import pandas as pd

# Define a list of file paths for easy modification
file_paths = [
    'sec_data/2024q1/num.txt',
    'sec_data/2024q1/pre.txt',
    'sec_data/2024q1/sub.txt',
    'sec_data/2024q1/tag.txt'
]

# Loop through each file and perform analysis
for i, file_path in enumerate(file_paths):
    print(f"\nAnalyzing {file_path} (File {i+1}/4)...")
    
    # Read the data into a Pandas DataFrame
    df = pd.read_csv(file_path, sep='\t')
    
    # Inspect the DataFrame
    print("First rows of the DataFrame:")
    print(df.head(10))
    
    # Get the DataFrame Information
    print("\nSummary Information:")
    print(df.info())
    
    # Check if there are any missing values in the DataFrame
    missing_values = df.isnull().sum()
    print("\nMissing Values:")
    print(missing_values)