e64b267ee3
- Re-ran dropped album matching with corrected names from user - Fixed final list to have exactly 89 correctly identified dropped albums - Removed any albums incorrectly marked as dropped that are in main list - Verified no duplicates between main list (1-500) and dropped list (501-589) - Total: 589 albums (500 current + 89 dropped) All dropped albums now correctly match albums missing from 2020→2023 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
87 lines
No EOL
2.9 KiB
Python
87 lines
No EOL
2.9 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
Fix the final dropped list with the corrected album names.
|
|
Replace current dropped albums with the correct ones.
|
|
"""
|
|
|
|
import csv
|
|
|
|
def normalize_text(text):
|
|
"""Normalize text for comparison"""
|
|
return text.lower().strip().replace('&', 'and').replace(' ', ' ')
|
|
|
|
def main():
|
|
# Read the correct dropped albums list
|
|
correct_dropped = []
|
|
with open('correct_dropped_albums.csv', 'r', encoding='utf-8') as file:
|
|
reader = csv.DictReader(file)
|
|
for row in reader:
|
|
correct_dropped.append({
|
|
'rank_2020': row['Original_Rank_2020'],
|
|
'artist': row['Artist'],
|
|
'album': row['Album']
|
|
})
|
|
|
|
print(f"📊 Loading {len(correct_dropped)} correct dropped albums")
|
|
|
|
# Get info/descriptions from 2020 data for dropped albums
|
|
info_desc_2020 = {}
|
|
with open('rolling_stone_top_500_albums_2020.csv', 'r', encoding='utf-8') as file:
|
|
reader = csv.DictReader(file)
|
|
for row in reader:
|
|
key = (row['Artist'], row['Album'])
|
|
info_desc_2020[key] = {
|
|
'info': row.get('Info', ''),
|
|
'description': row.get('Description', '')
|
|
}
|
|
|
|
# Read current CSV and remove all dropped albums
|
|
albums = []
|
|
with open('top_500_albums_2023.csv', 'r', encoding='utf-8') as file:
|
|
reader = csv.DictReader(file)
|
|
for row in reader:
|
|
if 'Dropped' not in row['Status']:
|
|
albums.append(row)
|
|
|
|
print(f"📊 Kept {len(albums)} non-dropped albums")
|
|
|
|
# Add the correct dropped albums
|
|
next_rank = 501
|
|
added_count = 0
|
|
|
|
for album in correct_dropped:
|
|
# Find info/description for this album
|
|
key = (album['artist'], album['album'])
|
|
info_data = info_desc_2020.get(key, {'info': '', 'description': ''})
|
|
|
|
albums.append({
|
|
'Rank': str(next_rank),
|
|
'Artist': album['artist'],
|
|
'Album': album['album'],
|
|
'Status': f"Dropped (was #{album['rank_2020']} in 2020)",
|
|
'Info': info_data['info'],
|
|
'Description': info_data['description']
|
|
})
|
|
next_rank += 1
|
|
added_count += 1
|
|
|
|
if added_count <= 10:
|
|
print(f"✓ Added: #{album['rank_2020']} - {album['artist']} - {album['album']}")
|
|
|
|
if added_count > 10:
|
|
print(f"... and {added_count - 10} more")
|
|
|
|
# Write updated 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✅ Updated dropped albums list")
|
|
print(f"📊 Total albums now: {len(albums)}")
|
|
print(f"📊 Main list (1-500): 500")
|
|
print(f"📊 Dropped (501-589): {added_count}")
|
|
|
|
if __name__ == "__main__":
|
|
main() |