Update src/streamlit_app.py

src/streamlit_app.py

@@ -4,7 +4,10 @@ import altair as alt
 import json
 import urllib.request
 
-st.set_page_config(page_title="Crimes in Chicago 2026", page_icon="?", layout="wide")
+# 🌟 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")
@@ -29,59 +32,45 @@ st.markdown(
 # Data loading
 # ---------------------------------------------------------------------------
 
-@st.cache_data(show_spinner="Loading Chicago crime data (full dataset)...")
+@st.cache_data(show_spinner="Loading Chicago crime data from CSV...")
 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:
+    """直接读取上传到 Hugging Face 的 CSV 文件，不再使用 API 循环请求。"""
+    try:
+        # 读取本地上传的 CSV 文件
+        df_raw = pd.read_csv("Crimes_-_2026_20260417.csv", low_memory=False)
+    except Exception as e:
+        st.error(f"Failed to load CSV file. 请确保文件名准确并已上传到 Hugging Face: {e}")
         return pd.DataFrame()
 
-    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")
+    df = df_raw.copy()
+    
+    # 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"])
 
-    df["Date_Only"] = df["date"].dt.floor("d")
+    # 🌟 修复 Pandas 'd' 为 'D' 弃用警告
+    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["Primary Type"] = df["Primary Type"].str.upper() if "Primary Type" in df.columns else "UNKNOWN"
 
-    if "district" in df.columns:
+    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" not in df.columns:
+    if "Community Area" in df.columns:
+        df["community_area"] = df["Community Area"]
+    else:
         df["community_area"] = None
 
     def get_period(h):
@@ -153,6 +142,7 @@ 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 +182,10 @@ 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 for performance)",
+    title=f"Chicago Crime Map (map shows {MAP_SAMPLE:,} sampled points)",
 )
 
-# Bar chart - full df
+# 🌟 Bar chart - 坚持使用全量数据集 df
 type_chart = (
     alt.Chart(df)
     .mark_bar()
@@ -211,7 +201,7 @@ type_chart = (
     .transform_filter(click_dist)
 )
 
-# Line chart - full df
+# 🌟 Line chart - 坚持使用全量数据集 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"]
@@ -263,12 +253,12 @@ line_chart = (total_line + period_lines).properties(
 ).resolve_scale(color="shared")
 
 dashboard = ((map_layer | type_chart) & line_chart).resolve_scale(color="independent")
+
+# 修复���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)
 
 # ---------------------------------------------------------------------------
 # SECTION 2 — When do crimes happen? heatmap + dropdown
-# Pre-aggregate to 7x24 = 168 rows in Python before rendering,
-# so switching crime types is instant - no re-streaming of raw data to browser.
 # ---------------------------------------------------------------------------
 st.markdown("---")
 st.header("When Do Crimes Happen in Chicago?")
@@ -278,16 +268,12 @@ 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.
     """
 )
 
 top_types_hm = df["Primary Type"].value_counts().head(10).index.tolist()
 selected_hm  = st.selectbox("Select Crime Type", options=["All"] + top_types_hm, index=0)
 
-# Key fix: groupby in Python first -> only 168 rows reach Altair -> instant render
 weekday_order = ["Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun"]
 hm_source = df if selected_hm == "All" else df[df["Primary Type"] == selected_hm]
 hm_agg = (
@@ -312,15 +298,13 @@ heatmap = (
     )
     .properties(
         width=700, height=380,
-        title=f"Crime Heatmap - {selected_hm} (full dataset, darker = more incidents)",
+        title=f"Crime Heatmap - {selected_hm} (full dataset)",
     )
 )
 st.altair_chart(heatmap, use_container_width=True)
 
 # ---------------------------------------------------------------------------
 # SECTION 3 — Poverty vs. Crime
-# Left: choropleth + binned geo-heatmap (no sampling, full density visible)
-# Right: scatter with full crime counts per community area
 # ---------------------------------------------------------------------------
 st.markdown("---")
 st.header("Does Poverty Predict Crime?")
@@ -328,15 +312,8 @@ 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 - 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)
+    community areas by their poverty rate. 
+    The scatter plot on the right makes the poverty-crime relationship explicit.
     """
 )
 
@@ -363,20 +340,34 @@ with col3:
             .properties(width=360, height=440, title="Chicago Poverty Rate by Community Area")
         )
 
-        # Binned geo-heatmap: full dataset, no sampling needed
-        # maxbins=50 -> ~2500 cells max, renders fast and shows full density
+        # 🌟 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！
+        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')
+
         crime_density = (
-            alt.Chart(df_geo)
-            .mark_rect(opacity=0.55)
+            alt.Chart(density_agg)
+            .mark_square(opacity=0.7)
             .encode(
-                longitude=alt.X("longitude:Q", bin=alt.Bin(maxbins=50)),
-                latitude=alt.Y("latitude:Q",   bin=alt.Bin(maxbins=50)),
+                longitude="lon_bin:Q",
+                latitude="lat_bin:Q",
                 color=alt.Color(
-                    "count():Q",
+                    "incident_count:Q",
                     scale=alt.Scale(scheme="blues"),
                     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")
+                ]
             )
         )
 
@@ -389,7 +380,6 @@ with col3:
 
 with col4:
     if not df_socio.empty and df["community_area"].notna().any():
-        # Full df for crime counts - no sampling
         df_crime_count = (
             df.dropna(subset=["community_area"])
             .groupby("community_area").size()
@@ -425,7 +415,7 @@ with col4:
             st.altair_chart(
                 (sc + reg).properties(
                     width=360, height=440,
-                    title="Higher Poverty -> More Crimes? (each dot = one community area)",
+                    title="Higher Poverty -> More Crimes?",
                 ),
                 use_container_width=True,
             )
@@ -447,6 +437,7 @@ st.markdown(
     | Socioeconomic Indicators by Community | City of Chicago Data Portal | [kn9c-c2s2](https://data.cityofchicago.org/Health-Human-Services/Census-Data-Selected-Socioeconomic-Indicators-in-C/kn9c-c2s2) |
     | Police District Boundaries (GeoJSON) | City of Chicago Data Portal | [24zt-jpfn](https://data.cityofchicago.org/Public-Safety/Boundaries-Police-Districts-current-/24zt-jpfn) |
     | Community Area Boundaries (GeoJSON) | City of Chicago Data Portal | [igwz-8jzy](https://data.cityofchicago.org/Facilities-Geographic-Boundaries/Boundaries-Community-Areas-current-/cauq-8yn6) |
+    
     All data accessed April 2026. Visualizations built with [Altair](https://altair-viz.github.io/) and [Streamlit](https://streamlit.io/).
     """
 )