c3a24799c8
- Added all 89 albums that were genuinely dropped from 2020 to 2023 - Fixed incorrect status markings (many albums marked "New in 2023" were not new) - Removed duplicates and albums incorrectly marked as dropped - Final count: 589 total (500 main list + 89 dropped) - Updated JavaScript validation for extended range - Created comprehensive analysis scripts to verify data Math now adds up correctly: 89 albums dropped to make room for new additions 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
74 lines
No EOL
2.7 KiB
Python
74 lines
No EOL
2.7 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
Final cleanup - remove any dropped albums that are actually in the main Top 500 list.
|
|
"""
|
|
|
|
import csv
|
|
|
|
def normalize_name(text):
|
|
"""Normalize for comparison"""
|
|
return text.lower().strip().replace(' ', ' ')
|
|
|
|
def main():
|
|
# Read current CSV
|
|
albums = []
|
|
with open('top_500_albums_2023.csv', 'r', encoding='utf-8') as file:
|
|
reader = csv.DictReader(file)
|
|
for row in reader:
|
|
albums.append(row)
|
|
|
|
print(f"📊 Total albums before final cleanup: {len(albums)}")
|
|
|
|
# Get all albums in main list (ranks 1-500)
|
|
main_list_albums = set()
|
|
for album in albums:
|
|
if int(album['Rank']) <= 500:
|
|
key = (normalize_name(album['Artist']), normalize_name(album['Album']))
|
|
main_list_albums.add(key)
|
|
|
|
print(f"📊 Albums in main Top 500 list: {len(main_list_albums)}")
|
|
|
|
# Find dropped albums that are actually in the main list
|
|
to_remove = []
|
|
for i, album in enumerate(albums):
|
|
if 'Dropped' in album['Status']:
|
|
key = (normalize_name(album['Artist']), normalize_name(album['Album']))
|
|
if key in main_list_albums:
|
|
print(f"❌ Found incorrectly dropped album that's in main list:")
|
|
print(f" Rank {album['Rank']} - {album['Artist']} - {album['Album']}")
|
|
to_remove.append(i)
|
|
|
|
# Remove incorrect entries
|
|
if to_remove:
|
|
print(f"\n🗑️ Removing {len(to_remove)} incorrect entries...")
|
|
for i in reversed(to_remove):
|
|
del albums[i]
|
|
|
|
# Renumber albums after 500
|
|
current_rank = 501
|
|
for album in albums:
|
|
if int(album['Rank']) > 500:
|
|
album['Rank'] = str(current_rank)
|
|
current_rank += 1
|
|
|
|
# Write final CSV
|
|
with open('top_500_albums_2023.csv', 'w', newline='', encoding='utf-8') as file:
|
|
fieldnames = ['Rank', 'Artist', 'Album', 'Status', 'Info', 'Description']
|
|
writer = csv.DictWriter(file, fieldnames=fieldnames)
|
|
writer.writeheader()
|
|
writer.writerows(albums)
|
|
|
|
print(f"\n✅ Final cleanup complete!")
|
|
print(f"📊 Total albums now: {len(albums)}")
|
|
print(f"📊 Total dropped albums: {len([a for a in albums if 'Dropped' in a['Status']])}")
|
|
|
|
# Verify the math
|
|
new_albums = len([a for a in albums if a['Status'] == 'New in 2023' and int(a['Rank']) <= 500])
|
|
dropped_albums = len([a for a in albums if 'Dropped' in a['Status']])
|
|
print(f"\n🔍 Verification:")
|
|
print(f" New albums in 2023: {new_albums}")
|
|
print(f" Dropped albums: {dropped_albums}")
|
|
print(f" Should both equal: {'✅ YES' if new_albums == dropped_albums else '❌ NO'}")
|
|
|
|
if __name__ == "__main__":
|
|
main() |