from KMeans_Jaccard_Dist import kMeans code example

Example 1: scikit learn k means

from sklearn.cluster import KMeans
df = np.array([[1,4],[2,2],[2,5],[3,3],[3,4],[4,7],[5,6],[6,4],[6,7],[7,6],[7,9],[8,7],[8,9],[9,4],[9,8]])
kmeans = KMeans(n_clusters=3, init='k-means++', max_iter=300, n_init=10)
y_pred = kmeans.fit_predict(df)

Example 2: k-means clustering python

from sklearn.cluster import KMeans
kmeans = KMeans(init="random", n_clusters=3, n_init=10, max_iter=300, random_state=42 )
kmeans.fit(x_train) #Replace your training dataset instead of x_train
# The lowest SSE value
print(kmeans.inertia_)
# Final locations of the centroid
print(kmeans.cluster_centers_)
# The number of iterations required to converge
print(kmeans.n_iter_)
# first five predicted labels 
print(kmeans.labels_[:5])


# init controls the initialization technique. The standard version of the k-means algorithm is implemented by setting init to "random". Setting this to "k-means++" employs an advanced trick to speed up convergence, which you’ll use later.

# n_clusters sets k for the clustering step. This is the most important parameter for k-means.

# n_init sets the number of initializations to perform. This is important because two runs can converge on different cluster assignments. The default behavior for the scikit-learn algorithm is to perform ten k-means runs and return the results of the one with the lowest SSE.

# max_iter sets the number of maximum iterations for each initialization of the k-means algorithm.