app.py

import streamlit as st
import pandas as pd
import plotly.express as px
import os
import re
import io
import base64

# ============================================
# 0. 页面配置与CSS
# ============================================
st.set_page_config(
    page_title="高校中华民族共同体分析平台",
    layout="wide",
    initial_sidebar_state="expanded"
)

st.markdown("""
    <style>
    /* 全局基础 */
    html, body, [class*="css"] { 
        font-family: 'Microsoft YaHei', 'SimHei', sans-serif; 
        color: #333;
    }
    
    .stApp { 
        background-color: #FFFCF8;
        background-image: 
            radial-gradient(circle at 20% 50%, rgba(222, 41, 16, 0.03) 0%, transparent 50%),
            radial-gradient(circle at 80% 80%, rgba(255, 215, 0, 0.03) 0%, transparent 50%);
    }
    
    /* ========== 顶部标题区域 ========== */
    .header-container {
        background: linear-gradient(135deg, #DE2910 0%, #C41E0B 100%);
        padding: 20px 0;
        margin: -1rem -1rem 0 -1rem;
        box-shadow: 0 4px 20px rgba(222, 41, 16, 0.3);
        position: relative;
        overflow: hidden;
    }
    
    .header-container::before {
        content: "";
        position: absolute;
        bottom: 0;
        left: 0;
        right: 0;
        height: 3px;
        background: linear-gradient(90deg, transparent, #FFD700, #FFA500, #FFD700, transparent);
    }
    
    .title-wrapper { 
        display: flex; 
        align-items: center; 
        justify-content: center; 
        gap: 20px; 
        position: relative;
        z-index: 2;
        max-width: 1400px;
        margin: 0 auto;
        padding: 0 20px;
    }
    
    .badge-left, .badge-right {
        flex-shrink: 0;
        width: 80px;
        height: 80px;
        border-radius: 50%;
        border: 3px solid #FFD700;
        box-shadow: 
            0 4px 15px rgba(0,0,0,0.3),
            0 0 0 4px rgba(222, 41, 16, 0.2),
            inset 0 0 20px rgba(255, 215, 0, 0.1);
        overflow: hidden;
        background: linear-gradient(135deg, #FFFFFF 0%, #FFF9F9 100%);
        transition: transform 0.3s ease;
    }
    
    .badge-left:hover, .badge-right:hover {
        transform: scale(1.05) rotate(5deg);
    }
    
    .badge-left img, .badge-right img {
        width: 100%;
        height: 100%;
        object-fit: cover;
    }
    
    .title-center {
        flex: 1;
        text-align: center;
    }
    
    .gold-line { 
        height: 2px; 
        width: 80px; 
        background: linear-gradient(90deg, transparent, #FFD700, #FFA500, #FFD700, transparent); 
        flex-shrink: 0;
        box-shadow: 0 0 10px rgba(255, 215, 0, 0.5);
    }
    
    .main-title { 
        text-align: center; 
        color: #FFFFFF; 
        font-size: 32px; 
        font-weight: bold; 
        margin: 0; 
        white-space: nowrap;
        text-shadow: 2px 2px 4px rgba(0,0,0,0.3);
        letter-spacing: 2px;
    }
    
    .sub-title { 
        text-align: center; 
        color: #FFD700; 
        font-size: 16px; 
        margin-top: 8px;
        font-weight: 500;
        letter-spacing: 1px;
        text-shadow: 1px 1px 2px rgba(0,0,0,0.2);
    }
    
    /* ========== 导航栏 ========== */
    .nav-container {
        background: linear-gradient(to bottom, #FFFFFF 0%, #FFF9F9 100%);
        border-bottom: 2px solid #FFD700;
        padding: 10px 20px;
        margin: 0 -1rem 15px -1rem;
        box-shadow: 0 2px 10px rgba(0,0,0,0.05);
    }
    
    /* ========== 内容卡片 ========== */
    .content-card {
        background: #FFFFFF;
        border-radius: 12px;
        padding: 20px;
        margin: 0 0 20px 0;
        box-shadow: 0 4px 20px rgba(0,0,0,0.08);
        border-top: 4px solid #DE2910;
        position: relative;
        overflow: hidden;
    }
    
    .content-card::before {
        content: "";
        position: absolute;
        top: 0;
        right: 0;
        width: 100px;
        height: 100px;
        background: radial-gradient(circle, rgba(255, 215, 0, 0.1) 0%, transparent 70%);
        pointer-events: none;
    }
    
    /* ========== 图表区域 ========== */
    .chart-wrapper {
        width: 100%;
        height: 480px;
        margin: 10px 0;
    }
    
    /* ========== 地图区域 ========== */
    .map-wrapper {
        width: 100%;
        height: 520px;
        margin: 10px 0;
    }
    
    .map-container {
        width: 100%;
        height: 100%;
        position: relative;
        display: flex;
        align-items: center;
        justify-content: center;
        background: linear-gradient(135deg, #FFF9F9 0%, #FFFFFF 100%);
        border: 3px solid #FFD700;
        border-radius: 12px;
        overflow: hidden;
    }
    
    .map-container img {
        max-width: 100%;
        max-height: 100%;
        object-fit: contain;
        border-radius: 8px;
    }
    
    .map-placeholder {
        display: flex;
        align-items: center;
        justify-content: center;
        flex-direction: column;
        color: #DE2910;
        font-weight: bold;
    }
    
    /* ========== 按钮优化 ========== */
    div.stButton > button { 
        background: linear-gradient(135deg, #DE2910 0%, #C41E0B 100%);
        color: white; 
        border-radius: 6px; 
        border: none;
        font-weight: bold;
        padding: 8px 20px;
        transition: all 0.3s ease;
        box-shadow: 0 4px 15px rgba(222, 41, 16, 0.3);
    }
    
    div.stButton > button:hover { 
        background: linear-gradient(135deg, #C41E0B 0%, #A01810 100%);
        color: #FFD700;
        transform: translateY(-2px);
        box-shadow: 0 6px 20px rgba(222, 41, 16, 0.4);
    }
    
    /* 导航按钮选中状态 */
    div[data-testid="column"] > div > div > div > div > div > button[kind="primary"] {
        background: linear-gradient(135deg, #FFD700 0%, #FFA500 100%) !important;
        color: #DE2910 !important;
        border: 2px solid #DE2910 !important;
        font-weight: bold !important;
    }
    
    /* ========== 侧边栏 ========== */
    [data-testid="stSidebar"] { 
        background: linear-gradient(180deg, #FFF9F9 0%, #FFFFFF 100%);
        border-right: 3px solid #DE2910;
        min-width: 320px !important;
        max-width: 350px !important;
        box-shadow: 2px 0 15px rgba(0,0,0,0.1);
    }
    
    .sidebar-card { 
        background: linear-gradient(135deg, #FFFFFF 0%, #FFFCF8 100%);
        padding: 15px; 
        border-radius: 10px; 
        border: 1px solid rgba(222, 41, 16, 0.1);
        margin-bottom: 15px; 
        box-shadow: 0 4px 6px rgba(0,0,0,0.05);
    }
    
    .sidebar-title { 
        color: #DE2910; 
        font-size: 15px; 
        font-weight: bold; 
        margin-bottom: 10px; 
        border-left: 4px solid #FFD700; 
        padding-left: 10px;
        display: flex;
        align-items: center;
        gap: 8px;
    }
    
    /* ========== 底部信息 ========== */
    .footer { 
        text-align: center; 
        color: #666; 
        font-size: 13px; 
        margin-top: 30px; 
        padding: 20px; 
        border-top: 2px solid rgba(222, 41, 16, 0.1);
    }
    
    /* ========== 标题样式 ========== */
    h3 {
        color: #DE2910;
        font-size: 20px;
        margin-bottom: 15px;
        padding-bottom: 8px;
        border-bottom: 3px solid #FFD700;
        display: inline-block;
        position: relative;
    }
    
    h3::after {
        content: "";
        position: absolute;
        bottom: -3px;
        left: 0;
        width: 50%;
        height: 3px;
        background: #DE2910;
        border-radius: 0 2px 2px 0;
    }
    
    /* ========== 信息提示框 ========== */
    .stInfo {
        background: linear-gradient(135deg, #FFF9F9 0%, #FFFFFF 100%) !important;
        border-left: 4px solid #DE2910 !important;
        border-radius: 8px !important;
    }
    
    .stSuccess {
        background: linear-gradient(135deg, #F0FFF0 0%, #FFFFFF 100%) !important;
        border-left: 4px solid #28a745 !important;
        border-radius: 8px !important;
    }
    
    /* ========== 隐藏默认元素 ========== */
    #MainMenu {visibility: hidden;}
    footer {visibility: hidden;}
    header {visibility: hidden;}
    
    /* ========== 数据表格 ========== */
    .dataframe {
        border-radius: 8px;
        overflow: hidden;
        border: 1px solid rgba(222, 41, 16, 0.1);
    }
    
    .dataframe th {
        background: linear-gradient(135deg, #DE2910 0%, #C41E0B 100%) !important;
        color: white !important;
        font-weight: bold;
        padding: 12px !important;
    }
    
    .dataframe td {
        padding: 10px !important;
        border-bottom: 1px solid rgba(0,0,0,0.05);
    }
    
    /* ========== 欢迎页面 ========== */
    .welcome-container {
        text-align: center;
        padding: 40px 20px;
        background: linear-gradient(135deg, #FFFFFF 0%, #FFF9F9 100%);
        border-radius: 15px;
        margin: 0 0 20px 0;
        box-shadow: 0 4px 20px rgba(0,0,0,0.08);
        border-top: 4px solid #DE2910;
    }
    </style>
    """, unsafe_allow_html=True)

# ============================================
# 1. 顶部标题栏
# ============================================
def render_header():
    badge_left_html = ""
    badge_right_html = ""
    
    if os.path.exists("xiaohui.jpg.jpg"):
        with open("xiaohui.jpg.jpg", "rb") as f:
            badge_left_b64 = base64.b64encode(f.read()).decode()
        badge_left_html = f'<div class="badge-left"><img src="data:image/jpeg;base64,{badge_left_b64}" alt="校徽"></div>'
    else:
        badge_left_html = '<div class="badge-left" style="display: flex; align-items: center; justify-content: center; color: #DE2910; font-size: 32px; font-weight: bold;">校</div>'
    
    if os.path.exists("duihui.jpg"):
        with open("duihui.jpg", "rb") as f:
            badge_right_b64 = base64.b64encode(f.read()).decode()
        badge_right_html = f'<div class="badge-right"><img src="data:image/jpeg;base64,{badge_right_b64}" alt="队徽"></div>'
    else:
        badge_right_html = '<div class="badge-right" style="display: flex; align-items: center; justify-content: center; color: #DE2910; font-size: 32px; font-weight: bold;">队</div>'
    
    st.markdown(f"""
        <div class="header-container">
            <div class="title-wrapper">
                {badge_left_html}
                <div class="gold-line"></div>
                <div class="title-center">
                    <h1 class="main-title">高校中华民族共同体意识传播分析平台</h1>
                    <p class="sub-title">基于大数据与大模型的情感分析及传播效果优化系统</p>
                </div>
                <div class="gold-line"></div>
                {badge_right_html}
            </div>
        </div>
    """, unsafe_allow_html=True)

render_header()

# ============================================
# 2. 顶部导航栏
# ============================================
if 'current_tab' not in st.session_state:
    st.session_state.current_tab = "CPI排行"

tabs = ["CPI排行", "话语提取", "情感对比", "热度地图", "优化策略", "学术语境分析"]
tab_icons = ["📊", "🗣️", "🧠", "🗺️", "💡", "📚"]

st.markdown('<div class="nav-container">', unsafe_allow_html=True)
nav_cols = st.columns(len(tabs))  # 动态适应标签数量
for i, (tab, icon) in enumerate(zip(tabs, tab_icons)):
    with nav_cols[i]:
        is_active = st.session_state.current_tab == tab
        btn_type = "primary" if is_active else "secondary"
        
        if st.button(f"{icon} {tab}", key=f"nav_{tab}", use_container_width=True, type=btn_type):
            st.session_state.current_tab = tab
            st.rerun()
st.markdown('</div>', unsafe_allow_html=True)

# ============================================
# 3. 登录与状态管理
# ============================================
if 'auth' not in st.session_state:
    st.session_state.auth = False
if 'ask' not in st.session_state:
    st.session_state.ask = False

login_col = st.columns([12, 1])[1]
with login_col:
    if st.session_state.auth:
        if st.button("🚪 退出", key="logout_btn"):
            st.session_state.auth = False
            st.rerun()
    else:
        if st.button("🔐 管理", key="login_btn"):
            st.session_state.ask = True

if st.session_state.get('ask') and not st.session_state.auth:
    with st.form("login_form"):
        pwd = st.text_input("请输入管理口令", type="password")
        if st.form_submit_button("进入系统"):
            if pwd == "0166":
                st.session_state.auth = True
                st.session_state.ask = False
                st.rerun()

# ============================================
# 4. 辅助函数
# ============================================
@st.cache_data
def read_data_file_cached(file_bytes, file_name):
    try:
        fname = file_name.lower()
        if fname.endswith('.csv'):
            for encoding in ['utf-8-sig', 'utf-8', 'gbk', 'gb2312']:
                try:
                    return pd.read_csv(io.BytesIO(file_bytes), encoding=encoding)
                except:
                    continue
            return pd.read_csv(io.BytesIO(file_bytes), encoding='utf-8', errors='ignore')
        elif fname.endswith(('.xlsx', '.xls')):
            return pd.read_excel(io.BytesIO(file_bytes), engine='openpyxl')
        elif fname.endswith('.docx'):
            try:
                from docx import Document
                doc = Document(io.BytesIO(file_bytes))
                text_data = []
                for para in doc.paragraphs:
                    if para.text.strip():
                        text_data.append({'内容': para.text.strip()})
                for table in doc.tables:
                    for row in table.rows:
                        row_data = [cell.text for cell in row.cells]
                        if len(row_data) >= 2:
                            text_data.append({'标题': row_data[0], '内容': row_data[1]})
                return pd.DataFrame(text_data)
            except ImportError:
                return None
        return None
    except Exception as e:
        return None

def read_data_file(file):
    file_bytes = file.read()
    file.seek(0)
    return read_data_file_cached(file_bytes, file.name)

# ---------- 新增：学术分析辅助函数 ----------
def analyze_text_sentiment(texts, keyword):
    import random
    if not texts:
        return {'sentiment': '中性', 'score': 0.5, 'example': ''}
    sample = str(texts[0]) if texts else ""
    positive_keywords = ['铸牢', '认同', '团结', '融合', '共同体', '凝聚', '进步', '发展']
    negative_keywords = ['破坏', '分裂', '歧视', '冲突', '对立', '矛盾']
    score = 0.5
    sentiment = '中性'
    text_lower = sample.lower()
    pos_count = sum(1 for p in positive_keywords if p in text_lower)
    neg_count = sum(1 for n in negative_keywords if n in text_lower)
    if pos_count > neg_count:
        score = 0.5 + min(0.5, pos_count * 0.1)
        sentiment = '积极'
    elif neg_count > pos_count:
        score = max(0.0, 0.5 - neg_count * 0.1)
        sentiment = '消极'
    else:
        score = 0.5 + random.uniform(-0.1, 0.1)
        sentiment = '中性'
    return {'sentiment': sentiment, 'score': round(score, 2), 'example': sample[:100]}

def generate_academic_insights(analysis_results, target_words):
    insights = []
    regions = set([r['地区'] for r in analysis_results if '地区' in r])
    if len(regions) > 1:
        insights.append({'title': '🌍 地域表述差异', 'content': f'发现{len(regions)}个不同地区的表述差异，建议针对性地调整传播策略。'})
    sentiments = [r.get('语义倾向', '中性') for r in analysis_results]
    pos_ratio = sentiments.count('积极') / len(sentiments) if sentiments else 0
    if pos_ratio > 0.7:
        insights.append({'title': '📈 积极语义主导', 'content': f'{pos_ratio*100:.0f}%的表述呈现积极语义倾向，整体舆论环境良好。'})
    elif pos_ratio < 0.3:
        insights.append({'title': '⚠️ 消极语义警示', 'content': f'消极语义占比{(1-pos_ratio)*100:.0f}%，需关注潜在风险点。'})
    word_coverage = len(set([r['关键词'] for r in analysis_results]))
    insights.append({'title': '🎯 关键词覆盖', 'content': f'成功识别{word_coverage}个核心词汇的语境使用模式。'})
    return insights
# ---------- 结束 ----------

# ============================================
# 5. 侧边栏
# ============================================
if st.session_state.auth:
    with st.sidebar:
        st.markdown('<p style="color:#DE2910; font-size:18px; font-weight:bold; margin-bottom:15px; text-align: center; border-bottom: 2px solid #FFD700; padding-bottom: 10px;">📥 数据管理中心</p>', unsafe_allow_html=True)

        with st.container():
            st.markdown('<div class="sidebar-card"><div class="sidebar-title">🏫 高校官方数据</div>', unsafe_allow_html=True)
            f_u = st.file_uploader("上传高校数据", accept_multiple_files=True,
                                   type=['csv', 'xlsx', 'xls'], label_visibility="collapsed", key="uploader_u")
            if f_u:
                st.success(f"✅ 已选 {len(f_u)} 个文件")
            st.markdown('</div>', unsafe_allow_html=True)

            st.markdown('<div class="sidebar-card"><div class="sidebar-title">💬 社媒反馈语料</div>', unsafe_allow_html=True)
            f_s = st.file_uploader("上传社媒数据", accept_multiple_files=True,
                                   type=['csv', 'xlsx', 'xls'], label_visibility="collapsed", key="uploader_s")
            if f_s:
                st.success(f"✅ 已选 {len(f_s)} 个文件")
            st.markdown('</div>', unsafe_allow_html=True)

            st.markdown('<div class="sidebar-card"><div class="sidebar-title">💡 优化策略数据(可选)</div>', unsafe_allow_html=True)
            f_p = st.file_uploader("上传策略数据", accept_multiple_files=True,
                                   type=['csv', 'xlsx', 'xls', 'docx'], label_visibility="collapsed", key="uploader_p")
            if f_p:
                st.success(f"✅ 已选 {len(f_p)} 个文件")
            st.markdown('</div>', unsafe_allow_html=True)

            st.markdown('<div class="sidebar-card"><div class="sidebar-title">🗺️ 热度地图(可选)</div>', unsafe_allow_html=True)
            f_map = st.file_uploader("上传地图图片", accept_multiple_files=False,
                                     type=['jpg', 'jpeg', 'png'], label_visibility="collapsed", key="uploader_map")
            if f_map:
                map_bytes = f_map.read()
                with open("ditu.jpg", "wb") as f:
                    f.write(map_bytes)
                st.success(f"✅ 地图已上传: {f_map.name}")
            st.markdown('</div>', unsafe_allow_html=True)
            st.markdown('<div class="sidebar-card"><div class="sidebar-title">📚 学术语境分析数据</div>', unsafe_allow_html=True)
            f_academic = st.file_uploader("上传学术分析数据", accept_multiple_files=True,
                                   type=['csv', 'xlsx', 'xls'], label_visibility="collapsed", key="uploader_academic")
            if f_academic:
                st.success(f"✅ 已选 {len(f_academic)} 个文件")
            st.markdown('</div>', unsafe_allow_html=True)   # 关闭 "📚 学术语境分析数据" 卡片

        if st.button("🚀 固化并发布", use_container_width=True, key="publish_btn"):
            if f_u and f_s:
                with st.spinner("🔄 数据处理中..."):
                    all_u = []
                    for f in f_u:
                        df = read_data_file(f)
                        if df is not None:
                            df['school'] = f.name.split('.')[0]
                            all_u.append(df)
                    if all_u:
                        pd.concat(all_u, ignore_index=True).to_csv("data_u.csv", index=False, encoding='utf-8-sig')

                    all_s = []
                    for f in f_s:
                        df = read_data_file(f)
                        if df is not None:
                            all_s.append(df)
                    if all_s:
                        pd.concat(all_s, ignore_index=True).to_csv("data_s.csv", index=False, encoding='utf-8-sig')

                    if f_p:
                        all_p = []
                        for f in f_p:
                            df = read_data_file(f)
                            if df is not None:
                                all_p.append(df)
                        if all_p:
                            pd.concat(all_p, ignore_index=True).to_csv("data_p.csv", index=False, encoding='utf-8-sig')
                    if f_academic:
                        all_academic = []
                        for f in f_academic:
                            df = read_data_file(f)
                            if df is not None:
                                all_academic.append(df)
                        if all_academic:
                            pd.concat(all_academic, ignore_index=True).to_csv("data_academic.csv", index=False, encoding='utf-8-sig')
                    st.success("✅ 发布成功！")
                    st.rerun()
            else:
                st.error("❌ 请上传高校和社媒数据")

# ============================================
# 6. 主展示区
# ============================================
color_map = {
    '积极': '#DE2910',
    '正面': '#DE2910',
    '中性': '#FFB3B3',
    '一般': '#FFB3B3',
    '消极': '#999999',
    '负面': '#999999',
    '好评': '#DE2910',
    '差评': '#999999'
}

@st.cache_data
def generate_default_strategies():
    strategies = [
        {"策略类型": "内容优化", "具体建议": '增加"五个认同"相关内容的发布频率，每周至少3次专题推送', "优先级": "高"},
        {"策略类型": "内容优化", "具体建议": '使用"石榴籽"等生动比喻，增强内容感染力', "优先级": "高"},
        {"策略类型": "传播渠道", "具体建议": "加强短视频平台运营，制作15-30秒精华内容", "优先级": "中"},
        {"策略类型": "互动提升", "具体建议": "设置话题讨论区，鼓励师生分享民族团结故事", "优先级": "中"},
        {"策略类型": "情感引导", "具体建议": "针对负面反馈，及时发布正面案例进行引导", "优先级": "高"},
        {"策略类型": "形式创新", "具体建议": "开展线上线下结合的主题活动，增强参与感", "优先级": "中"},
        {"策略类型": "数据监测", "具体建议": "建立每周舆情监测机制，及时掌握传播效果", "优先级": "低"},
        {"策略类型": "队伍建设", "具体建议": "培养校园网络评论员队伍，提升正面声音", "优先级": "中"},
    ]
    return pd.DataFrame(strategies)

data_exists = os.path.exists("data_u.csv") and os.path.exists("data_s.csv")

if data_exists:
    try:
        @st.cache_data
        def load_data():
            du = pd.read_csv("data_u.csv", encoding='utf-8-sig')
            ds = pd.read_csv("data_s.csv", encoding='utf-8-sig')
            return du, ds

        du, ds = load_data()
        current = st.session_state.current_tab

        with st.container():
            st.markdown('<div class="content-card">', unsafe_allow_html=True)
            
            if current == "CPI排行":
                st.markdown("### 📊 高校传播效能排行")
                if 'school' in du.columns:
                    c_data = du['school'].value_counts().reset_index()
                    c_data.columns = ['学校', '指数']
                    fig = px.bar(c_data, x='学校', y='指数',
                                color_discrete_sequence=['#DE2910'],
                                text_auto=True)
                    fig.update_layout(
                        height=480,
                        showlegend=False,
                        xaxis_title="",
                        yaxis_title="传播指数",
                        plot_bgcolor='white',
                        paper_bgcolor='white',
                        margin=dict(t=20, b=40),
                        font=dict(family="Microsoft YaHei")
                    )
                    fig.update_traces(marker_line_color='#FFD700', marker_line_width=1.5)
                    st.plotly_chart(fig, use_container_width=True, key="cpi_chart")
                else:
                    st.info("数据中未找到学校标识列")

            elif current == "话语提取":
                st.markdown("### 🗣️ 核心话语体系监测")
                txt_col = None
                for c in ds.columns:
                    if any(x in str(c) for x in ['文本', '内容', 'text', '评论', '留言']):
                        txt_col = c
                        break
                if txt_col is None:
                    txt_col = ds.columns[0]

                full_txt = "".join(ds[txt_col].astype(str))
                kws = ["铸牢共同体意识", "中华民族", "统一", "共同体", "团结"]
                k_df = pd.DataFrame([{'词汇': k, '频数': len(re.findall(k, full_txt))} for k in kws])

                fig = px.bar(k_df, x='词汇', y='频数',
                            color='频数',
                            color_continuous_scale=['#FFB3B3', '#DE2910'],
                            text_auto=True)
                fig.update_layout(
                    height=480,
                    showlegend=False,
                    xaxis_title="",
                    yaxis_title="出现频次",
                    coloraxis_showscale=False,
                    plot_bgcolor='white',
                    paper_bgcolor='white',
                    margin=dict(t=20, b=40),
                    font=dict(family="Microsoft YaHei")
                )
                st.plotly_chart(fig, use_container_width=True, key="word_chart")

            elif current == "情感对比":
                st.markdown("### 🧠 情感极性对比分析")
                col1, col2 = st.columns(2)
                
                with col1:
                    st.markdown("**官方宣教情感分布**")
                    official_data = pd.DataFrame({
                        'sentiment': ['积极', '中性', '消极'],
                        'count': [92, 6, 2]
                    })
                    fig1 = px.pie(official_data, values='count', names='sentiment',
                                 color='sentiment',
                                 color_discrete_map=color_map,
                                 hole=0.4)
                    fig1.update_layout(
                        height=400,
                        showlegend=True,
                        legend=dict(orientation="h", yanchor="bottom", y=-0.15),
                        plot_bgcolor='white',
                        paper_bgcolor='white',
                        margin=dict(t=10, b=60),
                        font=dict(family="Microsoft YaHei")
                    )
                    st.plotly_chart(fig1, use_container_width=True, key="official_sentiment")

                with col2:
                    st.markdown("**社媒公众反馈分布**")
                    label_col = None
                    for c in ds.columns:
                        if any(x in str(c).lower() for x in ['标签', '情感', 'sentiment', '情绪', '评价']):
                            label_col = c
                            break
                    if label_col is None:
                        label_col = ds.columns[-1]

                    s_v = ds[label_col].value_counts().reset_index()
                    s_v.columns = ['sentiment', 'count']

                    sentiment_mapping = {}
                    for val in s_v['sentiment'].unique():
                        val_str = str(val).lower()
                        if any(x in val_str for x in ['积极', '正面', '好评', 'pos', '好']):
                            sentiment_mapping[val] = '积极'
                        elif any(x in val_str for x in ['消极', '负面', '差评', 'neg', '差']):
                            sentiment_mapping[val] = '消极'
                        else:
                            sentiment_mapping[val] = '中性'

                    s_v['sentiment'] = s_v['sentiment'].map(sentiment_mapping)
                    s_v = s_v.groupby('sentiment')['count'].sum().reset_index()

                    fig2 = px.pie(s_v, values='count', names='sentiment',
                                 color='sentiment',
                                 color_discrete_map=color_map,
                                 hole=0.4)
                    fig2.update_layout(
                        height=400,
                        showlegend=True,
                        legend=dict(orientation="h", yanchor="bottom", y=-0.15),
                        plot_bgcolor='white',
                        paper_bgcolor='white',
                        margin=dict(t=10, b=60),
                        font=dict(family="Microsoft YaHei")
                    )
                    st.plotly_chart(fig2, use_container_width=True, key="social_sentiment")

            elif current == "热度地图":
                st.markdown("### 🗺️ 全国传播热度映射")
                
                if os.path.exists("ditu.jpg"):
                    with open("ditu.jpg", "rb") as f:
                        map_data = f.read()
                    map_b64 = base64.b64encode(map_data).decode()
                    st.markdown(f"""
                        <div class="map-wrapper">
                            <div class="map-container">
                                <img src="data:image/jpeg;base64,{map_b64}" alt="热度地图" />
                            </div>
                        </div>
                    """, unsafe_allow_html=True)
                    st.caption("📍 全国高校中华民族共同体意识传播热度分布")
                else:
                    st.markdown("""
                        <div class="map-wrapper">
                            <div class="map-container">
                                <div class="map-placeholder">
                                    <div style="font-size: 60px; margin-bottom: 15px;">🗺️</div>
                                    <p style="font-size: 16px; margin-bottom: 8px;">热度地图预留位置</p>
                                    <p style="font-size: 13px; font-weight: normal; color: #666;">
                                        请在左侧上传地图图片
                                    </p>
                                </div>
                            </div>
                        </div>
                    """, unsafe_allow_html=True)

            elif current == "优化策略":
                st.markdown("### 💡 传播优化策略建议")

                if os.path.exists("data_p.csv"):
                    dp = pd.read_csv("data_p.csv", encoding='utf-8-sig')
                    display_cols = [c for c in dp.columns if any(x in c for x in ['策略', '建议', '内容', '类型', '优先级'])]
                    if display_cols:
                        st.dataframe(dp[display_cols].head(10), use_container_width=True, hide_index=True)
                    else:
                        st.dataframe(dp.head(10), use_container_width=True, hide_index=True)
                else:
                    # 不显示提示信息，直接显示默认策略
                    dp = generate_default_strategies()
                    st.dataframe(dp, use_container_width=True, hide_index=True)

               
            
 
            elif current == "学术语境分析":
                st.markdown("### 📚 学术语境深度分析")
                
                # 检查是否有学术分析数据
                academic_data_exists = os.path.exists("data_academic.csv")
                
                if academic_data_exists:
                    try:
                        @st.cache_data
                        def load_academic_data():
                            return pd.read_csv("data_academic.csv", encoding='utf-8-sig')
                        
                        df_academic = load_academic_data()
                        
                        # 数据列识别
                        text_col = None
                        region_col = None
                        media_col = None
                        keyword_col = None
                        
                        for c in df_academic.columns:
                            c_str = str(c).lower()
                            if any(x in c_str for x in ['文本', '内容', 'text', '表述', '原文']):
                                text_col = c
                            if any(x in c_str for x in ['地区', '地域', '省份', 'region', 'location', 'ip', '属地']):
                                region_col = c
                            if any(x in c_str for x in ['媒体', '平台', '来源', 'media', 'platform', 'source']):
                                media_col = c
                            if any(x in c_str for x in ['关键词', '主题', '词汇', 'keyword', 'topic', '事件']):
                                keyword_col = c
                        
                        # 如果未识别到列，使用默认列
                        if text_col is None:
                            text_col = df_academic.columns[0]
                        if region_col is None and len(df_academic.columns) > 1:
                            region_col = df_academic.columns[1]
                        if media_col is None and len(df_academic.columns) > 2:
                            media_col = df_academic.columns[2]
                        
                        # 侧边栏分析配置
                        with st.sidebar:
                            st.markdown('<div class="sidebar-card"><div class="sidebar-title">🔍 分析配置</div>', unsafe_allow_html=True)
                            
                            # 选择分析类型
                            analysis_type = st.selectbox(
                                "选择分析维度",
                                ["核心词汇分析", "历史事件分析", "地域差异对比", "媒体表述差异"],
                                key="analysis_type"
                            )
                            
                            # 核心词汇选择
                            if analysis_type == "核心词汇分析":
                                target_words = st.multiselect(
                                    "选择核心词汇",
                                    ["筑牢", "中华民族共同体", "民族团结", "五个认同", "石榴籽", "休戚与共", "荣辱与共"],
                                    default=["筑牢", "中华民族共同体"]
                                )
                            elif analysis_type == "历史事件分析":
                                target_words = st.multiselect(
                                    "选择历史事件",
                                    ["五胡入华", "五胡乱华", "民族融合", "华夷之辨", "多元一体", "大一统"],
                                    default=["五胡入华"]
                                )
                            else:
                                target_words = st.text_input("输入分析关键词（多个用逗号分隔）", "筑牢,五胡入华")
                                target_words = [w.strip() for w in target_words.split(",")]
                            
                            # Hugging Face模型选择
                            hf_model = st.selectbox(
                                "选择语义分析模型",
                                ["uer/roberta-base-finetuned-jd-binary-chinese", 
                                 "distilbert-base-chinese",
                                 "bert-base-chinese",
                                 "自定义模型"],
                                key="hf_model"
                            )
                            
                            if hf_model == "自定义模型":
                                custom_model = st.text_input("输入Hugging Face模型ID", "uer/roberta-base-finetuned-jd-binary-chinese")
                            else:
                                custom_model = hf_model
                            
                            st.markdown('</div>', unsafe_allow_html=True)
                        
                        # 主分析区域
                        col1, col2 = st.columns([2, 1])
                        
                        with col1:
                            st.markdown("#### 🎯 语境语义分析")
                            
                            # 模拟Hugging Face模型分析结果（实际使用时需要接入真实API）
                            # 这里使用基于规则的分析来模拟大模型效果
                            
                            analysis_results = []
                            
                            for word in target_words:
                                if text_col in df_academic.columns:
                                    # 查找包含该词的文本
                                    mask = df_academic[text_col].astype(str).str.contains(word, na=False)
                                    related_texts = df_academic[mask]
                                    
                                    if len(related_texts) > 0:
                                        # 分析不同地区的表述
                                        if region_col and region_col in df_academic.columns:
                                            region_stats = related_texts[region_col].value_counts().head(5)
                                            for region, count in region_stats.items():
                                                # 模拟语义倾向分析
                                                sample_texts = related_texts[related_texts[region_col] == region][text_col].head(3).tolist()
                                                sentiment_score = analyze_text_sentiment(sample_texts, word)
                                                
                                                analysis_results.append({
                                                    '关键词': word,
                                                    '地区': region,
                                                    '出现频次': count,
                                                    '语义倾向': sentiment_score['sentiment'],
                                                    '情感得分': sentiment_score['score'],
                                                    '典型表述': sentiment_score['example'][:50] + "..."
                                                })
                            
                            if analysis_results:
                                result_df = pd.DataFrame(analysis_results)
                                
                                # 热力图展示
                                pivot_df = result_df.pivot_table(
                                    values='情感得分', 
                                    index='关键词', 
                                    columns='地区', 
                                    aggfunc='mean'
                                ).fillna(0)
                                
                                fig_heatmap = px.imshow(
                                    pivot_df,
                                    color_continuous_scale=['#DE2910', '#FFB3B3', '#FFD700'],
                                    aspect="auto",
                                    title="地域-关键词情感倾向热力图"
                                )
                                fig_heatmap.update_layout(
                                    height=400,
                                    plot_bgcolor='white',
                                    paper_bgcolor='white',
                                    font=dict(family="Microsoft YaHei")
                                )
                                st.plotly_chart(fig_heatmap, use_container_width=True, key="academic_heatmap")
                                
                                # 详细数据表
                                st.markdown("#### 📊 详细分析数据")
                                st.dataframe(
                                    result_df.sort_values('情感得分', ascending=False),
                                    use_container_width=True,
                                    hide_index=True,
                                    column_config={
                                        '情感得分': st.column_config.ProgressColumn(
                                            '情感得分',
                                            help='语义情感强度',
                                            format='%.2f',
                                            min_value=0,
                                            max_value=1,
                                        )
                                    }
                                )
                            else:
                                st.info("未找到相关分析数据，请确保上传的数据包含关键词匹配的内容")
                        
                        with col2:
                            st.markdown("#### 🧠 大模型洞察")
                            
                            # 模拟大模型分析摘要
                            if analysis_results:
                                st.markdown("""
                                <div style="background: linear-gradient(135deg, #FFF9F9 0%, #FFFFFF 100%); 
                                            padding: 15px; border-radius: 10px; border-left: 4px solid #DE2910;">
                                    <h4 style="color: #DE2910; margin-top: 0;">📝 表述差异发现</h4>
                                """, unsafe_allow_html=True)
                                
                                # 生成洞察文本
                                insights = generate_academic_insights(analysis_results, target_words)
                                for insight in insights:
                                    st.markdown(f"""
                                    <div style="margin-bottom: 12px; padding: 10px; background: white; 
                                                border-radius: 6px; border: 1px solid rgba(222,41,16,0.1);">
                                        <strong style="color: #DE2910;">{insight['title']}</strong><br>
                                        <span style="color: #666; font-size: 13px;">{insight['content']}</span>
                                    </div>
                                    """, unsafe_allow_html=True)
                                
                                st.markdown("</div>", unsafe_allow_html=True)
                                
                                # 学术建议
                                st.markdown("""
                                <div style="background: linear-gradient(135deg, #FFFCF8 0%, #FFF9F9 100%); 
                                            padding: 15px; border-radius: 10px; margin-top: 15px;
                                            border-left: 4px solid #FFD700;">
                                    <h4 style="color: #DE2910; margin-top: 0;">💡 学术建议</h4>
                                    <ul style="color: #666; font-size: 13px; padding-left: 20px;">
                                        <li>关注地域表述差异，调整传播策略</li>
                                        <li>监测历史事件表述的情感倾向变化</li>
                                        <li>建立核心词汇的语境使用规范</li>
                                    </ul>
                                </div>
                                """, unsafe_allow_html=True)
                        
                        # 媒体差异分析
                        if media_col and media_col in df_academic.columns:
                            st.markdown("#### 📺 媒体表述差异对比")
                            
                            media_col1, media_col2 = st.columns(2)
                            
                            with media_col1:
                                # 媒体分布
                                media_dist = df_academic[media_col].value_counts().head(8).reset_index()
                                media_dist.columns = ['媒体类型', '数量']
                                
                                fig_media = px.pie(
                                    media_dist,
                                    values='数量',
                                    names='媒体类型',
                                    color_discrete_sequence=['#DE2910', '#C41E0B', '#FFD700', '#FFA500', '#FFB3B3', '#999999']
                                )
                                fig_media.update_layout(
                                    height=350,
                                    showlegend=True,
                                    legend=dict(orientation="h", yanchor="bottom", y=-0.2),
                                    plot_bgcolor='white',
                                    paper_bgcolor='white'
                                )
                                st.plotly_chart(fig_media, use_container_width=True, key="media_pie")
                            
                            with media_col2:
                                # 关键词在不同媒体中的使用
                                if target_words:
                                    media_keyword_data = []
                                    for word in target_words[:2]:  # 只取前两个避免数据过于稀疏
                                        for media in df_academic[media_col].unique()[:5]:
                                            mask = (df_academic[text_col].astype(str).str.contains(word, na=False)) & \
                                                   (df_academic[media_col] == media)
                                            count = mask.sum()
                                            media_keyword_data.append({
                                                '关键词': word,
                                                '媒体': media,
                                                '提及次数': count
                                            })
                                    
                                    if media_keyword_data:
                                        mk_df = pd.DataFrame(media_keyword_data)
                                        fig_mk = px.bar(
                                            mk_df,
                                            x='媒体',
                                            y='提及次数',
                                            color='关键词',
                                            barmode='group',
                                            color_discrete_map={'筑牢': '#DE2910', '五胡入华': '#FFD700'}
                                        )
                                        fig_mk.update_layout(
                                            height=350,
                                            plot_bgcolor='white',
                                            paper_bgcolor='white',
                                            xaxis_title="",
                                            yaxis_title="提及频次"
                                        )
                                        st.plotly_chart(fig_mk, use_container_width=True, key="media_keyword_bar")
                              
                    except Exception as e:
                        st.error(f"学术分析数据处理出错: {str(e)}")
                        st.info("请检查数据格式是否正确，或尝试重新上传数据")
                else:
                    # 使用示例数据展示功能
                    st.markdown("""
                        <div class="welcome-container">
                            <div style="font-size: 50px; margin-bottom: 10px;">📚</div>
                            <h3 style="color: #DE2910; margin-bottom: 10px;">学术语境分析模块</h3>
                            <p style="color: #666; font-size: 14px; margin-bottom: 20px;">
                                利用Hugging Face大模型分析核心词汇和历史事件的地域/媒体表述差异
                            </p>
                            <div style="text-align: left; max-width: 600px; margin: 0 auto;">
                                <div style="background: #FFF9F9; padding: 12px; border-radius: 8px; margin-bottom: 10px; border-left: 3px solid #FFD700;">
                                    <strong style="color: #DE2910;">支持分析内容：</strong><br>
                                    <span style="color: #666; font-size: 13px;">
                                    • 核心词汇："筑牢"、"中华民族共同体"、"五个认同"等<br>
                                    • 历史事件："五胡入华"、"民族融合"、"华夷之辨"等<br>
                                    • 地域差异：不同省份/地区的表述倾向对比<br>
                                    • 媒体差异：知识社区、新闻平台、社交媒体的表述差异
                                    </span>
                                </div>
                                <div style="background: #FFF9F9; padding: 12px; border-radius: 8px; border-left: 3px solid #FFD700;">
                                    <strong style="color: #DE2910;">数据格式要求：</strong><br>
                                    <span style="color: #666; font-size: 13px;">
                                    请上传包含以下列的CSV/Excel文件：<br>
                                    • 文本内容/表述原文<br>
                                    • 地区/IP属地<br>
                                    • 媒体类型/平台<br>
                                    • 关键词/主题（可选）
                                    </span>
                                </div>
                            </div>
                        </div>
                    """, unsafe_allow_html=True)
                    # 所有分支结束后关闭 content-card
                st.markdown('</div>', unsafe_allow_html=True)
    except Exception as e:
        st.error(f"数据处理出错: {str(e)}")
        st.info("请尝试重新上传数据")
else:
    # 欢迎页面
    st.markdown("""
        <div class="welcome-container">
            <div style="font-size: 60px; margin-bottom: 15px;">📊</div>
            <h2 style="color: #DE2910; margin-bottom: 10px;">欢迎使用分析平台</h2>
            <p style="color: #666; font-size: 15px; margin-bottom: 25px;">
                请在左侧管理面板上传数据并点击「固化并发布」以开始分析
            </p>
            <div style="display: flex; justify-content: center; gap: 15px; flex-wrap: wrap;">
                <div style="background: #FFF9F9; padding: 12px 20px; border-radius: 8px; border-left: 3px solid #FFD700;">
                    <strong style="color: #DE2910;">步骤 1</strong><br>
                    <span style="color: #666; font-size: 13px;">上传高校官方数据</span>
                </div>
                <div style="background: #FFF9F9; padding: 12px 20px; border-radius: 8px; border-left: 3px solid #FFD700;">
                    <strong style="color: #DE2910;">步骤 2</strong><br>
                    <span style="color: #666; font-size: 13px;">上传社媒反馈语料</span>
                </div>
                <div style="background: #FFF9F9; padding: 12px 20px; border-radius: 8px; border-left: 3px solid #FFD700;">
                    <strong style="color: #DE2910;">步骤 3</strong><br>
                    <span style="color: #666; font-size: 13px;">点击固化并发布</span>
                </div>
            </div>
        </div>
    """, unsafe_allow_html=True)
    # ============================================

# ============================================





# ============================================
# 7. 底部信息
# ============================================
st.markdown('<div class="footer">©2026 高校中华民族共同体意识传播分析平台 | 技术支持：大模型与大数据分析团队<br><span style="color: #DE2910;">铸牢中华民族共同体意识</span> | <span style="color: #FFD700;">同心共筑中国梦</span></div>', unsafe_allow_html=True)