import pandas as pd
from milestone_attribution_dataset_module import sanitize_nbs_data
from constants_module import NEOSERRA_COLUMNS, OUT_COLUMNS

def test_client(file_path, client_id):
    print(f"\nTesting {file_path} for client {client_id}")
    df = pd.read_csv(file_path)
    
    # Filter for the client to see raw data
    raw_client = df[df[NEOSERRA_COLUMNS.client_id] == client_id]
    print("Raw client data:")
    print(raw_client)
    
    # Run the sanitization
    cleaned_df = sanitize_nbs_data(
        df,
        col_neo_center=NEOSERRA_COLUMNS.center,
        col_neo_client_id=NEOSERRA_COLUMNS.client_id,
        col_neo_milestone_date=NEOSERRA_COLUMNS.milestone_date,
        col_neo_attribution_date=NEOSERRA_COLUMNS.attribution_date,
        col_neo_attribution_source=NEOSERRA_COLUMNS.milestone_attribution_source,
        col_neo_affirmation=NEOSERRA_COLUMNS.milestone_affirmation,
        col_neo_milestone_type=NEOSERRA_COLUMNS.milestone_type_name,
        col_out_documentation_level=OUT_COLUMNS.milestone_documentation_level,
        col_neo_reportable=NEOSERRA_COLUMNS.reportable,
        business_start_impact_val=NEOSERRA_COLUMNS.business_start_impact_val,
        business_established_val=NEOSERRA_COLUMNS.business_established_val
    )
    
    # Filter for the client in cleaned data
    cleaned_client = cleaned_df[cleaned_df[NEOSERRA_COLUMNS.client_id] == client_id]
    print("Cleaned client data:")
    print(cleaned_client)

if __name__ == "__main__":
    client_id = "KUP270610"
    test_client("export_module_no_bus_estab.csv", client_id)
    test_client("export_module_with_bus_estab.csv", client_id)