Update src/streamlit_app.py

src/streamlit_app.py

@@ -27,32 +27,56 @@ st.markdown(
 # Data loading (Now using local CSV for extreme speedup)
 # ---------------------------------------------------------------------------
 @st.cache_data(show_spinner="Loading local Chicago crime data...")
+@st.cache_data(show_spinner="Loading local Chicago crime data...")
 def load_crime_data():
-    """Read directly from the local CSV file instead of slow API pagination."""
+    """Robust loading for Hugging Face Spaces (handles path issues)."""
+    import os
+
     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
+        # ✅ 获取当前脚本所在目录（关键！！）
+        BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+
+        # ✅ 构造绝对路径
+        file_path = os.path.join(BASE_DIR, "Crimes_-_2026_20260417.csv")
+
+        # ✅ Debug信息（第一次部署时非常重要）
+        st.write("📂 Current working dir:", os.getcwd())
+        st.write("📂 BASE_DIR:", BASE_DIR)
+        st.write("📄 Files in BASE_DIR:", os.listdir(BASE_DIR))
+        st.write("📄 Trying to read:", file_path)
+
+        # ✅ 读取 CSV
+        df = pd.read_csv(file_path)
+
+        # 标准化列名
         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。")
+        st.error("❌ CSV file not found. Check filename and path.")
         return pd.DataFrame()
     except Exception as e:
-        st.error(f"读取本地数据失败: {e}")
+        st.error(f"❌ Failed to read CSV: {e}")
         return pd.DataFrame()
 
+    # -------------------------
+    # 后处理（你原来的逻辑）
+    # -------------------------
     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")
-    
+
     df = df.dropna(subset=["date"])
+
     df["Date_Only"] = df["date"].dt.floor("d")
-    df["Hour"]      = df["date"].dt.hour
-    df["weekday"]   = df["date"].dt.day_name().str[:3]
-    df["Primary Type"] = df["primary_type"].str.upper() if "primary_type" in df.columns else "UNKNOWN"
-    
+    df["Hour"] = df["date"].dt.hour
+    df["weekday"] = df["date"].dt.day_name().str[:3]
+
+    df["Primary Type"] = (
+        df["primary_type"].str.upper()
+        if "primary_type" in df.columns else "UNKNOWN"
+    )
+
     if "district" in df.columns:
         df["District_Str"] = (
             pd.to_numeric(df["district"], errors="coerce")
@@ -61,17 +85,22 @@ def load_crime_data():
         df["District"] = df["District_Str"]
     else:
         df["District_Str"] = df["District"] = "-1"
-    
+
     if "community_area" not in df.columns:
         df["community_area"] = None
-    
+
     def get_period(h):
-        if   6  < h <= 12: return "Morning (6am-12pm)"
-        elif 12 < h <= 18: return "Afternoon (12pm-6pm)"
-        elif 18 < h <= 24: return "Evening (6pm-12am)"
-        else:              return "Late Night (12am-6am)"
-    
+        if 6 < h <= 12:
+            return "Morning (6am-12pm)"
+        elif 12 < h <= 18:
+            return "Afternoon (12pm-6pm)"
+        elif 18 < h <= 24:
+            return "Evening (6pm-12am)"
+        else:
+            return "Late Night (12am-6am)"
+
     df["Period"] = df["Hour"].apply(get_period)
+
     return df
 
 @st.cache_data(show_spinner="Loading socioeconomic data...")