import os
base_path = "asl_kaggle"

# Check if train.csv exists
print(f"train.csv exists: {os.path.exists(os.path.join(base_path, 'train.csv'))}")

# Check first few rows
import pandas as pd
train_df = pd.read_csv(os.path.join(base_path, "train.csv"))
print("\nFirst few rows:")
print(train_df.head())

# Check if parquet files exist
sample_path = os.path.join(base_path, train_df.iloc[0]['path'])
print(f"\nFirst parquet file exists: {os.path.exists(sample_path)}")
print(f"Full path: {sample_path}")# Test extraction on one file
test_path = os.path.join(base_path, train_df.iloc[0]['path'])
print(f"Testing: {test_path}")

df = pd.read_parquet(test_path)
print(f"\nDataFrame shape: {df.shape}")
print(f"Columns: {df.columns.tolist()}")
print(f"Types present: {df['type'].unique()}")
print(f"Frames: {len(df['frame'].unique())}")
print(f"\nFirst few rows:")
print(df.head(10))