Create app.py

app.py

@@ -46,26 +46,29 @@ if uploaded_file is not None:
     # 使用保存的 DBSCAN 模型進行聚類
     dbscan_labels = dbscan.fit_predict(pca_df)
     
-    # 繪製 K-means 聚類結果
-    fig, ax = plt.subplots(1, 3, figsize=(15, 5))
+    # ================== K-means 聚類圖表 ==================
+    st.subheader("K-means 聚類結果")
+    fig_kmeans, ax_kmeans = plt.subplots()
+    ax_kmeans.scatter(pca_df['PC1'], pca_df['PC2'], c=kmeans_labels, cmap='viridis')
+    ax_kmeans.set_title('K-means Clustering')
+    ax_kmeans.set_xlabel('PC1')
+    ax_kmeans.set_ylabel('PC2')
+    st.pyplot(fig_kmeans)
     
-    # K-means 繪圖
-    ax[0].scatter(pca_df['PC1'], pca_df['PC2'], c=kmeans_labels, cmap='viridis')
-    ax[0].set_title('K-means Clustering')
-    ax[0].set_xlabel('PC1')
-    ax[0].set_ylabel('PC2')
+    # ================== 階層式聚類圖表 ==================
+    st.subheader("階層式聚類結果")
+    fig_hclust, ax_hclust = plt.subplots()
+    ax_hclust.scatter(pca_df['PC1'], pca_df['PC2'], c=hclust_labels, cmap='viridis')
+    ax_hclust.set_title('Hierarchical Clustering')
+    ax_hclust.set_xlabel('PC1')
+    ax_hclust.set_ylabel('PC2')
+    st.pyplot(fig_hclust)
     
-    # 階層式聚類繪圖
-    ax[1].scatter(pca_df['PC1'], pca_df['PC2'], c=hclust_labels, cmap='viridis')
-    ax[1].set_title('Hierarchical Clustering')
-    ax[1].set_xlabel('PC1')
-    ax[1].set_ylabel('PC2')
-    
-    # DBSCAN 繪圖
-    ax[2].scatter(pca_df['PC1'], pca_df['PC2'], c=dbscan_labels, cmap='viridis')
-    ax[2].set_title('DBSCAN Clustering')
-    ax[2].set_xlabel('PC1')
-    ax[2].set_ylabel('PC2')
-    
-    # 顯示圖表
-    st.pyplot(fig)
+    # ================== DBSCAN 聚類圖表 ==================
+    st.subheader("DBSCAN 聚類結果")
+    fig_dbscan, ax_dbscan = plt.subplots()
+    ax_dbscan.scatter(pca_df['PC1'], pca_df['PC2'], c=dbscan_labels, cmap='viridis')
+    ax_dbscan.set_title('DBSCAN Clustering')
+    ax_dbscan.set_xlabel('PC1')
+    ax_dbscan.set_ylabel('PC2')
+    st.pyplot(fig_dbscan)