# Drop rows where description is missing
df_clean = df.dropna(subset=['description'])

# Add a viral flag for repos with over 50k stars
df_clean = df_clean.copy()
df_clean['viral'] = df_clean['stars'].apply(lambda x: 'Yes' if x > 50000 else 'No')

# Sort by stars descending
df_clean = df_clean.sort_values('stars', ascending=False).reset_index(drop=True)

print("Before cleaning:", len(df))
print("After cleaning:", len(df_clean))