From 29b5da47782a2af1a14d4ac2bf70c1896a96e986 Mon Sep 17 00:00:00 2001
From: matt <matt.adam.wisnowski@gmail.com>
Date: Sat, 18 Oct 2025 22:32:54 -0700
Subject: [PATCH] fix: correct DataFrame column filtering and enhance debug
 output

- Fix KeyError in generate_theme_catalog.py: use isCommander column correctly
- DataFrame.get() doesn't work like dict.get() - use column name directly
- Enhanced debug step to print full row data for better diagnostics
---
 .github/workflows/build-similarity-cache.yml | 36 +++++++++-----------
 code/scripts/generate_theme_catalog.py       |  8 +++--
 2 files changed, 23 insertions(+), 21 deletions(-)

diff --git a/.github/workflows/build-similarity-cache.yml b/.github/workflows/build-similarity-cache.yml
index d135cea..a4a4bbc 100644
--- a/.github/workflows/build-similarity-cache.yml
+++ b/.github/workflows/build-similarity-cache.yml
@@ -109,25 +109,23 @@ jobs:
           print(f'Columns: {list(df.columns)}')
           print('')
           
-          # Show first 10 rows with their themeTags
-          print('First 10 cards with themeTags:')
-          print('=' * 80)
-          for idx, row in df.head(10).iterrows():
-              name = row.get('name', 'UNKNOWN')
-              tags = row.get('themeTags', [])
-              tag_count = len(tags) if isinstance(tags, list) else 0
-              print(f'{idx}: {name}')
-              print(f'   Type: {type(tags).__name__}')
-              print(f'   Count: {tag_count}')
-              if tag_count > 0:
-                  # Show first 5 tags
-                  sample = tags[:5] if tag_count > 5 else tags
-                  print(f'   Tags: {sample}')
-                  if tag_count > 5:
-                      print(f'   ... and {tag_count - 5} more')
-              else:
-                  print(f'   Tags: (empty)')
-              print('')
+          # Show first 5 rows completely
+          print('First 5 complete rows:')
+          print('=' * 100)
+          for idx, row in df.head(5).iterrows():
+              print(f'Row {idx}:')
+              for col in df.columns:
+                  value = row[col]
+                  if isinstance(value, (list, tuple)) or hasattr(value, '__array__'):
+                      # For array-like, show type and length
+                      try:
+                          length = len(value)
+                          print(f'  {col}: {type(value).__name__}[{length}] = {value}')
+                      except:
+                          print(f'  {col}: {type(value).__name__} = {value}')
+                  else:
+                      print(f'  {col}: {value}')
+              print('-' * 100)
           "
       
       - name: Generate theme catalog
diff --git a/code/scripts/generate_theme_catalog.py b/code/scripts/generate_theme_catalog.py
index d76cb22..70cb8ad 100644
--- a/code/scripts/generate_theme_catalog.py
+++ b/code/scripts/generate_theme_catalog.py
@@ -247,9 +247,13 @@ def build_theme_catalog(
         all_cards_parquet, theme_variants=theme_variants
     )
     
-    # For commander counts, filter all_cards by is_commander column
+    # For commander counts, filter all_cards by isCommander column
     df_commanders = pd.read_parquet(all_cards_parquet)
-    df_commanders = df_commanders[df_commanders.get('is_commander', False)]
+    if 'isCommander' in df_commanders.columns:
+        df_commanders = df_commanders[df_commanders['isCommander']]
+    else:
+        # Fallback: assume all cards could be commanders if column missing
+        pass
     commander_counts = Counter()
     for tags in df_commanders['themeTags'].tolist():
         if tags is None or (isinstance(tags, float) and pd.isna(tags)):