sort_order]
self.sample_distances_[cluster_label] = {
"sample_labels": dist_labels,
"distances": dists,
}
return self
def fit(self, X, K, sample_labels=None, estimator_params=None):
"""Fits a Sklearn KMeans model to X.
Parameters
----------
X : array-like, shape (n_samples, n_features)
Training data.
K : int
The number of clusters.
sample_labels : array-like, shape (n_samples), optional
Labels for each of the samples in X.
estimator_params : dict, optional
The parameters to pass to the KMeans estimators.
Returns
-------
self
"""
self._reset()
# Note: previously set n_init=50
self.model_ = SklearnKMeans(K)
if estimator_params is not None:
assert isinstance(estimator_params, dict)
self.model_.set_params(**estimator_params)
# Compute Kmeans model
self.model_.fit(X)
if sample_labels is None:
sample_labels = ["sample_{}".format(i) for i in range(X.shape[0])]
assert len(sample_labels) == X.shape[0]
self.sample_labels_ = np.array(sample_labels)
self.n_clusters_ = K
# Record sample label/distance from its cluster center
self.sample_distances_ = OrderedDict()
for cluster_label in range(self.n_clusters_):
assert cluster_label not in self.sample_distances_
member_rows = X[self.cluster_labels_ == cluster_label, :]
member_labels = self.sample_labels_[self.cluster_labels_ ==
cluster_label]
centroid = np.expand_dims(self.cluster_centers_[cluster_label],
axis=0)
# "All clusters must have at least 1 member!"
if member_rows.shape[0] == 0:
return None
# Calculate distance between each member row and the current cluster
dists = np.empty(member_rows.shape[0])
dist_labels = []
for j, (row, label) in enumerate(zip(member_rows, member_labels)):
dists[j] = cdist(np.expand_dims(row, axis=0), centroid,
"euclidean").squeeze()
dist_labels.append(label)
# Sort the distances/labels in ascending order
sort_order = np.argsort(dists)
dists = dists[sort_order]
dist_labels = np.array(dist_labels)[sort_order]
self.sample_distances_[cluster_label] = {
"sample_labels": dist_labels,
"distances": dists,
}
return self
