def main():
# Load the dataset
X, y = datasets.make_moons(n_samples=300, noise=0.08, shuffle=False)
print(X.shape)
# Cluster the data using Agnes
agnes_cluster = AGNES(10)
centroids, labels = agnes_cluster.fit(X)
p = Plot()
p.plot_in_2d(X, labels, "Preds")
p.plot_in_2d(X, y, "Actual")
def main():
# Load the dataset
X, y = datasets.make_blobs()
# Cluster the data
clf = GaussianMixtureModel(k=3)
y_pred = clf.predict(X)
p = Plot()
p.plot_in_2d(X, y_pred, title="GMM Clustering")
p.plot_in_2d(X, y, title="Actual Clustering")
def main():
# Load the dataset
X , y = datasets.make_moons(n_samples=300, noise=0.08, shuffle=False)
# Cluster the data using DBSCAN
kmedoid_cluster = KMediod(X , 2 , 1)
medoids , labels = kmedoid_cluster.fit(10, max_steps=1000)
print(medoids , labels)
p = Plot()
p.plot_in_2d(X , labels , "Preds")
p.plot_in_2d(X , y , "Actual")
def main():
# Load the dataset
X, y = datasets.make_moons(n_samples=300, noise=0.1, shuffle=False)
# Cluster the data using DBSCAN
clf = DBSCAN(eps=0.17, min_samples=5)
y_pred = clf.predict(X)
# Project the data onto the 2 primary principal components
p = Plot()
p.plot_in_2d(X, y_pred, title="DBSCAN")
p.plot_in_2d(X, y, title="Actual Clustering")
def main():
# Load the dataset
X, y = datasets.make_moons(n_samples=300, noise=0.08, shuffle=False)
# Cluster the data using DBSCAN
clf = DBSCAN(eps=0.17, min_samples=5)
y_pred = clf.predict(X)
# Project the data onto the 2 primary principal components
p = Plot()
p.plot_in_2d(X, y_pred, title="DBSCAN")
p.plot_in_2d(X, y, title="Actual Clustering")
def main():
# Load the dataset
X, y = datasets.make_blobs()
# Cluster the data using K-Medoids
clf = PAM(k=3)
y_pred = clf.predict(X)
# Project the data onto the 2 primary principal components
p = Plot()
p.plot_in_2d(X, y_pred, title="PAM Clustering")
p.plot_in_2d(X, y, title="Actual Clustering")
def main():
# Load the dataset
X, y = datasets.make_blobs()
# Cluster the data using K-Means
clf = KMeans(k=3)
y_pred = clf.predict(X)
# Project the data onto the 2 primary principal components
p = Plot()
p.plot_in_2d(X, y_pred, title="K-Means Clustering")
p.plot_in_2d(X, y, title="Actual Clustering")
self.responsibilities[-2])
return diff <= self.tolerance
def predict(self, X):
""" Run GMM and return the cluster indices """
# Initialize the gaussians randomly
self._init_random_gaussians(X)
# Run EM until convergence or for max iterations
for _ in range(self.max_iterations):
self._expectation(X)
self._maximization(X)
# Check convergence
if self._converged():
break
# Make new assignments and return them
self._expectation(X)
# Assign samples to cluster that has largest probability
sample_assignments = self.responsibility.argmax(axis=1)
return sample_assignments
if __name__ == '__main__':
# Load the dataset
X, y = datasets.make_blobs()
# Cluster the data
clf = GaussianMixtureModel(k=3)
y_pred = clf.predict(X)
p = Plot()
p.plot_in_2d(X, y_pred, title="GMM Clustering")
p.plot_in_2d(X, y, title="Actual Clustering")