Update app.py

app.py

@@ -1,37 +1,26 @@
-# Standard library imports
 import logging
-import os
-import math
-
-# Third-party imports
+import gradio as gr
 import pandas as pd
+import plotly.express as px
+import folium
 import numpy as np
 import geopandas as gpd
-import folium
-import plotly.express as px
 from folium.plugins import MarkerCluster
 from sklearn.neighbors import BallTree
 from geopy.geocoders import Nominatim
 from geopy.extra.rate_limiter import RateLimiter
-
-# Gradio imports
-import gradio as gr
-from gradio.components import Map  # Import Map component
+import math
+import os
 
 # Logger setup
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
 # Load datasets
-try:
-    df_md_final1 = pd.read_csv("data/location-of-auto-businesses.csv")
-    cbg_geographic_data = pd.read_csv("data/cbg_geographic_data.csv")
-except FileNotFoundError as e:
-    logger.error(f"Error loading data files: {e}")
-    raise
+df_md_final1 = pd.read_csv("data/location-of-auto-businesses.csv")
+cbg_geographic_data = pd.read_csv("data/cbg_geographic_data.csv")
 
 # Create DataFrames for the 2020 and 2010 populations
-# For demonstration, we are using hardcoded data
 population_2020_data = {
     'County': ['Shelby', 'Davidson', 'Knox', 'Hamilton', 'Rutherford', 'Williamson', 'Montgomery', 'Sumner', 'Blount', 'Washington', 
                'Madison', 'Sevier', 'Maury', 'Wilson', 'Bradley'],
@@ -47,105 +36,94 @@ df_population_2010.rename(columns={'cntyname': 'County', 'pop10': 'Population_20
 df_population_comparison = pd.merge(df_population_2010, df_population_2020, on='County')
 
 # Define Business Types
-def assign_business_type(name):
-    if pd.isna(name):
-        return "Other Auto Repair Shops"
-    name = name.lower()
-    if "autozone" in name:
-        return "Autozone"
-    elif "napa auto parts" in name:
-        return "Napa Auto"
-    elif "firestone complete auto care" in name:
-        return "Firestone"
-    elif "o'reilly auto parts" in name:
-        return "O'Reilly Auto"
-    elif "advance auto parts" in name:
-        return "Advance Auto"
-    elif any(dealer in name for dealer in ["toyota", "honda", "kia", "nissan", "chevy", "ford", "carmax", "gmc"]):
-        return "Car Dealership"
-    else:
-        return "Other Auto Repair Shops"
-
-df_md_final1['business_type'] = df_md_final1['name'].apply(assign_business_type)
-
-# Load shapefiles
-def load_shapefile(shapefile_path, state_fips='47', state_abbr='TN'):
-    if not os.path.exists(shapefile_path):
-        raise FileNotFoundError(f"Shapefile not found at {shapefile_path}. Please ensure the file exists.")
-    geo_df = gpd.read_file(shapefile_path)
-    if 'statefp' in geo_df.columns:
-        geo_df = geo_df[geo_df['statefp'] == state_fips]
-    elif 'hsastate' in geo_df.columns:
-        geo_df = geo_df[geo_df['hsastate'] == state_abbr]
-    elif 'hrrstate' in geo_df.columns:
-        geo_df = geo_df[geo_df['hrrstate'] == state_abbr]
-    elif 'STATEFP' in geo_df.columns:
-        geo_df = geo_df[geo_df['STATEFP'] == state_fips]
-    else:
-        raise KeyError("Column to filter state in shapefile not found.")
-    return geo_df
+df_md_final1['business_type'] = np.where(df_md_final1['name'].str.contains("Autozone", case=False, na=False), "Autozone", 
+    np.where(df_md_final1['name'].str.contains("Napa Auto Parts", case=False, na=False), "Napa Auto", 
+        np.where(df_md_final1['name'].str.contains("Firestone Complete Auto Care", case=False, na=False), "Firestone",                                 
+            np.where(df_md_final1['name'].str.contains("O'Reilly Auto Parts", case=False, na=False), "O'Reilly Auto",
+                np.where(df_md_final1['name'].str.contains("Advance Auto Parts", case=False, na=False), "Advance Auto",
+                    np.where(df_md_final1['name'].str.contains("Toyota|Honda|Kia|Nissan|Chevy|Ford|Carmax|GMC", case=False, na=False), 
+                             "Car Dealership", 
+                             "Other Auto Repair Shops")
+                )
+            )
+        )
+    )
+)
 
 # Load the County shapefile
 county_shapefile_path = "data/county/01_county-shape-file.shp"
-counties_geo = load_shapefile(county_shapefile_path, state_fips='47')
+if not os.path.exists(county_shapefile_path):
+    raise FileNotFoundError(f"County shapefile not found at {county_shapefile_path}. Please ensure the file exists.")
+    
+counties_geo = gpd.read_file(county_shapefile_path)
+counties_geo = counties_geo[counties_geo['statefp'] == '47']  # Tennessee FIPS code
 
 # Load the HSA shapefile
 hsa_shapefile_path = "data/hsa/01_hsa-shape-file.shp"
-hsa_geo = load_shapefile(hsa_shapefile_path, state_abbr='TN')
+if not os.path.exists(hsa_shapefile_path):
+    raise FileNotFoundError(f"HSA shapefile not found at {hsa_shapefile_path}. Please ensure the file exists.")
+    
+hsa_geo = gpd.read_file(hsa_shapefile_path)
+if 'hsastate' in hsa_geo.columns:
+    hsa_geo = hsa_geo[hsa_geo['hsastate'].isin(['TN'])]
+elif 'STATEFP' in hsa_geo.columns:
+    hsa_geo = hsa_geo[hsa_geo['STATEFP'].isin(['47'])]
+else:
+    raise KeyError("Column to filter state in HSA shapefile not found.")
 
 # Load the HRR shapefile
 hrr_shapefile_path = "data/hrr/01_hrr-shape-file.shp"
-hrr_geo = load_shapefile(hrr_shapefile_path, state_abbr='TN')
-
-# Business type colors
-business_colors = {
-    "Autozone": "red",
-    "Napa Auto": "blue",
-    "Firestone": "green",
-    "O'Reilly Auto": "purple",
-    "Advance Auto": "orange",
-    "Car Dealership": "darkred",
-    "Other Auto Repair Shops": "gray"
-}
+if not os.path.exists(hrr_shapefile_path):
+    raise FileNotFoundError(f"HRR shapefile not found at {hrr_shapefile_path}. Please ensure the file exists.")
+    
+hrr_geo = gpd.read_file(hrr_shapefile_path)
+if 'hrrstate' in hrr_geo.columns:
+    hrr_geo = hrr_geo[hrr_geo['hrrstate'].isin(['TN'])]
+elif 'STATEFP' in hrr_geo.columns:
+    hrr_geo = hrr_geo[hrr_geo['STATEFP'].isin(['47'])]
+else:
+    raise KeyError("Column to filter state in HRR shapefile not found.")
 
 # Function to create a Folium map with selected geographical boundaries and markers
-def create_map(geo_layer="Counties", business_filters=None):
-    if business_filters is None:
-        business_filters = ["All"]
+def create_map(geo_layer="Counties", business_filters=["All"]):
     logger.info(f"Creating map with geo_layer: {geo_layer} and business_filters: {business_filters}")
     
     m = folium.Map(location=[35.8601, -86.6602], zoom_start=7)
     
-    # Select the appropriate GeoDataFrame based on geo_layer
-    geo_data_dict = {"Counties": counties_geo, "HSAs": hsa_geo, "HRRs": hrr_geo}
-    geo_data = geo_data_dict.get(geo_layer, counties_geo)  # Default to counties
-    logger.info(f"Geo layer {geo_layer} selected.")
-    
-    # Add selected geographical boundaries
-    folium.GeoJson(geo_data, name=geo_layer).add_to(m)
+    try:
+        # Select the appropriate GeoDataFrame based on geo_layer
+        if geo_layer == "Counties":
+            geo_data = counties_geo
+        elif geo_layer == "HSAs":
+            geo_data = hsa_geo
+        elif geo_layer == "HRRs":
+            geo_data = hrr_geo
+        else:
+            geo_data = counties_geo  # Default to counties
+        logger.info(f"Geo layer {geo_layer} selected.")
+        
+        # Add selected geographical boundaries
+        folium.GeoJson(geo_data, name=geo_layer).add_to(m)
+    except Exception as e:
+        logger.error(f"Error loading GeoData for {geo_layer}: {e}")
     
     # Initialize Marker Cluster
     marker_cluster = MarkerCluster().add_to(m)
     
-    # Filter based on Business
+    # Filter based on Business 
     if "All" not in business_filters:
         filtered_df = df_md_final1[df_md_final1['business_type'].isin(business_filters)]
     else:
         filtered_df = df_md_final1.copy()
     
     logger.info(f"Filtered {len(filtered_df)} businesses based on filters: {business_filters}")
-    
+
     # Add markers to the map
     for _, row in filtered_df.iterrows():
-        business_type = row['business_type']
-        marker_color = business_colors.get(business_type, 'blue')
         folium.Marker(
             location=[row['md_y'], row['md_x']],
-            popup=folium.Popup(
-                f"<b>{row['name']}</b><br>{row.get('address', 'N/A')}, "
-                f"{row.get('city', 'N/A')}, TN {row.get('postal_code', 'N/A')}",
-                max_width=300),
-            icon=folium.Icon(color=marker_color, icon='info-sign')
+            popup=f"<b>{row['name']}</b><br>{row.get('address', 'N/A')}, {row.get('city', 'N/A')}, TN {row.get('postal_code', 'N/A')}",
+            icon=folium.Icon(color='blue', icon='info-sign')
         ).add_to(marker_cluster)
     
     folium.LayerControl().add_to(m)
@@ -170,7 +148,6 @@ def plot_2020_population_top15():
 def plot_population_comparison():
     df_melted = df_population_comparison.melt(id_vars='County', value_vars=['Population_2010', 'Population_2020'],
                                               var_name='Year', value_name='Population')
-    df_melted['Year'] = df_melted['Year'].str.replace('Population_', '')
     fig = px.bar(df_melted, 
                  x='County', 
                  y='Population', 
@@ -178,12 +155,13 @@ def plot_population_comparison():
                  barmode='group', 
                  title="Tennessee Population Comparison: 2010 vs 2020", 
                  labels={'County': 'County', 'Population': 'Population'},
-                 color_discrete_map={'2010': 'purple', '2020': 'blue'})
+                 color_discrete_map={'Population_2010': 'purple', 'Population_2020': 'blue'})
     
     fig.update_layout(xaxis={'categoryorder': 'total descending'}, template='plotly_white')
     return fig
 
 # Nearest Neighbor Search Setup
+# Prepare the data for nearest neighbor search
 def prepare_nearest_neighbor():
     # Convert coordinates to radians for BallTree
     coords = df_md_final1[['md_y', 'md_x']].to_numpy()
@@ -229,11 +207,7 @@ def find_nearest_shop(address=None, latitude=None, longitude=None):
     # Add nearest shop marker
     folium.Marker(
         location=[nearest_shop['md_y'], nearest_shop['md_x']],
-        popup=folium.Popup(
-            f"Nearest Shop: {nearest_shop['name']}<br>{nearest_shop.get('address', 'N/A')}, "
-            f"{nearest_shop.get('city', 'N/A')}, TN {nearest_shop.get('postal_code', 'N/A')}<br>"
-            f"Distance: {distance_km:.2f} km",
-            max_width=300),
+        popup=f"Nearest Shop: {nearest_shop['name']}<br>{nearest_shop.get('address', 'N/A')}, {nearest_shop.get('city', 'N/A')}, TN {nearest_shop.get('postal_code', 'N/A')}<br>Distance: {distance_km:.2f} km",
         icon=folium.Icon(color='green', icon='shopping-cart')
     ).add_to(m)
 
@@ -248,9 +222,78 @@ with gr.Blocks(theme=gr.themes.Default()) as app:
     
     with gr.Tab("Overview"):
         gr.Markdown("## 📊 Tennessee Population Statistics")
-        gr.Markdown("### 2010 vs 2020 Population Comparison")
-        pop_comp = gr.Plot(plot_population_comparison)
+        
+        with gr.Row():
+            
+            with gr.Column():
+                gr.Markdown("### 2010 vs 2020 Population Comparison")
+                pop_comp = gr.Plot(plot_population_comparison)
+        
         gr.Markdown("### 🛠️ Auto Businesses in Tennessee")
+
+        manual_table = gr.Dataframe(
+            headers=["Location Name", "Street Address", "City", "State", "Postal Code"],
+            datatype=["str", "str", "str", "str", "str"],
+            value=[
+                ["AutoZone Auto Parts - Nashville #2080", "100 Donelson Pike", "Nashville", "Tennessee", "37214"],
+                ["AutoZone Auto Parts - Nashville #3597", "1007 Murfreesboro Pike", "Nashville", "Tennessee", "37217"],
+                ["AutoZone Auto Parts - Nashville #2095", "2340 Murfreesboro Pike", "Nashville", "Tennessee", "37217"],
+                ["AutoZone Auto Parts - Nashville #69", "2800 Gallatin Pike", "Nashville", "Tennessee", "37216"],
+                ["AutoZone Auto Parts - Nashville #67", "2917 Nolensville Pike", "Nashville", "Tennessee", "37211"],
+                ["AutoZone Auto Parts - Nashville #66", "3041 Dickerson", "Nashville", "Tennessee", "37207"],
+                ["AutoZone Auto Parts - Nashville #346", "3712 Clarksville Pike", "Nashville", "Tennessee", "37218"],
+                ["AutoZone Auto Parts - Nashville #68", "3913 Charlotte Ave", "Nashville", "Tennessee", "37209"],
+                ["AutoZone Auto Parts - Nashville #146", "4815 Nolensville Rd", "Nashville", "Tennessee", "37211"],
+                ["AutoZone Auto Parts - Nashville #5963", "5731 Nolensville Pike", "Nashville", "Tennessee", "37211"],
+                ["AutoZone Auto Parts - Nashville #2302", "6217 Charlotte Pike", "Nashville", "Tennessee", "37209"],
+                ["AutoZone Auto Parts - Nashville #6320", "7621 Hwy 70 S # 3", "Nashville", "Tennessee", "37221"],
+                ["AutoZone Auto Parts - Knoxville #4549", "10650 Kingston Pike", "Knoxville", "Tennessee", "37922"],
+                ["AutoZone Auto Parts - Knoxville #3884", "110 Holston Ferry Rd", "Knoxville", "Tennessee", "37924"],
+                ["AutoZone Auto Parts - Knoxville #700", "2800 North Broadway", "Knoxville", "Tennessee", "37917"],
+                ["AutoZone Auto Parts - Knoxville #167", "3100 Magnolia Ave", "Knoxville", "Tennessee", "37914"],
+                ["AutoZone Auto Parts - Knoxville #228", "3315 S Chapman Hwy", "Knoxville", "Tennessee", "37920"],
+                ["AutoZone Auto Parts - Knoxville #3603", "4768 Centerline Dr", "Knoxville", "Tennessee", "37917"],
+                ["AutoZone Auto Parts - Knoxville #154", "4910 N Broadway", "Knoxville", "Tennessee", "37918"],
+                ["AutoZone Auto Parts - Knoxville #308", "5715 Western Ave", "Knoxville", "Tennessee", "37921"],
+                ["AutoZone Auto Parts - Knoxville #356", "5723 Clinton Hwy", "Knoxville", "Tennessee", "37912"],
+                ["AutoZone Auto Parts - Knoxville #2075", "7421 Maynardville", "Knoxville", "Tennessee", "37938"],
+                ["AutoZone Auto Parts - Knoxville #118", "8309 Kingston Pike", "Knoxville", "Tennessee", "37919"],
+                ["AutoZone Auto Parts - Knoxville #126", "9305 Kingston Pike", "Knoxville", "Tennessee", "37922"],
+                ["AutoZone Auto Parts - Memphis #5625", "1203 E Shelby Dr", "Memphis", "Tennessee", "38116"],
+                ["AutoZone Auto Parts - Memphis", "1209 E Raines Rd", "Memphis", "Tennessee", "38116"],
+                ["AutoZone Auto Parts - Memphis #4395", "1290 Lamar Ave", "Memphis", "Tennessee", "38104"],
+                ["AutoZone Auto Parts - Memphis #8", "1363 Getwell Rd", "Memphis", "Tennessee", "38111"],
+                ["AutoZone Auto Parts - Memphis #2", "1510 Elvis Presley Blvd", "Memphis", "Tennessee", "38106"],
+                ["AutoZone Auto Parts - Memphis #2098", "1770 Sycamore View Rd", "Memphis", "Tennessee", "38134"],
+                ["AutoZone Auto Parts - Memphis #27", "1850 S Third St", "Memphis", "Tennessee", "38109"],
+                ["AutoZone Auto Parts - Memphis #5421", "2010 Whitten Rd", "Memphis", "Tennessee", "38134"],
+                ["AutoZone Auto Parts - Memphis #30", "2076 Frayser Blvd", "Memphis", "Tennessee", "38127"],
+                ["AutoZone Auto Parts - Memphis #46", "2323 Lamar Ave", "Memphis", "Tennessee", "38114"],
+                ["AutoZone Auto Parts - Memphis #5756", "2449 Jackson Ave", "Memphis", "Tennessee", "38108"],
+                ["AutoZone Auto Parts - Memphis #6000", "2761 Kirby Rd", "Memphis", "Tennessee", "38119"],
+                ["AutoZone Auto Parts - Memphis #45", "2900 Covington Pk", "Memphis", "Tennessee", "38128"],
+                ["AutoZone Auto Parts - Memphis #598", "3166 N Thomas", "Memphis", "Tennessee", "38127"],
+                ["AutoZone Auto Parts - Memphis #324", "3171 Summer Ave", "Memphis", "Tennessee", "38112"],
+                ["AutoZone Auto Parts - Chattanooga #180", "2021 E 3rd St", "Chattanooga", "Tennessee", "37404"],
+                ["AutoZone Auto Parts - Chattanooga #5517", "2114 Gunbarrel Rd", "Chattanooga", "Tennessee", "37421"],
+                ["AutoZone Auto Parts - Chattanooga #149", "3201 Dayton Blvd", "Chattanooga", "Tennessee", "37415"],
+                ["AutoZone Auto Parts - Chattanooga #116", "3536 Brainerd Rd", "Chattanooga", "Tennessee", "37411"],
+                ["AutoZone Auto Parts - Chattanooga #123", "4307 Rossville Blvd", "Chattanooga", "Tennessee", "37407"],
+                ["AutoZone Auto Parts - Chattanooga #76", "4818 Hwy 58", "Chattanooga", "Tennessee", "37416"],
+                ["AutoZone Auto Parts - Chattanooga #151", "5317 Ringgold Rd", "Chattanooga", "Tennessee", "37412"],
+                ["AutoZone Auto Parts - Chattanooga #2072", "7630 E Brainerd Rd", "Chattanooga", "Tennessee", "37421"],
+                ["AutoZone Auto Parts - Clarksville #6301", "101 Merchants Blvd", "Clarksville", "Tennessee", "37040"],
+                ["AutoZone Auto Parts - Clarksville #64", "1105 Riverwood Pl", "Clarksville", "Tennessee", "37040"],
+                ["AutoZone Auto Parts - Clarksville #70", "1444 Fort Campbell Blvd", "Clarksville", "Tennessee", "37042"],
+                ["AutoZone Auto Parts - Clarksville #3890", "1832 Tiny Town Rd", "Clarksville", "Tennessee", "37042"],
+                ["AutoZone Auto Parts - Clarksville #586", "1959 Madison St", "Clarksville", "Tennessee", "37043"],
+                ["AutoZone Auto Parts - Clarksville #3880", "2653 Ft Campbell Blvd", "Clarksville", "Tennessee", "37042"]
+        ],
+        row_count=52,  # Updated for the total number of rows
+        interactive=False
+        ) 
+    
+        gr.Markdown("### 📍 Interactive Map")
         map_output_overview = gr.HTML(create_map(geo_layer="Counties", business_filters=["All"]))
     
     with gr.Tab("📍 Shops in TN Counties"):
@@ -318,8 +361,7 @@ with gr.Blocks(theme=gr.themes.Default()) as app:
                 address_input = gr.Textbox(label="Enter Address", placeholder="e.g., 123 Main St, Nashville, TN")
                 address_suggestions = gr.Dropdown(label="Suggestions", choices=[])
                 gr.Markdown("**OR**")
-                gr.Markdown("### Click on the Map to Select Your Location")
-                location_input = Map(label="Select Location")  # Use Map component
+                # Note: Interactive map clicks are not implemented in this version
             with gr.Column(scale=4):
                 nearest_map = gr.HTML()
         message_output = gr.Textbox(label="Message", interactive=False)
@@ -360,22 +402,12 @@ with gr.Blocks(theme=gr.themes.Default()) as app:
             message, updated_map = find_nearest_shop(address=selected_address)
             return message, updated_map
 
-        # Function to update the map based on map click
-        def update_nearest_map_from_click(map_data):
-            if not map_data:
-                return "Please select a location on the map.", None
-            latitude, longitude = map_data['latitude'], map_data['longitude']
-            message, updated_map = find_nearest_shop(latitude=latitude, longitude=longitude)
-            return message, updated_map
-
         # When the user types in the address_input, update suggestions
         address_input.input(fn=get_address_suggestions, inputs=address_input, outputs=address_suggestions, every=1.0)
         # When the user presses Enter in address_input, update map
         address_input.submit(fn=update_nearest_map_from_input, inputs=address_input, outputs=[message_output, nearest_map])
         # When the user selects an address from suggestions, update the map
         address_suggestions.change(fn=update_nearest_map_from_suggestion, inputs=address_suggestions, outputs=[message_output, nearest_map])
-        # When the user clicks on the map
-        location_input.change(fn=update_nearest_map_from_click, inputs=location_input, outputs=[message_output, nearest_map])
     
     with gr.Tab("🔍 Help"):
         gr.Markdown("""
@@ -387,15 +419,14 @@ with gr.Blocks(theme=gr.themes.Default()) as app:
             - **Filter by Business Type:** Use the checkboxes to select one or multiple business types to display on the map.
             - **Filter by Geographical Area:** Depending on the tab, you can filter businesses based on Counties, HSAs, or HRRs.
             - **Reset Filters:** Click the reset button to clear all selected filters and view all businesses.
-            - **Interactive Map:** Zoom in/out, click on markers to view business details.
+            - **Interactive Map:** Zoom in/out, click on markers to view business details, and use the search bar to find specific businesses.
         
         - **Nearest Shop Finder Tab:**
             - **Enter Address:** Type your address in the textbox. As you type, address suggestions will appear. Select one or press Enter to find the nearest auto shop.
-            - **Click on Map:** Alternatively, click on the map to select your location.
             - **View Results:** The map will display your location and the nearest auto shop with a line connecting them.
         
         """)
     
     gr.Markdown("### 📄 Source: Yellow Pages")
 
-app.launch(server_name="0.0.0.0", server_port=7860, share=True)
+app.launch(server_name="0.0.0.0", server_port=7860, share=True)