Notebook on nbviewer (original) (raw)

sns.regplot(x='x', y='y', data=k_means_data, order=2, label='Sklearn K-Means', x_estimator=np.mean) sns.regplot(x='x', y='y', data=dbscan_data, order=2, label='Sklearn DBSCAN', x_estimator=np.mean) sns.regplot(x='x', y='y', data=scipy_k_means_data, order=2, label='Scipy K-Means', x_estimator=np.mean) sns.regplot(x='x', y='y', data=hdbscan_data, order=2, label='HDBSCAN', x_estimator=np.mean) sns.regplot(x='x', y='y', data=fastclust_data, order=2, label='Fastcluster Single Linkage', x_estimator=np.mean) sns.regplot(x='x', y='y', data=scipy_single_data, order=2, label='Scipy Single Linkage', x_estimator=np.mean) sns.regplot(x='x', y='y', data=debacl_data, order=2, label='DeBaCl Geom Tree', x_estimator=np.mean) sns.regplot(x='x', y='y', data=spectral_data, order=2, label='Sklearn Spectral', x_estimator=np.mean) sns.regplot(x='x', y='y', data=agg_data, order=2, label='Sklearn Agglomerative', x_estimator=np.mean) sns.regplot(x='x', y='y', data=ap_data, order=2, label='Sklearn Affinity Propagation', x_estimator=np.mean) plt.gca().axis([0, 34000, 0, 120]) plt.gca().set_xlabel('Number of data points') plt.gca().set_ylabel('Time taken to cluster (s)') plt.title('Performance Comparison of Clustering Implementations') plt.legend()