教師なし学習のためのアンサンブル手法: 類似行列のクラスタリング

 import numpy as np from scipy import sparse  def build_binary_matrix( clabels ): data_len = len(clabels) matrix=np.zeros((data_len,data_len))for i in range(data_len):matrix[i,:] = clabels == clabels[i]return matrix  labels = np.array( [1,1,1,2,3,3,2,4] ) build_binary_matrix(labels)

 from sklearn.datasets import fetch_openml from sklearn.decomposition import PCA from sklearn.cluster import MiniBatchKMeans, KMeans from sklearn.model_selection import train_test_split  mnist = fetch_openml('mnist_784') X = mnist.data y = mnist.target  X, _, y, _ = train_test_split(X,y, train_size=10000, stratify=y, random_state=42 )  pca = PCA(n_components=0.99) X_pca = pca.fit_transform(X)

 NUM_MODELS = 500 MIN_N_CLUSTERS = 2 MAX_N_CLUSTERS = 300  np.random.seed(214) model_sizes = np.random.randint(MIN_N_CLUSTERS, MAX_N_CLUSTERS+1, size=NUM_MODELS) clt_models = [KMeans(n_clusters=i, n_init=4, random_state=214) for i in model_sizes]  for i, model in enumerate(clt_models):print( f"Fitting - {i+1}/{NUM_MODELS}" )model.fit(X_pca)

def build_similarity_matrix( models_labels ):n_runs, n_data = models_labels.shape[0], models_labels.shape[1] sim_matrix = np.zeros( (n_data, n_data) ) for i in range(n_runs):sim_matrix += build_binary_matrix( models_labels[i,:] ) sim_matrix = sim_matrix/n_runs return sim_matrix

 models_labels = np.array([ model.labels_ for model in clt_models ]) sim_matrix = build_similarity_matrix(models_labels)

Pos_sim_matrix = sim_matrix

 from sklearn.cluster import SpectralClustering spec_clt = SpectralClustering(n_clusters=10, affinity='precomputed',n_init=5, random_state=214) final_labels = spec_clt.fit_predict(pos_sim_matrix)

from seaborn import heatmap import matplotlib.pyplot as plt  def data_contingency_matrix(true_labels, pred_labels): fig, (ax) = plt.subplots(1, 1, figsize=(8,8)) n_clusters = len(np.unique(pred_labels))n_classes = len(np.unique(true_labels))label_names = np.unique(true_labels)label_names.sort() contingency_matrix = np.zeros( (n_classes, n_clusters) ) for i, true_label in enumerate(label_names):for j in range(n_clusters):contingency_matrix[i, j] = np.sum(np.logical_and(pred_labels==j, true_labels==true_label)) heatmap(contingency_matrix.astype(int), ax=ax,annot=True, annot_kws={"fontsize":14}, fmt='d') ax.set_xlabel("Clusters", fontsize=18)ax.set_xticks( [i+0.5 for i in range(n_clusters)] )ax.set_xticklabels([i for i in range(n_clusters)], fontsize=14) ax.set_ylabel("Original classes", fontsize=18)ax.set_yticks( [i+0.5 for i in range(n_classes)] )ax.set_yticklabels(label_names, fontsize=14, va="center") ax.set_title("Contingency Matrix\n", ha='center', fontsize=20)

from sklearn.metrics import normalized_mutual_info_score, adjusted_rand_score  def purity( true_labels, pred_labels ): n_clusters = len(np.unique(pred_labels))n_classes = len(np.unique(true_labels))label_names = np.unique(true_labels) purity_vector = np.zeros( (n_classes) )contingency_matrix = np.zeros( (n_classes, n_clusters) ) for i, true_label in enumerate(label_names):for j in range(n_clusters):contingency_matrix[i, j] = np.sum(np.logical_and(pred_labels==j, true_labels==true_label)) purity_vector = np.max(contingency_matrix, axis=1)/np.sum(contingency_matrix, axis=1) print( f"Mean Class Purity - {np.mean(purity_vector):.2f}" ) for i, true_label in enumerate(label_names):print( f" {true_label} - {purity_vector[i]:.2f}" )   cluster_purity_vector = np.zeros( (n_clusters) )cluster_purity_vector = np.max(contingency_matrix, axis=0)/np.sum(contingency_matrix, axis=0) print( f"Mean Cluster Purity - {np.mean(cluster_purity_vector):.2f}" ) for i in range(n_clusters):print( f" {i} - {cluster_purity_vector[i]:.2f}" )   kmeans_model = KMeans(10, n_init=50, random_state=214) km_labels = kmeans_model.fit_predict(X_pca)  data_contingency_matrix(y, km_labels)  print( "Single KMeans NMI - ", normalized_mutual_info_score(y, km_labels) ) print( "Single KMeans ARI - ", adjusted_rand_score(y, km_labels) ) purity(y, km_labels)

 data_contingency_matrix(y, final_labels)  print( "Ensamble NMI - ", normalized_mutual_info_score(y, final_labels) ) print( "Ensamble ARI - ", adjusted_rand_score(y, final_labels) ) purity(y, final_labels)