K Means Clustering in Python

k-means-clustering.py

from numpy import unique
from numpy import where
from matplotlib import pyplot
from sklearn.datasets import make_classification
from sklearn.cluster import KMeans

if __name__ == '__main__':
    # initialize the data set we'll work with
    training_data, _ = make_classification(
        n_samples=2000,
        n_features=3,
        n_informative=2,
        n_redundant=0,
        n_clusters_per_class=1,
        random_state=10
    )

    # define the model
    kmeans_model = KMeans(n_clusters=2)

    # assign each data point to a cluster
    dbscan_result = kmeans_model.fit_predict(training_data)

    # get all of the unique clusters
    dbscan_clusters = unique(dbscan_result)

    # plot the DBSCAN clusters
    for dbscan_cluster in dbscan_clusters:
        # get data points that fall in this cluster
        index = where(dbscan_result == dbscan_cluster)
        # make the plot
        pyplot.scatter(training_data[index, 0], training_data[index, 1])

    # show the DBSCAN plot
    pyplot.show()

plot.md