# Import the necessary libraries
        import geopandas as gpd
        
        # Specify the path to the GeoJSON file
        # GeoJSON is a format for encoding a variety of geographic data structures using JavaScript Object Notation (JSON).
        # It is commonly used to represent geographical features along with their associated non-spatial attributes.
        url = "ZMB_adm.json"
        district_geo = f"{url}"
        
        # Read the GeoJSON file into a GeoDataFrame
        # This will allow us to work with the geographic data in a structured format using GeoPandas.
        # try-except block to handle potential errors that might occur if the file is not found or if there are issues with the file format
        try:
            geoJSON_df = gpd.read_file(district_geo)
        except Exception as e:
            print(f"An error occurred: {e}")
        
        # Display the first few rows of the GeoDataFrame to inspect the data
        # This helps us verify that the data has been loaded correctly and gives us an initial look at the structure of the data.
        geoJSON_df.head()
        

# Check the first few rows to confirm that the renaming was successful
        geoJSON_df.head()
        

# Import the necessary libraries
        import pandas as pd
        import numpy as np
        
        # Import indicators and health facility data
        # The na_values parameter specifies additional strings to recognize as NA/NaN.
        # The delimiter is set to ',' as the CSV files are comma-separated.
        indicators_df = pd.read_csv("indicators.csv", na_values="NA", delimiter=',', header=0, index_col=False)
        df_facilities = pd.read_csv("catchment_areas.csv", na_values="NA", delimiter=',', header=0, index_col=False)
        
        # Replace all zero values with NaN to ensure they do not affect average computations
        # This is useful for handling cases where zero values may represent missing data rather than actual zero counts.
        # Column abbreviations:
        # msg_groups - Mother Support Groups (number)
        # improved_techs - Improved Agricultural Technologies (number of households practicing)
        # new_boreholes - New Boreholes (number)
        indicators_df["msg_groups"] = indicators_df["msg_groups"].replace(0, np.nan)
        indicators_df["improved_techs"] = indicators_df["improved_techs"].replace(0, np.nan)
        indicators_df["new_boreholes"] = indicators_df["new_boreholes"].replace(0, np.nan)
        
        # Display summary statistics of the DataFrame
        # This provides an overview of the central tendency, dispersion, and shape of the dataset’s distribution.
        indicators_df.describe()
        

indicators_df.head()
        

# Rename columns in the df_facilities DataFrame
        # This changes the column names for better readability and consistency.
        df_facilities = df_facilities.rename(columns={
            "Country": "country",
            "District": "district",
            "Province": "province"
        })
        
        # Display the first 10 rows of the DataFrame to verify the renaming
        df_facilities.head(10)
        

# Display the first 5 rows of the DataFrame to verify the renaming
        geoData.head()
        

# Extract latitude and longitude columns from df_facilities
        # This creates a DataFrame containing only the latitude and longitude columns.
        locations = df_facilities[['latitude', 'longitude']]
        
        # Convert the DataFrame to a list of lists
        # Each inner list represents a location with latitude and longitude values.
        facility_locationlist = locations.values.tolist()
        
        # Display the length of the list of locations
        # This shows the total number of locations in the list.
        print(len(facility_locationlist))
        
        # Access and display the 8th entry in the list (index 7, as indexing starts at 0)
        # This shows the latitude and longitude of the 8th facility.
        print(facility_locationlist[7])
        

# Filter df_facilities to include only rows where 'new_boreholes' is greater than or equal to 1
        # This creates a new DataFrame df_boreholes that contains facilities with at least one new borehole.
        df_boreholes = df_facilities[df_facilities['new_boreholes'] >= 1]
        
        # Inspect the resulting DataFrame
        df_boreholes.head()
        

# how many facilities meet the condition
        len(df_boreholes)
        

import geopandas as gpd
        import folium
        import folium.plugins as plugins
        import branca.colormap as cm
        import pandas as pd
        
        # Set CRS for geoData
        geoJSON_df.crs = "EPSG:4326"
        
        # Aggregate data to get total number of boreholes and facilities per district
        boreholes_per_district = df_boreholes.groupby('district')['new_boreholes'].sum().reset_index()
        facilities_per_district = df_facilities.groupby('district')['name'].count().reset_index()
        community_gardens_per_district = df_facilities.groupby('district')['community_gardens'].sum().reset_index()
        facilities_per_district.rename(columns={"name": "total_facilities"}, inplace=True)
        
        # Merge aggregated data with geoJSON_df
        geoJSON_df = geoJSON_df.merge(indicators_df[['district', 'msg_groups']], on='district', how='left')
        geoJSON_df = geoJSON_df.merge(boreholes_per_district, on='district', how='left')
        geoJSON_df = geoJSON_df.merge(community_gardens_per_district, on='district', how='left')
        geoJSON_df = geoJSON_df.merge(facilities_per_district, on='district', how='left')
        
        # Create the Folium map centered on Zambia
        m = folium.Map(location=[-13.1, 27], zoom_start=6.3, width='100%', height='100%', control_scale=True, tiles='CartoDB Positron')
        
        # Choropleth layer with hover functionality
        choropleth = folium.Choropleth(
            geo_data=geoJSON_df,
            data=indicators_df,
            columns=['district', 'msg_groups'],
            key_on="feature.properties.district",
            fill_color="YlGnBu",
            fill_opacity=0.7,
            line_opacity=0.2,
            bins=5,
            legend_name="# of Nutrition Support Groups",
            name="Nutrition Support Groups Density",
            highlight=True
        ).add_to(m)
        
        # Add hover functionality with GeoJsonTooltip
        folium.GeoJson(
            geoJSON_df,
            style_function=lambda feature: {
                'fillColor': '#ffffff00',
                'color': '#000000',
                'weight': 0.1,
                'dashArray': '5, 5',
                'fillOpacity': 0,
            },
            tooltip=folium.GeoJsonTooltip(
                fields=['district', 'total_facilities', 'msg_groups', 'new_boreholes', 'community_gardens'],
                aliases=['District: ',  'Health Facilities: ', 'Nutrition Support Groups: ', 'New Boreholes: ','Community Gardens: '],
                localize=True,
                sticky=False,
                labels=True,
                style="""
                    background-color: #F0EFEF;
                    border: 1px solid black;
                    border-radius: 3px;
                    box-shadow: 3px;
                """,
                max_width=300,
            )
        ).add_to(choropleth)
        
        # Improved Agricultural Technologies Layer
        group0 = folium.FeatureGroup(name='<span style="color: #007580;">Improved Agricultural Technologies</span>')
        for i in range(len(indicators_df)):
            folium.CircleMarker(
                location=[indicators_df.iloc[i]['latitude'], indicators_df.iloc[i]['longitude']],
                popup="Improved Agricultural Technologies " + str(indicators_df.iloc[i]['district']) + ' ' + str(indicators_df.iloc[i]['improved_techs']),
                radius=scaled_feature(i, 'improved_techs', mn=5, mx=20),
                color='#007580',
                fill=True,
                fill_color='#007580'
            ).add_to(group0)
        m.add_child(group0)
        
        # New Boreholes Layer
        colormap = cm.LinearColormap(colors=['orange', 'blue', 'red'], vmin=0, vmax=5)
        for i in range(len(df_boreholes)):
            folium.Circle(
                location=[df_boreholes.iloc[i]['latitude'], df_boreholes.iloc[i]['longitude']],
                radius=20,
                fill=True,
                color=colormap(df_boreholes.iloc[i]['new_boreholes']),
                popup="New Boreholes " + str(df_boreholes.iloc[i]['new_boreholes']),
                fill_opacity=0.5
            ).add_to(m)
        m.add_child(colormap)
        colormap.caption = '# of Newly Installed Boreholes'
        
        # Health Facilities Layer with Hover Functionality
        group2 = folium.FeatureGroup(name='Health Facilities')
        marker_cluster = folium.plugins.MarkerCluster().add_to(group2)
        
        for point in range(len(facility_locationlist)):
            folium.Marker(
                location=facility_locationlist[point],
                popup=folium.Popup(df_facilities['name'][point], max_width=200),
                tooltip=folium.Tooltip(f"Facility: {df_facilities['name'][point]}")
            ).add_to(marker_cluster)
        
        group2.add_to(m)
        
        # Add layer control
        folium.LayerControl().add_to(m)
        
        # Display the map
        m