Update src/streamlit_app.py

src/streamlit_app.py

@@ -24,39 +24,25 @@ st.markdown(
 )
 
 # ---------------------------------------------------------------------------
-# Data loading
+# Data loading (Now using local CSV for extreme speedup)
 # ---------------------------------------------------------------------------
-@st.cache_data(show_spinner="Loading Chicago crime data (full dataset)...")
+@st.cache_data(show_spinner="Loading local Chicago crime data...")
 def load_crime_data():
-    """Fetch ALL 2026 records in batches. Bar/line/heatmap use the full df;
-    only geo rendering on maps uses sampling."""
-    all_chunks = []
-    limit  = 50000
-    offset = 0
-    while True:
-        url = (
-            "https://data.cityofchicago.org/resource/ijzp-q8t2.json"
-            "?$where=year=2026"
-            f"&$limit={limit}"
-            f"&$offset={offset}"
-            "&$order=date%20DESC"
-        )
-        try:
-            chunk = pd.read_json(url)
-        except Exception as e:
-            st.error(f"Failed to load crime data at offset {offset}: {e}")
-            break
-        if chunk.empty:
-            break
-        all_chunks.append(chunk)
-        if len(chunk) < limit:
-            break
-        offset += limit
-    
-    if not all_chunks:
+    """Read directly from the local CSV file instead of slow API pagination."""
+    try:
+        # 直接读取本地上传的 CSV 文件
+        df = pd.read_csv("Crimes_-_2026_20260417.csv")
+        
+        # 将原本诸如 "Primary Type" 的表头标准化为 "primary_type" 以适配后续代码
+        df.columns = [c.lower().replace(" ", "_") for c in df.columns]
+        
+    except FileNotFoundError:
+        st.error("找不到文件 'Crimes_-_2026_20260417.csv'。请确保它与此脚本位于同一目录下。")
         return pd.DataFrame()
-    
-    df = pd.concat(all_chunks, ignore_index=True)
+    except Exception as e:
+        st.error(f"读取本地数据失败: {e}")
+        return pd.DataFrame()
+
     df["date"] = pd.to_datetime(df["date"], errors="coerce")
     for col in ["latitude", "longitude"]:
         df[col] = pd.to_numeric(df.get(col, pd.Series(dtype=float)), errors="coerce")
@@ -351,7 +337,7 @@ with col3:
             .properties(width=360, height=440, title="Chicago Poverty Rate by Community Area")
         )
         
-        # --- FIX: Pre-aggregate data for geographic binning in Pandas ---
+        # --- Pre-aggregate data for geographic binning in Pandas ---
         # 舍入到 2 位小数创建了与 maxbins=50 相似的地理网格
         df_geo_binned = df_geo.copy()
         df_geo_binned['lat_bin'] = df_geo_binned['latitude'].round(2)