Day56_ANS
2019/06/26 04:33 PM
機器學習新手論壇
Richard
觀看數：0
回答數：2
收藏數：0
ml100-2
ml100-2-d56
底下這句話是否有筆誤?還是我理解錯誤?
由結果可以看出 2比3的分數高很多, 5以後的數字也都有所增加, 照輪廓分析來說, 2 與 5 都會是不錯的選擇
以這個範例我們可以知道, 輪廓分析可以提供我們比較洽當的分群選項
這是跑出來的結果:
For n_clusters = 2 The average silhouette_score is : 0.5027144446956527
For n_clusters = 3 The average silhouette_score is : 0.6105565451092732
For n_clusters = 4 The average silhouette_score is : 0.6270122040179333
For n_clusters = 5 The average silhouette_score is : 0.6115749260799671
For n_clusters = 6 The average silhouette_score is : 0.5499388428924794
For n_clusters = 7 The average silhouette_score is : 0.4695416652197068
For n_clusters = 8 The average silhouette_score is : 0.4231800504179843