chot ket qua 08_07

Project_Code_and_Results/3_PCA_and_HCA/Profiling_H4_Decision_Contingency.csv

@@ -0,0 +1,4 @@
+Cluster,0,1,0_Pct,1_Pct
+1,27,20,57.446808510638306,42.5531914893617
+2,32,29,52.459016393442624,47.540983606557376
+3,44,155,22.110552763819097,77.88944723618091

Project_Code_and_Results/3_PCA_and_HCA/Profiling_H4_Donation_Contingency.csv

@@ -0,0 +1,4 @@
+Cluster,0,1,0_Pct,1_Pct
+1,10,37,21.27659574468085,78.72340425531915
+2,22,39,36.0655737704918,63.934426229508205
+3,4,195,2.0100502512562812,97.98994974874373

Project_Code_and_Results/3_PCA_and_HCA/run_h4_profiling.py

@@ -0,0 +1,27 @@
+import sys
+sys.stdout.reconfigure(encoding='utf-8')
+import pandas as pd
+import scipy.stats as stats
+import os
+
+base_dir = r'c:\Users\NASPC\Documents\Du án tại SG tháng 8\Project_Code_and_Results'
+df = pd.read_excel(r'c:\Users\NASPC\Documents\Du án tại SG tháng 8\Data_VN_filter_v5_with_clusters.xlsx')
+
+results = []
+for var in ['Donation', 'Decision']:
+    df_clean = df.dropna(subset=['Cluster', var])
+    ct = pd.crosstab(df_clean['Cluster'], df_clean[var])
+    chi2, p, dof, _ = stats.chi2_contingency(ct)
+    
+    ct_pct = ct.div(ct.sum(axis=1), axis=0) * 100
+    print(f"\n--- {var} ---")
+    print("Counts:")
+    print(ct)
+    print("\nPercentages:")
+    print(ct_pct)
+    print(f"Chi-square: {chi2:.4f}, p-value: {p:.4f}")
+    
+    res = pd.concat([ct, ct_pct.add_suffix('_Pct')], axis=1)
+    res.to_csv(os.path.join(base_dir, '3_PCA_and_HCA', f'Profiling_H4_{var}_Contingency.csv'))
+
+print("\nĐã xuất kết quả kiểm định H4.")