Pareto / Cumulative Share Analysis

import pandas as pd
import numpy as np

df = pd.DataFrame({'product': [f'P{i:03d}' for i in range(50)],'revenue': np.random.pareto(1.5, 50) * 1000}).sort_values('revenue', ascending=False).reset_index(drop=True)

df['cum_revenue'] = df['revenue'].cumsum()
df['cum_share']   = df['cum_revenue'] / df['revenue'].sum()
df['rank']        = df.index + 1

top_80 = df[df['cum_share'] <= 0.80]
print(f'Top {len(top_80)} products drive 80% of revenue')
print(df.head(10)[['product','revenue','cum_share']])