In [77]:
# Next, we will create a Treemap using the ompany name and revenue values
# Define the top 10 industries and a color mapping for them
industry_color_map = {
'Financials': '#1f77b4', # Blue
'Retail': '#ff7f0e', # Orange
'Petroleum industry': '#2ca02c', # Green
'Pharmaceutical industry': '#d62728', # Red
'Technology': '#9467bd', # Purple
'Healthcare': '#8c564b', # Brown
'Insurance': '#e377c2', # Pink
'Telecommunications': '#7f7f7f', # Gray
'Airline': '#bcbd22', # Yellow-green
'Technology and cloud computing': '#17becf' # Cyan
}
# If an industry is not in the color map, categorize it as 'Others'
df['Industry'] = df['Industry'].apply(lambda x: x if x in industry_color_map else 'Others')
# Update the color map to include 'Others'
industry_color_map['Others'] = '#aec7e8' # Light Blue for 'Others'
# Clean and filter the dataframe
df_cleaned = df.dropna(subset=['Revenue (USD millions)', 'Industry'])
df_cleaned = df_cleaned[df_cleaned['Revenue (USD millions)'] > 0]
# Normalize revenue values for better sizing in the treemap
normed_revenue = df_cleaned['Revenue (USD millions)']
# Map colors to industries
colors = df_cleaned['Industry'].map(industry_color_map)
# Create Treemap using squarify
plt.figure(figsize=(12, 8))
squarify.plot(sizes=normed_revenue,
label=df_cleaned['Name'],
color=colors,
alpha=0.8)
# Add title and clean up axis
plt.title('Top 100 Companies by Revenue')
plt.axis('off')
plt.show()
