Update app.py

app.py

@@ -2,7 +2,7 @@ import requests
 from bs4 import BeautifulSoup
 import pandas as pd
 import folium
-from folium.plugins import MarkerCluster, HeatMap
+from folium.plugins import MarkerCluster
 import plotly.graph_objects as go
 from geopy.geocoders import Nominatim
 import re
@@ -10,7 +10,7 @@ import streamlit as st
 
 # Streamlit title and description
 st.title("Restaurant Data Extractor")
-st.write("Extracting restaurant data and displaying it on a map.")
+st.write("Extract restaurant data, visualize with a pie chart and bar chart, and display locations on a map.")
 
 # Read data from Google Sheets
 sheet_id = "1xUfnD1WCF5ldqECI8YXIko1gCpaDDCwTztL17kjI42U"
@@ -33,84 +33,113 @@ def extract_region(address):
     else:
         return "Unknown"
 
-# Progress bar in Streamlit
-progress_bar = st.progress(0)
-total_urls = len(urls)
-
-# Iterate through each URL
-for idx, url in enumerate(urls):
-    response = requests.get(url)
-    soup = BeautifulSoup(response.content, "html.parser")
-
-    try:
-        store_name = soup.find("h2", class_="restaurant-details__heading--title").text.strip()
-    except AttributeError:
-        store_name = None
-
-    try:
-        address = soup.find("li", class_="restaurant-details__heading--address").text.strip()
-        region = extract_region(address)
-    except AttributeError:
-        address = None
-        region = "Unknown"
-
-    try:
-        location = geolocator.geocode(address)
-        if location:
-            latitude = location.latitude
-            longitude = location.longitude
-        else:
+# Function to fetch and parse data
+def fetch_data():
+    global df
+    # Progress bar in Streamlit
+    progress_bar = st.progress(0)
+    total_urls = len(urls)
+
+    # Iterate through each URL
+    for idx, url in enumerate(urls):
+        response = requests.get(url)
+        soup = BeautifulSoup(response.content, "html.parser")
+
+        try:
+            store_name = soup.find("h2", class_="restaurant-details__heading--title").text.strip()
+        except AttributeError:
+            store_name = None
+
+        try:
+            address = soup.find("li", class_="restaurant-details__heading--address").text.strip()
+            region = extract_region(address)
+        except AttributeError:
+            address = None
+            region = "Unknown"
+
+        try:
+            location = geolocator.geocode(address)
+            if location:
+                latitude = location.latitude
+                longitude = location.longitude
+            else:
+                latitude = None
+                longitude = None
+        except:
             latitude = None
             longitude = None
-    except:
-        latitude = None
-        longitude = None
-
-    new_row = pd.DataFrame({
-        "Store Name": [store_name],
-        "Address": [address],
-        "Latitude": [latitude],
-        "Longitude": [longitude],
-        "Region": [region]
-    })
-
-    df = pd.concat([df, new_row], ignore_index=True)
-
-    # Update progress bar
-    progress_bar.progress((idx + 1) / total_urls)
-
-# Save the DataFrame to CSV with UTF-8 encoding
-csv_file = "restaurants_data.csv"
-df.to_csv(csv_file, encoding="utf-8-sig", index=False)
-
-# Display a download button for the CSV file
-st.write(f"Data saved to {csv_file}")
-st.download_button(
-    label="Download restaurant data as CSV",
-    data=open(csv_file, "rb").read(),
-    file_name=csv_file,
-    mime="text/csv"
-)
-
-# Display a map using Folium in Streamlit
-st.subheader("Restaurant Locations Map")
-
-# 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)
-for index, row in df.iterrows():
-    if pd.notnull(row["Latitude"]) and pd.notnull(row["Longitude"]):
-        folium.Marker(
-            location=[row["Latitude"], row["Longitude"]],
-            popup=row["Store Name"],
-            tooltip=row["Address"]
-        ).add_to(marker_cluster)
-
-# Display the map in Streamlit
-st.components.v1.html(m._repr_html_(), height=600)
-
-# Optional: Display the DataFrame as a table
-st.subheader("Restaurant Data")
-st.dataframe(df)
+
+        new_row = pd.DataFrame({
+            "Store Name": [store_name],
+            "Address": [address],
+            "Latitude": [latitude],
+            "Longitude": [longitude],
+            "Region": [region]
+        })
+
+        df = pd.concat([df, new_row], ignore_index=True)
+
+        # Update progress bar
+        progress_bar.progress((idx + 1) / total_urls)
+
+# Button to trigger data fetching
+if st.button("Fetch Restaurant Data"):
+    fetch_data()
+    
+    # Save the DataFrame to CSV with UTF-8 encoding
+    csv_file = "restaurants_data.csv"
+    df.to_csv(csv_file, encoding="utf-8-sig", index=False)
+
+    # Display download button for the CSV
+    st.download_button(
+        label="Download restaurant data as CSV",
+        data=open(csv_file, "rb").read(),
+        file_name=csv_file,
+        mime="text/csv"
+    )
+
+    # Group the data by region
+    region_group = df.groupby("Region").size().reset_index(name='Count')
+
+    # Plot pie chart
+    pie_chart = go.Figure(go.Pie(
+        labels=region_group["Region"],
+        values=region_group["Count"],
+        hoverinfo="label+percent",
+        textinfo="value+percent",
+    ))
+    st.subheader("Restaurant Distribution by Region (Pie Chart)")
+    st.plotly_chart(pie_chart)
+
+    # Plot bar chart
+    bar_chart = go.Figure(go.Bar(
+        x=region_group["Region"],
+        y=region_group["Count"],
+        text=region_group["Count"],
+        textposition='auto'
+    ))
+    st.subheader("Restaurant Count by Region (Bar Chart)")
+    st.plotly_chart(bar_chart)
+
+    # Display a map using Folium
+    st.subheader("Restaurant Locations Map")
+
+    # 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)
+    for index, row in df.iterrows():
+        if pd.notnull(row["Latitude"]) and pd.notnull(row["Longitude"]):
+            folium.Marker(
+                location=[row["Latitude"], row["Longitude"]],
+                popup=row["Store Name"],
+                tooltip=row["Address"]
+            ).add_to(marker_cluster)
+
+    # Display the map in Streamlit
+    st.components.v1.html(m._repr_html_(), height=600)
+
+    # Optional: Display the DataFrame as a table
+    st.subheader("Restaurant Data")
+    st.dataframe(df)