Upload 3 files

app.py

@@ -0,0 +1,201 @@
+import gradio as gr
+import pandas as pd
+import plotly.express as px
+import plotly.graph_objects as go
+import numpy as np
+import math
+import random
+
+# Load and preprocess data
+df = pd.read_csv('Hurun_Global_Rich_List_2025_COORD.csv')
+df['Wealth $B'] = pd.to_numeric(df['Wealth $B'], errors='coerce')
+df = df.dropna(subset=['lat', 'lon'])
+df['Log Wealth'] = np.log10(df['Wealth $B'])
+
+# Extract country from location
+df['Country'] = df['Location'].str.split(',').str[-1].str.strip()
+
+# Add jitter to coordinates to prevent overlapping
+def add_jitter(coords, jitter_range=0.2):
+    """Add random jitter to coordinates to prevent overlapping markers"""
+    # Create a dictionary to track coordinate counts
+    coord_counts = {}
+    jittered_coords = []
+    
+    for coord in coords:
+        # Round coordinates to 2 decimal places for grouping
+        rounded = (round(coord[0], 2), round(coord[1], 2))
+        
+        # Count how many times we've seen this approximate location
+        count = coord_counts.get(rounded, 0)
+        coord_counts[rounded] = count + 1
+        
+        # Only add jitter if there are multiple points at this location
+        if count > 0:
+            # Calculate jitter based on count to spread points
+            angle = 2 * math.pi * (count / 8)  # Spread in 8 directions
+            distance = jitter_range * min(0.5 + count/10, 1.5)  # Scale with count
+            
+            jitter_lat = math.sin(angle) * distance
+            jitter_lon = math.cos(angle) * distance
+            
+            jittered_coords.append((coord[0] + jitter_lat, coord[1] + jitter_lon))
+        else:
+            jittered_coords.append(coord)
+    
+    return jittered_coords
+
+# Create logarithmic scale for visualization
+def create_globe():
+    # Calculate logarithmic values for visualization
+    df['Size'] = df['Log Wealth'] * 8
+    df['Color Value'] = df['Log Wealth']
+    
+    # Add jitter to coordinates
+    coords = list(zip(df['lat'], df['lon']))
+    jittered_coords = add_jitter(coords)
+    df['lat_jitter'] = [c[0] for c in jittered_coords]
+    df['lon_jitter'] = [c[1] for c in jittered_coords]
+    
+    # Generate linear tick positions for legend
+    min_log = df['Log Wealth'].min()
+    max_log = df['Log Wealth'].max()
+    
+    wealth_ticks = [1, 10, 30, 100, 300, 1000]
+    log_ticks = [math.log10(x) for x in wealth_ticks if x <= 10**max_log and x >= 10**min_log]
+    tick_labels = [f"${x}B" for x in wealth_ticks if x <= 10**max_log and x >= 10**min_log]
+    
+    fig = go.Figure(go.Scattergeo(
+        lon = df['lon_jitter'],
+        lat = df['lat_jitter'],
+        text = df.apply(lambda row: (
+            f"<b>{row['Name']}</b><br>"
+            f"Rank: {row['Rank']}<br>"
+            f"Wealth: ${row['Wealth $B']}B<br>"
+            f"Enterprise: {row['Enterprise']}<br>"
+            f"Sector: {row['Sector']}<br>"
+            f"Age: {row['Age']}<br>"
+            f"Location: {row['Location']}"
+        ), axis=1),
+        marker = dict(
+            size = df['Size'],
+            color = df['Color Value'],
+            colorscale = 'Turbo',
+            opacity = 0.7,
+            line_color='rgb(40,40,40)',
+            line_width=0.5,
+            sizemode = 'diameter',
+            colorbar = dict(
+                title="Wealth (Billion USD)",
+                thickness=15,
+                len=0.35,
+                bgcolor='rgba(255,255,255,0.5)',
+                tickvals = log_ticks,
+                ticktext = tick_labels
+            )
+        ),
+        hoverinfo = 'text',
+        name = ''
+    ))
+    
+    fig.update_geos(
+        projection_type="orthographic",
+        showcoastlines=True,
+        coastlinecolor="RebeccaPurple",
+        showland=True,
+        landcolor="rgb(243, 243, 243)",
+        showocean=True,
+        oceancolor="rgb(217, 244, 252)"
+    )
+    
+    fig.update_layout(
+        height=500,
+        margin={"r":0,"t":0,"l":0,"b":0},
+        paper_bgcolor='rgba(0,0,0,0)',
+        geo=dict(bgcolor='rgba(0,0,0,0)')
+    )
+    return fig
+
+# Create distribution plots
+def create_age_plot():
+    fig = px.histogram(df, x='Age', nbins=20, 
+                      title='Age Distribution',
+                      color_discrete_sequence=['#636EFA'])
+    fig.update_layout(height=300)
+    return fig
+
+def create_country_plot():
+    top_countries = df['Country'].value_counts().head(10)
+    fig = px.bar(top_countries, 
+                title='Top 10 Countries',
+                labels={'value': 'Count', 'index': 'Country'},
+                color=top_countries.index,
+                color_discrete_sequence=px.colors.qualitative.Pastel)
+    fig.update_layout(height=300, showlegend=False)
+    return fig
+
+def create_gender_plot():
+    gender_counts = df['Sex'].value_counts()
+    fig = px.pie(gender_counts, 
+                names=gender_counts.index, 
+                values=gender_counts.values,
+                title='Gender Distribution',
+                hole=0.4)
+    fig.update_layout(height=300)
+    return fig
+
+def create_sector_plot():
+    top_sectors = df['Sector'].value_counts().head(10)
+    fig = px.bar(top_sectors, 
+                title='Top 10 Sectors',
+                labels={'value': 'Count', 'index': 'Sector'},
+                color=top_sectors.index,
+                color_discrete_sequence=px.colors.qualitative.Pastel)
+    fig.update_layout(height=300, showlegend=False)
+    return fig
+
+# Create display dataframe without extra columns
+display_columns = ['Rank', 'Rank change', 'Wealth $B', 'Enterprise', 'Sector', 
+                   'Name', 'Sex', 'Age', 'Sidekick', 'Location']
+display_df = df[display_columns].sort_values('Rank').reset_index(drop=True)
+
+# Create Gradio interface
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# 🗺️ Global Billionaires Dashboard 2025")
+    gr.Markdown("Interactive visualisation of the world's wealthiest individuals")
+    
+    with gr.Row():
+        with gr.Column():
+            gr.Markdown("### 🌍 Global Wealth Distribution")
+            gr.Markdown("Circle size and color intensity both represent wealth on a logarithmic scale")
+            gr.Markdown("Nearby points are slightly randomized to prevent overlapping")
+            globe = gr.Plot(create_globe(), label="Globe")
+    
+    with gr.Row():
+        with gr.Column():
+            gr.Markdown("### 📊 Distribution Analysis")
+    
+    with gr.Row():
+        with gr.Column():
+            age_plot = gr.Plot(create_age_plot())
+        with gr.Column():
+            country_plot = gr.Plot(create_country_plot())
+    
+    with gr.Row():
+        with gr.Column():
+            gender_plot = gr.Plot(create_gender_plot())
+        with gr.Column():
+            sector_plot = gr.Plot(create_sector_plot())
+    
+    with gr.Row():
+        with gr.Column():
+            gr.Markdown("### 📋 Full Billionaire Data")
+            data_table = gr.Dataframe(
+                value=display_df,
+                interactive=True,
+                column_widths=["auto"] * len(display_columns),
+                wrap=True,
+                col_count=(len(display_columns), "fixed")
+            )
+
+demo.launch()

requirements.txt

@@ -0,0 +1,5 @@
+plotly
+gradio
+pandas
+numpy
+lxml