from crawler import BilibiliDanmuCrawler
from data_processor import DataProcessor
from visualizer import Visualizer
import pandas as pd

def generate_conclusions(top_apps: pd.DataFrame, word_freq: pd.DataFrame, processed_df: pd.DataFrame):
    """生成分析结论"""
    print("\n" + "=" * 60)
    print("                   大语言模型应用分析结论")
    print("=" * 60)
    
    # 1. 主流应用领域
    print("\n📊 1. 主流应用领域分析:")
    for i, (app, count) in enumerate(zip(top_apps['应用领域'], top_apps['出现次数']), 1):
        percentage = (count / top_apps['出现次数'].sum()) * 100
        print(f"   {i}. {app}: {count}次提及 ({percentage:.1f}%)")
    
    # 2. 技术关注点
    print("\n🔬 2. 技术关注点分析:")
    tech_keywords = ['模型', 'AI', '智能', '生成', '训练', '部署', '算法']
    tech_words = [word for word, freq in zip(word_freq['词语'], word_freq['频次']) 
                 if any(kw in word for kw in tech_keywords)][:8]
    print(f"   技术相关高频词: {', '.join(tech_words)}")
    
    # 3. 用户态度分析
    positive_words = ['好', '强', '棒', '方便', '高效', '推荐', '优秀', '实用']
    negative_words = ['问题', '担心', '风险', '贵', '难', '复杂', '取代', '改进']
    
    positive_count = sum(freq for word, freq in zip(word_freq['词语'], word_freq['频次']) 
                        if any(pw in word for pw in positive_words))
    negative_count = sum(freq for word, freq in zip(word_freq['词语'], word_freq['频次']) 
                        if any(nw in word for nw in negative_words))
    
    total_attitude = positive_count + negative_count
    if total_attitude > 0:
        positive_ratio = (positive_count / total_attitude) * 100
    else:
        positive_ratio = 0
    
    print(f"\n😊 3. 用户态度倾向分析:")
    print(f"   积极态度词汇出现次数: {positive_count}")
    print(f"   消极态度词汇出现次数: {negative_count}")
    print(f"   积极评价占比: {positive_ratio:.1f}%")
    
    # 4. 应用成本关注
    cost_keywords = ['成本', '价格', '收费', '免费', '贵', '费用']
    cost_mentions = sum(1 for danmu in processed_df['original_danmu'] 
                       if any(ck in danmu for ck in cost_keywords))
    print(f"\n💰 4. 应用成本关注度: {cost_mentions}次提及")
    
    # 5. 就业影响关注
    employment_keywords = ['取代', '就业', '工作', '岗位', '职业', '失业']
    employment_mentions = sum(1 for danmu in processed_df['original_danmu'] 
                            if any(ek in danmu for ek in employment_keywords))
    print(f"👥 5. 就业影响关注度: {employment_mentions}次提及")
    
    # 6. 数据安全隐私关注
    security_keywords = ['隐私', '安全', '数据', '泄露', '保护']
    security_mentions = sum(1 for danmu in processed_df['original_danmu'] 
                          if any(sk in danmu for sk in security_keywords))
    print(f"🔒 6. 数据安全隐私关注度: {security_mentions}次提及")
    
    # 7. 主要结论
    print("\n🎯 7. 主要结论:")
    conclusions = [
        "大语言模型在编程开发和内容创作领域应用最为广泛",
        "用户对AI技术的积极评价占主导地位",
        "应用成本和就业影响是用户主要关注点",
        "数据安全和隐私保护意识逐渐增强",
        "多模态和本地部署成为技术发展趋势"
    ]
    
    for i, conclusion in enumerate(conclusions, 1):
        print(f"   • {conclusion}")

def main():
    print("=" * 50)
    print("   大语言模型应用评论分析系统")
    print("=" * 50)
    
    try:
        # 步骤1: 数据爬取
        print("\n🚀 步骤1: 数据爬取")
        from crawler import main as crawler_main
        raw_df = crawler_main()
        
        # 步骤2: 数据处理
        print("\n🔧 步骤2: 数据处理")
        from data_processor import main as processor_main
        processed_df, top_apps, word_freq = processor_main()
        
        # 步骤3: 数据可视化
        print("\n📈 步骤3: 数据可视化")
        from visualizer import main as visualizer_main
        visualizer_main()
        
        # 步骤4: 生成分析报告
        print("\n📝 步骤4: 生成分析结论")
        generate_conclusions(top_apps, word_freq, processed_df)
        
        print("\n✅ 分析完成！所有结果已保存到相应目录。")
        
    except Exception as e:
        print(f"❌ 程序执行出错: {e}")
        print("请检查依赖是否安装正确，或查看具体错误信息")

if __name__ == "__main__":
    main()