Delete app.py

app.py

@@ -1,621 +0,0 @@
-import streamlit as st
-import pandas as pd
-import uuid
-from datetime import datetime, timedelta
-import atexit
-import os
-import base64
-
-# 頁面配置
-st.set_page_config(
-    page_title="Bayesian Hierarchical Model - Pokémon Speed Analysis",
-    page_icon="⚡",
-    layout="wide",
-    initial_sidebar_state="expanded"
-)
-
-# 自定義 CSS
-st.markdown("""
-<style>
-    .streamlit-expanderHeader {
-        background-color: #e8f1f8;
-        border: 1px solid #b0cfe8;
-        border-radius: 5px;
-        font-weight: 600;
-        color: #1b4f72;
-    }
-    .streamlit-expanderHeader:hover {
-        background-color: #d0e7f8;
-    }
-    .stMetric {
-        background-color: #f8fbff;
-        padding: 10px;
-        border-radius: 5px;
-        border: 1px solid #d0e4f5;
-    }
-    .stButton > button {
-        width: 100%;
-        border-radius: 20px;
-        font-weight: 600;
-        transition: all 0.3s ease;
-    }
-    .stButton > button:hover {
-        transform: translateY(-2px);
-        box-shadow: 0 4px 8px rgba(0,0,0,0.2);
-    }
-    .success-box {
-        background-color: #d4edda;
-        border: 1px solid #c3e6cb;
-        border-radius: 5px;
-        padding: 10px;
-        margin: 10px 0;
-    }
-    .warning-box {
-        background-color: #fff3cd;
-        border: 1px solid #ffeaa7;
-        border-radius: 5px;
-        padding: 10px;
-        margin: 10px 0;
-    }
-    .info-box {
-        background-color: #d1ecf1;
-        border: 1px solid #bee5eb;
-        border-radius: 5px;
-        padding: 10px;
-        margin: 10px 0;
-    }
-</style>
-""", unsafe_allow_html=True)
-
-# 導入自定義模組
-from bayesian_core import BayesianHierarchicalAnalyzer
-from bayesian_llm_assistant import BayesianLLMAssistant
-
-# 清理函數
-def cleanup_old_sessions():
-    """清理超過 1 小時的 session"""
-    current_time = datetime.now()
-    for session_id in list(BayesianHierarchicalAnalyzer._session_results.keys()):
-        result = BayesianHierarchicalAnalyzer._session_results.get(session_id)
-        if result:
-            result_time = datetime.fromisoformat(result['timestamp'])
-            if current_time - result_time > timedelta(hours=1):
-                BayesianHierarchicalAnalyzer.clear_session_results(session_id)
-
-# 註冊清理函數
-atexit.register(cleanup_old_sessions)
-
-# 初始化 session state
-if 'session_id' not in st.session_state:
-    st.session_state.session_id = str(uuid.uuid4())
-if 'analysis_results' not in st.session_state:
-    st.session_state.analysis_results = None
-if 'chat_history' not in st.session_state:
-    st.session_state.chat_history = []
-if 'analyzer' not in st.session_state:
-    st.session_state.analyzer = None
-
-# 標題
-st.title("⚡ Bayesian Hierarchical Model Analysis")
-st.markdown("### 寶可夢速度對勝率影響的階層貝氏分析")
-st.markdown("---")
-
-# Sidebar
-with st.sidebar:
-    st.header("⚙️ 配置設定")
-    
-    # Google Gemini API Key
-    api_key = st.text_input(
-        "Google Gemini API Key",
-        type="password",
-        help="輸入您的 Google Gemini API Key 以使用 AI 助手"
-    )
-    
-    if api_key:
-        st.session_state.api_key = api_key
-        st.success("✅ API Key 已載入")
-    
-    st.markdown("---")
-    
-    # 清理按鈕
-    if st.button("🧹 清理過期資料"):
-        cleanup_old_sessions()
-        st.success("✅ 清理完成")
-        st.rerun()
-    
-    st.markdown("---")
-    
-    # 資料來源選擇
-    st.subheader("📊 資料來源")
-    data_source = st.radio(
-        "選擇資料來源：",
-        ["使用預設資料集", "上傳您的資料"]
-    )
-    
-    uploaded_file = None
-    if data_source == "上傳您的資料":
-        uploaded_file = st.file_uploader(
-            "上傳 CSV 檔案",
-            type=['csv'],
-            help="上傳寶可夢速度分析資料"
-        )
-        
-        with st.expander("📖 資料格式說明"):
-            st.markdown("""
-            **必要欄位格式：**
-            - `Trial_Type`: 寶可夢屬性（如 Water, Fire, Grass）
-            - `rc`: 控制組（速度慢）的勝場數
-            - `nc`: 控制組的總場數
-            - `rt`: 實驗組（速度快）的勝場數
-            - `nt`: 實驗組的總場數
-            
-            **範例：**
-            ```
-            Trial_Type, rc, nc, rt, nt
-            Water,      45, 100, 60, 100
-            Fire,       38, 100, 55, 100
-            Grass,      42, 100, 58, 100
-            ```
-            """)
-    
-    st.markdown("---")
-    
-    # MCMC 抽樣參數設定
-    st.subheader("🎲 MCMC 抽樣參數")
-    
-    with st.expander("⚙️ 進階設定"):
-        n_samples = st.slider(
-            "抽樣數 (Samples)",
-            min_value=500,
-            max_value=5000,
-            value=2000,
-            step=500,
-            help="更多樣本 = 更準確，但更慢"
-        )
-        
-        n_tune = st.slider(
-            "調整期樣本 (Tuning)",
-            min_value=500,
-            max_value=2000,
-            value=1000,
-            step=100,
-            help="調整期用於優化抽樣器"
-        )
-        
-        n_chains = st.selectbox(
-            "鏈數 (Chains)",
-            options=[1, 2, 4],
-            index=0,
-            help="多條鏈可以檢測收斂問題"
-        )
-        
-        target_accept = st.slider(
-            "目標接受率",
-            min_value=0.80,
-            max_value=0.99,
-            value=0.95,
-            step=0.01,
-            help="更高的接受率 = 更準確，但更慢"
-        )
-    
-    st.markdown("---")
-    
-    # 關於系統
-    with st.expander("ℹ️ 關於此系統"):
-        st.markdown("""
-        **貝氏階層模型分析系統**
-        
-        本系統使用貝氏階層模型來分析速度對不同屬性寶可夢勝率的影響。
-        
-        **主要功能：**
-        - 🔬 貝氏推論與 MCMC 抽樣
-        - 📊 階層模型（跨屬性資訊借用）
-        - 📈 完整視覺化（4 個圖表）
-        - 💬 AI 助手解釋
-        - 🎮 對戰策略建議
-        
-        **模型優勢：**
-        - 量化不確定性
-        - 處理小樣本
-        - 估計屬性間異質性
-        - 穩健的統計推論
-        """)
-
-# 主要內容區 - 雙 Tab
-tab1, tab2 = st.tabs(["📊 貝氏分析", "💬 AI 助手"])
-
-# Tab 1: 貝氏分析
-with tab1:
-    st.header("📊 貝氏階層模型分析")
-    
-    # 載入資料
-    if data_source == "使用預設資料集":
-        # 檢查預設資料是否存在
-        default_data_path = "pokemon_speed_meta_results.csv"
-        if os.path.exists(default_data_path):
-            df = pd.read_csv(default_data_path)
-            st.success(f"✅ 已載入預設資料集（{len(df)} 個屬性）")
-        else:
-            st.warning("⚠️ 找不到預設資料集，請上傳您的資料")
-            df = None
-    else:
-        if uploaded_file is not None:
-            df = pd.read_csv(uploaded_file)
-            st.success(f"✅ 已載入資料（{len(df)} 個屬性）")
-        else:
-            df = None
-            st.info("📁 請在左側上傳 CSV 檔案")
-    
-    if df is not None:
-        # 顯示資料預覽
-        with st.expander("👀 資料預覽"):
-            st.dataframe(df, use_container_width=True)
-        
-        st.markdown("---")
-        
-        # 執行分析按鈕
-        col1, col2, col3 = st.columns([2, 1, 2])
-        
-        with col2:
-            analyze_button = st.button("🔬 開始貝氏分析", type="primary", use_container_width=True)
-        
-        # 執行分析
-        if analyze_button:
-            # 初始化分析器
-            if st.session_state.analyzer is None:
-                st.session_state.analyzer = BayesianHierarchicalAnalyzer(st.session_state.session_id)
-            
-            try:
-                st.session_state.analyzer.load_data(df)
-                
-                # 進度條
-                progress_bar = st.progress(0)
-                status_text = st.empty()
-                
-                def update_progress(message, percent):
-                    status_text.text(message)
-                    progress_bar.progress(percent / 100)
-                
-                # 執行分析
-                with st.spinner("正在執行貝氏分析..."):
-                    results = st.session_state.analyzer.run_analysis(
-                        n_samples=n_samples,
-                        n_tune=n_tune,
-                        n_chains=n_chains,
-                        target_accept=target_accept,
-                        progress_callback=update_progress
-                    )
-                    st.session_state.analysis_results = results
-                
-                progress_bar.empty()
-                status_text.empty()
-                st.success("✅ 分析完成！")
-                st.balloons()
-                
-            except Exception as e:
-                st.error(f"❌ 分析失敗: {str(e)}")
-        
-        # 顯示結果
-        if st.session_state.analysis_results is not None:
-            results = st.session_state.analysis_results
-            
-            st.markdown("---")
-            st.markdown("## 📈 分析結果")
-            
-            # 建立 4 個子 Tab
-            result_tabs = st.tabs(["📊 概覽", "📉 Trace Plot", "🎯 Posterior", "🌲 Forest Plot"])
-            
-            # Tab: 概覽
-            with result_tabs[0]:
-                st.markdown("### 🎯 關鍵指標")
-                
-                # 顯示關鍵指標
-                col1, col2, col3 = st.columns(3)
-                
-                with col1:
-                    st.metric(
-                        label="整體效應 (d)",
-                        value=f"{results['d_mean']:.4f}",
-                        delta=f"HDI: [{results['d_hdi_lower']:.3f}, {results['d_hdi_upper']:.3f}]"
-                    )
-                
-                with col2:
-                    st.metric(
-                        label="屬性間變異 (sigma)",
-                        value=f"{results['sigma_mean']:.4f}",
-                        delta=f"SD: {results['sigma_sd']:.4f}"
-                    )
-                
-                with col3:
-                    st.metric(
-                        label="速度勝算比 (OR)",
-                        value=f"{results['or_speed_mean']:.3f}",
-                        delta=f"HDI: [{results['or_speed_hdi_lower']:.3f}, {results['or_speed_hdi_upper']:.3f}]"
-                    )
-                
-                st.markdown("---")
-                
-                # 顯著性判斷
-                if results['is_significant']:
-                    st.markdown("""
-                    <div class="success-box">
-                    <h4>✅ 結果顯著</h4>
-                    <p>速度對勝率有<strong>顯著影響</strong>（95% HDI 不包含 0）</p>
-                    </div>
-                    """, unsafe_allow_html=True)
-                else:
-                    st.markdown("""
-                    <div class="warning-box">
-                    <h4>⚠️ 結果不顯著</h4>
-                    <p>速度對勝率<strong>無顯著影響</strong>（95% HDI 包含 0）</p>
-                    </div>
-                    """, unsafe_allow_html=True)
-                
-                st.markdown("---")
-                
-                # 文字摘要
-                st.markdown("### 📋 統計摘要")
-                st.text_area(
-                    "Summary Statistics",
-                    results['summary_text'],
-                    height=300
-                )
-                
-                # 下載摘要
-                st.download_button(
-                    label="📥 下載統計摘要 (.txt)",
-                    data=results['summary_text'],
-                    file_name=f"bayesian_summary_{results['timestamp'][:10]}.txt",
-                    mime="text/plain"
-                )
-                
-                st.markdown("---")
-                
-                # 各屬性詳細結果
-                st.markdown("### 🎮 各屬性詳細結果")
-                
-                delta_df = pd.DataFrame(results['delta_results'])
-                delta_df['Significant'] = delta_df['is_significant'].apply(lambda x: '★' if x else '')
-                delta_df = delta_df[['trial_type', 'delta_mean', 'delta_sd', 'delta_hdi_lower', 'delta_hdi_upper', 'Significant']]
-                delta_df.columns = ['屬性', 'Delta 平均', 'Delta 標準差', 'HDI 下界', 'HDI 上界', '顯著']
-                
-                st.dataframe(
-                    delta_df.style.format({
-                        'Delta 平均': '{:.4f}',
-                        'Delta 標準差': '{:.4f}',
-                        'HDI 下界': '{:.4f}',
-                        'HDI 上界': '{:.4f}'
-                    }),
-                    use_container_width=True
-                )
-            
-            # Tab: Trace Plot
-            with result_tabs[1]:
-                st.markdown("### 📉 Trace Plot - 收斂診斷")
-                
-                st.markdown("""
-                <div class="info-box">
-                <h4>📖 如何解讀 Trace Plot：</h4>
-                <ul>
-                <li><strong>左欄</strong>：MCMC 抽樣軌跡（應該像「毛毛蟲」，平穩無趨勢）</li>
-                <li><strong>右欄</strong>：後驗分佈密度圖</li>
-                <li><strong>良好收斂</strong>：軌跡圖混合良好，無明顯趨勢或週期</li>
-                <li><strong>問題跡象</strong>：軌跡圖有趨勢、卡住、或未混合</li>
-                </ul>
-                </div>
-                """, unsafe_allow_html=True)
-                
-                if results['trace_plot']:
-                    st.image(f"data:image/png;base64,{results['trace_plot']}", use_column_width=True)
-                else:
-                    st.warning("⚠️ Trace Plot 未生成")
-            
-            # Tab: Posterior Plot
-            with result_tabs[2]:
-                st.markdown("### 🎯 Posterior Distributions - 後驗分佈")
-                
-                st.markdown("""
-                <div class="info-box">
-                <h4>📖 如何解讀 Posterior Plot：</h4>
-                <ul>
-                <li><strong>d</strong>：整體平均效應（log odds ratio）</li>
-                <li><strong>sigma</strong>：屬性間變異（越大表示屬性間差異越大）</li>
-                <li><strong>or_speed</strong>：速度勝算比（exp(d)）</li>
-                <li><strong>95% HDI</strong>：最高密度區間（類似信賴區間）</li>
-                <li><strong>顯著性</strong>：HDI 不包含 0（d）或 1（or_speed）即為顯著</li>
-                </ul>
-                </div>
-                """, unsafe_allow_html=True)
-                
-                if results['posterior_plot']:
-                    st.image(f"data:image/png;base64,{results['posterior_plot']}", use_column_width=True)
-                else:
-                    st.warning("⚠️ Posterior Plot 未生成")
-            
-            # Tab: Forest Plot
-            with result_tabs[3]:
-                st.markdown("### 🌲 Forest Plot - 各屬性效應")
-                
-                st.markdown("""
-                <div class="info-box">
-                <h4>📖 如何解讀 Forest Plot：</h4>
-                <ul>
-                <li><strong>點</strong>：各屬性的平均效應（delta）</li>
-                <li><strong>橫線</strong>：95% 信賴區間</li>
-                <li><strong>紅虛線</strong>：無效應參考線（delta = 0）</li>
-                <li><strong>星號 ★</strong>：該屬性效應顯著</li>
-                <li><strong>右側</strong>：速度快有利於該屬性</li>
-                <li><strong>左側</strong>：速度慢有利於該屬性（罕見）</li>
-                </ul>
-                </div>
-                """, unsafe_allow_html=True)
-                
-                if results['forest_plot']:
-                    st.image(f"data:image/png;base64,{results['forest_plot']}", use_column_width=True)
-                else:
-                    st.warning("⚠️ Forest Plot 未生成")
-                
-                st.markdown("---")
-                
-                # 顯著屬性總結
-                significant_types = [dr for dr in results['delta_results'] if dr['is_significant']]
-                
-                if significant_types:
-                    st.markdown(f"### ⭐ 顯著屬性總結 ({len(significant_types)}/{results['n_trials']})")
-                    
-                    for dr in significant_types:
-                        if dr['delta_mean'] > 0:
-                            st.success(f"**{dr['trial_type']}**: 速度快有顯著優勢 (Delta = {dr['delta_mean']:.3f})")
-                        else:
-                            st.warning(f"**{dr['trial_type']}**: 速度慢有顯著優勢 (Delta = {dr['delta_mean']:.3f})")
-                else:
-                    st.info("沒有屬性顯示顯著的速度效應")
-
-# Tab 2: AI 助手
-with tab2:
-    st.header("💬 AI 分析助手")
-    
-    if not st.session_state.get('api_key'):
-        st.warning("⚠️ 請在左側輸入您的 Google Gemini API Key 以使用 AI 助手")
-    elif st.session_state.analysis_results is None:
-        st.info("ℹ️ 請先在「貝氏分析」頁面執行分析")
-    else:
-        # 初始化 LLM 助手
-        if 'llm_assistant' not in st.session_state:
-            st.session_state.llm_assistant = BayesianLLMAssistant(
-                api_key=st.session_state.api_key,
-                session_id=st.session_state.session_id
-            )
-        
-        # 聊天容器
-        chat_container = st.container()
-        
-        with chat_container:
-            for message in st.session_state.chat_history:
-                with st.chat_message(message["role"]):
-                    st.markdown(message["content"])
-        
-        # 使用者輸入
-        if prompt := st.chat_input("詢問關於分析結果的任何問題..."):
-            # 添加使用者訊息
-            st.session_state.chat_history.append({
-                "role": "user",
-                "content": prompt
-            })
-            
-            with st.chat_message("user"):
-                st.markdown(prompt)
-            
-            # AI 回應
-            with st.chat_message("assistant"):
-                with st.spinner("思考中..."):
-                    try:
-                        response = st.session_state.llm_assistant.get_response(
-                            user_message=prompt,
-                            analysis_results=st.session_state.analysis_results
-                        )
-                        st.markdown(response)
-                    except Exception as e:
-                        error_msg = f"❌ 錯誤: {str(e)}\n\n請檢查 API key 或重新表達問題。"
-                        st.error(error_msg)
-                        response = error_msg
-            
-            # 添加助手回應
-            st.session_state.chat_history.append({
-                "role": "assistant",
-                "content": response
-            })
-        
-        st.markdown("---")
-        
-        # 快速問題按鈕
-        st.subheader("💡 快速問題")
-        
-        quick_questions = [
-            "📊 給我分析總結",
-            "🎯 解釋 d 參數",
-            "🔍 解釋 sigma",
-            "📖 什麼是貝氏統計？",
-            "🏗️ 什麼是階層模型？",
-            "📉 如何看 Trace Plot？",
-            "🎮 比較各屬性",
-            "⚔️ 對戰策略建議"
-        ]
-        
-        cols = st.columns(4)
-        for idx, question in enumerate(quick_questions):
-            col_idx = idx % 4
-            if cols[col_idx].button(question, key=f"quick_{idx}", use_container_width=True):
-                # 根據問題選擇對應的方法
-                if "總結" in question:
-                    response = st.session_state.llm_assistant.generate_summary(
-                        st.session_state.analysis_results
-                    )
-                elif "d 參數" in question:
-                    response = st.session_state.llm_assistant.explain_metric(
-                        'd',
-                        st.session_state.analysis_results
-                    )
-                elif "sigma" in question:
-                    response = st.session_state.llm_assistant.explain_metric(
-                        'sigma',
-                        st.session_state.analysis_results
-                    )
-                elif "貝氏統計" in question:
-                    response = st.session_state.llm_assistant.explain_bayesian_concepts()
-                elif "階層模型" in question:
-                    response = st.session_state.llm_assistant.explain_hierarchical_model()
-                elif "Trace Plot" in question:
-                    response = st.session_state.llm_assistant.explain_convergence()
-                elif "比較" in question:
-                    response = st.session_state.llm_assistant.compare_types(
-                        st.session_state.analysis_results
-                    )
-                elif "策略" in question:
-                    response = st.session_state.llm_assistant.battle_strategy_advice(
-                        st.session_state.analysis_results
-                    )
-                else:
-                    response = st.session_state.llm_assistant.get_response(
-                        question,
-                        st.session_state.analysis_results
-                    )
-                
-                st.session_state.chat_history.append({
-                    "role": "user",
-                    "content": question
-                })
-                
-                st.session_state.chat_history.append({
-                    "role": "assistant",
-                    "content": response
-                })
-                
-                st.rerun()
-        
-        # 重置對話按鈕
-        st.markdown("---")
-        if st.button("🔄 重置對話"):
-            st.session_state.llm_assistant.reset_conversation()
-            st.session_state.chat_history = []
-            st.success("✅ 對話已重置")
-            st.rerun()
-
-# DAG 圖（如果有的話，放在側邊欄底部）
-if st.session_state.analysis_results and st.session_state.analysis_results.get('dag_plot'):
-    with st.sidebar:
-        st.markdown("---")
-        with st.expander("🔀 DAG 模型結構圖"):
-            st.image(f"data:image/png;base64,{st.session_state.analysis_results['dag_plot']}")
-
-# Footer
-st.markdown("---")
-st.markdown(
-    f"""
-    <div style='text-align: center'>
-        <p>⚡ Bayesian Hierarchical Model for Pokémon Speed Analysis | Built with PyMC & Streamlit</p>
-        <p>Session ID: {st.session_state.session_id[:8]} | Powered by Google Gemini</p>
-    </div>
-    """,
-    unsafe_allow_html=True
-)