7-9. DBSCAN 2

DBSCAN 적용하기 – make_circles() 데이터 세트

### 클러스터 결과를 담은 DataFrame과 사이킷런의 Cluster 객체등을 인자로 받아 클러스터링 결과를 시각화하는 함수  
def visualize_cluster_plot(clusterobj, dataframe, label_name, iscenter=True):
    if iscenter :
        centers = clusterobj.cluster_centers_
        
    unique_labels = np.unique(dataframe[label_name].values)
    markers=['o', 's', '^', 'x', '*']
    isNoise=False

    for label in unique_labels:
        label_cluster = dataframe[dataframe[label_name]==label]
        if label == -1:
            cluster_legend = 'Noise'
            isNoise=True
        else :
            cluster_legend = 'Cluster '+str(label)
        
        plt.scatter(x=label_cluster['ftr1'], y=label_cluster['ftr2'], s=70,\
                    edgecolor='k', marker=markers[label], label=cluster_legend)
        
        if iscenter:
            center_x_y = centers[label]
            plt.scatter(x=center_x_y[0], y=center_x_y[1], s=250, color='white',
                        alpha=0.9, edgecolor='k', marker=markers[label])
            plt.scatter(x=center_x_y[0], y=center_x_y[1], s=70, color='k',\
                        edgecolor='k', marker='$%d$' % label)
    if isNoise:
        legend_loc='upper center'
    else: legend_loc='upper right'
    
    plt.legend(loc=legend_loc)
    plt.show()

 

from sklearn.datasets import make_circles

X, y = make_circles(n_samples=1000, shuffle=True, noise=0.05, random_state=0, factor=0.5)
clusterDF = pd.DataFrame(data=X, columns=['ftr1', 'ftr2'])
clusterDF['target'] = y

visualize_cluster_plot(None, clusterDF, 'target', iscenter=False)

 

# KMeans로 make_circles( ) 데이터 셋을 클러스터링 수행. 
from sklearn.cluster import KMeans

kmeans = KMeans(n_clusters=2, max_iter=1000, random_state=0)
kmeans_labels = kmeans.fit_predict(X)
clusterDF['kmeans_cluster'] = kmeans_labels

visualize_cluster_plot(kmeans, clusterDF, 'kmeans_cluster', iscenter=True)

 

# GMM으로 make_circles( ) 데이터 셋을 클러스터링 수행. 
from sklearn.mixture import GaussianMixture

gmm = GaussianMixture(n_components=2, random_state=0)
gmm_label = gmm.fit(X).predict(X)
clusterDF['gmm_cluster'] = gmm_label

visualize_cluster_plot(gmm, clusterDF, 'gmm_cluster', iscenter=False)

 

# DBSCAN으로 make_circles( ) 데이터 셋을 클러스터링 수행. 
from sklearn.cluster import DBSCAN

dbscan = DBSCAN(eps=0.2, min_samples=10, metric='euclidean')
dbscan_labels = dbscan.fit_predict(X)
clusterDF['dbscan_cluster'] = dbscan_labels

visualize_cluster_plot(dbscan, clusterDF, 'dbscan_cluster', iscenter=False)