Upload data3/check_match.py with huggingface_hub

data3/check_match.py

@@ -0,0 +1,41 @@
+#!/usr/bin/env python3
+import csv
+import json
+
+# Read row 57 from CSV (1-indexed, so row 56 in 0-indexed)
+print("Reading row 57 from CSV...")
+with open('function_dataset_v2.csv', 'r') as f:
+    reader = csv.DictReader(f)
+    for i, row in enumerate(reader):
+        if i == 56:  # 57th row (0-indexed)
+            print(f"Row {i+1}:")
+            print(f"  original_index: {row['original_index']}")
+            print(f"  repo_name: '{row['repo_name']}'")
+            print(f"  path: '{row['path']}'")
+            print(f"  language: '{row['language']}'")
+            print(f"  function_name: '{row['function_name']}'")
+            break
+
+# Also check a sample JSONL
+print("\n\nChecking first JSONL entry...")
+with open('programming_problems.jsonl', 'r') as f:
+    data = json.loads(f.readline())
+    print(f"original_index: {data['metadata']['original_index']}")
+    print(f"function_name: {data['metadata']['function_name']}")
+    print(f"Current repo_name: '{data['metadata']['repo_name']}'")
+    print(f"Current path: '{data['metadata']['path']}'")
+    print(f"Current language: '{data['metadata']['language']}'")
+
+# Count how many rows in CSV have complete info
+print("\n\nCounting CSV rows with complete metadata...")
+with open('function_dataset_v2.csv', 'r') as f:
+    reader = csv.DictReader(f)
+    total = 0
+    complete = 0
+    for row in reader:
+        total += 1
+        if row['repo_name'] and row['path'] and row['language']:
+            complete += 1
+    print(f"Total CSV rows: {total}")
+    print(f"Rows with complete metadata: {complete}")
+    print(f"Rows with missing metadata: {total - complete}")