Update app.py

app.py

@@ -1,5 +1,3 @@
-import requests
-from bs4 import BeautifulSoup
 import pandas as pd
 import folium
 from folium.plugins import MarkerCluster, HeatMap
@@ -12,15 +10,17 @@ import streamlit as st
 import time
 
 # Streamlit title and description
-st.title("米其林餐廳指南爬蟲與分析")
-st.write("提取餐廳數據，可視化區域分佈，並在地圖上顯示位置和推薦度熱力圖。")
+st.title("米其林餐廳指南分析")
+st.write("分析餐廳數據，可視化區域分佈，並在地圖上顯示位置和餐廳數量熱力圖。")
 
 # Read data from Google Sheets
 sheet_id = "1xUfnD1WCF5ldqECI8YXIko1gCpaDDCwTztL17kjI42U"
 df = pd.read_csv(f"https://docs.google.com/spreadsheets/d/{sheet_id}/export?format=csv")
 
-# Print column names
+# Print column names and first few rows
 st.write("資料框的列名：", df.columns.tolist())
+st.write("資料預覽：")
+st.dataframe(df.head())
 
 # Initialize Nominatim geocoder
 geolocator = Nominatim(user_agent="my_unique_app/3.0")
@@ -40,130 +40,107 @@ def get_lat_lon(district):
         location = geolocator.geocode(f"台南市{district}")
         if location:
             time.sleep(1)  # Delay to avoid rate limiting
-            return location.latitude, location.longitude
+            return location.latitude, longitude
     except GeocoderInsufficientPrivileges:
         st.error("地理編碼器遇到權限問題，請稍後再試。")
     return None, None
 
-# Check if required columns exist
-required_columns = ['Address', 'Store Name', '推薦度']
-missing_columns = [col for col in required_columns if col not in df.columns]
-
-if missing_columns:
-    st.error(f"資料中缺少以下列：{', '.join(missing_columns)}")
-    st.stop()
-
-# Apply geocoding to the dataframe
-df['Region'] = df['Address'].apply(extract_region)
-df['Latitude'], df['Longitude'] = zip(*df['Region'].apply(get_lat_lon))
-
-# Display the DataFrame as a table at the top
-st.subheader("餐廳數據")
-st.dataframe(df)
-
-# Group the data by region and sum the number of restaurants
-region_group = df.groupby("Region").agg({'Store Name': 'count', '推薦度': 'mean'}).reset_index()
-region_group.columns = ['Region', 'Count', 'Avg_Recommendation']
-
-# Create hierarchical data for the Sunburst chart
-region_group['Total'] = 'All Regions'  # Add a root level
-hierarchical_data = region_group[['Total', 'Region', 'Count']]
-
-# Plot interactive Sunburst chart
-sunburst = go.Figure(go.Sunburst(
-    labels=hierarchical_data['Region'].tolist() + hierarchical_data['Total'].tolist(),
-    parents=hierarchical_data['Total'].tolist() + [''],
-    values=hierarchical_data['Count'].tolist() + [hierarchical_data['Count'].sum()],
-    branchvalues="total",
-    hovertemplate='<b>%{label}</b><br>餐廳數量: %{value}<extra></extra>',
-    maxdepth=2,
-))
-
-sunburst.update_layout(
-    title="餐廳分佈（點擊可放大查看）",
-    title_x=0.5,
-    title_font=dict(size=24, family="Arial"),
-    height=600,
-    margin=dict(t=50, b=50, l=0, r=0)
-)
-
-# Add custom JavaScript for click events
-sunburst.update_layout(
-    updatemenus=[{
-        'type': 'buttons',
-        'showactive': False,
-        'buttons': [{
-            'label': '重置視圖',
-            'method': 'update',
-            'args': [{'visible': [True] * len(sunburst.data)},
-                     {'title': '餐廳分佈（點擊可放大查看）'}]
-        }]
-    }]
-)
-
-st.subheader("餐廳分佈（Sunburst 圖）")
-st.plotly_chart(sunburst, use_container_width=True)
-
-# Plot bar chart with custom colors and labels
-bar_chart = go.Figure(go.Bar(
-    x=region_group["Region"],
-    y=region_group["Count"],
-    text=region_group["Count"],
-    textposition='auto',
-    marker=dict(color=px.colors.qualitative.Set2)
-))
-
-bar_chart.update_layout(
-    title="各區域餐廳數量",
-    title_x=0.5,
-    title_font=dict(size=24, family="Arial"),
-    height=400,
-    margin=dict(t=50, b=50, l=50, r=50),
-    xaxis_title="區域",
-    yaxis_title="餐廳數量",
-    xaxis=dict(tickangle=-45)
-)
-st.subheader("各區域餐廳數量（條形圖）")
-st.plotly_chart(bar_chart)
-
-# 推薦度與地理位置的關聯性
-st.header("推薦度與地理位置的關聯性")
-
-# 區域性推薦度分析
-fig_bar = px.bar(region_group, x="Region", y="Avg_Recommendation", 
-                 title="不同區域的平均推薦度比較", 
-                 color_discrete_sequence=['#66CDAA'])
-st.plotly_chart(fig_bar)
-
-# Display a map using Folium
-st.subheader("餐廳位置地圖（含推薦度熱力圖）")
-
-# Create map centered around Tainan
-m = folium.Map(location=[23.0, 120.2], zoom_start=12)
-
-# Add marker cluster to the map
-marker_cluster = MarkerCluster().add_to(m)
-
-# Prepare data for heatmap
-heat_data = []
-
-for index, row in df.iterrows():
-    if pd.notnull(row["Latitude"]) and pd.notnull(row["Longitude"]):
-        folium.Marker(
-            location=[row["Latitude"], row["Longitude"]],
-            popup=f"{row['Store Name']} (推薦度: {row['推薦度']})",
-            tooltip=row["Address"]
-        ).add_to(marker_cluster)
-        heat_data.append([row["Latitude"], row["Longitude"], row["推薦度"]])
-
-# Add heatmap layer
-HeatMap(heat_data, radius=15, blur=10, max_zoom=1, name="推薦度熱力圖").add_to(m)
-
-# Add layer control
-folium.LayerControl().add_to(m)
-
-# Display the map in Streamlit
-st.components.v1.html(m._repr_html_(), height=600)
+# Assuming we have a column that represents the region or can be used to derive it
+# If we don't have such a column, we'll need to skip this part
+if '區域' in df.columns:
+    region_column = '區域'
+elif '地址' in df.columns:
+    df['區域'] = df['地址'].apply(extract_region)
+    region_column = '區域'
+else:
+    st.error("無法找到區域資訊，某些分析將無法進行。")
+    region_column = None
+
+# Group the data by region and count the number of restaurants
+if region_column:
+    region_group = df.groupby(region_column).size().reset_index(name='Count')
+
+    # Create hierarchical data for the Sunburst chart
+    region_group['Total'] = 'All Regions'  # Add a root level
+    hierarchical_data = region_group[['Total', region_column, 'Count']]
+
+    # Plot interactive Sunburst chart
+    sunburst = go.Figure(go.Sunburst(
+        labels=hierarchical_data[region_column].tolist() + hierarchical_data['Total'].tolist(),
+        parents=hierarchical_data['Total'].tolist() + [''],
+        values=hierarchical_data['Count'].tolist() + [hierarchical_data['Count'].sum()],
+        branchvalues="total",
+        hovertemplate='<b>%{label}</b><br>餐廳數量: %{value}<extra></extra>',
+        maxdepth=2,
+    ))
+
+    sunburst.update_layout(
+        title="餐廳分佈（點擊可放大查看）",
+        title_x=0.5,
+        title_font=dict(size=24, family="Arial"),
+        height=600,
+        margin=dict(t=50, b=50, l=0, r=0)
+    )
+
+    st.subheader("餐廳分佈（Sunburst 圖）")
+    st.plotly_chart(sunburst, use_container_width=True)
+
+    # Plot bar chart with custom colors and labels
+    bar_chart = go.Figure(go.Bar(
+        x=region_group[region_column],
+        y=region_group["Count"],
+        text=region_group["Count"],
+        textposition='auto',
+        marker=dict(color=px.colors.qualitative.Set2)
+    ))
+
+    bar_chart.update_layout(
+        title="各區域餐廳數量",
+        title_x=0.5,
+        title_font=dict(size=24, family="Arial"),
+        height=400,
+        margin=dict(t=50, b=50, l=50, r=50),
+        xaxis_title="區域",
+        yaxis_title="餐廳數量",
+        xaxis=dict(tickangle=-45)
+    )
+    st.subheader("各區域餐廳數量（條形圖）")
+    st.plotly_chart(bar_chart)
+
+# Display a map using Folium if we have latitude and longitude
+if '緯度' in df.columns and '經度' in df.columns:
+    st.subheader("餐廳位置地圖（含數量熱力圖）")
+
+    # Create map centered around the mean latitude and longitude
+    center_lat = df['緯度'].mean()
+    center_lon = df['經度'].mean()
+    m = folium.Map(location=[center_lat, center_lon], zoom_start=12)
+
+    # Add marker cluster to the map
+    marker_cluster = MarkerCluster().add_to(m)
+
+    # Prepare data for heatmap
+    heat_data = []
+
+    for index, row in df.iterrows():
+        if pd.notnull(row["緯度"]) and pd.notnull(row["經度"]):
+            folium.Marker(
+                location=[row["緯度"], row["經度"]],
+                popup=f"{row.get('店名', 'Unknown')}",
+                tooltip=row.get('地址', 'Unknown')
+            ).add_to(marker_cluster)
+            heat_data.append([row["緯度"], row["經度"], 1])  # Weight of 1 for each restaurant
+
+    # Add heatmap layer
+    HeatMap(heat_data, radius=15, blur=10, max_zoom=1, name="餐廳數量熱力圖").add_to(m)
+
+    # Add layer control
+    folium.LayerControl().add_to(m)
+
+    # Display the map in Streamlit
+    st.components.v1.html(m._repr_html_(), height=600)
+else:
+    st.error("無法顯示地圖，因為缺少緯度和經度資訊。")
 
 # Save the DataFrame to CSV with UTF-8 encoding
 csv_file = "restaurants_data.csv"