In this problem, we have sketched up the code for the K-Mean…
In this problem, we have sketched up the code for the K-Means Clustering algorithm. Please choose options to fill in the blanks. import numpy as np import matplotlib.pyplot as plt def kmeans(X,K,iteration): N = len(X) # Number of data points labels = np.zeros((N,1)) # Cluster labels for each data point centroids = np.zeros((K,X.shape[1])) # Centroid of each cluster # Innitialize: Randomly assign a number C(i) in (1,…,K) to each index i = 1…N for i in range(len(labels)): labels[i] = np.random.randint(0,K) for iteration in range(iteration): # Compute the centroid of cluster K for k in range(K): dp = X[np.where(labels == k)[0]] centroids[k] = _________(1)___________ # Assign observation n to the cluster with closest centroid for n in range(N): distance = np.linalg.norm(X[n]-centroids,axis=1) labels[n] = _________(2)___________ # Compute the distance between each data point and their centroids within_cluster_distance = 0 for m in range(N): within_cluster_distance += _________(3)___________ return within_cluster_distance k_list = [] for i in range(1,10): k_list.append(kmeans(X1,i,10)) x = np.arange(1,10) plt.plot(x,k_list) plt.xlabel(‘K’) plt.ylabel(‘Within Cluster Distance’) plt.show() The format of input $$X$$ is shown below: What should go in the second blank(2)?
Read Details