ADD file via upload

visualization.py

@@ -0,0 +1,108 @@
+# -*- coding: utf-8 -*-
+import os  # 新增：导入os模块
+import matplotlib.pyplot as plt
+from wordcloud import WordCloud
+import pandas as pd
+import jieba
+
+# 设置中文字体
+plt.rcParams["font.family"] = ["SimHei", "WenQuanYi Micro Hei", "Heiti TC"]
+
+class DanmakuVisualizer:
+    def __init__(self, danmu_path, excel_path):
+        self.danmu_path = danmu_path
+        self.excel_path = excel_path
+        self.danmu_text = ""
+        self.top8 = pd.DataFrame()  # 初始化空DataFrame
+        
+        # 读取弹幕数据（新增异常处理）
+        try:
+            if os.path.exists(danmu_path) and os.path.getsize(danmu_path) > 0:
+                with open(danmu_path, "r", encoding="utf-8") as f:
+                    self.danmu_text = " ".join([line.strip() for line in f if line.strip()])
+            else:
+                print(f"警告：弹幕文件 {danmu_path} 不存在或为空")
+        except Exception as e:
+            print(f"读取弹幕文件失败：{e}")
+        
+        # 读取Excel数据（新增异常处理）
+        try:
+            if os.path.exists(excel_path) and os.path.getsize(excel_path) > 0:
+                self.top8 = pd.read_excel(excel_path)
+            else:
+                print(f"警告：统计文件 {excel_path} 不存在或为空")
+        except Exception as e:
+            print(f"读取统计文件失败：{e}")
+        
+        # 停用词
+        self.stop_words = {
+            "已三连", "求资料", "打卡", "不错", "很好", "牛逼", "卧槽",
+            "学习", "分享", "感谢", "点赞", "三连", "教程", "B站", "老师"
+        }
+
+    def generate_wordcloud(self):
+        """生成词云图"""
+        if not self.danmu_text.strip():
+            print("警告：无有效弹幕数据，无法生成词云")
+            return
+        
+        # 过滤停用词
+        filtered_words = [w for w in jieba.cut(self.danmu_text) if len(w) > 1 and w not in self.stop_words]
+        filtered_text = " ".join(filtered_words)
+        
+        if not filtered_text:
+            print("警告：过滤后无有效词汇，无法生成词云")
+            return
+        
+        # 生成词云（增强字体兼容性）
+        try:
+            # 多系统字体支持
+            font_paths = [
+                "C:/Windows/Fonts/msyh.ttc",  # Windows
+                "/System/Library/Fonts/PingFang.ttc",  # macOS
+                "/usr/share/fonts/opentype/noto/NotoSansCJK-Regular.ttc"  # Linux
+            ]
+            font_path = None
+            for path in font_paths:
+                if os.path.exists(path):
+                    font_path = path
+                    break
+
+            wc = WordCloud(
+                font_path=font_path,
+                width=1200, height=800,
+                background_color="white",
+                max_words=200
+            ).generate(filtered_text)
+            
+            # 保存词云图
+            wc.to_file("./data/wordcloud.png")
+            plt.figure(figsize=(12, 8))
+            plt.imshow(wc)
+            plt.axis("off")
+            plt.title("弹幕高频词云图")
+            plt.show()
+            print("词云图已保存至./data/wordcloud.png")
+        except Exception as e:
+            print(f"生成词云失败：{e}")
+
+    def plot_top8_bar(self):
+        """绘制Top8高频词柱状图"""
+        # 新增：检查数据是否有效
+        if self.top8.empty or len(self.top8) < 8:
+            print("警告：统计数据不足，无法绘制柱状图")
+            return
+        
+        try:
+            plt.figure(figsize=(10, 6))
+            plt.bar(self.top8["关键词"], self.top8["词频"], color="skyblue")
+            plt.title("弹幕Top8高频词")
+            plt.xlabel("关键词")
+            plt.ylabel("词频")
+            plt.xticks(rotation=45)
+            plt.tight_layout()
+            plt.savefig("./data/top8_bar.png")
+            plt.show()
+            print("Top8柱状图已保存至./data/top8_bar.png")
+        except Exception as e:
+            print(f"绘制柱状图失败：{e}")