akiba/CA
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity

fix: analysis 500s, caching, alert page perf

Browse Source 
P0: Fix KeyError in 3 analysis endpoints. geojson.py stores 1d risk
as "risk_value" but analysis.py accessed "risk_1d" — always crashed.

Backend: Add lru_cache to GeoJSON/CSV/Parquet loaders, date helpers,
and district loader. Add try/except and FileNotFoundError guards.

Frontend: Debounce riskRange, merge counts into useMemo, stabilize
handleGridClick with ref, memoize nearest-grid scan, wrap AlertMap
in React.memo, switch useLodGrid from fetch to cachedGet.
This commit is contained in:
Akiba So
2026-06-05 02:27:10 +08:00
parent fc468464b2
commit e64ca3b4f5
9 changed files with 154 additions and 114 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
backend/routers/analysis.py
View File

@@ -83,7 +83,7 @@ async def get_trend(days: int = Query(default=7, ge=1, le=30)):
if filepath.exists():
grids = parse_geojson_file(filepath)
if grids:
avg_risk = sum(g["risk_1d"] for g in grids) / len(grids)
avg_risk = sum(g["risk_value"] for g in grids) / len(grids)
values.append(round(avg_risk, 4))
else:
values.append(0)
@@ -125,8 +125,8 @@ async def get_districts():
if not districts:
# Fallback: return city-wide aggregation
avg_risk = sum(g["risk_1d"] for g in grids) / len(grids) if grids else 0
high_risk_count = sum(1 for g in grids if g["risk_1d"] >= RISK_HIGH)
avg_risk = sum(g["risk_value"] for g in grids) / len(grids) if grids else 0
high_risk_count = sum(1 for g in grids if g["risk_value"] >= RISK_HIGH)
return DistrictsResponse(
districts=[
@@ -150,14 +150,14 @@ async def get_districts():
for district in districts:
if point_in_polygon(grid["latitude"], grid["longitude"], district["coordinates"]):
district_data[district["name"]]["grids"].append(grid)
if grid["risk_1d"] >= RISK_HIGH:
if grid["risk_value"] >= RISK_HIGH:
district_data[district["name"]]["high_risk"] += 1
assigned = True
break
if not assigned:
unassigned["grids"].append(grid)
if grid["risk_1d"] >= RISK_HIGH:
if grid["risk_value"] >= RISK_HIGH:
unassigned["high_risk"] += 1
# Build response
@@ -169,7 +169,7 @@ async def get_districts():
if not grids_in_district:
continue
avg_risk = sum(g["risk_1d"] for g in grids_in_district) / len(grids_in_district)
avg_risk = sum(g["risk_value"] for g in grids_in_district) / len(grids_in_district)
high_risk_count = district_data[name]["high_risk"]
# Mock total cases based on risk and grid count
@@ -187,7 +187,7 @@ async def get_districts():
# Add unassigned as "其他" if significant
if unassigned["grids"]:
avg_risk = sum(g["risk_1d"] for g in unassigned["grids"]) / len(unassigned["grids"])
avg_risk = sum(g["risk_value"] for g in unassigned["grids"]) / len(unassigned["grids"])
result.append(
DistrictRisk(
name="其他",
@@ -224,8 +224,8 @@ async def get_correlations():
# Calculate mock correlations based on risk patterns
# In production, this would use actual weather and health data
avg_risk = sum(g["risk_1d"] for g in grids) / len(grids)
risk_variance = sum((g["risk_1d"] - avg_risk) ** 2 for g in grids) / len(grids)
avg_risk = sum(g["risk_value"] for g in grids) / len(grids)
risk_variance = sum((g["risk_value"] - avg_risk) ** 2 for g in grids) / len(grids)
# Generate realistic correlation coefficients
correlations = [

14
backend/routers/geocoded.py
View File

@@ -5,6 +5,7 @@ from fastapi import APIRouter, HTTPException
from pydantic import BaseModel
from typing import List, Optional
import logging
from functools import lru_cache
import pandas as pd
from pathlib import Path
@@ -15,6 +16,11 @@ router = APIRouter(prefix="/api/geocoded", tags=["geocoded"])
PROJECT_ROOT = Path(__file__).parent.parent.parent
DATA_DIR = PROJECT_ROOT / "outputs"
@lru_cache(maxsize=1)
def _load_csv(path: Path) -> pd.DataFrame:
return pd.read_csv(path)
class GridCaseData(BaseModel):
"""Grid case data for visualization"""
grid_id: int
@@ -60,7 +66,7 @@ async def get_grid_cases():
raise HTTPException(status_code=404, detail="Grid data not found")
try:
df = pd.read_csv(grid_file)
df = _load_csv(grid_file)
grids = []
for _, row in df.iterrows():
@@ -105,7 +111,7 @@ async def get_geocoded_cases(
raise HTTPException(status_code=404, detail="Geocoded data not found")
try:
df = pd.read_csv(cases_file)
df = _load_csv(cases_file)
# Drop rows with missing coordinates
df = df.dropna(subset=['latitude', 'longitude'])
@@ -122,7 +128,7 @@ async def get_geocoded_cases(
df = df.head(limit)
cases = []
for _, row in df.iterrows():
for row in df.to_dict('records'):
street_val = row.get('street')
if pd.isna(street_val):
street_val = None
@@ -157,7 +163,7 @@ async def get_geocoded_count():
raise HTTPException(status_code=404, detail="Geocoded data not found")
try:
df = pd.read_csv(cases_file)
df = _load_csv(cases_file)
street_matched = len(df[df['geocode_method'] == 'street'])
district_fallback = len(df[df['geocode_method'] == 'district'])

30
backend/routers/grid.py
View File

@@ -1,5 +1,6 @@
from fastapi import APIRouter, HTTPException, Query
from datetime import datetime, timedelta
from functools import lru_cache
from pathlib import Path
from typing import Optional
import logging
@@ -22,6 +23,12 @@ from models import (
router = APIRouter(prefix="/api", tags=["grid"])
@lru_cache(maxsize=1)
def _load_parquet(path: Path) -> "pd.DataFrame":
import pandas as pd
return pd.read_parquet(path)
@router.get("/history/aggregated", response_model=HistoricalAggregationResponse)
async def get_historical_aggregated(
start_date: str = Query(..., description="Start date (YYYY-MM-DD)"),
@@ -45,7 +52,13 @@ async def get_historical_aggregated(
import pandas as pd
cases_df = pd.read_parquet(PROJECT_ROOT / "processed" / "cases_by_district_daily.parquet")
try:
cases_df = _load_parquet(PROJECT_ROOT / "processed" / "cases_by_district_daily.parquet")
except FileNotFoundError:
return HistoricalAggregationResponse(
aggregations=[], total_records=0,
date_range=(start_date, end_date), timestamp=datetime.now().isoformat(),
)
cases_df['date'] = pd.to_datetime(cases_df['date'])
filtered_cases = cases_df[
@@ -78,7 +91,10 @@ async def get_historical_aggregated(
grouped = filtered_cases.copy()
grouped['date'] = grouped['date'].dt.strftime('%Y-%m-%d')
weather_df = pd.read_parquet(PROJECT_ROOT / "processed" / "weather" / "station_daily_2022.parquet")
try:
weather_df = _load_parquet(PROJECT_ROOT / "processed" / "weather" / "station_daily_2022.parquet")
except FileNotFoundError:
weather_df = pd.DataFrame(columns=['date', 'AQI', 'PM25', 'PM10'])
weather_df['date'] = pd.to_datetime(weather_df['date']).dt.strftime('%Y-%m-%d')
# Weather data doesn't have district - aggregate by date only
@@ -124,12 +140,12 @@ async def get_grids_geojson(
import pandas as pd
try:
grid_df = pd.read_parquet(PROJECT_ROOT / "processed" / "grid_100m_index.parquet")
grid_df = _load_parquet(PROJECT_ROOT / "processed" / "grid_100m_index.parquet")
except FileNotFoundError:
return GridGeoJSONResponse(type="FeatureCollection", features=[], timestamp=datetime.now().isoformat())
try:
district_map = pd.read_parquet(PROJECT_ROOT / "processed" / "grid_district_mapping.parquet")
district_map = _load_parquet(PROJECT_ROOT / "processed" / "grid_district_mapping.parquet")
except FileNotFoundError:
return GridGeoJSONResponse(type="FeatureCollection", features=[], timestamp=datetime.now().isoformat())
@@ -139,7 +155,7 @@ async def get_grids_geojson(
merged = merged[merged['district_name'].str.contains(district.replace('区', ''), na=False, regex=False)]
try:
cases_df = pd.read_parquet(PROJECT_ROOT / "processed" / "cases_by_district_daily.parquet")
cases_df = _load_parquet(PROJECT_ROOT / "processed" / "cases_by_district_daily.parquet")
except FileNotFoundError:
return GridGeoJSONResponse(type="FeatureCollection", features=[], timestamp=datetime.now().isoformat())
cases_df['date'] = pd.to_datetime(cases_df['date']).dt.strftime('%Y-%m-%d')
@@ -313,7 +329,7 @@ async def get_grid_history(
"""
import pandas as pd
district_map = pd.read_parquet(PROJECT_ROOT / "processed" / "grid_district_mapping.parquet")
district_map = _load_parquet(PROJECT_ROOT / "processed" / "grid_district_mapping.parquet")
grid_info = district_map[district_map['grid_id'] == grid_id]
if len(grid_info) == 0:
@@ -321,7 +337,7 @@ async def get_grid_history(
district = grid_info.iloc[0]['district_name']
cases_df = pd.read_parquet(PROJECT_ROOT / "processed" / "cases_by_district_daily.parquet")
cases_df = _load_parquet(PROJECT_ROOT / "processed" / "cases_by_district_daily.parquet")
cases_df['date'] = pd.to_datetime(cases_df['date'])
end_date = datetime.now()

3
backend/utils/date_helpers.py
View File

@@ -3,6 +3,7 @@ Date utilities: finding latest dates from GeoJSON files, parsing date strings.
"""
import glob
import re
from functools import lru_cache
from pathlib import Path
from fastapi import HTTPException
@@ -10,6 +11,7 @@ from fastapi import HTTPException
from config import DATA_DIR, DATE_FORMAT_GEOJSON
@lru_cache(maxsize=1)
def get_latest_date() -> str:
"""Get latest available date from GeoJSON files in DATA_DIR."""
pattern = str(DATA_DIR / "risk_*.geojson")
@@ -29,6 +31,7 @@ def get_latest_date() -> str:
return max(dates)
@lru_cache(maxsize=1)
def get_available_dates(days: int = 30) -> list[str]:
"""Get list of available dates, most recent first."""
pattern = str(DATA_DIR / "risk_*.geojson")

14
backend/utils/geojson.py
View File

@@ -2,17 +2,26 @@
GeoJSON file parsing utilities.
"""
import json
import logging
from functools import lru_cache
from pathlib import Path
from typing import Any
from config import WUHAN_BOUNDARY_PATH
from utils.risk import risk_value_to_level
logger = logging.getLogger(__name__)
@lru_cache(maxsize=8)
def parse_geojson_file(filepath: Path) -> list[dict[str, Any]]:
"""Parse GeoJSON file and extract grid data with standard fields."""
with open(filepath, "r", encoding="utf-8") as f:
geojson = json.load(f)
try:
with open(filepath, "r", encoding="utf-8") as f:
geojson = json.load(f)
except (json.JSONDecodeError, OSError) as e:
logger.warning("Failed to parse GeoJSON file %s: %s", filepath, e)
return []
grids: list[dict[str, Any]] = []
for feature in geojson.get("features", []):
@@ -33,6 +42,7 @@ def parse_geojson_file(filepath: Path) -> list[dict[str, Any]]:
return grids
@lru_cache(maxsize=1)
def load_districts() -> list[dict[str, Any]]:
"""Load Wuhan district boundaries from GeoJSON."""
if not WUHAN_BOUNDARY_PATH.exists():