chuyển đổi cấu trúc

2026-07-08 15:11:34 +07:00
parent b041ccc11a
commit b22d327c5f
45 changed files with 201 additions and 4 deletions
@@ -0,0 +1,117 @@
+{
+    "Age": {
+        "Mean": 35.25316455696203,
+        "Std": 16.342855691857576,
+        "Min": 19.0,
+        "Max": 79.0,
+        "Shapiro-Wilk_W": 0.8454128859887641,
+        "Shapiro-Wilk_p": 1.310419664520166e-07,
+        "Normal_Distribution": false
+    },
+    "Gender": {
+        "2": 55.0,
+        "1": 44.3,
+        "3": 0.7
+    },
+    "Income": {
+        "439.9999999999999": 15.5,
+        "586.6666666666666": 8.0,
+        "220.0": 6.5,
+        "330.0": 4.5,
+        "550.0": 4.5,
+        "293.3333333333333": 4.0,
+        "264.0": 4.0,
+        "660.0": 4.0,
+        "132.0": 3.5,
+        "165.0": 3.0,
+        "176.0": 3.0,
+        "528.0": 3.0,
+        "733.3333333333334": 2.5,
+        "33.0": 2.5,
+        "385.0": 2.5,
+        "110.0": 2.0,
+        "275.0": 2.0,
+        "366.6666666666667": 2.0,
+        "513.3333333333333": 2.0,
+        "183.3333333333333": 1.5,
+        "73.33333333333333": 1.5,
+        "352.0": 1.5,
+        "322.6666666666666": 1.0,
+        "234.6666666666667": 1.0,
+        "146.6666666666667": 1.0,
+        "88.0": 1.0,
+        "308.0": 1.0,
+        "54.99999999999999": 1.0,
+        "35.2": 1.0,
+        "879.9999999999999": 1.0,
+        "495.0": 1.0,
+        "484.0": 1.0,
+        "809.5999999999999": 0.5,
+        "704.0": 0.5,
+        "990.0": 0.5,
+        "44.0": 0.5,
+        "188.5714285714286": 0.5,
+        "256.6666666666666": 0.5,
+        "469.3333333333333": 0.5,
+        "806.6666666666666": 0.5,
+        "282.8571428571428": 0.5,
+        "1320.0": 0.5,
+        "605.0": 0.5,
+        "572.0": 0.5,
+        "616.0": 0.5
+    },
+    "Literacy": {
+        "6": 43.0,
+        "4": 31.9,
+        "3": 16.3,
+        "2": 4.6,
+        "1": 2.9,
+        "5": 1.3
+    },
+    "Career": {
+        "4": 30.3,
+        "1": 24.8,
+        "3": 15.3,
+        "2": 14.7,
+        "6": 14.0,
+        "5": 1.0
+    },
+    "Habits": {
+        "Distance": {
+            "1": "31.3% (n=96)",
+            "2": "24.8% (n=76)",
+            "3": "17.6% (n=54)",
+            "4": "16.0% (n=49)",
+            "5": "10.1% (n=31)",
+            "6": "0.3% (n=1)"
+        },
+        "Frequency": {
+            "4": "27.0% (n=83)",
+            "5": "25.4% (n=78)",
+            "2": "17.6% (n=54)",
+            "1": "15.3% (n=47)",
+            "3": "14.7% (n=45)"
+        },
+        "Time": {
+            "4": "35.2% (n=108)",
+            "5": "28.3% (n=87)",
+            "3": "27.4% (n=84)",
+            "2": "7.2% (n=22)",
+            "1": "2.0% (n=6)"
+        },
+        "Transportation": {
+            "3": "57.0% (n=175)",
+            "2": "19.9% (n=61)",
+            "1": "16.3% (n=50)",
+            "4": "5.2% (n=16)",
+            "5": "1.6% (n=5)"
+        }
+    },
+    "Activities": {
+        "Jogging": 0.21,
+        "Workout": 0.35,
+        "Sightseeing": 0.76,
+        "Talking": 0.54,
+        "Photography": 0.27
+    }
+}
@@ -0,0 +1,93 @@
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+from scipy import stats
+import json
+
+df = pd.read_excel('Data_VN_filter_v5.xlsx')
+
+# Tùy chỉnh font chữ matplotlib nếu cần
+plt.rcParams.update({'font.size': 12})
+
+output_data = {}
+
+# 1. Kiểm tra biến Tuổi (Age)
+if 'Age' in df.columns:
+    # Convert age to numeric just in case
+    age_data = pd.to_numeric(df['Age'], errors='coerce').dropna()
+    stat, p = stats.shapiro(age_data)
+    output_data['Age'] = {
+        'Mean': age_data.mean(),
+        'Std': age_data.std(),
+        'Min': age_data.min(),
+        'Max': age_data.max(),
+        'Shapiro-Wilk_W': stat,
+        'Shapiro-Wilk_p': p,
+        'Normal_Distribution': bool(p > 0.05)
+    }
+    
+    # Plot Age histogram
+    plt.figure(figsize=(8, 5))
+    sns.histplot(age_data, kde=True, color='skyblue')
+    plt.title('Phân phối Tuổi (Age)')
+    plt.xlabel('Tuổi')
+    plt.ylabel('Tần số')
+    plt.savefig('Age_Distribution.png', dpi=300, bbox_inches='tight')
+    plt.close()
+
+# 2. Nhân khẩu học (Demographics)
+demo_cols = ['Gender', 'Income', 'Literacy', 'Career']
+fig, axes = plt.subplots(2, 2, figsize=(16, 12))
+fig.suptitle('Cơ cấu Nhân khẩu học của Mẫu Khảo sát (N = 307)', fontsize=18, fontweight='bold', y=1.02)
+
+for i, col in enumerate(demo_cols):
+    if col in df.columns:
+        ax = axes[i//2, i%2]
+        val_counts = df[col].value_counts()
+        
+        # Nếu biến có quá nhiều giá trị (như Income), vẽ Histogram thay vì Pie chart
+        if len(val_counts) > 10 or col == 'Income':
+            numeric_data = pd.to_numeric(df[col], errors='coerce').dropna()
+            sns.histplot(numeric_data, kde=True, ax=ax, color='coral', bins=20)
+            ax.set_title(f'Phân phối {col}', fontsize=14, pad=10)
+            ax.set_xlabel(col)
+            ax.set_ylabel('Tần số')
+        else:
+            # Plot Pie Chart cho biến phân loại
+            wedges, texts, autotexts = ax.pie(val_counts, autopct='%1.1f%%', startangle=140, 
+                                              colors=sns.color_palette('Set2'), pctdistance=0.8)
+            ax.legend(wedges, val_counts.index, title=col, loc="center left", bbox_to_anchor=(1, 0.5))
+            ax.set_title(f'Tỷ lệ {col}', fontsize=14, pad=10)
+        
+        output_data[col] = df[col].value_counts(normalize=True).mul(100).round(1).to_dict()
+
+plt.tight_layout()
+plt.savefig('Demographics_Charts.png', dpi=300, bbox_inches='tight')
+plt.close()
+
+# 3. Thói quen tương tác (Interactions)
+habit_cols = ['Distance', 'Frequency', 'Time', 'Transportation']
+output_data['Habits'] = {}
+for col in habit_cols:
+    if col in df.columns:
+        counts = df[col].value_counts()
+        pcts = df[col].value_counts(normalize=True).mul(100).round(1)
+        output_data['Habits'][col] = {str(k): f"{pcts[k]}% (n={counts[k]})" for k in counts.index}
+
+# 4. Các hoạt động phổ biến (Activities)
+# Bảng hỏi thường dùng Yes/No (1/0) hoặc Likert. Tính tỷ lệ % chọn Yes (1).
+act_cols = ['Jogging', 'Workout', 'Pet', 'Sightseeing', 'Talking', 'Photography']
+output_data['Activities'] = {}
+for col in act_cols:
+    # Nếu biến là 'Pet Walking' thay vì 'Pet'
+    actual_col = col if col in df.columns else (col + ' Walking' if col + ' Walking' in df.columns else None)
+    if actual_col:
+        mean_val = pd.to_numeric(df[actual_col], errors='coerce').mean()
+        # Nếu mean < 1.5, có thể là dữ liệu nhị phân (0-1), ngược lại là Likert
+        output_data['Activities'][actual_col] = round(mean_val, 2)
+
+# Save summary to JSON
+with open('descriptive_output.json', 'w', encoding='utf-8') as f:
+    json.dump(output_data, f, ensure_ascii=False, indent=4)
+
+print("Descriptive statistics run complete. Outputs saved.")
@@ -0,0 +1,8 @@
+,Temperature,Noise,Stormwind,Respiratory,Exercises,Culture,Beauty,Education,Society,Spirit,Dirty,Unsafe,Danger
+Park,0.5861277411758214,0.46872135461497316,0.5433785341732876,0.552634098528652,0.6278282242144403,0.5249311710036608,0.6010523214572643,0.6698801970338424,0.592175252811864,0.5873765414225279,-0.4119222589542689,-0.36935992311052424,-0.47499404654301275
+Residential,0.610813681241285,0.5010876976294922,0.5812495058768619,0.6308055529227076,0.6905711940417876,0.5336682510392587,0.7050811390341176,0.6880894492038738,0.6281007540295365,0.6725382465666585,-0.4172763562532894,-0.3683423748854766,-0.47006223532477215
+Garden,0.45224716780106355,0.3994427050538716,0.41423108867853403,0.4171592620121273,0.5703375228779752,0.42420205471782707,0.5225523665124601,0.5586006221718542,0.4604821197705184,0.4741367465117808,-0.3021035545730409,-0.2690208910002917,-0.33928178580122825
+Rooftop,0.4960914195506356,0.4389763334105073,0.4741573996062278,0.4043299683546717,0.5234138548608293,0.40036627443478834,0.5613291264190557,0.5137072417522562,0.4507351073588117,0.533245963504779,-0.3044536381978058,-0.3287078138585324,-0.3540628872780644
+Recreation,0.40870892534299835,0.36018022246155923,0.38726035929996405,0.327640261869753,0.4435840120247182,0.41597785467253595,0.41702432907643733,0.46845721173859056,0.337735516408859,0.346506311430844,-0.08584770592904668,-0.14113338302330178,-0.2698727403572271
+Agriculture,-0.3186847619885256,-0.22410153490737583,-0.31116783542012505,-0.31164843416963245,-0.29672463363412205,-0.08295065998935172,-0.407725512606722,-0.34041202068253673,-0.33774567405476646,-0.3661505107268029,0.4906684665223075,0.4667053886536356,0.5249948486680992
+Nature,-0.4377274782376116,-0.2893202018289482,-0.47487184947631206,-0.4416794342162952,-0.4395911413850507,-0.2583285861208512,-0.4891875676625891,-0.4669790589031381,-0.4642512201471137,-0.5258378364708906,0.5182221077803194,0.5103204875306926,0.5338960402111311
@@ -0,0 +1,14 @@
+,0,1
+Temperature,-0.15445511914940652,0.006990515901429791
+Noise,-0.07615894298740968,0.00700492282153885
+Stormwind,-0.1563914823055307,0.007878888704259901
+Respiratory,-0.14800873993854352,-0.011635761620414456
+Exercises,-0.16208617036601874,-0.0003806098068870642
+Culture,-0.04550439013316019,0.00881620114706321
+Beauty,-0.19796961667785237,-0.0012069882779817856
+Education,-0.17984311395007466,0.008345565782577814
+Society,-0.16523244764182207,-0.011179747262609863
+Spirit,-0.1938278638629291,-0.01479224672248243
+Dirty,0.662990083180058,0.026367956173616355
+Unsafe,0.6446258846820032,-0.0004123561994046179
+Danger,0.7399178159934315,-0.028168947040193765
@@ -0,0 +1,8 @@
+,0,1
+Park,-0.20737329331501148,-0.002436125971632047
+Residential,-0.2155834258211865,-0.011730849372120936
+Garden,-0.14244079709884974,-0.004395477787898166
+Rooftop,-0.15500847340894128,-0.003399988119557015
+Recreation,-0.0682883185805637,0.027918075759378963
+Agriculture,0.5601149289877119,-0.005751109303690985
+Nature,0.6998145216538895,-0.0007509375795379177
@@ -0,0 +1,8 @@
+,Temperature,Noise,Stormwind,Respiratory,Exercises,Culture,Beauty,Education,Society,Spirit,Dirty,Unsafe,Danger
+Park,0.5861277411758214,0.4687213546149731,0.5433785341732876,0.552634098528652,0.6278282242144403,0.5249311710036608,0.6010523214572643,0.6698801970338424,0.592175252811864,0.5873765414225279,-0.4119222589542689,-0.3693599231105242,-0.4749940465430127
+Residential,0.610813681241285,0.5010876976294922,0.5812495058768619,0.6308055529227076,0.6905711940417876,0.5336682510392587,0.7050811390341176,0.6880894492038738,0.6281007540295365,0.6725382465666585,-0.4172763562532894,-0.3683423748854766,-0.4700622353247721
+Garden,0.4522471678010635,0.3994427050538716,0.414231088678534,0.4171592620121273,0.5703375228779752,0.424202054717827,0.5225523665124601,0.5586006221718542,0.4604821197705184,0.4741367465117808,-0.3021035545730409,-0.2690208910002917,-0.3392817858012282
+Rooftop,0.4960914195506356,0.4389763334105073,0.4741573996062278,0.4043299683546717,0.5234138548608293,0.4003662744347883,0.5613291264190557,0.5137072417522562,0.4507351073588117,0.533245963504779,-0.3044536381978058,-0.3287078138585324,-0.3540628872780644
+Recreation,0.4087089253429983,0.3601802224615592,0.387260359299964,0.327640261869753,0.4435840120247182,0.4159778546725359,0.4170243290764373,0.4684572117385905,0.337735516408859,0.346506311430844,-0.0858477059290466,-0.1411333830233017,-0.2698727403572271
+Agriculture,-0.3186847619885256,-0.2241015349073758,-0.311167835420125,-0.3116484341696324,-0.296724633634122,-0.0829506599893517,-0.407725512606722,-0.3404120206825367,-0.3377456740547664,-0.3661505107268029,0.4906684665223075,0.4667053886536356,0.5249948486680992
+Nature,-0.4377274782376116,-0.2893202018289482,-0.474871849476312,-0.4416794342162952,-0.4395911413850507,-0.2583285861208512,-0.4891875676625891,-0.4669790589031381,-0.4642512201471137,-0.5258378364708906,0.5182221077803194,0.5103204875306926,0.5338960402111311
@@ -0,0 +1,93 @@
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import prince
+
+# Load data
+df = pd.read_excel('Data_VN_filter_v5.xlsx')
+
+# Extract variables
+ugs_cols = ['Park', 'Residential', 'Garden', 'Rooftop', 'Recreation', 'Agriculture', 'Nature']
+
+# Detailed ESS and DES variables
+ess_des_detailed = [
+    # RES (Điều hòa)
+    'Temperature', 'Noise', 'Stormwind', 'Respiratory',
+    # CES (Văn hóa)
+    'Exercises', 'Culture', 'Beauty', 'Education', 'Society', 'Spirit',
+    # DES (Bất lợi)
+    'Dirty', 'Unsafe', 'Danger'
+]
+
+# Ensure the columns exist in df
+available_detailed = [col for col in ess_des_detailed if col in df.columns]
+
+# We want to run CA on the relationships between the 7 UGS types and the 13 specific services.
+# Dữ liệu thang đo Likert thường là dữ liệu thứ bậc (Ordinal), nên dùng Spearman's rho sẽ chính xác hơn Pearson.
+data = df[ugs_cols + available_detailed].dropna()
+corr = data.corr(method='spearman').loc[ugs_cols, available_detailed]
+
+# Tương tự như trước, dịch chuyển ma trận hệ số RHO để các giá trị đều dương (dùng cho CA)
+# Alternatively, since prince CA handles frequencies, we can just pass the raw data? 
+# If we pass raw data of shape (307, 20), CA will treat rows as individuals. 
+# We want to see relationships between UGS and Detailed Services. Passing the correlation matrix (shifted) is a good proxy for similarity.
+corr_shifted = corr + 1
+
+# Initialize CA
+ca = prince.CA(n_components=2, n_iter=3, copy=True, check_input=True, engine='scipy', random_state=42)
+ca = ca.fit(corr_shifted)
+
+# Extract column and row coordinates
+row_coords = ca.row_coordinates(corr_shifted) # UGS
+col_coords = ca.column_coordinates(corr_shifted) # Detailed Services
+
+# Save to CSV
+corr.to_csv('CA_Detailed_Correlation_Matrix.csv')
+row_coords.to_csv('CA_Detailed_UGS_Coords.csv')
+col_coords.to_csv('CA_Detailed_Services_Coords.csv')
+
+# Plot Biplot
+fig, ax = plt.subplots(figsize=(20, 15))
+
+# Plot UGS points (blue dots)
+p_ugs = ax.scatter(row_coords[0], row_coords[1], c='blue', label='UGS Types', s=80, marker='o', edgecolors='black')
+
+# Plot ESS/DES points (red/green squares)
+res_cols = ['Temperature', 'Noise', 'Stormwind', 'Respiratory']
+ces_cols = ['Exercises', 'Culture', 'Beauty', 'Education', 'Society', 'Spirit']
+des_cols = ['Dirty', 'Unsafe', 'Danger']
+
+p_ess = []
+for col in available_detailed:
+    color = 'green' if col in res_cols else ('purple' if col in ces_cols else 'red')
+    p = ax.scatter(col_coords.loc[col, 0], col_coords.loc[col, 1], c=color, marker='s', s=80, edgecolors='black')
+    p_ess.append(p)
+
+# Gắn nhãn (Text) tĩnh để đảm bảo tính nhất quán (Deterministic) 100% mỗi lần chạy
+# Phân tách vị trí nhãn: UGS nằm lệch trên-trái, ESS/DES nằm lệch dưới-phải
+for i, txt in enumerate(ugs_cols):
+    ax.annotate(txt, (row_coords.iloc[i, 0], row_coords.iloc[i, 1]), 
+                xytext=(-10, 10), textcoords='offset points', 
+                color='blue', fontweight='bold', fontsize=12, ha='right', va='bottom')
+
+for col in available_detailed:
+    color = 'green' if col in res_cols else ('purple' if col in ces_cols else 'red')
+    ax.annotate(col, (col_coords.loc[col, 0], col_coords.loc[col, 1]), 
+                xytext=(10, -10), textcoords='offset points', 
+                color=color, fontsize=12, fontweight='bold', ha='left', va='top')
+
+# Add dummy plots for legend
+ax.scatter([], [], c='green', marker='s', label='RES (Điều hòa)')
+ax.scatter([], [], c='purple', marker='s', label='CES (Văn hóa)')
+ax.scatter([], [], c='red', marker='s', label='DES (Bất lợi)')
+
+ax.axhline(0, color='grey', linestyle='--', linewidth=1)
+ax.axvline(0, color='grey', linestyle='--', linewidth=1)
+ax.set_title('Detailed CA Biplot (UGS vs Specific ESS/DES)', fontsize=16)
+ax.set_xlabel('Component 0', fontsize=12)
+ax.set_ylabel('Component 1', fontsize=12)
+ax.legend(loc='center left', bbox_to_anchor=(1.02, 0.5), fontsize=12)
+plt.grid(True, linestyle=':', alpha=0.6)
+plt.savefig('CA_plot_detailed.png', dpi=300, bbox_inches='tight')
+print("\nDetailed CA Plot saved to CA_plot_detailed.png")
+print("Detailed data exported to CSV files.")
@@ -0,0 +1,24 @@
+import pandas as pd
+import seaborn as sns
+import matplotlib.pyplot as plt
+
+# Đọc ma trận RHO đã tính từ file CSV
+corr = pd.read_csv('CA_Detailed_Correlation_Matrix.csv', index_col=0)
+
+# Vẽ biểu đồ nhiệt (Heatmap)
+plt.figure(figsize=(14, 8))
+sns.heatmap(corr, annot=True, fmt=".2f", cmap="coolwarm", center=0, 
+            vmin=-1, vmax=1, linewidths=.5, cbar_kws={"shrink": .8})
+
+plt.title('Spearman RHO Correlation Matrix (UGS vs Specific ESS/DES)', fontsize=16, pad=20)
+plt.ylabel('UGS Types', fontsize=12)
+plt.xlabel('ESS/DES Variables', fontsize=12)
+
+# Xoay nhãn trục X để dễ đọc hơn
+plt.xticks(rotation=45, ha='right')
+plt.yticks(rotation=0)
+
+plt.tight_layout()
+plt.savefig('RHO_Heatmap.png', dpi=300)
+corr.to_csv('RHO_Matrix.csv')
+print("Heatmap saved to RHO_Heatmap.png and data to RHO_Matrix.csv")
@@ -0,0 +1,14 @@
+,PC1,PC2,Uniqueness
+Temperature,0.7859143713690758,-0.15342458640921602,0.35879949716071136
+Noise,0.7392275315643728,-0.14504349077151615,0.43250504236205733
+Stormwind,0.7983317716636736,-0.15246305454979966,0.33942139934968485
+Respiratory,0.8141977005065351,-0.16078705379178215,0.31122962782282915
+Exercises,0.7861049487051457,-0.22688720348435373,0.3305612065163297
+Culture,0.7978897043499087,-0.05932506148429913,0.35985255677229944
+Beauty,0.8700711219058058,-0.1556431549883994,0.2187514511308295
+Education,0.8379709091142482,-0.2606539630840815,0.22986426700680263
+Society,0.8178019516337711,-0.097610506717968,0.3216721568822566
+Spirit,0.8499003710179431,-0.1980420960982776,0.23844868751656323
+Dirty,-0.12911798501226357,0.9075618096917915,0.15966010753533333
+Unsafe,-0.12502417318133396,0.8926423245694102,0.1875586365076436
+Danger,-0.19294042642503595,0.8920213064079019,0.1670719807652653
@@ -0,0 +1,4 @@
+Cluster,1,2,3,4,5,6,1_Pct,2_Pct,3_Pct,4_Pct,5_Pct,6_Pct
+1,23,4,7,9,0,4,48.93617021276596,8.51063829787234,14.893617021276595,19.148936170212767,0.0,8.51063829787234
+2,10,16,3,12,3,17,16.39344262295082,26.229508196721312,4.918032786885246,19.672131147540984,4.918032786885246,27.86885245901639
+3,43,25,37,72,0,22,21.608040201005025,12.562814070351758,18.592964824120603,36.18090452261307,0.0,11.055276381909549
@@ -0,0 +1,4 @@
+Cluster,1,2,3,4,5,6,1_Pct,2_Pct,3_Pct,4_Pct,5_Pct,6_Pct
+1,9,10,10,9,9,0,19.148936170212767,21.27659574468085,21.27659574468085,19.148936170212767,19.148936170212767,0.0
+2,16,13,11,11,10,0,26.229508196721312,21.311475409836063,18.0327868852459,18.0327868852459,16.39344262295082,0.0
+3,71,53,33,29,12,1,35.678391959798994,26.633165829145728,16.582914572864322,14.572864321608039,6.030150753768844,0.5025125628140703
@@ -0,0 +1,4 @@
+Cluster,1,2,3,4,5,1_Pct,2_Pct,3_Pct,4_Pct,5_Pct
+1,8,12,9,9,9,17.02127659574468,25.53191489361702,19.148936170212767,19.148936170212767,19.148936170212767
+2,21,18,6,9,7,34.42622950819672,29.508196721311474,9.836065573770492,14.754098360655737,11.475409836065573
+3,18,24,30,65,62,9.045226130653267,12.060301507537687,15.07537688442211,32.663316582914575,31.155778894472363
@@ -0,0 +1,4 @@
+Cluster,1,2,3,1_Pct,2_Pct,3_Pct
+1,18,27,2,38.297872340425535,57.446808510638306,4.25531914893617
+2,27,34,0,44.26229508196721,55.73770491803278,0.0
+3,91,108,0,45.7286432160804,54.2713567839196,0.0
@@ -0,0 +1,4 @@
+Cluster,1,2,3,4,5,6,1_Pct,2_Pct,3_Pct,4_Pct,5_Pct,6_Pct
+1,0,3,8,8,0,28,0.0,6.382978723404255,17.02127659574468,17.02127659574468,0.0,59.57446808510638
+2,0,7,12,25,4,13,0.0,11.475409836065573,19.672131147540984,40.98360655737705,6.557377049180328,21.311475409836063
+3,9,4,30,65,0,91,4.522613065326634,2.0100502512562812,15.07537688442211,32.663316582914575,0.0,45.7286432160804
@@ -0,0 +1,4 @@
+Cluster,1,2,3,4,5,1_Pct,2_Pct,3_Pct,4_Pct,5_Pct
+1,0,3,8,23,13,0.0,6.382978723404255,17.02127659574468,48.93617021276596,27.659574468085108
+2,6,9,15,17,14,9.836065573770492,14.754098360655737,24.59016393442623,27.86885245901639,22.950819672131146
+3,0,10,61,68,60,0.0,5.025125628140704,30.65326633165829,34.17085427135678,30.15075376884422
@@ -0,0 +1,4 @@
+Cluster,1,2,3,4,5,1_Pct,2_Pct,3_Pct,4_Pct,5_Pct
+1,8,10,21,6,2,17.02127659574468,21.27659574468085,44.680851063829785,12.76595744680851,4.25531914893617
+2,10,14,31,4,2,16.39344262295082,22.950819672131146,50.81967213114754,6.557377049180328,3.278688524590164
+3,32,37,123,6,1,16.08040201005025,18.592964824120603,61.80904522613066,3.015075376884422,0.5025125628140703
@@ -0,0 +1,239 @@
+import sys
+sys.stdout.reconfigure(encoding='utf-8')
+import pandas as pd
+import numpy as np
+import scipy.stats as stats
+from scipy.cluster.hierarchy import linkage, fcluster
+import matplotlib.pyplot as plt
+import seaborn as sns
+from factor_analyzer.factor_analyzer import calculate_kmo, calculate_bartlett_sphericity
+import os
+
+# --- Helper function for Varimax Rotation ---
+def varimax(loadings, max_iter=500, tolerance=1e-6):
+    X = loadings.copy()
+    n_rows, n_cols = X.shape
+    if n_cols < 2:
+        return X, np.eye(n_cols)
+    
+    R = np.eye(n_cols)
+    d = 0
+    for i in range(max_iter):
+        d_old = d
+        Lambda = np.dot(X, R)
+        grad = np.dot(X.T, Lambda**3 - (1.0 / n_rows) * np.dot(Lambda, np.diag(np.sum(Lambda**2, axis=0))))
+        u, s, vh = np.linalg.svd(grad)
+        R = np.dot(u, vh)
+        d = np.sum(s)
+        if d_old != 0 and (d - d_old) / d_old < tolerance:
+            break
+            
+    rotated_loadings = np.dot(X, R)
+    return rotated_loadings, R
+
+# --- Setup Paths ---
+base_dir = r"c:\Users\NASPC\Documents\Du án tại SG tháng 8"
+output_dir = os.path.join(base_dir, "PCA_HCA_Results")
+if not os.path.exists(output_dir):
+    os.makedirs(output_dir)
+
+file_path = os.path.join(base_dir, 'Data_VN_filter_v5.xlsx')
+df = pd.read_excel(file_path)
+
+# --- 1. Variables Definition ---
+pca_vars = [
+    'Temperature', 'Noise', 'Stormwind', 'Respiratory', # RES
+    'Exercises', 'Culture', 'Beauty', 'Education', 'Society', 'Spirit', # CES
+    'Dirty', 'Unsafe', 'Danger' # DES
+]
+demographic_vars = ['Gender', 'Career', 'Literacy']
+habit_vars = ['Distance', 'Frequency', 'Time', 'Transportation']
+
+# Ensure variables exist and drop NaNs for PCA
+df_pca = df[pca_vars].dropna()
+n_samples = len(df_pca)
+print(f"--- Bước 2: Phân tích thành phần chính (PCA) ---")
+print(f"Cỡ mẫu (N): {n_samples}")
+
+# --- 2. KMO & Bartlett's Test ---
+kmo_all, kmo_model = calculate_kmo(df_pca)
+bartlett_stat, bartlett_p = calculate_bartlett_sphericity(df_pca)
+
+print("\nBảng 1: Kaiser-Meyer-Olkin Test")
+print(f"Overall MSA: {kmo_model:.5f}")
+for var, kmo_val in zip(pca_vars, kmo_all):
+    print(f"  {var}: {kmo_val:.5f}")
+
+print("\nBảng 2: Bartlett's Test of Sphericity")
+df_bartlett = len(pca_vars) * (len(pca_vars) - 1) / 2
+print(f"X^2: {bartlett_stat:.5f}, df: {int(df_bartlett)}, p: {bartlett_p}")
+
+# --- 3. PCA with Varimax Rotation ---
+# Standardize with ddof=1 to match JASP
+X_mean = df_pca.mean()
+X_std = df_pca.std(ddof=1)
+X_scaled = (df_pca - X_mean) / X_std
+
+# Correlation matrix
+R_corr = np.corrcoef(df_pca.T)
+eigenvalues, eigenvectors = np.linalg.eigh(R_corr)
+
+# Sort descending
+idx = np.argsort(eigenvalues)[::-1]
+eigenvalues = eigenvalues[idx]
+eigenvectors = eigenvectors[:, idx]
+
+print("\nBảng 6: Component Characteristics (Unrotated)")
+for i, ev in enumerate(eigenvalues[:5]): # Print top 5 for illustration
+    print(f"Component {i+1}: Eigenvalue = {ev:.5f}, Proportion = {ev/sum(eigenvalues):.5f}")
+
+# Extract 2 components
+unrotated_loadings = eigenvectors[:, :2] * np.sqrt(eigenvalues[:2])
+rotated_loadings, R = varimax(unrotated_loadings)
+
+# Align signs with JASP: PC1 positive for Beauty, PC2 positive for Dirty
+idx_beauty = pca_vars.index('Beauty')
+idx_dirty = pca_vars.index('Dirty')
+
+if rotated_loadings[idx_beauty, 0] < 0:
+    rotated_loadings[:, 0] = -rotated_loadings[:, 0]
+    R[:, 0] = -R[:, 0]
+if rotated_loadings[idx_dirty, 1] < 0:
+    rotated_loadings[:, 1] = -rotated_loadings[:, 1]
+    R[:, 1] = -R[:, 1]
+
+uniqueness = 1 - np.sum(rotated_loadings**2, axis=1)
+
+print("\nBảng 5: Component Loadings (Varimax Rotated)")
+loadings_df = pd.DataFrame(rotated_loadings, index=pca_vars, columns=['PC1', 'PC2'])
+loadings_df['Uniqueness'] = uniqueness
+print(loadings_df.round(5).to_string())
+
+# Save Loadings to CSV
+loadings_df.to_csv(os.path.join(output_dir, 'PCA_Component_Loadings.csv'))
+
+# --- 4. Plot PCA Loading Biplot ---
+plt.figure(figsize=(10, 8))
+plt.scatter(rotated_loadings[:, 0], rotated_loadings[:, 1], color='blue', alpha=0.5)
+for i, txt in enumerate(pca_vars):
+    plt.annotate(txt, (rotated_loadings[i, 0], rotated_loadings[i, 1]), xytext=(5,5), textcoords='offset points')
+plt.axhline(0, color='black',linewidth=1, ls='--')
+plt.axvline(0, color='black',linewidth=1, ls='--')
+plt.xlabel('Component 1 (ESS)')
+plt.ylabel('Component 2 (DES)')
+plt.title('PCA Loading Plot (Varimax Rotated)')
+plt.grid(True, linestyle=':', alpha=0.6)
+plt.savefig(os.path.join(output_dir, 'PCA_Loading_Plot.png'), dpi=300)
+plt.close()
+
+# --- 5. Component Scores for HCA ---
+# Calculate Standardized Component Scores
+scores_std = (np.dot(X_scaled, eigenvectors[:, :2]) / np.sqrt(eigenvalues[:2])).dot(R)
+
+print("\n--- Bước 3: Phân tích cụm phân cấp (HCA) & Chi-square ---")
+# --- 6. HCA (Ward's Method) ---
+Z = linkage(scores_std, method='ward')
+clusters = fcluster(Z, 3, criterion='maxclust')
+
+# Map clusters to original dataframe
+# Note: Since we dropped NaNs for PCA, we need to carefully assign back
+# Assuming original df has no NaNs in these columns based on previous logs (N=307 valid).
+# Just to be safe, we assign via index.
+df.loc[df_pca.index, 'Cluster'] = clusters
+df.loc[df_pca.index, 'PC1_Score'] = scores_std[:, 0]
+df.loc[df_pca.index, 'PC2_Score'] = scores_std[:, 1]
+
+# Align cluster labels with JASP based on sizes (199, 61, 47) and Means
+cluster_sizes = df['Cluster'].value_counts()
+print(f"\nGiai đoạn 3.1 - Gom cụm (HCA)")
+print("Cluster Sizes (Before Label Alignment):")
+print(cluster_sizes)
+
+# Map our generic cluster IDs (1, 2, 3) to JASP's cluster IDs
+# From our previous test:
+# Our Cluster with size 199 -> JASP Cluster 3 (Hài hòa & Thụ hưởng)
+# Our Cluster with size 61 -> JASP Cluster 2 (Thờ ơ)
+# Our Cluster with size 47 -> JASP Cluster 1 (Thực dụng & Lo ngại)
+mapping = {}
+for clst, size in cluster_sizes.items():
+    if size == 199:
+        mapping[clst] = 3
+    elif size == 61:
+        mapping[clst] = 2
+    elif size == 47:
+        mapping[clst] = 1
+    else:
+        mapping[clst] = clst # fallback
+
+df['Cluster'] = df['Cluster'].map(mapping)
+print("\nCluster Sizes (Aligned with JASP):")
+print(df['Cluster'].value_counts())
+
+cluster_means = df.groupby('Cluster')[['PC1_Score', 'PC2_Score']].mean()
+print("\nBảng 3: Cluster Means")
+print(cluster_means.round(5))
+
+# Plot Cluster Means
+cluster_means.plot(kind='bar', figsize=(10, 6))
+plt.title('Cluster Means for PC1 and PC2')
+plt.ylabel('Mean Standardized Score')
+plt.xlabel('Cluster')
+plt.axhline(0, color='black', linewidth=0.8, ls='--')
+plt.xticks(rotation=0)
+plt.savefig(os.path.join(output_dir, 'HCA_Cluster_Means_Plot.png'), dpi=300)
+plt.close()
+
+# Save DataFrame with Clusters
+output_dataset_path = os.path.join(base_dir, 'Data_VN_filter_v5_with_clusters.xlsx')
+df.to_excel(output_dataset_path, index=False)
+print(f"\nĐã lưu dataset mới kèm nhãn Cụm và Điểm nhân tố tại: {output_dataset_path}")
+
+# --- 7. Profiling (Chi-Square) ---
+def compute_cramer_v(chi2, n, shape):
+    return np.sqrt(chi2 / (n * (min(shape) - 1)))
+
+def profile_clusters(df, variables, title):
+    print(f"\n{title}")
+    results = []
+    
+    for var in variables:
+        if var not in df.columns:
+            continue
+        # Contingency table (cross-tabulation)
+        ct = pd.crosstab(df['Cluster'], df[var])
+        
+        # Chi-square test
+        chi2, p, dof, expected = stats.chi2_contingency(ct)
+        n = ct.sum().sum()
+        
+        # Cramer's V and Phi
+        v = compute_cramer_v(chi2, n, ct.shape)
+        
+        print(f"\n--- {var} ---")
+        print("Contingency Table (Counts):")
+        print(ct)
+        print(f"Chi-Square: {chi2:.5f}, df: {dof}, p: {p:.5f}")
+        print(f"Cramer's V (Contingency coefficient approx): {v:.5f}")
+        
+        results.append({
+            'Variable': var,
+            'Chi_Square': chi2,
+            'df': dof,
+            'p_value': p,
+            'Cramers_V': v
+        })
+        
+        # Detailed Table (like JASP) with row percentages
+        ct_pct = ct.div(ct.sum(axis=1), axis=0) * 100
+        # save detailed to csv just in case
+        ct_detailed = pd.concat([ct, ct_pct.add_suffix('_Pct')], axis=1)
+        ct_detailed.to_csv(os.path.join(output_dir, f'Profiling_{var}_Contingency.csv'))
+
+    res_df = pd.DataFrame(results)
+    res_df.to_csv(os.path.join(output_dir, f'Profiling_{title.replace(" ", "_")}_Summary.csv'), index=False)
+
+profile_clusters(df, demographic_vars, "Lần so sánh 1: Nhân khẩu học (Demographics)")
+profile_clusters(df, habit_vars, "Lần so sánh 2: Thói quen tương tác (Habits)")
+
+print("\n--- HOÀN THÀNH ---")
+print(f"Các bảng kết quả và biểu đồ đã được lưu tại: {output_dir}")
@@ -0,0 +1,40 @@
+,Beta (B),P-value,Odds Ratio EXP(B),Significance
+Rooftop,3.0756,0.0079,21.6626,**
+Frequency_4,5.5916,0.0129,268.1578,*
+Career_6,9.1882,0.0176,9781.3356,*
+Career_4,6.1367,0.022,462.5281,*
+Career_3,7.1144,0.0315,1229.5645,*
+Income,0.011,0.0387,1.0111,*
+MEAN CES,2.9215,0.0495,18.5696,*
+Garden,-2.2436,0.0545,0.1061,
+const,-22.5952,0.0608,0.0,
+Transportation_3,4.0109,0.0812,55.1958,
+Nature,-1.545,0.1226,0.2133,
+Frequency_5,2.4568,0.1369,11.668,
+MEAN DES,-0.5645,0.188,0.5686,
+Frequency_3,2.0046,0.2622,7.4228,
+Gender_2,1.6345,0.2689,5.1269,
+Transportation_5,8.8139,0.2931,6726.8423,
+MEAN RES,-0.8526,0.3366,0.4263,
+Recreation,-0.5931,0.3811,0.5526,
+Agriculture,0.6439,0.4038,1.904,
+Distance_2,1.3034,0.4172,3.6819,
+Park,0.7798,0.431,2.181,
+Transportation_4,2.0649,0.4405,7.8846,
+Time_4,1.74,0.5326,5.6971,
+Distance_4,-1.2593,0.5443,0.2838,
+Distance_3,1.2619,0.6309,3.532,
+Literacy_3,-3.3014,0.6631,0.0368,
+Frequency_2,0.683,0.7017,1.9799,
+Career_5,1.4116,0.7259,4.1024,
+Literacy_2,-2.6458,0.7276,0.071,
+Time_5,-0.8678,0.7459,0.4199,
+Residential,0.3326,0.7564,1.3946,
+Career_2,0.7339,0.7868,2.0831,
+Time_3,-0.7335,0.7979,0.4802,
+Literacy_6,1.6746,0.8247,5.3367,
+Transportation_2,0.3599,0.8906,1.4332,
+Literacy_4,-0.8905,0.9037,0.4105,
+Distance_5,-0.1975,0.933,0.8208,
+Time_2,0.2227,0.9368,1.2494,
+Literacy_5,-6.5281,0.978,0.0015,
@@ -0,0 +1,25 @@
+,Beta (B),P-value,Odds Ratio EXP(B),Significance
+const,-13.3839,0.0078,0.0,**
+Frequency,0.7183,0.0098,2.051,**
+Career_6,4.1539,0.0105,63.6799,*
+Rooftop,1.7017,0.0123,5.4833,*
+Income,0.0045,0.0229,1.0045,*
+Transportation_4,4.6473,0.0284,104.3069,*
+MEAN CES,1.8488,0.0288,6.3523,*
+Career_4,2.8862,0.0334,17.9242,*
+Career_3,3.4267,0.0368,30.7762,*
+Garden,-1.4026,0.0446,0.246,*
+MEAN DES,-0.4982,0.0586,0.6076,
+Transportation_3,2.1343,0.0739,8.4512,
+Literacy,0.5519,0.0906,1.7365,
+Gender_2,1.1137,0.1406,3.0455,
+Nature,-0.6135,0.2466,0.5415,
+MEAN RES,-0.6547,0.2723,0.5196,
+Residential,0.6836,0.391,1.981,
+Time,-0.1722,0.5721,0.8418,
+Distance,-0.161,0.6202,0.8513,
+Transportation_2,0.6629,0.6341,1.9404,
+Recreation,-0.1187,0.7927,0.8881,
+Career_2,0.347,0.8054,1.4148,
+Park,-0.1024,0.8656,0.9027,
+Agriculture,-0.0665,0.8894,0.9356,
@@ -0,0 +1,40 @@
+,Beta (B),P-value,Odds Ratio EXP(B),Significance
+const,241.6608,,8.952878165232437e+104,
+Income,-0.9832,,0.3741,
+MEAN RES,-6.4358,,0.0016,
+MEAN CES,72.6282,,3.4836963617736678e+31,
+MEAN DES,-95.8865,,0.0,
+Park,-50.6859,,0.0,
+Residential,258.3765,,1.6273086710804255e+112,
+Garden,-10.3217,,0.0,
+Rooftop,-133.4091,,0.0,
+Recreation,-20.842,,0.0,
+Agriculture,0.7005,,2.0148,
+Nature,-82.9613,,0.0,
+Gender_2,-102.1304,,0.0,
+Career_2,221.4766,,1.534848675005764e+96,
+Career_3,85.8488,,1.9215803519284693e+37,
+Career_4,29.8107,,8843571707594.404,
+Career_5,-19.9903,,0.0,
+Career_6,271.5147,,8.266885235464909e+117,
+Literacy_2,-45.5232,,0.0,
+Literacy_3,74.167,,1.6230180759688443e+32,
+Literacy_4,-130.4477,,0.0,
+Literacy_5,41.9698,,1.6875893967463475e+18,
+Literacy_6,239.8173,,1.4168061493135717e+104,
+Frequency_2,-64.3464,,0.0,
+Frequency_3,129.1509,,1.2289014711896098e+56,
+Frequency_4,16.8335,,20449449.0163,
+Frequency_5,90.1682,,1.4439203359332122e+39,
+Distance_2,121.504,,5.868283849671952e+52,
+Distance_3,-19.3408,,0.0,
+Distance_4,-8.0289,,0.0003,
+Distance_5,106.1989,,1.3231308267100774e+46,
+Time_2,123.4271,,4.015015109349733e+53,
+Time_3,293.3949,,2.628883873565357e+127,
+Time_4,172.2575,,6.463889160702152e+74,
+Time_5,91.6604,,6.420867256078891e+39,
+Transportation_2,86.2789,,2.9541644055797275e+37,
+Transportation_3,-67.1359,,0.0,
+Transportation_4,-197.7757,,0.0,
+Transportation_5,135.1477,,4.941998234455287e+58,
@@ -0,0 +1,18 @@
+,Beta (B),S.E.,P-value,Odds Ratio EXP(B),Significance
+MEAN DES,-0.8867,0.2551,0.0005,0.412,***
+Income,-0.0043,0.0013,0.0014,0.9957,**
+Distance,-0.5634,0.2603,0.0304,0.5693,*
+Gender_2,-1.3185,0.6722,0.0498,0.2675,*
+Career_3,2.368,1.2758,0.0634,10.6761,.
+Time,0.4763,0.2988,0.1109,1.6102,
+MEAN CES,1.0088,0.6344,0.1118,2.7424,
+Career_6,1.5794,1.0681,0.1392,4.8522,
+Literacy,0.3354,0.2392,0.1609,1.3985,
+Transportation_3,1.0788,0.7888,0.1714,2.9412,
+Transportation_2,1.2746,1.0966,0.2451,3.5774,
+Career_4,0.8155,0.8725,0.3499,2.2603,
+Career_2,0.7601,1.131,0.5015,2.1386,
+Frequency,0.1342,0.2411,0.5777,1.1437,
+MEAN RES,-0.335,0.605,0.5798,0.7153,
+Transportation_4,0.5981,1.2565,0.6341,1.8186,
+const,-0.0729,2.8797,0.9798,0.9297,
@@ -0,0 +1,24 @@
+,Beta (B),P-value,Odds Ratio EXP(B),Significance
+Income,-0.017,0.0117,0.9832,*
+MEAN DES,-5.6329,0.0249,0.0036,*
+Gender_2,-7.432,0.027,0.0006,*
+Time_4,5.816,0.0298,335.6267,*
+Time_3,5.3233,0.0298,205.0572,*
+const,27.0847,0.0353,579100469868.4305,*
+Distance_4,-8.7398,0.0361,0.0002,*
+Rooftop,-5.4289,0.0401,0.0044,*
+Time_5,5.3394,0.0409,208.3824,*
+Distance_2,6.5306,0.0559,685.8324,
+Frequency_4,-5.2178,0.0633,0.0054,
+Residential,5.1802,0.0838,177.7147,
+Time_2,4.0494,0.1046,57.3616,
+Frequency_2,-3.975,0.1085,0.0188,
+Distance_3,-7.5816,0.1122,0.0005,
+MEAN CES,3.2436,0.1387,25.6258,
+MEAN RES,-1.1166,0.2921,0.3274,
+Distance_5,-2.7017,0.3015,0.0671,
+Park,-0.7466,0.427,0.474,
+Frequency_5,-1.4957,0.5301,0.2241,
+Frequency_3,1.1843,0.6466,3.2683,
+Garden,0.3512,0.7775,1.4208,
+Recreation,-0.2539,0.8091,0.7758,
@@ -0,0 +1,39 @@
+,Beta (B),P-value,Odds Ratio EXP(B),Significance
+Income,-2.8338,,0.0588,
+MEAN RES,48.1663,,8.286505072393699e+20,
+MEAN CES,-76.1806,,0.0,
+MEAN DES,-526.8965,,0.0,
+Park,248.7626,,1.0869776475523444e+108,
+Residential,640.3286,,1.2336668793552433e+278,
+Garden,-72.3975,,0.0,
+Rooftop,-315.0215,,0.0,
+Recreation,-154.3187,,0.0,
+Agriculture,187.0536,,1.7232967765552025e+81,
+Nature,-245.4922,,0.0,
+Gender_2,-839.4743,,0.0,
+Career_2,859.4998,,inf,
+Career_3,297.7703,,2.0893254878873172e+129,
+Career_4,66.9201,,1.1562405239310425e+29,
+Career_5,-83.3945,,0.0,
+Career_6,1086.722,,inf,
+Literacy_2,-283.0314,,0.0,
+Literacy_3,224.4999,,3.1555822056480755e+97,
+Literacy_4,-346.8743,,0.0,
+Literacy_5,-43.1503,,0.0,
+Literacy_6,852.4063,,inf,
+Frequency_2,-517.3563,,0.0,
+Frequency_3,784.8878,,inf,
+Frequency_4,107.516,,4.938524666347628e+46,
+Frequency_5,177.2764,,9.775622061244049e+76,
+Distance_2,699.6584,,7.207639799224717e+303,
+Distance_3,-293.3604,,0.0,
+Distance_4,-263.5867,,0.0,
+Distance_5,878.1242,,inf,
+Time_2,537.512,,2.7448363654811603e+233,
+Time_3,1220.1209,,inf,
+Time_4,862.3738,,inf,
+Time_5,821.0535,,inf,
+Transportation_2,545.895,,1.1999777427858181e+237,
+Transportation_3,-10.0038,,0.0,
+Transportation_4,-849.1301,,0.0,
+Transportation_5,445.7974,,4.0490831821011e+193,
@@ -0,0 +1,29 @@
+import pandas as pd
+import numpy as np
+
+df = pd.read_excel('Data_VN_filter_v5.xlsx')
+target_vars = ['Donation', 'Decision']
+numeric_vars = ['Income', 'MEAN RES', 'MEAN CES', 'MEAN DES'] + ['Park', 'Residential', 'Garden', 'Rooftop', 'Recreation', 'Agriculture', 'Nature']
+categorical_vars = ['Gender', 'Career', 'Literacy', 'Frequency', 'Distance', 'Time', 'Transportation']
+
+for col in categorical_vars:
+    df[col] = df[col].astype(str)
+
+all_vars = target_vars + numeric_vars + categorical_vars
+df_subset = df[all_vars].dropna()
+df_sample = df_subset.sample(n=200, random_state=42) if len(df_subset) > 200 else df_subset
+
+X = pd.get_dummies(df_sample[numeric_vars + categorical_vars], drop_first=True, dtype=float)
+
+# Find constant columns
+constant_cols = [col for col in X.columns if X[col].nunique() <= 1]
+print(f"Constant columns: {constant_cols}")
+
+# Drop constant columns
+X = X.drop(columns=constant_cols)
+
+# Find highly correlated columns
+corr_matrix = X.corr().abs()
+upper = corr_matrix.where(np.triu(np.ones(corr_matrix.shape), k=1).astype(bool))
+to_drop = [column for column in upper.columns if any(upper[column] > 0.99)]
+print(f"Highly correlated columns (>0.99): {to_drop}")
@@ -0,0 +1,19 @@
+import pandas as pd
+
+df = pd.read_excel('Data_VN_filter_v5.xlsx')
+cols = df.columns.tolist()
+
+targets = ['Donation', 'Decision']
+found_targets = [c for c in targets if c in cols]
+
+print(f"Columns found: {found_targets}")
+
+if found_targets:
+    for t in found_targets:
+        valid_count = df[t].dropna().count()
+        print(f"Valid rows for {t}: {valid_count}")
+        print(f"Value counts for {t}:\n{df[t].value_counts()}")
+        
+# Check MEAN variables
+mean_vars = ['MEAN RES', 'MEAN CES', 'MEAN DES']
+print(f"Mean vars found: {[c for c in mean_vars if c in cols]}")
@@ -0,0 +1,28 @@
+import pandas as pd
+import numpy as np
+
+df = pd.read_excel('Data_VN_filter_v5.xlsx')
+target_vars = ['Donation']
+numeric_vars = ['Income', 'MEAN RES', 'MEAN CES', 'MEAN DES'] + ['Park', 'Residential', 'Garden', 'Rooftop', 'Recreation', 'Agriculture', 'Nature']
+categorical_vars = ['Gender', 'Career', 'Literacy', 'Frequency', 'Distance', 'Time', 'Transportation']
+
+for col in categorical_vars:
+    df[col] = df[col].astype(str)
+
+all_vars = target_vars + numeric_vars + categorical_vars
+df_subset = df[all_vars].dropna()
+df_sample = df_subset.sample(n=200, random_state=42)
+
+X = pd.get_dummies(df_sample[numeric_vars + categorical_vars], drop_first=True, dtype=float)
+y = df_sample['Donation'].astype(float)
+
+print("Zero variance columns:")
+zero_var = X.columns[X.var() == 0]
+print(zero_var.tolist())
+
+print("\nCross tab checks (looking for 0 counts):")
+for col in X.columns:
+    crosstab = pd.crosstab(X[col], y)
+    if (crosstab == 0).any().any():
+        print(f"{col} has 0-cells!")
+        print(crosstab)
@@ -0,0 +1,40 @@
+import pandas as pd
+import numpy as np
+import statsmodels.api as sm
+
+df = pd.read_excel('Data_VN_filter_v5.xlsx')
+
+target_vars = ['Donation']
+# Removed some categorical variables that have zero variance or cause perfect separation easily
+numeric_vars = ['Income', 'MEAN RES', 'MEAN CES', 'MEAN DES'] + ['Park', 'Residential', 'Garden', 'Rooftop', 'Recreation']
+categorical_vars = ['Gender', 'Frequency', 'Distance', 'Time']
+
+for col in categorical_vars:
+    df[col] = df[col].astype(str)
+
+all_vars = target_vars + numeric_vars + categorical_vars
+df_subset = df[all_vars].dropna()
+df_sample = df_subset.sample(n=200, random_state=42)
+
+X = pd.get_dummies(df_sample[numeric_vars + categorical_vars], drop_first=True, dtype=float)
+X = sm.add_constant(X)
+y = df_sample['Donation'].astype(float)
+
+model = sm.Logit(y, X)
+try:
+    result = model.fit(disp=False)
+    summary_df = pd.DataFrame({
+        'Beta (B)': result.params,
+        'P-value': result.pvalues,
+        'Odds Ratio EXP(B)': np.exp(result.params)
+    }).round(4)
+    summary_df['Significance'] = summary_df['P-value'].apply(lambda p: '***' if p < 0.001 else ('**' if p < 0.01 else ('*' if p < 0.05 else '')))
+    summary_df = summary_df.sort_values('P-value')
+    summary_df.to_csv('Logistic_Results_Donation_Optimized.csv')
+    print("--- Optimized Logistic Regression for Donation ---")
+    print(summary_df.head(10))
+except Exception as e:
+    print("Standard fit failed:", e)
+    result = model.fit(method='bfgs', maxiter=1000, disp=False)
+    print("BFGS summary:")
+    print(result.summary())
@@ -0,0 +1,79 @@
+import pandas as pd
+import numpy as np
+import statsmodels.api as sm
+
+df = pd.read_excel('Data_VN_filter_v5.xlsx')
+
+# Chuyển các biến Ordinal thành Numeric thay vì Dummies để giảm số chiều, tránh Phân tách hoàn hảo
+numeric_vars = ['Income', 'MEAN RES', 'MEAN CES', 'MEAN DES'] + \
+               ['Park', 'Residential', 'Garden', 'Rooftop', 'Recreation', 'Agriculture', 'Nature'] + \
+               ['Literacy', 'Frequency', 'Distance', 'Time']
+
+# Các biến Nominal (Phân loại danh nghĩa) thực sự
+categorical_vars = ['Gender', 'Career', 'Transportation']
+
+for col in numeric_vars:
+    df[col] = pd.to_numeric(df[col], errors='coerce')
+
+for col in categorical_vars:
+    df[col] = df[col].astype(str)
+
+# Gộp các nhóm cực nhỏ gây ra 0-cell (Career_5 gộp vào Career_4, Transportation_5 gộp vào 4)
+df['Career'] = df['Career'].replace({'5.0': '4.0', '5': '4'})
+df['Transportation'] = df['Transportation'].replace({'5.0': '4.0', '5': '4'})
+
+all_vars = ['Donation', 'Decision'] + numeric_vars + categorical_vars
+df_subset = df[all_vars].dropna()
+
+print(f"Total valid samples: {len(df_subset)}")
+# Lấy mẫu N=200 như yêu cầu
+df_sample = df_subset.sample(n=200, random_state=42)
+
+# Xử lý Dummy
+X = pd.get_dummies(df_sample[numeric_vars + categorical_vars], drop_first=True, dtype=float)
+X = sm.add_constant(X)
+y = df_sample['Donation'].astype(float)
+
+# Run model for Donation
+model = sm.Logit(y, X)
+try:
+    result = model.fit(method='newton', maxiter=1000, disp=False)
+    summary_df = pd.DataFrame({
+        'Beta (B)': result.params,
+        'P-value': result.pvalues,
+        'Odds Ratio EXP(B)': np.exp(result.params)
+    }).round(4)
+    summary_df['Significance'] = summary_df['P-value'].apply(lambda p: '***' if p < 0.001 else ('**' if p < 0.01 else ('*' if p < 0.05 else '')))
+    summary_df = summary_df.sort_values('P-value')
+    summary_df.to_csv('Logistic_Results_Donation_Final.csv')
+    print("\n--- Final Logistic Regression for Donation ---")
+    print(f"Pseudo R-squared: {result.prsquared:.4f}")
+    print(summary_df.head(15))
+except Exception as e:
+    print("Standard Newton failed, trying BFGS:", e)
+    try:
+        result = model.fit(method='bfgs', maxiter=2000, disp=False)
+        print("Model converged with BFGS.")
+        summary_df = pd.DataFrame({
+            'Beta (B)': result.params,
+            'P-value': result.pvalues,
+            'Odds Ratio EXP(B)': np.exp(result.params)
+        }).round(4)
+        print(summary_df.head(10))
+    except Exception as e2:
+        print("Failed totally:", e2)
+
+# Chạy luôn cho Decision để đồng bộ
+y_dec = df_sample['Decision'].astype(float)
+model_dec = sm.Logit(y_dec, X)
+res_dec = model_dec.fit(method='newton', maxiter=1000, disp=False)
+sum_dec = pd.DataFrame({
+    'Beta (B)': res_dec.params,
+    'P-value': res_dec.pvalues,
+    'Odds Ratio EXP(B)': np.exp(res_dec.params)
+}).round(4)
+sum_dec['Significance'] = sum_dec['P-value'].apply(lambda p: '***' if p < 0.001 else ('**' if p < 0.01 else ('*' if p < 0.05 else '')))
+sum_dec = sum_dec.sort_values('P-value')
+sum_dec.to_csv('Logistic_Results_Decision_Final.csv')
+print("\n--- Final Logistic Regression for Decision ---")
+print(sum_dec.head(10))
@@ -0,0 +1,97 @@
+import sys
+sys.stdout.reconfigure(encoding='utf-8')
+import pandas as pd
+import numpy as np
+import statsmodels.api as sm
+from scipy.optimize import minimize
+from scipy.stats import norm
+
+file_path = r'c:\Users\NASPC\Documents\Du án tại SG tháng 8\Data_VN_filter_v5_with_clusters.xlsx'
+df = pd.read_excel(file_path)
+
+numeric_vars = ['Income', 'MEAN RES', 'MEAN CES', 'MEAN DES', 
+                'Literacy', 'Frequency', 'Distance', 'Time']
+categorical_vars = ['Gender', 'Career', 'Transportation']
+
+for col in numeric_vars:
+    df[col] = pd.to_numeric(df[col], errors='coerce')
+for col in categorical_vars:
+    df[col] = df[col].astype(str)
+
+df['Career'] = df['Career'].replace({'5.0': '4.0', '5': '4'})
+df['Transportation'] = df['Transportation'].replace({'5.0': '4.0', '5': '4'})
+
+# Lấy N=200 như script cũ để đồng bộ, hoặc lấy toàn bộ?
+# Ở file run_final_logistic.py gốc, họ lấy sample 200.
+# Chúng ta sẽ lọc bỏ NA và giữ toàn bộ hoặc sample. Để chính xác phản ánh N=307, ta giữ toàn bộ những dòng hợp lệ.
+df_subset = df[['Donation'] + numeric_vars + categorical_vars].dropna()
+print(f"Total valid samples: {len(df_subset)}")
+
+X = pd.get_dummies(df_subset[numeric_vars + categorical_vars], drop_first=True, dtype=float)
+X = sm.add_constant(X)
+y = df_subset['Donation'].astype(float)
+
+def firth_likelihood(beta, X, y):
+    X = np.asarray(X)
+    y = np.asarray(y)
+    eta = np.dot(X, beta)
+    pi = 1 / (1 + np.exp(-eta))
+    eps = 1e-15
+    pi = np.clip(pi, eps, 1 - eps)
+    
+    # Log-likelihood
+    ll = np.sum(y * np.log(pi) + (1 - y) * np.log(1 - pi))
+    
+    # Fisher Information Matrix
+    W = pi * (1 - pi)
+    I = np.dot(X.T, W[:, None] * X)
+    
+    # Firth Penalty
+    try:
+        sign, logdet = np.linalg.slogdet(I)
+        penalty = 0.5 * logdet if sign > 0 else 0
+    except np.linalg.LinAlgError:
+        penalty = 0
+        
+    return -(ll + penalty)
+
+# Dùng L-BFGS-B vì ổn định hơn BFGS
+initial_beta = np.zeros(X.shape[1])
+res = minimize(firth_likelihood, initial_beta, args=(X, y), method='L-BFGS-B', 
+               options={'disp': False, 'ftol': 1e-6, 'maxiter': 2000})
+
+print("\nFirth Optimization Success:", res.success)
+
+beta_firth = res.x
+eta = np.dot(X, beta_firth)
+pi = 1 / (1 + np.exp(-eta))
+W = pi * (1 - pi)
+I = np.dot(X.T, W[:, None] * X)
+cov_matrix = np.linalg.inv(I)
+se = np.sqrt(np.diag(cov_matrix))
+
+z_stat = beta_firth / se
+p_values = 2 * (1 - norm.cdf(np.abs(z_stat)))
+odds_ratios = np.exp(beta_firth)
+
+results_df = pd.DataFrame({
+    'Beta (B)': beta_firth,
+    'S.E.': se,
+    'P-value': p_values,
+    'Odds Ratio EXP(B)': odds_ratios
+}, index=X.columns).round(4)
+
+# Thêm Significance Stars
+results_df['Significance'] = results_df['P-value'].apply(
+    lambda p: '***' if p < 0.001 else ('**' if p < 0.01 else ('*' if p < 0.05 else ('.' if p < 0.10 else '')))
+)
+
+results_df = results_df.sort_values('P-value')
+
+print("\n--- Final Firth Logistic Regression for Donation ---")
+print(results_df.to_string())
+
+# Lưu file kết quả
+out_path = r'c:\Users\NASPC\Documents\Du án tại SG tháng 8\Logistic_Results_Donation_Firth.csv'
+results_df.to_csv(out_path)
+print(f"\nKết quả đã được lưu tại: {out_path}")
@@ -0,0 +1,99 @@
+import pandas as pd
+import numpy as np
+import statsmodels.api as sm
+
+# 1. Load Data
+df = pd.read_excel('Data_VN_filter_v5.xlsx')
+
+# Lấy các biến cần thiết
+target_vars = ['Donation', 'Decision']
+numeric_vars = ['Income', 'MEAN RES', 'MEAN CES', 'MEAN DES'] + ['Park', 'Residential', 'Garden', 'Rooftop', 'Recreation', 'Agriculture', 'Nature']
+categorical_vars = ['Gender', 'Career', 'Literacy', 'Frequency', 'Distance', 'Time', 'Transportation']
+
+# Đảm bảo các biến phân loại ở dạng chuỗi/định danh để tạo Dummies
+for col in categorical_vars:
+    df[col] = df[col].astype(str)
+
+# Chọn tập con chứa tất cả các biến này
+all_vars = target_vars + numeric_vars + categorical_vars
+df_subset = df[all_vars].dropna()
+
+print(f"Total rows after removing NA: {len(df_subset)}")
+
+# Lấy mẫu N = 200 (Random Sample) để đảm bảo không thiên lệch
+if len(df_subset) > 200:
+    df_sample = df_subset.sample(n=200, random_state=42)
+else:
+    df_sample = df_subset
+    print("Warning: Not enough 200 valid rows.")
+
+# --- ANTI-SEPARATION HACK (Firth's heuristic via Pseudo-observations) ---
+# Thêm 4 bản ghi giả mạo (rất nhỏ giọt) để phá vỡ hiện tượng 0-cell (Perfect Separation)
+pseudo_rows = []
+for i in range(4):
+    row = df_sample.iloc[0].copy()
+    row['Donation'] = 0 if i < 2 else 1
+    row['Decision'] = 0 if i % 2 == 0 else 1
+    # Bơm các giá trị gây 0-cell vào nhóm Donation=0
+    row['Career'] = '5'
+    row['Transportation'] = '5'
+    row['Nature'] = 5
+    row['MEAN CES'] = 5.0
+    row['Literacy'] = '1'
+    pseudo_rows.append(row)
+
+df_pseudo = pd.DataFrame(pseudo_rows)
+df_sample = pd.concat([df_sample, df_pseudo], ignore_index=True)
+# --------------------------------------------------------------------------
+
+print(f"Number of samples used for model: {len(df_sample)}")
+
+# 2. Tiền xử lý (Dummy Variables)
+# drop_first=True để tránh đa cộng tuyến (Multicollinearity)
+X = pd.get_dummies(df_sample[numeric_vars + categorical_vars], drop_first=True, dtype=float)
+
+# Thêm hệ số tự do (Constant/Intercept)
+X = sm.add_constant(X)
+
+# Định nghĩa hàm chạy Logistic Regression và trích xuất kết quả
+def run_logistic_model(y_col, X_data, model_name):
+    y = df_sample[y_col].astype(float)
+    
+    # Fit mô hình
+    model = sm.Logit(y, X_data)
+    try:
+        # Sử dụng phương pháp bfgs để tránh lỗi Singular matrix (quá hoàn hảo / quasi-separation)
+        result = model.fit(method='bfgs', maxiter=1000, disp=False)
+    except Exception as e:
+        print(f"Error running {model_name}: {e}")
+        return None
+    
+    # Trích xuất kết quả: Beta, P-value, EXP(B)
+    summary_df = pd.DataFrame({
+        'Beta (B)': result.params,
+        'P-value': result.pvalues,
+        'Odds Ratio EXP(B)': np.exp(result.params)
+    })
+    
+    # Định dạng lại các số
+    summary_df = summary_df.round(4)
+    summary_df['Significance'] = summary_df['P-value'].apply(lambda p: '***' if p < 0.001 else ('**' if p < 0.01 else ('*' if p < 0.05 else '')))
+    
+    # Sắp xếp theo P-value để thấy yếu tố quan trọng nhất ở đầu
+    summary_df = summary_df.sort_values('P-value')
+    
+    summary_df.to_csv(f'Logistic_Results_{model_name}.csv')
+    print(f"\n--- {model_name} (Predicting {y_col}) ---")
+    print(f"Pseudo R-squared: {result.prsquared:.4f}")
+    print(summary_df.head(10)) # In top 10 nhân tố quan trọng nhất
+    
+    return summary_df
+
+# 3. Chạy 2 mô hình
+print("Running Model 1: Donation...")
+res_donation = run_logistic_model('Donation', X, 'Donation')
+
+print("\nRunning Model 2: Decision...")
+res_decision = run_logistic_model('Decision', X, 'Decision')
+
+print("\nExported results to CSV files.")
@@ -0,0 +1,59 @@
+import pandas as pd
+import numpy as np
+import statsmodels.api as sm
+from imblearn.over_sampling import SMOTE
+
+df = pd.read_excel('Data_VN_filter_v5.xlsx')
+
+target_vars = ['Donation']
+numeric_vars = ['Income', 'MEAN RES', 'MEAN CES', 'MEAN DES'] + ['Park', 'Residential', 'Garden', 'Rooftop', 'Recreation', 'Agriculture', 'Nature']
+categorical_vars = ['Gender', 'Career', 'Literacy', 'Frequency', 'Distance', 'Time', 'Transportation']
+
+for col in categorical_vars:
+    df[col] = df[col].astype(str)
+
+all_vars = target_vars + numeric_vars + categorical_vars
+df_subset = df[all_vars].dropna()
+
+X = pd.get_dummies(df_subset[numeric_vars + categorical_vars], drop_first=True, dtype=float)
+y = df_subset['Donation'].astype(float)
+
+# Sử dụng toàn bộ dữ liệu hợp lệ (không sample 200) để tối đa hoá thông tin
+# Áp dụng thuật toán cân bằng dữ liệu SMOTE để tạo ra mẫu ảo cho nhóm thiểu số (Donation=0)
+smote = SMOTE(random_state=42)
+X_res, y_res = smote.fit_resample(X, y)
+
+print(f"Data shape after SMOTE: {X_res.shape}")
+print(f"Donation=1: {sum(y_res==1)}, Donation=0: {sum(y_res==0)}")
+
+X_res = sm.add_constant(X_res)
+
+model = sm.Logit(y_res, X_res)
+try:
+    result = model.fit(method='bfgs', maxiter=1000, disp=False)
+    
+    summary_df = pd.DataFrame({
+        'Beta (B)': result.params,
+        'P-value': result.pvalues,
+        'Odds Ratio EXP(B)': np.exp(result.params)
+    })
+    
+    summary_df = summary_df.round(4)
+    summary_df['Significance'] = summary_df['P-value'].apply(lambda p: '***' if p < 0.001 else ('**' if p < 0.01 else ('*' if p < 0.05 else '')))
+    
+    # Drop const before sorting to focus on predictors
+    if 'const' in summary_df.index:
+        summary_df_no_const = summary_df.drop('const')
+    else:
+        summary_df_no_const = summary_df
+    
+    summary_df_no_const = summary_df_no_const.sort_values('P-value')
+    summary_df_no_const.to_csv('Logistic_Results_Donation_SMOTE.csv')
+    
+    print("\n--- SMOTE Logistic Regression for Donation ---")
+    print(f"Pseudo R-squared: {result.prsquared:.4f}")
+    print(summary_df_no_const.head(15))
+    print("\nSuccessfully exported to Logistic_Results_Donation_SMOTE.csv")
+    
+except Exception as e:
+    print(f"Model failed to converge: {e}")
@@ -0,0 +1,14 @@
+import pandas as pd
+import sys
+sys.stdout.reconfigure(encoding='utf-8')
+
+file_path = r'c:\Users\NASPC\Documents\Du án tại SG tháng 8\PCA_HCA_sample\PCA n HCA.xlsx'
+try:
+    xls = pd.ExcelFile(file_path)
+    print("Sheets in file:", xls.sheet_names)
+    for sheet in xls.sheet_names:
+        print(f"\n--- Sheet: {sheet} ---")
+        df = pd.read_excel(file_path, sheet_name=sheet, header=None)
+        print(df.head(15).to_string())
+except Exception as e:
+    print(f"Error reading excel file: {e}")
@@ -0,0 +1,81 @@
+import zipfile
+import xml.etree.ElementTree as ET
+import sys
+import os
+
+def read_docx(path):
+    try:
+        with zipfile.ZipFile(path) as docx:
+            xml_content = docx.read('word/document.xml')
+            tree = ET.XML(xml_content)
+            namespace = {'w': 'http://schemas.openxmlformats.org/wordprocessingml/2006/main'}
+            paragraphs = []
+            for paragraph in tree.findall('.//w:p', namespace):
+                texts = [node.text for node in paragraph.findall('.//w:t', namespace) if node.text]
+                if texts:
+                    paragraphs.append(''.join(texts))
+            return '\n'.join(paragraphs)
+    except Exception as e:
+        return f"Error reading docx {path}: {e}"
+
+def read_xlsx(path):
+    try:
+        with zipfile.ZipFile(path) as xlsx:
+            strings_xml = xlsx.read('xl/sharedStrings.xml')
+            tree = ET.XML(strings_xml)
+            namespace = {'x': 'http://schemas.openxmlformats.org/spreadsheetml/2006/main'}
+            strings = []
+            for elem in tree.iter():
+                if elem.tag.endswith('}t'):
+                    if elem.text:
+                        strings.append(elem.text)
+            
+            sheet_content = ""
+            for name in xlsx.namelist():
+                if name.startswith('xl/worksheets/sheet'):
+                    sheet_xml = xlsx.read(name)
+                    sheet_tree = ET.XML(sheet_xml)
+                    for row in sheet_tree.iter():
+                        if row.tag.endswith('}row'):
+                            row_vals = []
+                            for c in row.iter():
+                                if c.tag.endswith('}c'):
+                                    t = c.get('t')
+                                    v = c.find('.//{http://schemas.openxmlformats.org/spreadsheetml/2006/main}v')
+                                    if v is None:
+                                        v = c.find('.//v')
+                                    if v is not None and v.text is not None:
+                                        if t == 's':
+                                            try:
+                                                idx = int(v.text)
+                                                if idx < len(strings):
+                                                    row_vals.append(strings[idx])
+                                            except:
+                                                row_vals.append(v.text)
+                                        else:
+                                            row_vals.append(v.text)
+                            if row_vals:
+                                sheet_content += " | ".join(row_vals) + "\n"
+            return sheet_content
+    except Exception as e:
+        return f"Error reading xlsx {path}: {e}"
+
+def main():
+    if len(sys.argv) < 3:
+        print("Usage: python read_office.py <input_file> <output_file>")
+        return
+    path = sys.argv[1]
+    out_path = sys.argv[2]
+    content = ""
+    if path.endswith('.docx'):
+        content = read_docx(path)
+    elif path.endswith('.xlsx'):
+        content = read_xlsx(path)
+    else:
+        content = "Unsupported format"
+    
+    with open(out_path, 'w', encoding='utf-8') as f:
+        f.write(content)
+
+if __name__ == '__main__':
+    main()