python kmeans

Question

我在用sklearn.cluster.Kmeans 练习。
比如现在有6个数据 1,2 3,4 5,6 7,8 0,4 4,0的数据

想请问下 python Kmeans 能设置指定哪几个值是特定的clusters吗？
（比如 前 1，2，3为 cluster 1， 后 4，5，6 为 cluster 2）
还有如何怎么设置让程序展示每一步的iteration？

Answer 1

基于轮廓系数来选择n_clusters

from sklearn.cluster import KMeans
from sklearn.metrics import silhouette_samples, silhouette_score
import matplotlib.pyplot as plt
import matplotlib.cm as cm
import numpy as np
for n_clusters in [2,3,4,5,6,7]:
    n_clusters = n_clusters
    fig, (ax1, ax2) = plt.subplots(1, 2)
    fig.set_size_inches(18, 7)
    ax1.set_xlim([-0.1, 1])
    ax1.set_ylim([0, X.shape[0] + (n_clusters + 1) * 10])
    clusterer = KMeans(n_clusters=n_clusters, random_state=10).fit(X)
    cluster_labels = clusterer.labels_
    silhouette_avg = silhouette_score(X, cluster_labels)
    print("For n_clusters =", n_clusters,
          "The average silhouette_score is :", silhouette_avg)
    sample_silhouette_values = silhouette_samples(X, cluster_labels)
    y_lower = 10
    for i in range(n_clusters):
        ith_cluster_silhouette_values = sample_silhouette_values[cluster_labels == i]
        ith_cluster_silhouette_values.sort()
        size_cluster_i = ith_cluster_silhouette_values.shape[0]
        y_upper = y_lower + size_cluster_i
        color = cm.nipy_spectral(float(i)/n_clusters)
        ax1.fill_betweenx(np.arange(y_lower, y_upper)
                         ,ith_cluster_silhouette_values
                         ,facecolor=color
                         ,alpha=0.7
                         )
        ax1.text(-0.05
                 , y_lower + 0.5 * size_cluster_i
                 , str(i))
        y_lower = y_upper + 10
    ax1.set_title("The silhouette plot for the various clusters.")
    ax1.set_xlabel("The silhouette coefficient values")
    ax1.set_ylabel("Cluster label")
    ax1.axvline(x=silhouette_avg, color="red", linestyle="--")
    ax1.set_yticks([])
    ax1.set_xticks([-0.1, 0, 0.2, 0.4, 0.6, 0.8, 1])
    colors = cm.nipy_spectral(cluster_labels.astype(float) / n_clusters)
    ax2.scatter(X[:, 0], X[:, 1]
               ,marker='o'
               ,s=8
               ,c=colors
               )
    centers = clusterer.cluster_centers_
    # Draw white circles at cluster centers
    ax2.scatter(centers[:, 0], centers[:, 1], marker='x',
                c="red", alpha=1, s=200)
    
    ax2.set_title("The visualization of the clustered data.")
    ax2.set_xlabel("Feature space for the 1st feature")
    ax2.set_ylabel("Feature space for the 2nd feature")
    plt.suptitle(("Silhouette analysis for KMeans clustering on sample data "
                  "with n_clusters = %d" % n_clusters),
                 fontsize=14, fontweight='bold')
    plt.show()