import streamlit as st
import pandas as pd
import numpy as np
import plotly.express as px

# 数据路径
DATA_PATH = "D:\\AI_Coding\\data\\心血管疾病.xlsx"

# 缓存数据加载和清洗函数
@st.cache_data
def load_and_preprocess_data():
    # 加载数据
    df = pd.read_excel(DATA_PATH)
    
    # 特征工程
    # 将age（天）转换为年（四舍五入）
    df['age_years'] = round(df['age'] / 365.25, 0)
    
    # 计算BMI
    df['bmi'] = df['weight'] / ((df['height'] / 100) ** 2)
    
    # 异常值处理
    # 删除舒张压≥收缩压的记录
    df = df[df['ap_lo'] < df['ap_hi']]
    
    # 删除血压极端异常值
    df = df[(df['ap_hi'] >= 90) & (df['ap_hi'] <= 250)]
    df = df[(df['ap_lo'] >= 60) & (df['ap_lo'] <= 150)]
    
    # 类别转换
    # 将cholesterol数值转换为描述性字符串
    cholesterol_map = {1: '正常', 2: '偏高', 3: '很高'}
    df['cholesterol_desc'] = df['cholesterol'].map(cholesterol_map)
    
    # 将gluc数值转换为描述性字符串
    gluc_map = {1: '正常', 2: '偏高', 3: '很高'}
    df['gluc_desc'] = df['gluc'].map(gluc_map)
    
    # 创建bmi_category
    def get_bmi_category(bmi):
        if bmi < 18.5:
            return '偏瘦'
        elif bmi < 24:
            return '正常'
        elif bmi < 28:
            return '超重'
        else:
            return '肥胖'
    
    df['bmi_category'] = df['bmi'].apply(get_bmi_category)
    
    return df

# 加载数据
df = load_and_preprocess_data()

# Streamlit应用
st.title('CardioAI - 心血管疾病数据可视化')

# 侧边栏筛选器
st.sidebar.header('数据筛选')

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

# gender多选框
gender_options = df['gender'].unique()
gender_filter = st.sidebar.multiselect(
    '性别 (1=女, 2=男)',
    options=gender_options,
    default=gender_options
)

# cardio多选框
cardio_options = df['cardio'].unique()
cardio_filter = st.sidebar.multiselect(
    '心血管疾病 (0=无, 1=有)',
    options=cardio_options,
    default=cardio_options
)

# 应用筛选器
filtered_df = df[
    (df['age_years'] >= age_range[0]) & 
    (df['age_years'] <= age_range[1]) &
    (df['gender'].isin(gender_filter)) &
    (df['cardio'].isin(cardio_filter))
]

# 主页展示
st.header('数据概览')

# 展示筛选后的总记录数
st.metric('筛选后的总记录数', len(filtered_df))

# 计算并展示心血管疾病总风险率
if len(filtered_df) > 0:
    cardio_rate = (filtered_df['cardio'].sum() / len(filtered_df)) * 100
    st.metric('心血管疾病总风险率', f"{cardio_rate:.2f}%")

# 图表
st.header('数据可视化')

# age_years分布直方图（按cardio区分）
st.subheader('年龄分布与心血管疾病关系')
fig_age = px.histogram(
    filtered_df,
    x='age_years',
    color='cardio',
    barmode='overlay',
    nbins=20,
    labels={'age_years': '年龄', 'cardio': '心血管疾病', 'count': '人数'},
    title='年龄分布 histogram'
)
fig_age.update_layout(
    xaxis_title='年龄',
    yaxis_title='人数',
    legend_title='心血管疾病'
)
st.plotly_chart(fig_age)

# bmi_category对cardio影响的堆叠柱状图
st.subheader('BMI类别与心血管疾病关系')
fig_bmi = px.histogram(
    filtered_df,
    x='bmi_category',
    color='cardio',
    barmode='stack',
    labels={'bmi_category': 'BMI类别', 'cardio': '心血管疾病', 'count': '人数'},
    title='BMI类别对心血管疾病影响的堆叠柱状图'
)
fig_bmi.update_layout(
    xaxis_title='BMI类别',
    yaxis_title='人数',
    legend_title='心血管疾病'
)
st.plotly_chart(fig_bmi)

# 展示数据样本
st.header('数据样本')
st.dataframe(filtered_df.head())