import pandas as pd
import numpy as np
from datetime import datetime

def audit_csv(file_path, delimiter=','):
    """Perform comprehensive CSV audit"""

    # Load CSV
    try:
        df = pd.read_csv(file_path, delimiter=delimiter)
    except Exception as e:
        return {"error": f"Failed to load CSV: {str(e)}"}

    audit_report = {
        "file_info": {
            "rows": len(df),
            "columns": len(df.columns),
            "headers": list(df.columns)
        },
        "issues": []
    }

    # Check for missing values
    missing_counts = df.isnull().sum()
    for col, count in missing_counts.items():
        if count > 0:
            percentage = (count / len(df)) * 100
            audit_report["issues"].append({
                "type": "missing_values",
                "column": col,
                "count": count,
                "percentage": round(percentage, 2)
            })

    # Check for duplicates
    duplicate_rows = df.duplicated().sum()
    if duplicate_rows > 0:
        audit_report["issues"].append({
            "type": "duplicates",
            "count": duplicate_rows
        })

    # Data type validation
    for col in df.columns:
        # Check for mixed types in object columns
        if df[col].dtype == 'object':
            sample_values = df[col].dropna().head(10)
            # Add specific type checks based on column name patterns

    return audit_report

undefined

undefined