添加Module1数据可视化仪表板和心血管疾病数据

1. 创建module1_dashboard/cardio_dashboard.py
   - Streamlit应用程序，提供交互式数据可视化
   - 包含数据清洗、特征工程、异常值处理
   - 集成年龄转换、BMI计算、类别转换
   - 侧边栏筛选器、Plotly图表展示
   - 智能路径解析，支持多种运行环境

2. 添加data/心血管疾病.xlsx数据文件
   - 心血管疾病原始数据集
   - 用于模型训练和可视化分析

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

module1_dashboard/cardio_dashboard.py

@@ -0,0 +1,394 @@
+#!/opt/anaconda3/envs/cardioenv/bin/python
+"""
+CardioAI - 心血管疾病数据可视化仪表板
+Streamlit应用程序，用于对心血管疾病数据进行清洗、特征工程和交互式可视化
+"""
+
+import streamlit as st
+import pandas as pd
+import numpy as np
+import plotly.express as px
+import plotly.graph_objects as go
+from plotly.subplots import make_subplots
+import warnings
+import os
+
+warnings.filterwarnings('ignore')
+
+# 页面配置
+st.set_page_config(
+    page_title="CardioAI - 心血管疾病智能分析",
+    page_icon="❤️",
+    layout="wide",
+    initial_sidebar_state="expanded"
+)
+
+# 数据路径
+DATA_PATH = "./data/心血管疾病.xlsx"
+
+
+@st.cache_data(ttl=3600)
+def load_and_process_data():
+    """
+    加载并处理心血管疾病数据
+    返回处理后的DataFrame
+    """
+    try:
+        # 调试信息：检查文件路径
+        current_dir = os.getcwd()
+        script_dir = os.path.dirname(os.path.abspath(__file__))
+        st.sidebar.info(f"当前工作目录: {current_dir}")
+        st.sidebar.info(f"脚本目录: {script_dir}")
+        st.sidebar.info(f"数据路径: {DATA_PATH}")
+
+        # 尝试多种路径
+        possible_paths = [
+            os.path.abspath(DATA_PATH),  # 绝对路径
+            DATA_PATH,  # 原始相对路径
+            os.path.join(current_dir, DATA_PATH),
+            os.path.join(current_dir, "data", "心血管疾病.xlsx"),
+            os.path.join(script_dir, "..", DATA_PATH),
+            os.path.join(script_dir, "..", "data", "心血管疾病.xlsx"),
+            os.path.join(script_dir, "data", "心血管疾病.xlsx")
+        ]
+
+        data_path = None
+        for path in possible_paths:
+            if os.path.exists(path):
+                data_path = path
+                st.sidebar.success(f"找到数据文件: {path}")
+                break
+
+        if data_path is None:
+            st.sidebar.error("未找到数据文件，请检查路径")
+            st.sidebar.info(f"尝试过的路径: {possible_paths}")
+            return pd.DataFrame()
+
+        # 加载数据
+        df = pd.read_excel(data_path)
+
+        # 1. 特征工程
+        # 将age(天)转换为年，四舍五入
+        df['age_years'] = (df['age'] / 365.25).round().astype(int)
+
+        # 计算BMI: weight / (height/100)^2
+        df['bmi'] = df['weight'] / ((df['height'] / 100) ** 2)
+
+        # 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']].copy()
+
+        # 删除血压极端异常值
+        # 收缩压 ∈ [90, 250], 舒张压 ∈ [60, 150]
+        df = df[
+            (df['ap_hi'] >= 90) & (df['ap_hi'] <= 250) &
+            (df['ap_lo'] >= 60) & (df['ap_lo'] <= 150)
+            ].copy()
+
+        # 3. 类别转换
+        # cholesterol转换
+        cholesterol_map = {
+            1: '正常',
+            2: '高于正常',
+            3: '很高'
+        }
+        df['cholesterol_str'] = df['cholesterol'].map(cholesterol_map)
+
+        # gluc转换
+        gluc_map = {
+            1: '正常',
+            2: '高于正常',
+            3: '很高'
+        }
+        df['gluc_str'] = df['gluc'].map(gluc_map)
+
+        # BMI分类
+        def categorize_bmi(bmi):
+            if bmi < 18.5:
+                return '偏瘦'
+            elif 18.5 <= bmi < 25:
+                return '正常'
+            elif 25 <= bmi < 30:
+                return '超重'
+            else:
+                return '肥胖'
+
+        df['bmi_category'] = df['bmi'].apply(categorize_bmi)
+
+        # 添加血压分类
+        df['bp_category'] = pd.cut(
+            df['ap_hi'],
+            bins=[0, 120, 140, 160, 180, 250],
+            labels=['正常', '偏高', '高血压1级', '高血压2级', '高血压3级']
+        )
+
+        return df
+
+    except Exception as e:
+        st.error(f"数据加载失败: {e}")
+        return pd.DataFrame()
+
+
+def create_filters(df):
+    """
+    创建侧边栏筛选器
+    返回筛选后的数据
+    """
+    st.sidebar.header("🔍 数据筛选")
+
+    # 年龄范围滑块
+    min_age = int(df['age_years'].min())
+    max_age = int(df['age_years'].max())
+    age_range = st.sidebar.slider(
+        "选择年龄范围",
+        min_value=min_age,
+        max_value=max_age,
+        value=(min_age, max_age),
+        step=1
+    )
+
+    # 性别筛选（多选）
+    gender_options = df['gender'].unique()
+    gender_options = sorted(gender_options)
+    gender_labels = {1: '女性', 2: '男性'}
+    selected_genders = st.sidebar.multiselect(
+        "选择性别",
+        options=gender_options,
+        default=gender_options,
+        format_func=lambda x: gender_labels.get(x, f"性别{x}")
+    )
+
+    # 心血管疾病筛选（多选）
+    cardio_options = df['cardio'].unique()
+    cardio_options = sorted(cardio_options)
+    cardio_labels = {0: '无疾病', 1: '有疾病'}
+    selected_cardio = st.sidebar.multiselect(
+        "选择心血管疾病状态",
+        options=cardio_options,
+        default=cardio_options,
+        format_func=lambda x: cardio_labels.get(x, f"状态{x}")
+    )
+
+    # 应用筛选
+    filtered_df = df[
+        (df['age_years'] >= age_range[0]) &
+        (df['age_years'] <= age_range[1]) &
+        (df['gender'].isin(selected_genders)) &
+        (df['cardio'].isin(selected_cardio))
+        ].copy()
+
+    return filtered_df, age_range, selected_genders, selected_cardio
+
+
+def display_metrics(filtered_df, original_df):
+    """
+    显示关键指标
+    """
+    col1, col2, col3, col4 = st.columns(4)
+
+    with col1:
+        st.metric(
+            label="总记录数",
+            value=f"{len(filtered_df):,}",
+            delta=f"{len(filtered_df) - len(original_df):+,}" if len(filtered_df) != len(original_df) else None
+        )
+
+    with col2:
+        disease_count = filtered_df['cardio'].sum()
+        disease_rate = (disease_count / len(filtered_df) * 100) if len(filtered_df) > 0 else 0
+        st.metric(
+            label="心血管疾病风险率",
+            value=f"{disease_rate:.1f}%",
+            delta=f"{disease_count:,} 例"
+        )
+
+    with col3:
+        avg_age = filtered_df['age_years'].mean()
+        st.metric(
+            label="平均年龄",
+            value=f"{avg_age:.1f} 岁"
+        )
+
+    with col4:
+        avg_bmi = filtered_df['bmi'].mean()
+        st.metric(
+            label="平均BMI",
+            value=f"{avg_bmi:.1f}"
+        )
+
+
+def create_visualizations(filtered_df):
+    """
+    创建可视化图表
+    """
+    st.subheader("📊 数据分析")
+
+    # 创建两列布局
+    col1, col2 = st.columns(2)
+
+    with col1:
+        st.markdown("##### 年龄分布（按心血管疾病状态）")
+        if not filtered_df.empty:
+            fig1 = px.histogram(
+                filtered_df,
+                x='age_years',
+                color='cardio',
+                nbins=30,
+                barmode='overlay',
+                color_discrete_map={0: '#636EFA', 1: '#EF553B'},
+                labels={
+                    'age_years': '年龄（岁）',
+                    'cardio': '心血管疾病',
+                    'count': '人数'
+                },
+                category_orders={'cardio': [0, 1]},
+                opacity=0.7
+            )
+            fig1.update_layout(
+                legend_title_text='疾病状态',
+                legend=dict(
+                    orientation="h",
+                    yanchor="bottom",
+                    y=1.02,
+                    xanchor="right",
+                    x=1
+                )
+            )
+            st.plotly_chart(fig1, use_container_width=True)
+        else:
+            st.info("没有数据可显示")
+
+    with col2:
+        st.markdown("##### BMI分类与心血管疾病关系")
+        if not filtered_df.empty:
+            # 创建交叉表
+            bmi_cardio_cross = pd.crosstab(
+                filtered_df['bmi_category'],
+                filtered_df['cardio'],
+                normalize='index'
+            ).reset_index()
+
+            # 转换为长格式
+            bmi_cardio_long = pd.melt(
+                bmi_cardio_cross,
+                id_vars=['bmi_category'],
+                value_vars=[0, 1],
+                var_name='cardio',
+                value_name='proportion'
+            )
+
+            # 添加标签
+            bmi_cardio_long['cardio_label'] = bmi_cardio_long['cardio'].map({0: '无疾病', 1: '有疾病'})
+
+            fig2 = px.bar(
+                bmi_cardio_long,
+                x='bmi_category',
+                y='proportion',
+                color='cardio_label',
+                barmode='stack',
+                color_discrete_map={'无疾病': '#00CC96', '有疾病': '#AB63FA'},
+                labels={
+                    'bmi_category': 'BMI分类',
+                    'proportion': '比例',
+                    'cardio_label': '疾病状态'
+                },
+                category_orders={
+                    'bmi_category': ['偏瘦', '正常', '超重', '肥胖']
+                }
+            )
+            fig2.update_layout(
+                yaxis_tickformat=',.0%',
+                legend_title_text='疾病状态'
+            )
+            st.plotly_chart(fig2, use_container_width=True)
+        else:
+            st.info("没有数据可显示")
+
+    # 额外分析
+    st.subheader("🔍 详细分析")
+
+    col3, col4 = st.columns(2)
+
+    with col3:
+        st.markdown("##### 胆固醇水平分布")
+        if not filtered_df.empty:
+            fig3 = px.pie(
+                filtered_df,
+                names='cholesterol_str',
+                color='cholesterol_str',
+                color_discrete_sequence=px.colors.sequential.RdBu
+            )
+            fig3.update_traces(textposition='inside', textinfo='percent+label')
+            st.plotly_chart(fig3, use_container_width=True)
+
+    with col4:
+        st.markdown("##### 血糖水平分布")
+        if not filtered_df.empty:
+            fig4 = px.pie(
+                filtered_df,
+                names='gluc_str',
+                color='gluc_str',
+                color_discrete_sequence=px.colors.sequential.Bluyl
+            )
+            fig4.update_traces(textposition='inside', textinfo='percent+label')
+            st.plotly_chart(fig4, use_container_width=True)
+
+
+def display_data_summary(filtered_df):
+    """
+    显示数据摘要
+    """
+    with st.expander("📋 数据摘要（点击展开）"):
+        st.dataframe(
+            filtered_df.describe().round(2),
+            use_container_width=True
+        )
+
+        st.markdown("##### 数据样本")
+        st.dataframe(
+            filtered_df.head(10),
+            use_container_width=True
+        )
+
+
+def main():
+    """
+    主函数
+    """
+    # 标题和介绍
+    st.title("❤️ CardioAI - 心血管疾病智能分析系统")
+    st.markdown("""
+    本仪表板提供心血管疾病数据的交互式可视化分析。使用侧边栏筛选器探索数据模式。
+    """)
+
+    # 加载数据
+    with st.spinner('正在加载和处理数据...'):
+        df = load_and_process_data()
+
+    if df.empty:
+        st.error("无法加载数据。请检查数据文件路径和格式。")
+        return
+
+    # 创建筛选器并获取筛选后的数据
+    filtered_df, age_range, selected_genders, selected_cardio = create_filters(df)
+
+    # 显示筛选条件
+    st.sidebar.markdown("---")
+    st.sidebar.markdown(f"**筛选结果:** {len(filtered_df):,} 条记录")
+
+    # 显示关键指标
+    display_metrics(filtered_df, df)
+
+    # 显示可视化图表
+    create_visualizations(filtered_df)
+
+    # 显示数据摘要
+    display_data_summary(filtered_df)
+
+    # 页脚
+    st.markdown("---")
+    st.caption("CardioAI - 心血管疾病智能辅助系统 | Module 1: 数据可视化仪表板")
+
+
+if __name__ == "__main__":
+    main()