# -*- coding: utf-8 -*-
"""
CardioAI - Module 1: 数据可视化仪表板
心血管疾病数据清洗、特征工程与交互式可视化
"""

import streamlit as st
import pandas as pd
import numpy as np
import plotly.express as px
from pathlib import Path
import os

# ============================================
# 配置与常量
# ============================================
CODE_ROOT = Path(r"E:\project_ai\claude_project1\aicodes")
DATA_PATH = Path(r"E:\project_ai\claude_project1\data\心血管疾病.xlsx")

# 类别映射字典
CHOLESTEROL_MAP = {
    1: "正常",
    2: "高于正常",
    3: "远高于正常"
}

GLUC_MAP = {
    1: "正常",
    2: "高于正常",
    3: "远高于正常"
}

GENDER_MAP = {
    1: "女性",
    2: "男性"
}

CARDIO_MAP = {
    0: "无疾病",
    1: "有疾病"
}


# ============================================
# 数据加载与清洗函数
# ============================================
@st.cache_data
def load_data():
    """
    加载心血管疾病数据

    Returns:
        pd.DataFrame: 原始数据
    """
    try:
        df = pd.read_excel(DATA_PATH, engine='openpyxl')
        return df
    except Exception as e:
        st.error(f"数据加载失败: {str(e)}")
        return pd.DataFrame()


@st.cache_data
def clean_and_process_data(df):
    """
    数据清洗与特征工程

    处理步骤:
    1. 将age(天)转换为年
    2. 计算BMI
    3. 删除血压异常值
    4. 类别转换
    5. 创建BMI分类

    Args:
        df (pd.DataFrame): 原始数据

    Returns:
        pd.DataFrame: 处理后的数据
    """
    if df.empty:
        return df

    df_clean = df.copy()

    # 1. 年龄转换: 天 -> 年 (四舍五入)
    df_clean['age_years'] = (df_clean['age'] / 365.25).round().astype(int)

    # 2. 计算BMI: weight / (height/100)^2
    df_clean['bmi'] = df_clean['weight'] / ((df_clean['height'] / 100) ** 2)

    # 3. 异常值处理

    # 删除舒张压 >= 收缩压的记录 (生理上不可能)
    df_clean = df_clean[df_clean['ap_lo'] < df_clean['ap_hi']]

    # 删除血压极端异常值 (收缩压范围: [90, 250], 舒张压范围: [60, 150])
    df_clean = df_clean[
        (df_clean['ap_hi'] >= 90) & (df_clean['ap_hi'] <= 250) &
        (df_clean['ap_lo'] >= 60) & (df_clean['ap_lo'] <= 150)
    ]

    # 4. 类别转换
    df_clean['cholesterol_desc'] = df_clean['cholesterol'].map(CHOLESTEROL_MAP)
    df_clean['gluc_desc'] = df_clean['gluc'].map(GLUC_MAP)
    df_clean['gender_desc'] = df_clean['gender'].map(GENDER_MAP)
    df_clean['cardio_desc'] = df_clean['cardio'].map(CARDIO_MAP)

    # 5. 创建BMI分类
    def categorize_bmi(bmi):
        if bmi < 18.5:
            return "体重过轻"
        elif bmi < 24:
            return "正常体重"
        elif bmi < 28:
            return "超重"
        else:
            return "肥胖"

    df_clean['bmi_category'] = df_clean['bmi'].apply(categorize_bmi)

    return df_clean


# ============================================
# 筛选函数
# ============================================
def apply_filters(df, age_range, gender_filter, cardio_filter):
    """
    根据用户选择的筛选条件过滤数据

    Args:
        df (pd.DataFrame): 处理后的数据
        age_range (tuple): 年龄范围 (min, max)
        gender_filter (list): 性别筛选列表
        cardio_filter (list): 心血管疾病状态筛选列表

    Returns:
        pd.DataFrame: 筛选后的数据
    """
    if df.empty:
        return df

    df_filtered = df.copy()

    # 年龄范围筛选
    df_filtered = df_filtered[
        df_filtered['age_years'].between(age_range[0], age_range[1])
    ]

    # 性别筛选
    if gender_filter:
        df_filtered = df_filtered[df_filtered['gender_desc'].isin(gender_filter)]

    # 心血管疾病状态筛选
    if cardio_filter:
        df_filtered = df_filtered[df_filtered['cardio_desc'].isin(cardio_filter)]

    return df_filtered


# ============================================
# 统计指标函数
# ============================================
def calculate_statistics(df):
    """
    计算统计指标

    Args:
        df (pd.DataFrame): 筛选后的数据

    Returns:
        dict: 包含总记录数和风险率的字典
    """
    if df.empty:
        return {"total_records": 0, "risk_rate": 0.0}

    total_records = len(df)
    disease_count = df['cardio'].sum()
    risk_rate = (disease_count / total_records * 100) if total_records > 0 else 0

    return {
        "total_records": total_records,
        "risk_rate": risk_rate
    }


# ============================================
# 可视化图表函数
# ============================================
def plot_age_distribution(df):
    """
    绘制年龄分布直方图 (按cardio区分)

    Args:
        df (pd.DataFrame): 数据

    Returns:
        plotly.graph_objects.Figure: 年龄分布图
    """
    if df.empty:
        return None

    fig = px.histogram(
        df,
        x='age_years',
        color='cardio_desc',
        nbins=30,
        title='年龄分布 (按心血管疾病状态)',
        labels={'age_years': '年龄 (岁)', 'count': '人数'},
        color_discrete_map={'无疾病': '#2ecc71', '有疾病': '#e74c3c'},
        barmode='overlay'
    )

    fig.update_layout(
        xaxis_title="年龄 (岁)",
        yaxis_title="人数",
        legend_title="疾病状态",
        hovermode='x unified'
    )

    return fig


def plot_bmi_vs_cardio(df):
    """
    绘制BMI分类对心血管疾病影响的堆叠柱状图

    Args:
        df (pd.DataFrame): 数据

    Returns:
        plotly.graph_objects.Figure: BMI与疾病关系图
    """
    if df.empty:
        return None

    # 计算每个BMI分类的疾病比例
    bmi_cardio = df.groupby(['bmi_category', 'cardio_desc']).size().reset_index(name='count')

    # 确保BMI分类顺序正确
    bmi_order = ["体重过轻", "正常体重", "超重", "肥胖"]
    bmi_cardio['bmi_category'] = pd.Categorical(
        bmi_cardio['bmi_category'],
        categories=bmi_order,
        ordered=True
    )
    bmi_cardio = bmi_cardio.sort_values('bmi_category')

    fig = px.bar(
        bmi_cardio,
        x='bmi_category',
        y='count',
        color='cardio_desc',
        title='BMI分类与心血管疾病关系',
        labels={'bmi_category': 'BMI分类', 'count': '人数'},
        color_discrete_map={'无疾病': '#2ecc71', '有疾病': '#e74c3c'},
        category_orders={'bmi_category': bmi_order}
    )

    fig.update_layout(
        xaxis_title="BMI分类",
        yaxis_title="人数",
        legend_title="疾病状态",
        barmode='stack'
    )

    return fig


# ============================================
# 主应用程序
# ============================================
def main():
    """Streamlit 主应用程序"""

    # 页面配置
    st.set_page_config(
        page_title="CardioAI - 心血管疾病数据分析仪表板",
        page_icon="❤️",
        layout="wide",
        initial_sidebar_state="expanded"
    )

    # 标题与描述
    st.title("❤️ CardioAI - 心血管疾病智能辅助系统")
    st.markdown("### Module 1: 数据可视化仪表板")
    st.markdown("---")

    # 数据加载
    with st.spinner("正在加载数据..."):
        raw_data = load_data()

    if raw_data.empty:
        st.error("无法加载数据，请检查数据路径是否正确。")
        st.stop()

    # 数据清洗与特征工程
    processed_data = clean_and_process_data(raw_data)

    if processed_data.empty:
        st.warning("数据清洗后无有效记录，请检查数据质量。")
        st.stop()

    # ============================================
    # 侧边栏 - 筛选器
    # ============================================
    st.sidebar.header("🔍 数据筛选")

    # 年龄范围滑块
    age_min = int(processed_data['age_years'].min())
    age_max = int(processed_data['age_years'].max())
    age_range = st.sidebar.slider(
        "年龄范围 (岁)",
        min_value=age_min,
        max_value=age_max,
        value=(age_min, age_max),
        step=1
    )

    # 性别多选框
    gender_options = processed_data['gender_desc'].unique().tolist()
    gender_filter = st.sidebar.multiselect(
        "性别",
        options=gender_options,
        default=gender_options
    )

    # 心血管疾病状态多选框
    cardio_options = processed_data['cardio_desc'].unique().tolist()
    cardio_filter = st.sidebar.multiselect(
        "心血管疾病状态",
        options=cardio_options,
        default=cardio_options
    )

    st.sidebar.markdown("---")
    st.sidebar.markdown("### 📊 数据概览")
    st.sidebar.markdown(f"- 原始记录数: **{len(raw_data):,}**")
    st.sidebar.markdown(f"- 清洗后记录数: **{len(processed_data):,}**")
    st.sidebar.markdown(f"- 数据清洗率: **{(1 - len(processed_data)/len(raw_data))*100:.2f}%**")

    # ============================================
    # 应用筛选条件
    # ============================================
    filtered_data = apply_filters(
        processed_data,
        age_range,
        gender_filter,
        cardio_filter
    )

    # ============================================
    # 主页 - 统计指标
    # ============================================
    st.subheader("📈 筛选结果统计")

    stats = calculate_statistics(filtered_data)

    col1, col2 = st.columns(2)

    with col1:
        st.metric(
            label="筛选后总记录数",
            value=f"{stats['total_records']:,}",
            delta=None
        )

    with col2:
        # 根据风险率设置颜色
        risk_rate = stats['risk_rate']
        risk_color = "normal" if risk_rate < 50 else "inverse"

        st.metric(
            label="心血管疾病风险率",
            value=f"{risk_rate:.2f}%",
            delta=None,
            delta_color=risk_color
        )

    st.markdown("---")

    # ============================================
    # 图表展示
    # ============================================
    st.subheader("📊 数据可视化")

    # 第一行: 年龄分布图
    col1, col2 = st.columns(2)

    with col1:
        age_fig = plot_age_distribution(filtered_data)
        if age_fig:
            st.plotly_chart(age_fig, use_container_width=True)

    with col2:
        # 添加性别分布饼图
        gender_dist = filtered_data['gender_desc'].value_counts().reset_index()
        gender_dist.columns = ['性别', '人数']
        gender_pie = px.pie(
            gender_dist,
            values='人数',
            names='性别',
            title='性别分布',
            color_discrete_sequence=['#3498db', '#e91e63']
        )
        st.plotly_chart(gender_pie, use_container_width=True)

    # 第二行: BMI与疾病关系图
    st.markdown("### BMI分类与心血管疾病风险")
    bmi_fig = plot_bmi_vs_cardio(filtered_data)
    if bmi_fig:
        st.plotly_chart(bmi_fig, use_container_width=True)

    # 第三行: 其他因素分析
    col1, col2 = st.columns(2)

    with col1:
        # 胆固醇分布
        chol_cardio = filtered_data.groupby(['cholesterol_desc', 'cardio_desc']).size().reset_index(name='count')
        chol_fig = px.bar(
            chol_cardio,
            x='cholesterol_desc',
            y='count',
            color='cardio_desc',
            title='胆固醇水平与心血管疾病',
            labels={'cholesterol_desc': '胆固醇水平', 'count': '人数'},
            color_discrete_map={'无疾病': '#2ecc71', '有疾病': '#e74c3c'}
        )
        st.plotly_chart(chol_fig, use_container_width=True)

    with col2:
        # 血糖分布
        gluc_cardio = filtered_data.groupby(['gluc_desc', 'cardio_desc']).size().reset_index(name='count')
        gluc_order = ["正常", "高于正常", "远高于正常"]
        gluc_cardio['gluc_desc'] = pd.Categorical(
            gluc_cardio['gluc_desc'],
            categories=gluc_order,
            ordered=True
        )
        gluc_cardio = gluc_cardio.sort_values('gluc_desc')

        gluc_fig = px.bar(
            gluc_cardio,
            x='gluc_desc',
            y='count',
            color='cardio_desc',
            title='血糖水平与心血管疾病',
            labels={'gluc_desc': '血糖水平', 'count': '人数'},
            category_orders={'gluc_desc': gluc_order},
            color_discrete_map={'无疾病': '#2ecc71', '有疾病': '#e74c3c'}
        )
        st.plotly_chart(gluc_fig, use_container_width=True)

    # ============================================
    # 数据表格预览
    # ============================================
    st.markdown("---")
    st.subheader("📋 数据预览")

    display_columns = [
        'age_years', 'gender_desc', 'height', 'weight', 'bmi', 'bmi_category',
        'ap_hi', 'ap_lo', 'cholesterol_desc', 'gluc_desc',
        'smoke', 'alco', 'active', 'cardio_desc'
    ]

    column_rename = {
        'age_years': '年龄(岁)',
        'gender_desc': '性别',
        'height': '身高(cm)',
        'weight': '体重(kg)',
        'bmi': 'BMI',
        'bmi_category': 'BMI分类',
        'ap_hi': '收缩压',
        'ap_lo': '舒张压',
        'cholesterol_desc': '胆固醇',
        'gluc_desc': '血糖',
        'smoke': '吸烟',
        'alco': '饮酒',
        'active': '运动',
        'cardio_desc': '心血管疾病'
    }

    if not filtered_data.empty:
        display_df = filtered_data[display_columns].copy()
        display_df = display_df.rename(columns=column_rename)
        st.dataframe(display_df.head(100), use_container_width=True, height=400)


# ============================================
# 程序入口
# ============================================
if __name__ == "__main__":
    main()