import joblib import pandas as pd import matplotlib.pyplot as plt import streamlit as st from sklearn.preprocessing import StandardScaler from sklearn.decomposition import PCA from scipy.cluster.hierarchy import fcluster # ================== 加載保存的模型 ================== scaler = joblib.load('scaler.sav') # 標準化模型 pca = joblib.load('pca_model.sav') # PCA 模型 kmeans = joblib.load('kmeans_model.sav') # K-means 模型 linked = joblib.load('hierarchical_model.sav') # 階層式聚類模型 dbscan = joblib.load('dbscan_model.sav') # DBSCAN 模型 # 定義繪圖函數 def plot_clusters(data, labels, title): plt.figure(figsize=(8, 6)) plt.scatter(data['PC1'], data['PC2'], c=labels, cmap='viridis', s=50) plt.title(title) plt.xlabel('Principal Component 1 (PC1)') plt.ylabel('Principal Component 2 (PC2)') plt.colorbar() plt.savefig('plot.png') plt.close() return 'plot.png' # 處理上傳的資料 def process_data(file): # 讀取新資料 new_data = pd.read_csv(file) # 移除 'Time' 欄位 new_numerical_data = new_data.drop(columns=['Time']) # 數據預處理 scaled_new_data = scaler.transform(new_numerical_data) # 標準化數據 pca_new_data = pca.transform(scaled_new_data) # 使用已保存的 PCA 模型進行轉換 # 創建包含主成分的 DataFrame pca_new_df = pd.DataFrame(pca_new_data, columns=['PC1', 'PC2']) # 使用加載的模型進行聚類 kmeans_new_labels = kmeans.predict(pca_new_df) hclust_new_labels = fcluster(linked, 3, criterion='maxclust') dbscan_new_labels = dbscan.fit_predict(pca_new_df) # 可視化結果 kmeans_plot = plot_clusters(pca_new_df, kmeans_new_labels, 'K-means Clustering') hclust_plot = plot_clusters(pca_new_df, hclust_new_labels, 'Hierarchical Clustering') dbscan_plot = plot_clusters(pca_new_df, dbscan_new_labels, 'DBSCAN Clustering') return kmeans_new_labels, hclust_new_labels, dbscan_new_labels, kmeans_plot, hclust_plot, dbscan_plot # Streamlit 應用程式 st.title("聚類模型應用") # 文件上傳 uploaded_file = st.file_uploader("上傳 CSV 檔案", type=["csv"]) if uploaded_file is not None: kmeans_labels, hclust_labels, dbscan_labels, kmeans_plot, hclust_plot, dbscan_plot = process_data(uploaded_file) # 顯示 K-means 標籤 st.subheader("K-means Labels") st.text(kmeans_labels) # 顯示 Hierarchical 標籤 st.subheader("Hierarchical Clustering Labels") st.text(hclust_labels) # 顯示 DBSCAN 標籤 st.subheader("DBSCAN Labels") st.text(dbscan_labels) # 顯示圖像 st.subheader("K-means Clustering Plot") st.image(kmeans_plot) st.subheader("Hierarchical Clustering Plot") st.image(hclust_plot) st.subheader("DBSCAN Clustering Plot") st.image(dbscan_plot)