CA/backend/routers/cases.py

"""
医疗病例数据 API 路由

提供门诊和住院数据的统计、趋势、区域分布等接口
"""

from fastapi import APIRouter, HTTPException, Query
from pydantic import BaseModel
from typing import Optional
from datetime import datetime, date
import pandas as pd
import re
from pathlib import Path
import json

DATE_PATTERN = re.compile(r"^\d{4}-\d{2}-\d{2}$")

router = APIRouter(prefix="/api/cases", tags=["cases"])

# 数据缓存
_cache = {
    "outpatient": None,
    "inpatient": None,
    "loaded_at": None,
}

# 武汉市区映射
WUHAN_DISTRICTS = {
    '江岸区': ['江岸'],
    '江汉区': ['江汉'],
    '武昌区': ['武昌'],
    '洪山区': ['洪山'],
    '汉阳区': ['汉阳'],
    '东西湖区': ['东西湖'],
    '黄陂区': ['黄陂'],
    '硚口区': ['硚口'],
    '江夏区': ['江夏'],
    '青山区': ['青山'],
    '新洲区': ['新洲'],
    '蔡甸区': ['蔡甸'],
    '东湖新技术开发区': ['东湖新技术开发区', '光谷'],
    '经开（汉南）区': ['经开', '汉南', '经济开发区'],
    '东湖生态旅游风景区': ['东湖生态旅游风景区']
}

PROJECT_ROOT = Path(__file__).parent.parent.parent
DATA_DIR = PROJECT_ROOT / "Datas"


def _extract_district(addr: str) -> str:
    """从地址提取武汉市区名"""
    if pd.isna(addr):
        return '未知'
    addr = str(addr)
    for district, keywords in WUHAN_DISTRICTS.items():
        for kw in keywords:
            if kw in addr:
                return district
    return '其他'


def _load_data():
    """加载并缓存数据"""
    if _cache["loaded_at"] is not None:
        return
    
    try:
        # 加载门诊数据
        df_out = pd.read_excel(DATA_DIR / "view_门诊.xlsx")
        df_out['date'] = pd.to_datetime(df_out['门诊日期_re'])
        df_out['district'] = df_out['现住址区'].fillna('未知')
        _cache["outpatient"] = df_out
        
        # 加载住院数据
        df_in = pd.read_excel(DATA_DIR / "view_住院.xlsx")
        df_in['date'] = pd.to_datetime(df_in['入院日期_re'])
        df_in['district'] = df_in['现住址_脱敏'].apply(_extract_district)
        _cache["inpatient"] = df_in
        
        _cache["loaded_at"] = datetime.now()
    except Exception as e:
        raise RuntimeError(f"数据加载失败：{str(e)}")


def _get_combined_data():
    """获取合并的病例数据"""
    _load_data()
    
    df_out = _cache["outpatient"][['date', 'district', '初诊', '主诉']].copy()
    df_out['type'] = 'outpatient'
    df_out['diagnosis'] = df_out['初诊']
    
    df_in = _cache["inpatient"][['date', 'district', '诊断名称']].copy()
    df_in['type'] = 'inpatient'
    df_in['diagnosis'] = df_in['诊断名称']
    df_in['主诉'] = None
    
    return pd.concat([df_out, df_in], ignore_index=True)


# ============== Response Models ==============

class StatsResponse(BaseModel):
    """统计数据响应"""
    total_outpatient: int
    total_inpatient: int
    date_range: dict
    top_districts: list
    top_diagnoses: list


class TrendPoint(BaseModel):
    """趋势数据点"""
    date: str
    outpatient: int
    inpatient: int
    total: int


class TrendResponse(BaseModel):
    """趋势数据响应"""
    trend: list[TrendPoint]
    summary: dict


class DistrictData(BaseModel):
    """区域数据"""
    district: str
    outpatient: int
    inpatient: int
    total: int
    outpatient_ratio: float
    inpatient_ratio: float


class DistrictsResponse(BaseModel):
    """区域分布响应"""
    districts: list[DistrictData]
    total: int


class RealtimeData(BaseModel):
    """实时数据"""
    today_outpatient: int
    today_inpatient: int
    today_total: int
    last_7d_avg: int
    change_ratio: float
    status: str


# ============== API Endpoints ==============

@router.get("/stats", response_model=StatsResponse, summary="获取病例统计数据")
async def get_cases_stats():
    """
    获取病例总体统计信息
    
    - 总门诊量、总住院量
    - 数据日期范围
    - 就诊量前 10 的区域
    - 最常见诊断前 10
    """
    _load_data()
    
    df_out = _cache["outpatient"]
    df_in = _cache["inpatient"]
    
    # 计算统计
    total_outpatient = len(df_out)
    total_inpatient = len(df_in)
    
    # 日期范围
    min_date = min(df_out['date'].min(), df_in['date'].min())
    max_date = max(df_out['date'].max(), df_in['date'].max())
    
    # 区域统计
    out_districts = df_out[df_out['district'] != '未知']['district'].value_counts().head(10)
    in_districts = df_in[df_in['district'] != '其他']['district'].value_counts().head(10)
    
    combined_districts = pd.concat([out_districts, in_districts]).groupby(level=0).sum().nlargest(10)
    top_districts = [{"district": d, "count": int(c)} for d, c in combined_districts.items()]
    
    # 诊断统计
    out_diagnoses = df_out['初诊'].value_counts().head(10)
    in_diagnoses = df_in['诊断名称'].value_counts().head(10)
    
    top_diagnoses = [
        {"diagnosis": str(d), "outpatient": int(out_diagnoses.get(d, 0)), "inpatient": int(in_diagnoses.get(d, 0))}
        for d in set(list(out_diagnoses.index[:5]) + list(in_diagnoses.index[:5]))
    ][:10]
    
    return StatsResponse(
        total_outpatient=total_outpatient,
        total_inpatient=total_inpatient,
        date_range={
            "start": min_date.strftime("%Y-%m-%d"),
            "end": max_date.strftime("%Y-%m-%d")
        },
        top_districts=top_districts,
        top_diagnoses=top_diagnoses
    )


@router.get("/trend", response_model=TrendResponse, summary="获取病例趋势数据")
async def get_cases_trend(
    start_date: Optional[str] = Query(None, description="开始日期 (YYYY-MM-DD)"),
    end_date: Optional[str] = Query(None, description="结束日期 (YYYY-MM-DD)"),
    group_by: str = Query("day", description="分组粒度：day, week, month"),
):
    """
    获取病例时间趋势数据
    
    - 支持按日、周、月分组
    - 可指定日期范围
    - 返回门诊、住院、总计趋势
    """
    if start_date and not DATE_PATTERN.match(start_date):
        raise HTTPException(status_code=400, detail="Invalid start_date format. Use YYYY-MM-DD")
    if end_date and not DATE_PATTERN.match(end_date):
        raise HTTPException(status_code=400, detail="Invalid end_date format. Use YYYY-MM-DD")

    df = _get_combined_data()

    # 日期过滤
    if start_date:
        df = df[df['date'] >= pd.to_datetime(start_date)]
    if end_date:
        df = df[df['date'] <= pd.to_datetime(end_date)]
    
    # 分组
    if group_by == "week":
        df['period'] = df['date'].dt.to_period('W').dt.start_time
    elif group_by == "month":
        df['period'] = df['date'].dt.to_period('M').dt.start_time
    else:
        df['period'] = df['date'].dt.date
    
    # 聚合
    out_trend = df[df['type'] == 'outpatient'].groupby('period').size()
    in_trend = df[df['type'] == 'inpatient'].groupby('period').size()
    
    periods = sorted(set(out_trend.index.tolist() + in_trend.index.tolist()))
    
    trend = []
    total_out = total_in = 0
    for p in periods:
        out_count = int(out_trend.get(p, 0))
        in_count = int(in_trend.get(p, 0))
        total_out += out_count
        total_in += in_count
        trend.append(TrendPoint(
            date=pd.Timestamp(p).strftime("%Y-%m-%d"),
            outpatient=out_count,
            inpatient=in_count,
            total=out_count + in_count
        ))
    
    return TrendResponse(
        trend=trend,
        summary={
            "total_outpatient": total_out,
            "total_inpatient": total_in,
            "period_count": len(periods),
            "avg_daily_outpatient": round(total_out / max(len(periods), 1), 2),
            "avg_daily_inpatient": round(total_in / max(len(periods), 1), 2),
        }
    )


@router.get("/districts", response_model=DistrictsResponse, summary="获取区域分布数据")
async def get_cases_districts(
    case_type: Optional[str] = Query(None, description="病例类型：outpatient, inpatient, all"),
    min_count: int = Query(10, description="最小病例数过滤"),
):
    """
    获取病例区域分布数据
    
    - 支持按病例类型筛选
    - 可设置最小病例数过滤
    - 返回各区门诊、住院量及占比
    """
    df = _get_combined_data()
    
    # 类型过滤
    if case_type == "outpatient":
        df = df[df['type'] == 'outpatient']
    elif case_type == "inpatient":
        df = df[df['type'] == 'inpatient']
    
    # 过滤未知区域
    df = df[(df['district'] != '未知') & (df['district'] != '其他')]
    
    # 聚合
    district_stats = df.groupby(['district', 'type']).size().unstack(fill_value=0)
    
    if 'outpatient' not in district_stats.columns:
        district_stats['outpatient'] = 0
    if 'inpatient' not in district_stats.columns:
        district_stats['inpatient'] = 0
    
    district_stats['total'] = district_stats['outpatient'] + district_stats['inpatient']
    
    # 过滤
    district_stats = district_stats[district_stats['total'] >= min_count]
    district_stats = district_stats.sort_values('total', ascending=False)
    
    total = int(district_stats['total'].sum())
    
    districts = []
    for district, row in district_stats.iterrows():
        districts.append(DistrictData(
            district=district,
            outpatient=int(row['outpatient']),
            inpatient=int(row['inpatient']),
            total=int(row['total']),
            outpatient_ratio=round(row['outpatient'] / row['total'] * 100, 2) if row['total'] > 0 else 0,
            inpatient_ratio=round(row['inpatient'] / row['total'] * 100, 2) if row['total'] > 0 else 0
        ))
    
    return DistrictsResponse(districts=districts, total=total)


@router.get("/realtime", response_model=RealtimeData, summary="获取实时数据")
async def get_cases_realtime():
    """
    获取实时病例数据
    
    - 今日就诊量
    - 近 7 日平均值
    - 变化率
    - 状态评估 (正常/偏高/偏低)
    """
    df = _get_combined_data()
    
    today = pd.Timestamp.today().normalize()
    last_7d = today - pd.Timedelta(days=7)
    
    # 今日数据
    today_data = df[df['date'] >= today]
    today_total = len(today_data)
    today_out = len(today_data[today_data['type'] == 'outpatient'])
    today_in = len(today_data[today_data['type'] == 'inpatient'])
    
    # 近 7 日平均
    last_7d_data = df[(df['date'] >= last_7d) & (df['date'] < today)]
    last_7d_avg = round(len(last_7d_data) / 7, 2) if len(last_7d_data) > 0 else 0
    
    # 变化率
    if last_7d_avg > 0:
        change_ratio = round((today_total - last_7d_avg) / last_7d_avg * 100, 2)
    else:
        change_ratio = 0.0
    
    # 状态评估
    if change_ratio > 20:
        status = "偏高"
    elif change_ratio < -20:
        status = "偏低"
    else:
        status = "正常"
    
    return RealtimeData(
        today_outpatient=today_out,
        today_inpatient=today_in,
        today_total=today_total,
        last_7d_avg=last_7d_avg,
        change_ratio=change_ratio,
        status=status
    )