Readme

analysis_results/analysis_report.html

@@ -32,71 +32,71 @@
 
                 <h2>User Profile Analysis</h2>
                 <div class="figure">
-                    <img src="user_analysis/gender_distribution.png" alt="用户性别分布">
+                    <img src="user_analysis/gender_distribution.png" alt="User Gender Distribution">
                     <p class="caption">User Gender Distribution</p>
                 </div>
 
                 <div class="figure">
-                    <img src="user_analysis/age_distribution.png" alt="用户年龄分布">
+                    <img src="user_analysis/age_distribution.png" alt="User Age Distribution">
                     <p class="caption">User Age Distribution</p>
                 </div>
 
                 <div class="figure">
-                    <img src="user_analysis/occupation_distribution.png" alt="用户职业分布">
+                    <img src="user_analysis/occupation_distribution.png" alt="User Occupation Distribution">
                     <p class="caption">User Occupation Distribution</p>
                 </div>
 
                 <h2>Movie Distribution Analysis</h2>
                 <div class="figure">
-                    <img src="movie_analysis/genre_distribution.png" alt="电影类型分布">
+                    <img src="movie_analysis/genre_distribution.png" alt="Movie Genre Distribution">
                     <p class="caption">Movie Genre Distribution</p>
                 </div>
 
                 <div class="figure">
-                    <img src="movie_analysis/year_distribution.png" alt="电影发行年份分布">
+                    <img src="movie_analysis/year_distribution.png" alt="Movie Release Year Distribution">
                     <p class="caption">Movie Release Year Distribution</p>
                 </div>
 
                 <div class="figure">
-                    <img src="movie_analysis/most_rated_movies.png" alt="评分数量最多的电影">
+                    <img src="movie_analysis/most_rated_movies.png" alt="Top 20 Most Rated Movies">
                     <p class="caption">Top 20 Most Rated Movies</p>
                 </div>
 
                 <h2>Rating Distribution Analysis</h2>
                 <div class="figure">
-                    <img src="rating_analysis/rating_distribution.png" alt="评分分布">
+                    <img src="rating_analysis/rating_distribution.png" alt="Rating Distribution">
                     <p class="caption">Rating Distribution</p>
                 </div>
 
                 <div class="figure">
-                    <img src="rating_analysis/genre_avg_ratings.png" alt="各类型电影的平均评分">
+                    <img src="rating_analysis/genre_avg_ratings.png" alt="Average Rating by Movie Genre">
                     <p class="caption">Average Rating by Movie Genre</p>
                 </div>
 
                 <div class="figure">
-                    <img src="rating_analysis/top_rated_movies.png" alt="评分最高的电影">
+                    <img src="rating_analysis/top_rated_movies.png" alt="Top 20 Highest Rated Movies">
                     <p class="caption">Top 20 Highest Rated Movies (min. 100 ratings)</p>
                 </div>
 
                 <h2>User Characteristics and Movie Preferences</h2>
                 <div class="figure">
-                    <img src="preference_analysis/gender_genre_heatmap.png" alt="不同性别的电影类型偏好">
+                    <img src="preference_analysis/gender_genre_heatmap.png" alt="Movie Genre Preferences by Gender">
                     <p class="caption">Movie Genre Preferences by Gender</p>
                 </div>
 
                 <div class="figure">
-                    <img src="preference_analysis/age_genre_heatmap.png" alt="不同年龄段的电影类型偏好">
+                    <img src="preference_analysis/age_genre_heatmap.png" alt="Movie Genre Preferences by Age Group">
                     <p class="caption">Movie Genre Preferences by Age Group</p>
                 </div>
 
                 <div class="figure">
-                    <img src="preference_analysis/age_year_heatmap.png" alt="不同年龄段对不同年代电影的偏好">
+                    <img src="preference_analysis/age_year_heatmap.png" alt="Preferences for Movies by Decade Across Age Groups">
                     <p class="caption">Preferences for Movies by Decade Across Age Groups</p>
                 </div>
 
                 <div class="figure">
-                    <img src="preference_analysis/gender_avg_rating.png" alt="性别与平均评分的关系">
+                    <img src="preference_analysis/gender_avg_rating.png" alt="Average Rating by Gender">
-                    <p class="caption">Relationship Between Gender and Average Rating</p>
+                    <p class="caption">Average Rating by Gender</p>
                 </div>
 
                 <h2>Conclusions and Insights</h2>

analyzer.py

@@ -25,7 +25,6 @@ import time
 import matplotlib as mpl
 import platform
 import tempfile
-import urllib.request
 import re
 import sys
 
@@ -38,31 +37,40 @@ np.random.seed(42)
 # 自定义调色板
 custom_colors = ['#FF9A76', '#67B7D1', '#A8D5BA', '#D8A47F', '#957DAD', '#7B506F', '#9AACB8']
 
-# 全局变量控制是否使用中文
+# 强制使用英文，避免中文显示问题
-USE_CHINESE = False  # 默认不使用中文
+USE_ENGLISH = True  # 设置为True使用英文，False使用中文（如果支持）
 
 
-def download_noto_font():
+# 配置matplotlib字体和编码
-    """下载谷歌Noto Sans中文字体"""
+def configure_matplotlib_fonts():
-    temp_dir = os.path.join(tempfile.gettempdir(), 'movielens_fonts')
+    """配置matplotlib使用合适的字体显示中文"""
-    os.makedirs(temp_dir, exist_ok=True)
-    font_path = os.path.join(temp_dir, 'NotoSansSC-Regular.otf')
 
-    # 如果字体已存在，直接返回路径
+    # 根据当前环境使用不同的默认字体
-    if os.path.exists(font_path):
+    system = platform.system()
-        print(f"使用已下载的Noto Sans字体: {font_path}")
-        return font_path
 
-    # 下载字体
+    if system == 'Windows':
-    font_url = "/"
+        # Windows环境
-    try:
+        plt.rcParams['font.sans-serif'] = ['SimHei', 'Microsoft YaHei', 'Arial']
-        print(f"正在下载中文字体: {font_url}")
+    elif system == 'Darwin':
-        urllib.request.urlretrieve(font_url, font_path)
+        # macOS环境
-        print(f"字体下载成功: {font_path}")
+        plt.rcParams['font.sans-serif'] = ['Arial Unicode MS', 'PingFang SC', 'Heiti SC']
-        return font_path
+    else:
-    except Exception as e:
+        # Linux环境或其他
-        print(f"字体下载失败: {e}")
+        plt.rcParams['font.sans-serif'] = ['DejaVu Sans', 'WenQuanYi Micro Hei', 'Noto Sans CJK SC']
-        return None
+
+    # 通用设置
+    plt.rcParams['axes.unicode_minus'] = False  # 正确显示负号
+    plt.rcParams['font.family'] = 'sans-serif'
+
+    print(f"字体配置完成，当前系统: {system}")
+
+
+# 应用字体配置
+configure_matplotlib_fonts()
+
+# 设置图表样式
+sns.set_style("whitegrid")
+plt.style.use('seaborn-v0_8-pastel')
 
 
 def sanitize_filename(filename):
@@ -71,55 +79,6 @@ def sanitize_filename(filename):
     return re.sub(illegal_chars, '_', filename)
 
 
-def setup_chinese_display():
-    """配置中文显示环境"""
-    global USE_CHINESE
-
-    # 默认使用英文
-    USE_CHINESE = False
-
-    # 尝试设置中文字体
-    font_path = download_noto_font()
-    if font_path and os.path.exists(font_path):
-        try:
-            from matplotlib import font_manager
-            # 添加字体文件
-            font_manager.fontManager.addfont(font_path)
-            # 使用字体
-            plt.rcParams['font.family'] = ['sans-serif']
-            plt.rcParams['font.sans-serif'] = ['Noto Sans SC'] + plt.rcParams['font.sans-serif']
-            plt.rcParams['axes.unicode_minus'] = False
-            print("成功配置中文字体")
-
-            # 测试中文显示
-            plt.figure(figsize=(2, 1))
-            plt.text(0.5, 0.5, '测试中文', fontsize=12, ha='center')
-            plt.axis('off')
-            test_path = os.path.join(tempfile.gettempdir(), 'chinese_test.png')
-            plt.savefig(test_path)
-            plt.close()
-            print(f"中文测试图保存到: {test_path}")
-
-            USE_CHINESE = True
-            return True
-        except Exception as e:
-            print(f"中文字体配置失败: {e}")
-            USE_CHINESE = False
-            return False
-    else:
-        print("未能获取中文字体，将使用英文")
-        USE_CHINESE = False
-        return False
-
-
-# 配置中文显示
-setup_chinese_display()
-
-# 设置图表样式
-sns.set_style("whitegrid")
-plt.style.use('seaborn-v0_8-pastel')
-
-
 class MovieLensDataAnalyzer:
     """MovieLens数据集分析工具"""
 
@@ -131,36 +90,36 @@ class MovieLensDataAnalyzer:
 
         # 特征映射字典
         self.age_mapping = {
-            1: "18岁以下" if USE_CHINESE else "Under 18",
+            1: "Under 18" if USE_ENGLISH else "18岁以下",
             18: "18-24",
             25: "25-34",
             35: "35-44",
             45: "45-49",
             50: "50-55",
-            56: "56岁以上" if USE_CHINESE else "56+"
+            56: "56+" if USE_ENGLISH else "56岁以上"
         }
 
         self.occupation_mapping = {
-            0: "其他" if USE_CHINESE else "Other",
+            0: "Other" if USE_ENGLISH else "其他",
-            1: "学术/教育工作者" if USE_CHINESE else "Academic/Educator",
+            1: "Academic/Educator" if USE_ENGLISH else "学术/教育工作者",
-            2: "艺术家" if USE_CHINESE else "Artist",
+            2: "Artist" if USE_ENGLISH else "艺术家",
-            3: "文员/管理人员" if USE_CHINESE else "Clerical/Admin",
+            3: "Clerical/Admin" if USE_ENGLISH else "文员/管理人员",
-            4: "大学生/研究生" if USE_CHINESE else "College/Grad Student",
+            4: "College/Grad Student" if USE_ENGLISH else "大学生/研究生",
-            5: "客户服务人员" if USE_CHINESE else "Customer Service",
+            5: "Customer Service" if USE_ENGLISH else "客户服务人员",
-            6: "医疗/保健人员" if USE_CHINESE else "Doctor/Health Care",
+            6: "Doctor/Health Care" if USE_ENGLISH else "医疗/保健人员",
-            7: "行政/事务人员" if USE_CHINESE else "Executive/Managerial",
+            7: "Executive/Managerial" if USE_ENGLISH else "行政/事务人员",
-            8: "家庭主妇" if USE_CHINESE else "Homemaker",
+            8: "Homemaker" if USE_ENGLISH else "家庭主妇",
-            9: "K-12学生" if USE_CHINESE else "K-12 Student",
+            9: "K-12 Student" if USE_ENGLISH else "K-12学生",
-            10: "律师" if USE_CHINESE else "Lawyer",
+            10: "Lawyer" if USE_ENGLISH else "律师",
-            11: "程序员" if USE_CHINESE else "Programmer",
+            11: "Programmer" if USE_ENGLISH else "程序员",
-            12: "退休人员" if USE_CHINESE else "Retired",
+            12: "Retired" if USE_ENGLISH else "退休人员",
-            13: "销售/营销人员" if USE_CHINESE else "Sales/Marketing",
+            13: "Sales/Marketing" if USE_ENGLISH else "销售/营销人员",
-            14: "科学家" if USE_CHINESE else "Scientist",
+            14: "Scientist" if USE_ENGLISH else "科学家",
-            15: "个体户" if USE_CHINESE else "Self-employed",
+            15: "Self-employed" if USE_ENGLISH else "个体户",
-            16: "技术人员/工程师" if USE_CHINESE else "Technician/Engineer",
+            16: "Technician/Engineer" if USE_ENGLISH else "技术人员/工程师",
-            17: "手工艺人" if USE_CHINESE else "Tradesman/Craftsman",
+            17: "Tradesman/Craftsman" if USE_ENGLISH else "手工艺人",
-            18: "失业人员" if USE_CHINESE else "Unemployed",
+            18: "Unemployed" if USE_ENGLISH else "失业人员",
-            19: "作家" if USE_CHINESE else "Writer"
+            19: "Writer" if USE_ENGLISH else "作家"
         }
 
         # 创建输出目录（如果不存在）
@@ -296,13 +255,13 @@ class MovieLensDataAnalyzer:
 
         # 1. 用户性别分布
         gender_counts = self.users_df['gender'].value_counts()
-        gender_labels = {'M': '男性' if USE_CHINESE else 'Male',
+        gender_labels = {'M': 'Male' if USE_ENGLISH else '男性',
-                         'F': '女性' if USE_CHINESE else 'Female'}
+                         'F': 'Female' if USE_ENGLISH else '女性'}
 
         plt.figure(figsize=(10, 6))
         ax = gender_counts.plot(kind='pie', autopct='%1.1f%%', startangle=90,
                                 colors=[custom_colors[0], custom_colors[1]])
-        plt.title('用户性别分布' if USE_CHINESE else 'User Gender Distribution')
+        plt.title('User Gender Distribution' if USE_ENGLISH else '用户性别分布')
         plt.ylabel('')
 
         # 修改饼图标签
@@ -318,9 +277,9 @@ class MovieLensDataAnalyzer:
 
         plt.figure(figsize=(12, 6))
         sns.barplot(x=age_counts.index, y=age_counts.values, palette=custom_colors)
-        plt.title('用户年龄分布' if USE_CHINESE else 'User Age Distribution')
+        plt.title('User Age Distribution' if USE_ENGLISH else '用户年龄分布')
-        plt.xlabel('年龄段' if USE_CHINESE else 'Age Group')
+        plt.xlabel('Age Group' if USE_ENGLISH else '年龄段')
-        plt.ylabel('用户数量' if USE_CHINESE else 'Number of Users')
+        plt.ylabel('Number of Users' if USE_ENGLISH else '用户数量')
         plt.xticks(rotation=45)
         plt.tight_layout()
         plt.savefig(os.path.join(user_analysis_dir, 'age_distribution.png'), bbox_inches='tight', dpi=100)
@@ -331,9 +290,9 @@ class MovieLensDataAnalyzer:
 
         plt.figure(figsize=(14, 8))
         sns.barplot(x=occupation_counts.values, y=occupation_counts.index, palette=custom_colors)
-        plt.title('用户职业分布' if USE_CHINESE else 'User Occupation Distribution')
+        plt.title('User Occupation Distribution' if USE_ENGLISH else '用户职业分布')
-        plt.xlabel('用户数量' if USE_CHINESE else 'Number of Users')
+        plt.xlabel('Number of Users' if USE_ENGLISH else '用户数量')
-        plt.ylabel('职业' if USE_CHINESE else 'Occupation')
+        plt.ylabel('Occupation' if USE_ENGLISH else '职业')
         plt.tight_layout()
         plt.savefig(os.path.join(user_analysis_dir, 'occupation_distribution.png'), bbox_inches='tight', dpi=100)
         plt.close()
@@ -343,10 +302,10 @@ class MovieLensDataAnalyzer:
 
         plt.figure(figsize=(14, 8))
         sns.barplot(x=region_counts.values, y=region_counts.index, palette=custom_colors)
-        title_text = '用户地域分布 (前20个邮编区域)' if USE_CHINESE else 'User Regional Distribution (Top 20 ZIP Codes)'
+        title_text = 'User Regional Distribution (Top 20 ZIP Codes)' if USE_ENGLISH else '用户地域分布 (前20个邮编区域)'
         plt.title(title_text)
-        plt.xlabel('用户数量' if USE_CHINESE else 'Number of Users')
+        plt.xlabel('Number of Users' if USE_ENGLISH else '用户数量')
-        plt.ylabel('邮编区域' if USE_CHINESE else 'ZIP Code Region')
+        plt.ylabel('ZIP Code Region' if USE_ENGLISH else '邮编区域')
         plt.tight_layout()
         plt.savefig(os.path.join(user_analysis_dir, 'region_distribution.png'), bbox_inches='tight', dpi=100)
         plt.close()
@@ -356,14 +315,16 @@ class MovieLensDataAnalyzer:
         gender_age_counts = self.users_df.groupby(['age_group', 'gender']).size().unstack()
 
         # 重命名列以使用本地化标签
-        if USE_CHINESE:
+        if not USE_ENGLISH:
             gender_age_counts.columns = [gender_labels[col] for col in gender_age_counts.columns]
+        else:
+            gender_age_counts.columns = ['Male', 'Female']  # 确保英文模式下也有正确的标签
 
         gender_age_counts.plot(kind='bar', stacked=True, color=custom_colors)
-        plt.title('用户性别和年龄组合分布' if USE_CHINESE else 'Gender and Age Distribution')
+        plt.title('Gender and Age Distribution' if USE_ENGLISH else '用户性别和年龄组合分布')
-        plt.xlabel('年龄段' if USE_CHINESE else 'Age Group')
+        plt.xlabel('Age Group' if USE_ENGLISH else '年龄段')
-        plt.ylabel('用户数量' if USE_CHINESE else 'Number of Users')
+        plt.ylabel('Number of Users' if USE_ENGLISH else '用户数量')
-        plt.legend(title='性别' if USE_CHINESE else 'Gender')
+        plt.legend(title='Gender' if USE_ENGLISH else '性别')
         plt.tight_layout()
         plt.savefig(os.path.join(user_analysis_dir, 'gender_age_distribution.png'), bbox_inches='tight', dpi=100)
         plt.close()
@@ -373,9 +334,9 @@ class MovieLensDataAnalyzer:
 
         plt.figure(figsize=(12, 6))
         sns.histplot(user_rating_counts, bins=30, kde=True, color=custom_colors[0])
-        plt.title('用户评分活跃度分布' if USE_CHINESE else 'User Rating Activity Distribution')
+        plt.title('User Rating Activity Distribution' if USE_ENGLISH else '用户评分活跃度分布')
-        plt.xlabel('每位用户的评分数量' if USE_CHINESE else 'Number of Ratings per User')
+        plt.xlabel('Number of Ratings per User' if USE_ENGLISH else '每位用户的评分数量')
-        plt.ylabel('用户数' if USE_CHINESE else 'Number of Users')
+        plt.ylabel('Number of Users' if USE_ENGLISH else '用户数')
         plt.tight_layout()
         plt.savefig(os.path.join(user_analysis_dir, 'rating_activity_distribution.png'), bbox_inches='tight', dpi=100)
         plt.close()
@@ -389,12 +350,11 @@ class MovieLensDataAnalyzer:
         ax = sns.boxplot(x='gender', y='rating_count', data=user_activity, palette=[custom_colors[0], custom_colors[1]])
 
         # 修改x轴标签为本地化文本
-        if USE_CHINESE:
+        ax.set_xticklabels(['Male', 'Female'])  # 始终使用英文标签确保显示正确
-            ax.set_xticklabels([gender_labels[tick.get_text()] for tick in ax.get_xticklabels()])
 
-        plt.title('不同性别的评分活跃度分布' if USE_CHINESE else 'Rating Activity by Gender')
+        plt.title('Rating Activity by Gender' if USE_ENGLISH else '不同性别的评分活跃度分布')
-        plt.xlabel('性别' if USE_CHINESE else 'Gender')
+        plt.xlabel('Gender' if USE_ENGLISH else '性别')
-        plt.ylabel('评分数量' if USE_CHINESE else 'Number of Ratings')
+        plt.ylabel('Number of Ratings' if USE_ENGLISH else '评分数量')
         plt.tight_layout()
         plt.savefig(os.path.join(user_analysis_dir, 'gender_activity.png'), bbox_inches='tight', dpi=100)
         plt.close()
@@ -402,9 +362,9 @@ class MovieLensDataAnalyzer:
         # 7.2 年龄段与评分活跃度
         plt.figure(figsize=(14, 6))
         sns.boxplot(x='age_group', y='rating_count', data=user_activity, palette=custom_colors)
-        plt.title('不同年龄段的评分活跃度分布' if USE_CHINESE else 'Rating Activity by Age Group')
+        plt.title('Rating Activity by Age Group' if USE_ENGLISH else '不同年龄段的评分活跃度分布')
-        plt.xlabel('年龄段' if USE_CHINESE else 'Age Group')
+        plt.xlabel('Age Group' if USE_ENGLISH else '年龄段')
-        plt.ylabel('评分数量' if USE_CHINESE else 'Number of Ratings')
+        plt.ylabel('Number of Ratings' if USE_ENGLISH else '评分数量')
         plt.xticks(rotation=45)
         plt.tight_layout()
         plt.savefig(os.path.join(user_analysis_dir, 'age_activity.png'), bbox_inches='tight', dpi=100)
@@ -413,9 +373,9 @@ class MovieLensDataAnalyzer:
         # 7.3 职业与评分活跃度
         plt.figure(figsize=(16, 10))
         sns.boxplot(x='occupation_name', y='rating_count', data=user_activity, palette=custom_colors)
-        plt.title('不同职业的评分活跃度分布' if USE_CHINESE else 'Rating Activity by Occupation')
+        plt.title('Rating Activity by Occupation' if USE_ENGLISH else '不同职业的评分活跃度分布')
-        plt.xlabel('职业' if USE_CHINESE else 'Occupation')
+        plt.xlabel('Occupation' if USE_ENGLISH else '职业')
-        plt.ylabel('评分数量' if USE_CHINESE else 'Number of Ratings')
+        plt.ylabel('Number of Ratings' if USE_ENGLISH else '评分数量')
         plt.xticks(rotation=90)
         plt.tight_layout()
         plt.savefig(os.path.join(user_analysis_dir, 'occupation_activity.png'), bbox_inches='tight', dpi=100)
@@ -441,9 +401,9 @@ class MovieLensDataAnalyzer:
 
         plt.figure(figsize=(16, 6))
         sns.barplot(x=year_counts.index, y=year_counts.values, color=custom_colors[0])
-        plt.title('电影发行年份分布' if USE_CHINESE else 'Movie Release Year Distribution')
+        plt.title('Movie Release Year Distribution' if USE_ENGLISH else '电影发行年份分布')
-        plt.xlabel('发行年份' if USE_CHINESE else 'Release Year')
+        plt.xlabel('Release Year' if USE_ENGLISH else '发行年份')
-        plt.ylabel('电影数量' if USE_CHINESE else 'Number of Movies')
+        plt.ylabel('Number of Movies' if USE_ENGLISH else '电影数量')
         plt.xticks(rotation=90)
         plt.tight_layout()
         plt.savefig(os.path.join(movie_analysis_dir, 'year_distribution.png'), bbox_inches='tight', dpi=100)
@@ -461,9 +421,9 @@ class MovieLensDataAnalyzer:
 
         plt.figure(figsize=(14, 8))
         sns.barplot(x=genre_series.values, y=genre_series.index, palette=custom_colors)
-        plt.title('电影类型分布' if USE_CHINESE else 'Movie Genre Distribution')
+        plt.title('Movie Genre Distribution' if USE_ENGLISH else '电影类型分布')
-        plt.xlabel('电影数量' if USE_CHINESE else 'Number of Movies')
+        plt.xlabel('Number of Movies' if USE_ENGLISH else '电影数量')
-        plt.ylabel('类型' if USE_CHINESE else 'Genre')
+        plt.ylabel('Genre' if USE_ENGLISH else '类型')
         plt.tight_layout()
         plt.savefig(os.path.join(movie_analysis_dir, 'genre_distribution.png'), bbox_inches='tight', dpi=100)
         plt.close()
@@ -473,9 +433,9 @@ class MovieLensDataAnalyzer:
 
         plt.figure(figsize=(12, 6))
         sns.histplot(movie_rating_counts, bins=30, kde=True, color=custom_colors[1])
-        plt.title('电影评分数量分布' if USE_CHINESE else 'Movie Rating Count Distribution')
+        plt.title('Movie Rating Count Distribution' if USE_ENGLISH else '电影评分数量分布')
-        plt.xlabel('每部电影的评分数量' if USE_CHINESE else 'Number of Ratings per Movie')
+        plt.xlabel('Number of Ratings per Movie' if USE_ENGLISH else '每部电影的评分数量')
-        plt.ylabel('电影数' if USE_CHINESE else 'Number of Movies')
+        plt.ylabel('Number of Movies' if USE_ENGLISH else '电影数')
         plt.tight_layout()
         plt.savefig(os.path.join(movie_analysis_dir, 'movie_rating_counts.png'), bbox_inches='tight', dpi=100)
         plt.close()
@@ -490,9 +450,9 @@ class MovieLensDataAnalyzer:
 
         plt.figure(figsize=(16, 10))
         sns.barplot(y='title', x='rating_count', data=top_movies_df, palette=custom_colors)
-        plt.title('评分数量最多的20部电影' if USE_CHINESE else 'Top 20 Most Rated Movies')
+        plt.title('Top 20 Most Rated Movies' if USE_ENGLISH else '评分数量最多的20部电影')
-        plt.xlabel('评分数量' if USE_CHINESE else 'Number of Ratings')
+        plt.xlabel('Number of Ratings' if USE_ENGLISH else '评分数量')
-        plt.ylabel('电影标题' if USE_CHINESE else 'Movie Title')
+        plt.ylabel('Movie Title' if USE_ENGLISH else '电影标题')
         plt.tight_layout()
         plt.savefig(os.path.join(movie_analysis_dir, 'most_rated_movies.png'), bbox_inches='tight', dpi=100)
         plt.close()
@@ -513,9 +473,9 @@ class MovieLensDataAnalyzer:
 
         plt.figure(figsize=(14, 8))
         sns.barplot(x=genre_avg_counts.values, y=genre_avg_counts.index, palette=custom_colors)
-        plt.title('各类型电影的平均评分数量' if USE_CHINESE else 'Average Number of Ratings by Genre')
+        plt.title('Average Number of Ratings by Genre' if USE_ENGLISH else '各类型电影的平均评分数量')
-        plt.xlabel('平均评分数量' if USE_CHINESE else 'Average Number of Ratings')
+        plt.xlabel('Average Number of Ratings' if USE_ENGLISH else '平均评分数量')
-        plt.ylabel('电影类型' if USE_CHINESE else 'Movie Genre')
+        plt.ylabel('Movie Genre' if USE_ENGLISH else '电影类型')
         plt.tight_layout()
         plt.savefig(os.path.join(movie_analysis_dir, 'genre_avg_rating_counts.png'), bbox_inches='tight', dpi=100)
         plt.close()
@@ -534,9 +494,9 @@ class MovieLensDataAnalyzer:
 
         plt.figure(figsize=(16, 6))
         sns.lineplot(x=year_avg_counts.index, y=year_avg_counts.values, marker='o', color=custom_colors[2])
-        plt.title('不同发行年份电影的平均评分数量' if USE_CHINESE else 'Average Number of Ratings by Release Year')
+        plt.title('Average Number of Ratings by Release Year' if USE_ENGLISH else '不同发行年份电影的平均评分数量')
-        plt.xlabel('发行年份' if USE_CHINESE else 'Release Year')
+        plt.xlabel('Release Year' if USE_ENGLISH else '发行年份')
-        plt.ylabel('平均评分数量' if USE_CHINESE else 'Average Number of Ratings')
+        plt.ylabel('Average Number of Ratings' if USE_ENGLISH else '平均评分数量')
         plt.grid(True, linestyle='--', alpha=0.7)
         plt.tight_layout()
         plt.savefig(os.path.join(movie_analysis_dir, 'year_avg_rating_counts.png'), bbox_inches='tight', dpi=100)
@@ -559,9 +519,9 @@ class MovieLensDataAnalyzer:
         plt.figure(figsize=(12, 6))
         rating_counts = self.ratings_df['rating'].value_counts().sort_index()
         sns.barplot(x=rating_counts.index, y=rating_counts.values, palette=custom_colors)
-        plt.title('评分值分布' if USE_CHINESE else 'Rating Value Distribution')
+        plt.title('Rating Value Distribution' if USE_ENGLISH else '评分值分布')
-        plt.xlabel('评分' if USE_CHINESE else 'Rating')
+        plt.xlabel('Rating' if USE_ENGLISH else '评分')
-        plt.ylabel('数量' if USE_CHINESE else 'Count')
+        plt.ylabel('Count' if USE_ENGLISH else '数量')
         plt.tight_layout()
         plt.savefig(os.path.join(rating_analysis_dir, 'rating_distribution.png'), bbox_inches='tight', dpi=100)
         plt.close()
@@ -577,17 +537,17 @@ class MovieLensDataAnalyzer:
                 bins=10,
                 palette=[custom_colors[0], custom_colors[1]]
             )
-            plt.title('原始评分与填补评分的分布对比' if USE_CHINESE else 'Original vs. Filled Ratings Distribution')
+            plt.title('Original vs. Filled Ratings Distribution' if USE_ENGLISH else '原始评分与填补评分的分布对比')
-            plt.xlabel('评分' if USE_CHINESE else 'Rating')
+            plt.xlabel('Rating' if USE_ENGLISH else '评分')
-            plt.ylabel('数量' if USE_CHINESE else 'Count')
+            plt.ylabel('Count' if USE_ENGLISH else '数量')
 
             # 修改图例标签
-            if USE_CHINESE:
+            if USE_ENGLISH:
-                labels = ['填补评分', '原始评分']
-                plt.legend(title='是否原始评分', labels=labels)
-            else:
                 labels = ['Filled Ratings', 'Original Ratings']
                 plt.legend(title='Rating Type', labels=labels)
+            else:
+                labels = ['填补评分', '原始评分']
+                plt.legend(title='是否原始评分', labels=labels)
 
             plt.tight_layout()
             plt.savefig(os.path.join(rating_analysis_dir, 'original_vs_filled_ratings.png'), bbox_inches='tight',
@@ -603,20 +563,20 @@ class MovieLensDataAnalyzer:
         plt.figure(figsize=(14, 8))
 
         ax1 = plt.gca()
-        ax1.set_xlabel('年份' if USE_CHINESE else 'Year')
+        ax1.set_xlabel('Year' if USE_ENGLISH else '年份')
-        ax1.set_ylabel('平均评分' if USE_CHINESE else 'Average Rating', color=custom_colors[0])
+        ax1.set_ylabel('Average Rating' if USE_ENGLISH else '平均评分', color=custom_colors[0])
         ax1.plot(yearly_ratings['year'], yearly_ratings['mean'], marker='o', color=custom_colors[0],
-                 label='平均评分' if USE_CHINESE else 'Average Rating')
+                 label='Average Rating' if USE_ENGLISH else '平均评分')
         ax1.tick_params(axis='y', labelcolor=custom_colors[0])
         ax1.grid(True, linestyle='--', alpha=0.7)
 
         ax2 = ax1.twinx()
-        ax2.set_ylabel('评分数量' if USE_CHINESE else 'Number of Ratings', color=custom_colors[1])
+        ax2.set_ylabel('Number of Ratings' if USE_ENGLISH else '评分数量', color=custom_colors[1])
         ax2.plot(yearly_ratings['year'], yearly_ratings['count'], marker='s', color=custom_colors[1],
-                 label='评分数量' if USE_CHINESE else 'Number of Ratings')
+                 label='Number of Ratings' if USE_ENGLISH else '评分数量')
         ax2.tick_params(axis='y', labelcolor=custom_colors[1])
 
-        plt.title('随时间变化的评分趋势' if USE_CHINESE else 'Rating Trends Over Time')
+        plt.title('Rating Trends Over Time' if USE_ENGLISH else '随时间变化的评分趋势')
 
         # 添加两个y轴的图例
         lines1, labels1 = ax1.get_legend_handles_labels()
@@ -659,9 +619,9 @@ class MovieLensDataAnalyzer:
 
         plt.figure(figsize=(14, 8))
         sns.barplot(y='genre', x='avg_rating', data=genre_stats, palette=custom_colors)
-        plt.title('各类型电影的平均评分' if USE_CHINESE else 'Average Rating by Genre')
+        plt.title('Average Rating by Genre' if USE_ENGLISH else '各类型电影的平均评分')
-        plt.xlabel('平均评分' if USE_CHINESE else 'Average Rating')
+        plt.xlabel('Average Rating' if USE_ENGLISH else '平均评分')
-        plt.ylabel('电影类型' if USE_CHINESE else 'Movie Genre')
+        plt.ylabel('Movie Genre' if USE_ENGLISH else '电影类型')
         plt.grid(True, linestyle='--', alpha=0.7)
         plt.tight_layout()
         plt.savefig(os.path.join(rating_analysis_dir, 'genre_avg_ratings.png'), bbox_inches='tight', dpi=100)
@@ -679,13 +639,13 @@ class MovieLensDataAnalyzer:
 
         # 在柱状图上添加评分数量标签
         for i, (_, row) in enumerate(top_rated_movies.iterrows()):
-            label_text = f"评分数: {int(row['count'])}" if USE_CHINESE else f"Ratings: {int(row['count'])}"
+            label_text = f"Ratings: {int(row['count'])}" if USE_ENGLISH else f"评分数: {int(row['count'])}"
             bars.text(row['mean'] + 0.05, i, label_text, va='center')
 
         plt.title(
-            '评分最高的20部电影 (至少有100个评分)' if USE_CHINESE else 'Top 20 Highest Rated Movies (min. 100 ratings)')
+            'Top 20 Highest Rated Movies (min. 100 ratings)' if USE_ENGLISH else '评分最高的20部电影 (至少有100个评分)')
-        plt.xlabel('平均评分' if USE_CHINESE else 'Average Rating')
+        plt.xlabel('Average Rating' if USE_ENGLISH else '平均评分')
-        plt.ylabel('电影标题' if USE_CHINESE else 'Movie Title')
+        plt.ylabel('Movie Title' if USE_ENGLISH else '电影标题')
         plt.tight_layout()
         plt.savefig(os.path.join(rating_analysis_dir, 'top_rated_movies.png'), bbox_inches='tight', dpi=100)
         plt.close()
@@ -708,20 +668,20 @@ class MovieLensDataAnalyzer:
         plt.figure(figsize=(16, 8))
 
         ax1 = plt.gca()
-        ax1.set_xlabel('发行年份' if USE_CHINESE else 'Release Year')
+        ax1.set_xlabel('Release Year' if USE_ENGLISH else '发行年份')
-        ax1.set_ylabel('平均评分' if USE_CHINESE else 'Average Rating', color=custom_colors[0])
+        ax1.set_ylabel('Average Rating' if USE_ENGLISH else '平均评分', color=custom_colors[0])
         ax1.plot(year_avg_ratings.index, year_avg_ratings.values, marker='o', color=custom_colors[0],
-                 label='平均评分' if USE_CHINESE else 'Average Rating')
+                 label='Average Rating' if USE_ENGLISH else '平均评分')
         ax1.tick_params(axis='y', labelcolor=custom_colors[0])
         ax1.grid(True, linestyle='--', alpha=0.7)
 
         ax2 = ax1.twinx()
-        ax2.set_ylabel('评分数量' if USE_CHINESE else 'Number of Ratings', color=custom_colors[1])
+        ax2.set_ylabel('Number of Ratings' if USE_ENGLISH else '评分数量', color=custom_colors[1])
         ax2.plot(year_rating_counts.index, year_rating_counts.values, marker='s', color=custom_colors[1],
-                 label='评分数量' if USE_CHINESE else 'Number of Ratings')
+                 label='Number of Ratings' if USE_ENGLISH else '评分数量')
         ax2.tick_params(axis='y', labelcolor=custom_colors[1])
 
-        plt.title('不同发行年份电影的平均评分' if USE_CHINESE else 'Average Rating by Release Year')
+        plt.title('Average Rating by Release Year' if USE_ENGLISH else '不同发行年份电影的平均评分')
 
         # 添加两个y轴的图例
         lines1, labels1 = ax1.get_legend_handles_labels()
@@ -752,8 +712,8 @@ class MovieLensDataAnalyzer:
         try:
             gender_genre_preferences = self._analyze_group_genre_preference(user_ratings, 'gender')
             # 为每个性别绘制前10个最喜爱的类型
-            gender_labels = {'M': '男性' if USE_CHINESE else 'Male',
+            gender_labels = {'M': 'Male' if USE_ENGLISH else '男性',
-                             'F': '女性' if USE_CHINESE else 'Female'}
+                             'F': 'Female' if USE_ENGLISH else '女性'}
 
             for gender in gender_genre_preferences.keys():
                 gender_preferences = gender_genre_preferences[gender].sort_values(ascending=False).head(10)
@@ -762,14 +722,14 @@ class MovieLensDataAnalyzer:
                 sns.barplot(x=gender_preferences.index, y=gender_preferences.values, palette=custom_colors)
 
                 # 设置本地化标题
-                if USE_CHINESE:
+                if USE_ENGLISH:
-                    title = f"{gender_labels[gender]}最喜爱的电影类型"
-                else:
                     title = f"Most Favorite Movie Genres for {gender_labels[gender]}"
+                else:
+                    title = f"{gender_labels[gender]}最喜爱的电影类型"
 
                 plt.title(title)
-                plt.xlabel('电影类型' if USE_CHINESE else 'Movie Genre')
+                plt.xlabel('Movie Genre' if USE_ENGLISH else '电影类型')
-                plt.ylabel('平均评分' if USE_CHINESE else 'Average Rating')
+                plt.ylabel('Average Rating' if USE_ENGLISH else '平均评分')
                 plt.ylim(3.0, 4.5)  # 设定Y轴范围，使得差异更明显
                 plt.xticks(rotation=45)
                 plt.tight_layout()
@@ -791,13 +751,10 @@ class MovieLensDataAnalyzer:
             gender_heatmap_data = gender_heatmap_data.sort_values('M', ascending=False)
 
             # 重命名列
-            if USE_CHINESE:
+            gender_heatmap_data.columns = ['Male', 'Female'] if USE_ENGLISH else ['男性', '女性']
-                gender_heatmap_data.columns = ['男性', '女性']
-            else:
-                gender_heatmap_data.columns = ['Male', 'Female']
 
             sns.heatmap(gender_heatmap_data, annot=True, cmap='coolwarm', fmt='.2f', linewidths=0.5)
-            plt.title('不同性别的电影类型偏好对比' if USE_CHINESE else 'Movie Genre Preferences by Gender')
+            plt.title('Movie Genre Preferences by Gender' if USE_ENGLISH else '不同性别的电影类型偏好对比')
             plt.tight_layout()
             plt.savefig(os.path.join(preference_analysis_dir, 'gender_genre_heatmap.png'), bbox_inches='tight', dpi=100)
             plt.close()
@@ -816,14 +773,14 @@ class MovieLensDataAnalyzer:
                 sns.barplot(x=age_preferences.index, y=age_preferences.values, palette=custom_colors)
 
                 # 设置本地化标题
-                if USE_CHINESE:
+                if USE_ENGLISH:
-                    title = f"{age_group}年龄段最喜爱的电影类型"
-                else:
                     title = f"Most Favorite Movie Genres for Age Group {age_group}"
+                else:
+                    title = f"{age_group}年龄段最喜爱的电影类型"
 
                 plt.title(title)
-                plt.xlabel('电影类型' if USE_CHINESE else 'Movie Genre')
+                plt.xlabel('Movie Genre' if USE_ENGLISH else '电影类型')
-                plt.ylabel('平均评分' if USE_CHINESE else 'Average Rating')
+                plt.ylabel('Average Rating' if USE_ENGLISH else '平均评分')
                 plt.ylim(3.2, 4.2)  # 设定Y轴范围，使得差异更明显
                 plt.xticks(rotation=45)
                 plt.tight_layout()
@@ -842,12 +799,12 @@ class MovieLensDataAnalyzer:
             age_heatmap_data = age_heatmap_data.loc[common_genres]
 
             # 按总体平均评分降序排列
-            age_heatmap_data['总体' if USE_CHINESE else 'Overall'] = age_heatmap_data.mean(axis=1)
+            age_heatmap_data['Overall'] = age_heatmap_data.mean(axis=1)
-            age_heatmap_data = age_heatmap_data.sort_values('总体' if USE_CHINESE else 'Overall', ascending=False)
+            age_heatmap_data = age_heatmap_data.sort_values('Overall', ascending=False)
-            age_heatmap_data = age_heatmap_data.drop('总体' if USE_CHINESE else 'Overall', axis=1)
+            age_heatmap_data = age_heatmap_data.drop('Overall', axis=1)
 
             sns.heatmap(age_heatmap_data, annot=True, cmap='coolwarm', fmt='.2f', linewidths=0.5)
-            plt.title('不同年龄段的电影类型偏好对比' if USE_CHINESE else 'Movie Genre Preferences by Age Group')
+            plt.title('Movie Genre Preferences by Age Group' if USE_ENGLISH else '不同年龄段的电影类型偏好对比')
             plt.tight_layout()
             plt.savefig(os.path.join(preference_analysis_dir, 'age_genre_heatmap.png'), bbox_inches='tight', dpi=100)
             plt.close()
@@ -860,12 +817,12 @@ class MovieLensDataAnalyzer:
 
             # 选择几个代表性职业
             selected_occupations = []
-            if USE_CHINESE:
+            if USE_ENGLISH:
-                selected_occupations = ['程序员', '学术/教育工作者', '大学生/研究生', '艺术家', '行政/事务人员',
+                selected_occupations = ['Programmer', 'Academic/Educator', 'College/Grad Student',
-                                        '退休人员', '失业人员']
+                                        'Artist', 'Executive/Managerial', 'Retired', 'Unemployed']
             else:
-                selected_occupations = ['Programmer', 'Academic/Educator', 'College/Grad Student', 'Artist',
+                selected_occupations = ['程序员', '学术/教育工作者', '大学生/研究生',
-                                        'Executive/Managerial', 'Retired', 'Unemployed']
+                                        '艺术家', '行政/事务人员', '退休人员', '失业人员']
 
             selected_occupations = [occ for occ in selected_occupations if occ in occupation_genre_preferences]
 
@@ -878,14 +835,14 @@ class MovieLensDataAnalyzer:
                     sns.barplot(x=occ_preferences.index, y=occ_preferences.values, palette=custom_colors)
 
                     # 设置本地化标题
-                    if USE_CHINESE:
+                    if USE_ENGLISH:
-                        title = f"{occupation}最喜爱的电影类型"
-                    else:
                         title = f"Most Favorite Movie Genres for {occupation}"
+                    else:
+                        title = f"{occupation}最喜爱的电影类型"
 
                     plt.title(title)
-                    plt.xlabel('电影类型' if USE_CHINESE else 'Movie Genre')
+                    plt.xlabel('Movie Genre' if USE_ENGLISH else '电影类型')
-                    plt.ylabel('平均评分' if USE_CHINESE else 'Average Rating')
+                    plt.ylabel('Average Rating' if USE_ENGLISH else '平均评分')
                     plt.ylim(3.2, 4.2)  # 设定Y轴范围，使得差异更明显
                     plt.xticks(rotation=45)
                     plt.tight_layout()
@@ -907,12 +864,12 @@ class MovieLensDataAnalyzer:
                 occ_heatmap_data = occ_heatmap_data.loc[common_genres]
 
                 # 按总体平均评分降序排列
-                occ_heatmap_data['总体' if USE_CHINESE else 'Overall'] = occ_heatmap_data.mean(axis=1)
+                occ_heatmap_data['Overall'] = occ_heatmap_data.mean(axis=1)
-                occ_heatmap_data = occ_heatmap_data.sort_values('总体' if USE_CHINESE else 'Overall', ascending=False)
+                occ_heatmap_data = occ_heatmap_data.sort_values('Overall', ascending=False)
-                occ_heatmap_data = occ_heatmap_data.drop('总体' if USE_CHINESE else 'Overall', axis=1)
+                occ_heatmap_data = occ_heatmap_data.drop('Overall', axis=1)
 
                 sns.heatmap(occ_heatmap_data, annot=True, cmap='coolwarm', fmt='.2f', linewidths=0.5)
-                plt.title('不同职业的电影类型偏好对比' if USE_CHINESE else 'Movie Genre Preferences by Occupation')
+                plt.title('Movie Genre Preferences by Occupation' if USE_ENGLISH else '不同职业的电影类型偏好对比')
                 plt.tight_layout()
                 plt.savefig(os.path.join(preference_analysis_dir, 'occupation_genre_heatmap.png'), bbox_inches='tight',
                             dpi=100)
@@ -993,7 +950,7 @@ class MovieLensDataAnalyzer:
             # 重新提取年份
             self.movies_df['year'] = self.movies_df['title'].apply(
                 lambda x: int(x[-5:-1]) if (
-                            len(x) > 5 and x[-1] == ')' and x[-6] == '(' and x[-5:-1].isdigit()) else None
+                        len(x) > 5 and x[-1] == ')' and x[-6] == '(' and x[-5:-1].isdigit()) else None
             )
 
         # 2. 检查是否有足够的年份数据
@@ -1046,9 +1003,9 @@ class MovieLensDataAnalyzer:
             plt.figure(figsize=(16, 10))
             sns.heatmap(pivot_data, annot=True, cmap='coolwarm', fmt='.2f', linewidths=0.5)
             plt.title(
-                '不同年龄段对不同年代电影的偏好' if USE_CHINESE else 'Preferences for Movies by Decade Across Age Groups')
+                'Preferences for Movies by Decade Across Age Groups' if USE_ENGLISH else '不同年龄段对不同年代电影的偏好')
-            plt.xlabel('电影发行年代' if USE_CHINESE else 'Movie Release Decade')
+            plt.xlabel('Movie Release Decade' if USE_ENGLISH else '电影发行年代')
-            plt.ylabel('用户年龄段' if USE_CHINESE else 'User Age Group')
+            plt.ylabel('User Age Group' if USE_ENGLISH else '用户年龄段')
             plt.tight_layout()
 
             # 8. 保存图表
@@ -1105,7 +1062,7 @@ class MovieLensDataAnalyzer:
                 heatmap_data.loc[age, '1990s'] += 0.3
             elif "18" in str(age):  # 年轻用户
                 heatmap_data.loc[age, '2000s'] += 0.3
-            elif "Under" in str(age) or "以下" in str(age):  # 未成年用户
+            elif "Under" in str(age) or str(age).startswith("18岁"):  # 未成年用户
                 heatmap_data.loc[age, '1990s'] += 0.2
                 heatmap_data.loc[age, '2000s'] += 0.4
 
@@ -1113,9 +1070,9 @@ class MovieLensDataAnalyzer:
         plt.figure(figsize=(16, 10))
         sns.heatmap(heatmap_data, annot=True, cmap='coolwarm', fmt='.2f', linewidths=0.5)
         plt.title(
-            '不同年龄段对不同年代电影的偏好 (模拟数据)' if USE_CHINESE else 'Preferences for Movies by Decade Across Age Groups (Simulated Data)')
+            'Preferences for Movies by Decade Across Age Groups (Simulated Data)' if USE_ENGLISH else '不同年龄段对不同年代电影的偏好 (模拟数据)')
-        plt.xlabel('电影发行年代' if USE_CHINESE else 'Movie Release Decade')
+        plt.xlabel('Movie Release Decade' if USE_ENGLISH else '电影发行年代')
-        plt.ylabel('用户年龄段' if USE_CHINESE else 'User Age Group')
+        plt.ylabel('User Age Group' if USE_ENGLISH else '用户年龄段')
         plt.tight_layout()
 
         # 6. 保存图表
@@ -1147,13 +1104,11 @@ class MovieLensDataAnalyzer:
         ax = sns.boxplot(x='gender', y='avg_rating', data=user_stats, palette=[custom_colors[0], custom_colors[1]])
 
         # 修改x轴标签
-        if USE_CHINESE:
+        ax.set_xticklabels(['Male', 'Female'])  # 强制使用英文标签确保显示
-            gender_labels = {'M': '男性', 'F': '女性'}
-            ax.set_xticklabels([gender_labels[tick.get_text()] for tick in ax.get_xticklabels()])
 
-        plt.title('性别与平均评分的关系' if USE_CHINESE else 'Average Rating by Gender')
+        plt.title('Average Rating by Gender' if USE_ENGLISH else '性别与平均评分的关系')
-        plt.xlabel('性别' if USE_CHINESE else 'Gender')
+        plt.xlabel('Gender' if USE_ENGLISH else '性别')
-        plt.ylabel('平均评分' if USE_CHINESE else 'Average Rating')
+        plt.ylabel('Average Rating' if USE_ENGLISH else '平均评分')
 
         # 添加统计检验结果
         male_ratings = user_stats[user_stats['gender'] == 'M']['avg_rating']
@@ -1161,7 +1116,7 @@ class MovieLensDataAnalyzer:
 
         if len(male_ratings) > 0 and len(female_ratings) > 0:
             t_stat, p_value = stats.ttest_ind(male_ratings, female_ratings)
-            annotation = f'T检验: p={p_value:.4f}' if USE_CHINESE else f'T-test: p={p_value:.4f}'
+            annotation = f'T-test: p={p_value:.4f}' if USE_ENGLISH else f'T检验: p={p_value:.4f}'
             plt.annotate(annotation, xy=(0.5, 0.05), xycoords='axes fraction')
 
         plt.tight_layout()
@@ -1171,9 +1126,9 @@ class MovieLensDataAnalyzer:
         # 2. 年龄组与平均评分的关系
         plt.figure(figsize=(14, 6))
         sns.boxplot(x='age_group', y='avg_rating', data=user_stats, palette=custom_colors)
-        plt.title('年龄组与平均评分的关系' if USE_CHINESE else 'Average Rating by Age Group')
+        plt.title('Average Rating by Age Group' if USE_ENGLISH else '年龄组与平均评分的关系')
-        plt.xlabel('年龄组' if USE_CHINESE else 'Age Group')
+        plt.xlabel('Age Group' if USE_ENGLISH else '年龄组')
-        plt.ylabel('平均评分' if USE_CHINESE else 'Average Rating')
+        plt.ylabel('Average Rating' if USE_ENGLISH else '平均评分')
         plt.xticks(rotation=45)
         plt.tight_layout()
         plt.savefig(os.path.join(output_dir, 'age_avg_rating.png'), bbox_inches='tight', dpi=100)
@@ -1184,13 +1139,11 @@ class MovieLensDataAnalyzer:
         ax = sns.boxplot(x='gender', y='rating_std', data=user_stats, palette=[custom_colors[0], custom_colors[1]])
 
         # 修改x轴标签
-        if USE_CHINESE:
+        ax.set_xticklabels(['Male', 'Female'])  # 强制使用英文标签确保显示
-            gender_labels = {'M': '男性', 'F': '女性'}
-            ax.set_xticklabels([gender_labels[tick.get_text()] for tick in ax.get_xticklabels()])
 
-        plt.title('性别与评分标准差的关系' if USE_CHINESE else 'Rating Standard Deviation by Gender')
+        plt.title('Rating Standard Deviation by Gender' if USE_ENGLISH else '性别与评分标准差的关系')
-        plt.xlabel('性别' if USE_CHINESE else 'Gender')
+        plt.xlabel('Gender' if USE_ENGLISH else '性别')
-        plt.ylabel('评分标准差' if USE_CHINESE else 'Rating Standard Deviation')
+        plt.ylabel('Rating Standard Deviation' if USE_ENGLISH else '评分标准差')
         plt.tight_layout()
         plt.savefig(os.path.join(output_dir, 'gender_rating_std.png'), bbox_inches='tight', dpi=100)
         plt.close()
@@ -1198,9 +1151,9 @@ class MovieLensDataAnalyzer:
         # 4. 年龄组与评分标准差的关系
         plt.figure(figsize=(14, 6))
         sns.boxplot(x='age_group', y='rating_std', data=user_stats, palette=custom_colors)
-        plt.title('年龄组与评分标准差的关系' if USE_CHINESE else 'Rating Standard Deviation by Age Group')
+        plt.title('Rating Standard Deviation by Age Group' if USE_ENGLISH else '年龄组与评分标准差的关系')
-        plt.xlabel('年龄组' if USE_CHINESE else 'Age Group')
+        plt.xlabel('Age Group' if USE_ENGLISH else '年龄组')
-        plt.ylabel('评分标准差' if USE_CHINESE else 'Rating Standard Deviation')
+        plt.ylabel('Rating Standard Deviation' if USE_ENGLISH else '评分标准差')
         plt.xticks(rotation=45)
         plt.tight_layout()
         plt.savefig(os.path.join(output_dir, 'age_rating_std.png'), bbox_inches='tight', dpi=100)
@@ -1209,9 +1162,9 @@ class MovieLensDataAnalyzer:
         # 5. 所有职业的平均评分对比
         plt.figure(figsize=(16, 10))
         sns.boxplot(x='occupation_name', y='avg_rating', data=user_stats, palette=custom_colors)
-        plt.title('职业与平均评分的关系' if USE_CHINESE else 'Average Rating by Occupation')
+        plt.title('Average Rating by Occupation' if USE_ENGLISH else '职业与平均评分的关系')
-        plt.xlabel('职业' if USE_CHINESE else 'Occupation')
+        plt.xlabel('Occupation' if USE_ENGLISH else '职业')
-        plt.ylabel('平均评分' if USE_CHINESE else 'Average Rating')
+        plt.ylabel('Average Rating' if USE_ENGLISH else '平均评分')
         plt.xticks(rotation=90)
         plt.tight_layout()
         plt.savefig(os.path.join(output_dir, 'occupation_avg_rating.png'), bbox_inches='tight', dpi=100)
@@ -1221,18 +1174,14 @@ class MovieLensDataAnalyzer:
         plt.figure(figsize=(12, 6))
 
         # 为性别标签添加本地化
-        if USE_CHINESE:
+        gender_mapping = {'M': 'Male', 'F': 'Female'}
-            gender_mapping = {'M': '男性', 'F': '女性'}
+        user_stats['gender_label'] = user_stats['gender'].map(gender_mapping)
-            user_stats['gender_label'] = user_stats['gender'].map(gender_mapping)
-            hue_column = 'gender_label'
-        else:
-            hue_column = 'gender'
 
-        sns.scatterplot(x='rating_count', y='avg_rating', hue=hue_column, data=user_stats,
+        sns.scatterplot(x='rating_count', y='avg_rating', hue='gender_label', data=user_stats,
                         palette=[custom_colors[0], custom_colors[1]])
-        plt.title('评分数量与平均评分的关系' if USE_CHINESE else 'Relationship Between Rating Count and Average Rating')
+        plt.title('Relationship Between Rating Count and Average Rating' if USE_ENGLISH else '评分数量与平均评分的关系')
-        plt.xlabel('评分数量' if USE_CHINESE else 'Number of Ratings')
+        plt.xlabel('Number of Ratings' if USE_ENGLISH else '评分数量')
-        plt.ylabel('平均评分' if USE_CHINESE else 'Average Rating')
+        plt.ylabel('Average Rating' if USE_ENGLISH else '平均评分')
         plt.xscale('log')  # 使用对数刻度更好地展示分布
         plt.grid(True, linestyle='--', alpha=0.7)
         plt.tight_layout()
@@ -1245,20 +1194,20 @@ class MovieLensDataAnalyzer:
 
         # 创建分析摘要
         summary = {
-            "数据概览" if USE_CHINESE else "Data Overview": {
+            "Data Overview" if USE_ENGLISH else "数据概览": {
-                "用户数量" if USE_CHINESE else "Number of Users": len(self.users_df),
+                "Number of Users" if USE_ENGLISH else "用户数量": len(self.users_df),
-                "电影数量" if USE_CHINESE else "Number of Movies": len(self.movies_df),
+                "Number of Movies" if USE_ENGLISH else "电影数量": len(self.movies_df),
-                "原始评分数量" if USE_CHINESE else "Original Ratings Count": len(self.ratings_df),
+                "Original Ratings Count" if USE_ENGLISH else "原始评分数量": len(self.ratings_df),
-                "填补后评分数量" if USE_CHINESE else "Filled Ratings Count": len(self.filled_ratings_df) if hasattr(
+                "Filled Ratings Count" if USE_ENGLISH else "填补后评分数量": len(self.filled_ratings_df) if hasattr(
                     self, 'filled_ratings_df') else "未使用填补数据",
             },
-            "用户分析" if USE_CHINESE else "User Analysis": {
+            "User Analysis" if USE_ENGLISH else "用户分析": {
-                "性别分布" if USE_CHINESE else "Gender Distribution": self.users_df['gender'].value_counts().to_dict(),
+                "Gender Distribution" if USE_ENGLISH else "性别分布": self.users_df['gender'].value_counts().to_dict(),
-                "年龄分布" if USE_CHINESE else "Age Distribution": self.users_df['age_group'].value_counts().to_dict(),
+                "Age Distribution" if USE_ENGLISH else "年龄分布": self.users_df['age_group'].value_counts().to_dict(),
             },
-            "评分分析" if USE_CHINESE else "Rating Analysis": {
+            "Rating Analysis" if USE_ENGLISH else "评分分析": {
-                "平均评分" if USE_CHINESE else "Average Rating": round(self.ratings_df['rating'].mean(), 2),
+                "Average Rating" if USE_ENGLISH else "平均评分": round(self.ratings_df['rating'].mean(), 2),
-                "评分分布" if USE_CHINESE else "Rating Distribution": self.ratings_df[
+                "Rating Distribution" if USE_ENGLISH else "评分分布": self.ratings_df[
                     'rating'].value_counts().sort_index().to_dict()
             }
         }
@@ -1268,7 +1217,7 @@ class MovieLensDataAnalyzer:
             json.dump(summary, f, ensure_ascii=False, indent=4)
 
         # 创建HTML报告
-        html_title = 'MovieLens数据集分析报告' if USE_CHINESE else 'MovieLens Dataset Analysis Report'
+        html_title = 'MovieLens Dataset Analysis Report' if USE_ENGLISH else 'MovieLens数据集分析报告'
         html_report = f"""
         <!DOCTYPE html>
         <html>
@@ -1294,90 +1243,90 @@ class MovieLensDataAnalyzer:
         </head>
         <body>
             <div class="container">
-                <h1>{"MovieLens数据集用户-电影偏好分析报告" if USE_CHINESE else "MovieLens Dataset User-Movie Preference Analysis Report"}</h1>
+                <h1>{"MovieLens Dataset User-Movie Preference Analysis Report" if USE_ENGLISH else "MovieLens数据集用户-电影偏好分析报告"}</h1>
 
                 <div class="summary">
-                    <h2>{"数据概览" if USE_CHINESE else "Data Overview"}</h2>
+                    <h2>{"Data Overview" if USE_ENGLISH else "数据概览"}</h2>
-                    <p>{"本分析基于MovieLens数据集，包含" if USE_CHINESE else "This analysis is based on the MovieLens dataset, containing"} {len(self.users_df)} {"位用户" if USE_CHINESE else "users"}、{len(self.movies_df)} {"部电影" if USE_CHINESE else "movies"} {"和" if USE_CHINESE else "and"} {len(self.ratings_df)} {"条原始评分记录" if USE_CHINESE else "original rating records"}。</p>
+                    <p>{"This analysis is based on the MovieLens dataset, containing" if USE_ENGLISH else "本分析基于MovieLens数据集，包含"} {len(self.users_df)} {"users" if USE_ENGLISH else "位用户"}、{len(self.movies_df)} {"movies" if USE_ENGLISH else "部电影"} {"and" if USE_ENGLISH else "和"} {len(self.ratings_df)} {"original rating records" if USE_ENGLISH else "条原始评分记录"}。</p>
                 </div>
 
-                <h2>{"用户基本情况分析" if USE_CHINESE else "User Profile Analysis"}</h2>
+                <h2>{"User Profile Analysis" if USE_ENGLISH else "用户基本情况分析"}</h2>
                 <div class="figure">
-                    <img src="user_analysis/gender_distribution.png" alt="用户性别分布">
+                    <img src="user_analysis/gender_distribution.png" alt="User Gender Distribution">
-                    <p class="caption">{"用户性别分布" if USE_CHINESE else "User Gender Distribution"}</p>
+                    <p class="caption">{"User Gender Distribution" if USE_ENGLISH else "用户性别分布"}</p>
                 </div>
 
                 <div class="figure">
-                    <img src="user_analysis/age_distribution.png" alt="用户年龄分布">
+                    <img src="user_analysis/age_distribution.png" alt="User Age Distribution">
-                    <p class="caption">{"用户年龄分布" if USE_CHINESE else "User Age Distribution"}</p>
+                    <p class="caption">{"User Age Distribution" if USE_ENGLISH else "用户年龄分布"}</p>
                 </div>
 
                 <div class="figure">
-                    <img src="user_analysis/occupation_distribution.png" alt="用户职业分布">
+                    <img src="user_analysis/occupation_distribution.png" alt="User Occupation Distribution">
-                    <p class="caption">{"用户职业分布" if USE_CHINESE else "User Occupation Distribution"}</p>
+                    <p class="caption">{"User Occupation Distribution" if USE_ENGLISH else "用户职业分布"}</p>
                 </div>
 
-                <h2>{"电影分布情况分析" if USE_CHINESE else "Movie Distribution Analysis"}</h2>
+                <h2>{"Movie Distribution Analysis" if USE_ENGLISH else "电影分布情况分析"}</h2>
                 <div class="figure">
-                    <img src="movie_analysis/genre_distribution.png" alt="电影类型分布">
+                    <img src="movie_analysis/genre_distribution.png" alt="Movie Genre Distribution">
-                    <p class="caption">{"电影类型分布" if USE_CHINESE else "Movie Genre Distribution"}</p>
+                    <p class="caption">{"Movie Genre Distribution" if USE_ENGLISH else "电影类型分布"}</p>
                 </div>
 
                 <div class="figure">
-                    <img src="movie_analysis/year_distribution.png" alt="电影发行年份分布">
+                    <img src="movie_analysis/year_distribution.png" alt="Movie Release Year Distribution">
-                    <p class="caption">{"电影发行年份分布" if USE_CHINESE else "Movie Release Year Distribution"}</p>
+                    <p class="caption">{"Movie Release Year Distribution" if USE_ENGLISH else "电影发行年份分布"}</p>
                 </div>
 
                 <div class="figure">
-                    <img src="movie_analysis/most_rated_movies.png" alt="评分数量最多的电影">
+                    <img src="movie_analysis/most_rated_movies.png" alt="Top 20 Most Rated Movies">
-                    <p class="caption">{"评分数量最多的20部电影" if USE_CHINESE else "Top 20 Most Rated Movies"}</p>
+                    <p class="caption">{"Top 20 Most Rated Movies" if USE_ENGLISH else "评分数量最多的20部电影"}</p>
                 </div>
 
-                <h2>{"评分分布情况分析" if USE_CHINESE else "Rating Distribution Analysis"}</h2>
+                <h2>{"Rating Distribution Analysis" if USE_ENGLISH else "评分分布情况分析"}</h2>
                 <div class="figure">
-                    <img src="rating_analysis/rating_distribution.png" alt="评分分布">
+                    <img src="rating_analysis/rating_distribution.png" alt="Rating Distribution">
-                    <p class="caption">{"评分分布情况" if USE_CHINESE else "Rating Distribution"}</p>
+                    <p class="caption">{"Rating Distribution" if USE_ENGLISH else "评分分布情况"}</p>
                 </div>
 
                 <div class="figure">
-                    <img src="rating_analysis/genre_avg_ratings.png" alt="各类型电影的平均评分">
+                    <img src="rating_analysis/genre_avg_ratings.png" alt="Average Rating by Movie Genre">
-                    <p class="caption">{"各类型电影的平均评分" if USE_CHINESE else "Average Rating by Movie Genre"}</p>
+                    <p class="caption">{"Average Rating by Movie Genre" if USE_ENGLISH else "各类型电影的平均评分"}</p>
                 </div>
 
                 <div class="figure">
-                    <img src="rating_analysis/top_rated_movies.png" alt="评分最高的电影">
+                    <img src="rating_analysis/top_rated_movies.png" alt="Top 20 Highest Rated Movies">
-                    <p class="caption">{"评分最高的20部电影（至少有100个评分）" if USE_CHINESE else "Top 20 Highest Rated Movies (min. 100 ratings)"}</p>
+                    <p class="caption">{"Top 20 Highest Rated Movies (min. 100 ratings)" if USE_ENGLISH else "评分最高的20部电影（至少有100个评分）"}</p>
                 </div>
 
-                <h2>{"用户特征与电影偏好分析" if USE_CHINESE else "User Characteristics and Movie Preferences"}</h2>
+                <h2>{"User Characteristics and Movie Preferences" if USE_ENGLISH else "用户特征与电影偏好分析"}</h2>
                 <div class="figure">
-                    <img src="preference_analysis/gender_genre_heatmap.png" alt="不同性别的电影类型偏好">
+                    <img src="preference_analysis/gender_genre_heatmap.png" alt="Movie Genre Preferences by Gender">
-                    <p class="caption">{"不同性别的电影类型偏好对比" if USE_CHINESE else "Movie Genre Preferences by Gender"}</p>
+                    <p class="caption">{"Movie Genre Preferences by Gender" if USE_ENGLISH else "不同性别的电影类型偏好对比"}</p>
                 </div>
 
                 <div class="figure">
-                    <img src="preference_analysis/age_genre_heatmap.png" alt="不同年龄段的电影类型偏好">
+                    <img src="preference_analysis/age_genre_heatmap.png" alt="Movie Genre Preferences by Age Group">
-                    <p class="caption">{"不同年龄段的电影类型偏好对比" if USE_CHINESE else "Movie Genre Preferences by Age Group"}</p>
+                    <p class="caption">{"Movie Genre Preferences by Age Group" if USE_ENGLISH else "不同年龄段的电影类型偏好对比"}</p>
                 </div>
 
                 <div class="figure">
-                    <img src="preference_analysis/age_year_heatmap.png" alt="不同年龄段对不同年代电影的偏好">
+                    <img src="preference_analysis/age_year_heatmap.png" alt="Preferences for Movies by Decade Across Age Groups">
-                    <p class="caption">{"不同年龄段对不同年代电影的偏好" if USE_CHINESE else "Preferences for Movies by Decade Across Age Groups"}</p>
+                    <p class="caption">{"Preferences for Movies by Decade Across Age Groups" if USE_ENGLISH else "不同年龄段对不同年代电影的偏好"}</p>
                 </div>
 
                 <div class="figure">
-                    <img src="preference_analysis/gender_avg_rating.png" alt="性别与平均评分的关系">
+                    <img src="preference_analysis/gender_avg_rating.png" alt="Average Rating by Gender">
-                    <p class="caption">{"性别与平均评分的关系" if USE_CHINESE else "Relationship Between Gender and Average Rating"}</p>
+                    <p class="caption">{"Average Rating by Gender" if USE_ENGLISH else "性别与平均评分的关系"}</p>
                 </div>
 
-                <h2>{"结论与洞察" if USE_CHINESE else "Conclusions and Insights"}</h2>
+                <h2>{"Conclusions and Insights" if USE_ENGLISH else "结论与洞察"}</h2>
-                <p>{"通过对MovieLens数据集的深入分析，我们发现了用户特征（如性别、年龄、职业）与电影偏好之间存在显著关联。主要结论包括：" if USE_CHINESE else "Through in-depth analysis of the MovieLens dataset, we found significant correlations between user characteristics (gender, age, occupation) and movie preferences. Key findings include:"}</p>
+                <p>{"Through in-depth analysis of the MovieLens dataset, we found significant correlations between user characteristics (gender, age, occupation) and movie preferences. Key findings include:" if USE_ENGLISH else "通过对MovieLens数据集的深入分析，我们发现了用户特征（如性别、年龄、职业）与电影偏好之间存在显著关联。主要结论包括："}</p>
                 <ul>
-                    <li>{"不同性别用户在电影类型偏好上存在明显差异" if USE_CHINESE else "Significant differences in movie genre preferences between genders"}</li>
+                    <li>{"Significant differences in movie genre preferences between genders" if USE_ENGLISH else "不同性别用户在电影类型偏好上存在明显差异"}</li>
-                    <li>{"年龄因素会影响用户对不同年代电影的评价" if USE_CHINESE else "Age influences how users rate movies from different decades"}</li>
+                    <li>{"Age influences how users rate movies from different decades" if USE_ENGLISH else "年龄因素会影响用户对不同年代电影的评价"}</li>
-                    <li>{"职业背景与电影类型偏好具有相关性" if USE_CHINESE else "Occupational background correlates with genre preferences"}</li>
+                    <li>{"Occupational background correlates with genre preferences" if USE_ENGLISH else "职业背景与电影类型偏好具有相关性"}</li>
                 </ul>
-                <p>{"这些发现对于电影推荐系统的设计和电影营销策略制定具有重要参考价值。" if USE_CHINESE else "These findings provide valuable reference for designing movie recommendation systems and developing movie marketing strategies."}</p>
+                <p>{"These findings provide valuable reference for designing movie recommendation systems and developing movie marketing strategies." if USE_ENGLISH else "这些发现对于电影推荐系统的设计和电影营销策略制定具有重要参考价值。"}</p>
             </div>
         </body>
         </html>