kmeans.py

from sklearn.cluster import KMeans
# set number of clusters
kclusters = 5
sf_grouped_clustering = sf_grouped.drop('Neighborhood', 1)
# run k-means clustering
kmeans = KMeans(n_clusters = kclusters, random_state = 0).fit(sf_grouped_clustering)
# check cluster labels generated for each row in the dataframe
kmeans.labels_[0:10]