Update src/streamlit_app.py

src/streamlit_app.py

@@ -3,17 +3,11 @@ import pandas as pd
 import altair as alt
 import json
 import urllib.request
-import os
-
-# 🌟 关键：解除 Altair 5000 行的限制，允许柱状图和折线图使用全量数据渲染
-alt.data_transformers.disable_max_rows()
 
 st.set_page_config(page_title="Crimes in Chicago 2026", page_icon="🚨", layout="wide")
-
 st.title("Crimes in Chicago - 2026")
 st.markdown("**Authors: Xinyi Chen, Zhongyin Wang** - Group 6")
 st.markdown("---")
-
 st.markdown(
     """
     ## What Is This About?
@@ -22,77 +16,78 @@ st.markdown(
     This interactive article walks you through 2026 Chicago crime data drawn directly from
     the [Chicago Data Portal](https://data.cityofchicago.org/) to help you explore the
     geography, timing, and social context of crime in one of America's largest cities.
+    The dataset records every reported crime incident in 2026, including the exact location,
+    date and time, crime type, and the police district that handled it. Each row is one
+    reported incident. We also include community-level socioeconomic data to examine the
+    relationship between poverty and crime rates across Chicago's neighborhoods.
     """
 )
 
 # ---------------------------------------------------------------------------
 # Data loading
 # ---------------------------------------------------------------------------
-
-@st.cache_data(show_spinner="Loading Chicago crime data from CSV...")
+@st.cache_data(show_spinner="Loading Chicago crime data (full dataset)...")
 def load_crime_data():
-    """自动寻找目录下的 Crimes 数据集，彻底告别文件名拼写报错"""
-    
-    # 1. 自动扫描当前文件夹
-    current_files = os.listdir('.')
-    csv_files = [f for f in current_files if 'Crimes' in f and f.endswith('.csv')]
+    """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
     
-    # 2. 如果什么都没找到，把当前文件夹里到底有什么打印出来，方便排错
-    if not csv_files:
-        st.error(f"找不到 CSV 文件！当前文件夹里只有这些文件: {current_files}")
+    if not all_chunks:
         return pd.DataFrame()
-        
-    # 3. 抓取找到的第一个文件
-    target_file = csv_files[0]
-    st.success(f"自动寻路成功！正在读取: {target_file}")
     
-    try:
-        df_raw = pd.read_csv(target_file, low_memory=False)
-    except Exception as e:
-        st.error(f"文件找到了，但读取失败: {e}")
-        return pd.DataFrame()
-
-    df = df_raw.copy()
+    df = pd.concat(all_chunks, ignore_index=True)
+    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")
     
-    # 适配 CSV 列名
-    df["date"] = pd.to_datetime(df["Date"], format='%m/%d/%Y %I:%M:%S %p', errors="coerce")
-    for col, orig_col in [("latitude", "Latitude"), ("longitude", "Longitude")]:
-        if orig_col in df.columns:
-            df[col] = pd.to_numeric(df[orig_col], errors="coerce")
-            
     df = df.dropna(subset=["date"])
-
-    # 🌟 修复 Pandas 'd' 为 'D' 弃用警告
-    df["Date_Only"] = df["date"].dt.floor("D")
+    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"
-
-    if "District" in df.columns:
+    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")
+            pd.to_numeric(df["district"], errors="coerce")
             .fillna(-1).astype(int).astype(str)
         )
         df["District"] = df["District_Str"]
     else:
         df["District_Str"] = df["District"] = "-1"
-
-    if "Community Area" in df.columns:
-        df["community_area"] = df["Community Area"]
-    else:
+    
+    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)"
-
+    
     df["Period"] = df["Hour"].apply(get_period)
     return df
 
-
 @st.cache_data(show_spinner="Loading socioeconomic data...")
 def load_socio():
     try:
@@ -105,7 +100,6 @@ def load_socio():
         st.warning(f"Could not load socioeconomic data: {e}")
         return pd.DataFrame(columns=["ca", "community_area_name", "poverty_rate"])
 
-
 @st.cache_data(show_spinner="Loading boundaries...")
 def load_geojson(url):
     try:
@@ -115,7 +109,6 @@ def load_geojson(url):
         st.warning(f"Could not load GeoJSON: {e}")
         return {"features": []}
 
-
 district_geojson  = load_geojson("https://data.cityofchicago.org/resource/24zt-jpfn.geojson")
 community_geojson = load_geojson("https://data.cityofchicago.org/resource/igwz-8jzy.geojson")
 
@@ -125,7 +118,7 @@ districts   = alt.Data(values=district_geojson["features"])
 communities = alt.Data(values=community_geojson["features"])
 
 if df.empty:
-    st.error("Crime data could not be loaded. Please check the logs.")
+    st.error("Crime data could not be loaded.")
     st.stop()
 
 df_geo = df.dropna(subset=["latitude", "longitude"]).copy()
@@ -151,8 +144,6 @@ st.markdown(
 brush      = alt.selection_interval(name="brush")
 click_type = alt.selection_point(fields=["Primary Type"], name="click_type")
 click_dist = alt.selection_point(fields=["District_Str"], name="click_dist")
-
-# 地图图层采样 (保护浏览器)，但右侧柱状图/折线图坚持用全量数据 df
 MAP_SAMPLE   = 5000
 df_map_sample = df_geo.sample(min(MAP_SAMPLE, len(df_geo)), random_state=42)
 
@@ -192,10 +183,10 @@ geo_points = (
 
 map_layer = (background + geo_points).project(type="mercator").properties(
     width=420, height=450,
-    title=f"Chicago Crime Map (map shows {MAP_SAMPLE:,} sampled points)",
+    title=f"Chicago Crime Map (map shows {MAP_SAMPLE:,} sampled points for performance)",
 )
 
-# 🌟 Bar chart - 坚持使用全量数据集 df
+# Bar chart - full df
 type_chart = (
     alt.Chart(df)
     .mark_bar()
@@ -211,7 +202,7 @@ type_chart = (
     .transform_filter(click_dist)
 )
 
-# 🌟 Line chart - 坚持使用全量数据集 df
+# Line chart - full df
 period_order = ["Morning (6am-12pm)", "Afternoon (12pm-6pm)",
                 "Evening (6pm-12am)", "Late Night (12am-6am)", "Total Daily"]
 period_range = ["#f4a261", "#e9c46a", "#e76f51", "#264653", "grey"]
@@ -263,8 +254,6 @@ line_chart = (total_line + period_lines).properties(
 ).resolve_scale(color="shared")
 
 dashboard = ((map_layer | type_chart) & line_chart).resolve_scale(color="independent")
-
-# 修复旧版警告，使用 width="stretch" (如果报错可改回 use_container_width=True)
 st.altair_chart(dashboard, use_container_width=True)
 
 # ---------------------------------------------------------------------------
@@ -278,6 +267,9 @@ st.markdown(
     the heatmap by crime category, or leave it on *All* to see the overall pattern.
     Each cell shows the total number of incidents at that day-of-week x hour-of-day
     combination across the full dataset; darker red means more incidents.
+    Across nearly every category, Friday and Saturday evenings (6 pm to midnight)
+    stand out as the most active windows, while the early-morning hours (2 to 5 am)
+    are consistently quietest.
     """
 )
 
@@ -308,7 +300,7 @@ heatmap = (
     )
     .properties(
         width=700, height=380,
-        title=f"Crime Heatmap - {selected_hm} (full dataset)",
+        title=f"Crime Heatmap - {selected_hm} (full dataset, darker = more incidents)",
     )
 )
 st.altair_chart(heatmap, use_container_width=True)
@@ -322,8 +314,17 @@ st.markdown(
     """
     Socioeconomic inequality is one of the most studied predictors of crime at the
     neighborhood level. The choropleth map on the left shades each of Chicago's 77
-    community areas by their poverty rate. 
-    The scatter plot on the right makes the poverty-crime relationship explicit.
+    community areas by their poverty rate - darker orange means higher poverty -
+    with a binned crime density heatmap overlaid. The heatmap uses the full dataset
+    with no sampling: each cell's color reflects how many incidents fall in that
+    geographic bin, giving a clear picture of crime hotspots.
+    
+    The scatter plot on the right makes the poverty-crime relationship explicit:
+    each dot is one community area, and the dashed line is a statistical trend.
+    There is a moderate positive correlation, though it is far from deterministic -
+    policy, policing patterns, and reporting rates all play a role.
+    
+    **Socioeconomic data source:** [Census Data - Chicago Data Portal](https://data.cityofchicago.org/Health-Human-Services/Census-Data-Selected-Socioeconomic-Indicators-in-C/kn9c-c2s2)
     """
 )
 
@@ -349,16 +350,20 @@ with col3:
             .project(type="mercator")
             .properties(width=360, height=440, title="Chicago Poverty Rate by Community Area")
         )
-
-        # 🌟 核心修复：预先聚合经纬度，解决 longitude/latitude 不能应用 bin 的严重报错问题！
+        
+        # --- FIX: 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['lon_bin'] = df_geo_binned['longitude'].round(2)
         df_geo_binned['lat_bin'] = df_geo_binned['latitude'].round(2)
-        density_agg = df_geo_binned.groupby(['lon_bin', 'lat_bin']).size().reset_index(name='incident_count')
+        df_geo_binned['lon_bin'] = df_geo_binned['longitude'].round(2)
+        
+        # 统计每个坐标网格的案件数量
+        density_agg = df_geo_binned.groupby(['lat_bin', 'lon_bin']).size().reset_index(name='incident_count')
 
+        # Binned geo-heatmap: 使用 mark_square 模拟网格热力图
         crime_density = (
             alt.Chart(density_agg)
-            .mark_square(opacity=0.7)
+            .mark_square(opacity=0.65, size=80) 
             .encode(
                 longitude="lon_bin:Q",
                 latitude="lat_bin:Q",
@@ -368,19 +373,12 @@ with col3:
                     title="Incident Count",
                     legend=alt.Legend(title="Incidents"),
                 ),
-                size=alt.Size(
-                    "incident_count:Q",
-                    scale=alt.Scale(range=[10, 150]), 
-                    legend=None
-                ),
                 tooltip=[
-                    alt.Tooltip("lon_bin:Q", title="Longitude (Grid)"),
-                    alt.Tooltip("lat_bin:Q", title="Latitude (Grid)"),
-                    alt.Tooltip("incident_count:Q", title="Incidents")
+                    alt.Tooltip("incident_count:Q", title="Total Incidents")
                 ]
             )
         )
-
+        
         st.altair_chart(
             (poverty_map + crime_density).resolve_scale(color="independent"),
             use_container_width=True,
@@ -398,11 +396,13 @@ with col4:
         df_crime_count["ca"] = (
             df_crime_count["community_area"].astype(float).astype(int).astype(str)
         )
+        
         df_scatter = pd.merge(
             df_socio[["ca", "community_area_name", "poverty_rate"]],
             df_crime_count[["ca", "crime_count"]],
             on="ca", how="inner",
         )
+        
         if len(df_scatter) > 5:
             sc = (
                 alt.Chart(df_scatter)
@@ -425,7 +425,7 @@ with col4:
             st.altair_chart(
                 (sc + reg).properties(
                     width=360, height=440,
-                    title="Higher Poverty -> More Crimes?",
+                    title="Higher Poverty -> More Crimes? (each dot = one community area)",
                 ),
                 use_container_width=True,
             )