Create app_V1.py

app_V1.py

@@ -0,0 +1,74 @@
+import streamlit as st
+import pandas as pd
+import matplotlib.pyplot as plt
+import joblib
+from sklearn.decomposition import PCA
+from sklearn.preprocessing import StandardScaler
+from sklearn.cluster import KMeans, DBSCAN
+from scipy.cluster.hierarchy import fcluster, linkage
+
+# 讀取保存的模型
+scaler = joblib.load('scaler.sav')
+pca = joblib.load('pca_model.sav')
+kmeans = joblib.load('kmeans_model.sav')
+linked = joblib.load('hierarchical_model.sav')
+dbscan = joblib.load('dbscan_model.sav')
+
+# 標題和簡介
+st.title("聚類分析 - KMeans, Hierarchical Clustering 和 DBSCAN")
+st.write("上傳 CSV 文件並查看聚類結果")
+
+# 上傳文件
+uploaded_file = st.file_uploader("上傳 CSV 文件", type=["csv"])
+
+if uploaded_file is not None:
+    # 讀取上傳的 CSV 文件
+    data = pd.read_csv(uploaded_file)
+    
+    # 移除 'Time' 欄位
+    numerical_data = data.drop(columns=['Time'])
+    
+    # 標準化數據
+    scaled_data = scaler.transform(numerical_data)
+    
+    # 使用 PCA 進行降維
+    pca_data = pca.transform(scaled_data)
+    
+    # 創建包含主成分的 DataFrame
+    pca_df = pd.DataFrame(pca_data, columns=['PC1', 'PC2'])
+    
+    # 使用保存的 K-means 模型進行聚類
+    kmeans_labels = kmeans.predict(pca_df)
+    
+    # 使用保存的階層式聚類結果
+    hclust_labels = fcluster(linked, 3, criterion='maxclust')
+    
+    # 使用保存的 DBSCAN 模型進行聚類
+    dbscan_labels = dbscan.fit_predict(pca_df)
+    
+    # ================== 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)
+    
+    # ================== 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)
+    
+    # ================== 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)